| Logout | Presenter Main Page | ||
| 8th International Conference on Software Engineering & Computer Systems 2023 (ICSECS2023) - View Tentative Schedule (With YouTube Links) | ||
| This schedule may change from time to time. Please always refer here for the latest updates. | ||
| 2023-08-25 | ||
| 15:00 - 17:00 | : | Registration @ Main Hall (Level 1) |
| 2023-08-26 | ||
| 08:30 - 08:45 | : | Opening @ Pandan Room |
| 08:45 - 09:15 | : | Keynote 1 @ Pandan Room |
| 09:15 - 09:45 | : | Morning Coffee Break @ Lada / Halia / Pandan Foyer |
| 09:45 - 10:15 | : | Keynote 2 @ Pandan Room |
| 10:30 - 11:00 | : | Keynote 3 @ Pandan Room |
| 11:15 - 13:00 | : | Session I-A @ Pandan Room |
| Session I-C @ Lada Room | ||
| Session I-B @ Halia Room | ||
| 13:00 - 14:00 | : | Networking Lunch @ Cinnamon Asian Kitchen |
| 14:00 - 16:00 | : | Session II-A @ Pandan Room |
| Session II-C @ Lada Room | ||
| Session II-B @ Halia Room | ||
| Session II-D (Virtual) @ Online | ||
| 16:00 - 16:30 | : | Afternoon Coffee Break @ Pandan / Halia / Pandan Foyer |
| 2023-08-27 | ||
| 08:30 - 10:00 | : | Session III-A @ Pandan Room |
| Session III-B @ Halia Room | ||
| 10:00 - 10:15 | : | Morning Coffee Break @ Halia Foyer |
| 10:15 - 12:45 | : | Session IV-A @ Pandan Room |
| Session IV-B @ Halia Room | ||
| Session IV-C (Virtual) @ Online | ||
| 12:30 - 13:00 | : | Closing Ceremony @ Pandan |
| 13:00 - 14:00 | : | Lunch @ @ Cinnamon Asian Kitchen |
| Keynotes | ||
| Data Analytics using Simulation for Sustainability Attainment in Operation Management | ||
| Speaker: Mazlina Abdul Majid | ||
| Abstract: Data analytics is one process in the Data Science field. While both fields involve working with data to gain insights, data analytics tends to focus more on analysing existing data to provide decisions in the present, while data science uses data with various approaches to build models that can predict future outcomes. There are four types of data analytics, and the usage depends on the specific business needs to achieve sustainable operation: 1. Descriptive Analytics, 2. Diagnostic Analytics, 3. Predictive Analytics, and 4. Prescriptive Analytics. Simulation is a powerful method that is suitable to perform all the data analytics types, but it is more significant to use for prediction (predictive) and assist in decision making (prescriptive). A simulation is an imitation of the system/process operation that represents its operation over time. Simulation is used to gain insight into the operation of a system by imitating the system function and using what-if scenarios (forecast events) to assist in decision-making (to do next). The capability of simulation in modelling and simulating a process over time helps for sustainability purposes. It imitates the flow of the existing operation, identifies the issues, experiments with various scenarios of operation and provides the best scenario solution with the combined analysis by Mathematical, Statistics or Artificial Intelligence methods. Thus, simulation enables organizations to forecast events with predictive analytics and find the best solutions with prescriptive analytics for improving the business strategy to attain sustainable operation. This talk describes the role of simulation in data analytics with an example from one case study. | ||
| Advancing Gait Analysis and Beyond | ||
| Speaker: Nooritawati Md Tahir | ||
| Abstract: Gait, the distinctive manner in which we walk or move, stands as a deeply individualistic trait that defies imitation. Rigorously studied as both a means of recognition and a biometric feature within the realm of human identification, gait holds the promise of unlocking new avenues of potential. In the realm of biomedicine, gait analysis emerges as a signature representation of human movement patterns, possessing the latent power to serve as an early harbinger of aberrant locomotion. Extensive research has endeavoured to discern the nuances distinguishing the gait characteristics of healthy individuals from those undergoing rehabilitation. Moreover, gait analysis techniques metamorphose into a diagnostic tool, offering clinicians valuable insights for patient assessment and monitoring. This session will unravel the challenges that underlie gait analysis and classification, while illuminating a pathway towards a future where these innovations transcend current boundaries. As the chronicle of gait unfolds, it beckons us to embark on a journey toward a more insightful and understanding of human movement. | ||
| The Importance of Cybersecurity | ||
| Speaker: Keen Fai Chew | ||
| Abstract: In this address, I want to highlight the critical importance of cybersecurity in today's digital era. Our personal and organizational lives are heavily reliant on technology, making us vulnerable to cyber threats. Without proper protection, our devices and data are at risk of being compromised. This affects individuals' privacy, organizations' reputation, and even national security. Hackers employ various tactics, such as malware and phishing attacks, to exploit vulnerabilities and steal sensitive information. These attacks can lead to identity theft, financial loss, and disruption of critical systems. National security is also at stake, as cyber attacks can target infrastructures, defense systems, and healthcare, causing widespread chaos. To combat these threats, we must take collective responsibility. Individuals should prioritize strong passwords, cautious online behavior, and regular updates. Organizations need to train employees and invest in cybersecurity tools. Governments should enforce regulations and build a robust cybersecurity framework. By working together, we can create a secure digital environment for everyone. | ||
| Detailed Schedule | ||
| Date: 2023-08-26 | ||
| Session I-A (11:15 - 13:00 @ Pandan Room) | ||
| Session Chair: ANIS FARIHAN BINTI MAT RAFFEI | ||
| 11:15-11:30 | Project Cost’s Early Warning Analysis via Microsoft Power BI (Business Intelligence) (Paper ID: 11) | |
| Presenter: Farah Aini Amin Nordin - Bio | ||
| Farah Aini Amin Nordin (PETRONAS) | ||
| 11:30-11:45 | Recognition Textual Entailment on Bahasa using Biplet Individual Comparison and BiLSTM (Paper ID: 27) | |
| Presenter: I Made Suwija Putra - Bio | ||
| I Made Suwija Putra (Department of Informatics, Institut Teknologi Sepuluh Nopember Surabaya), Daniel Siahaan (Department of Informatics, Institut Teknologi Sepuluh Nopember Surabaya), Ahmad Saikhu (Department of Informatics, Institut Teknologi Sepuluh Nopember Surabaya) | ||
| 11:45-12:00 | Improving Sarcasm Detection in Mash-Up Language Through Hybrid Pretrained Word Embedding (Paper ID: 31) | |
| Presenter: Mochamad Alfan Rosid - Bio | ||
| Mochamad Alfan Rosid (Institut Teknologi Sepuluh Nopember Surabaya), Daniel Siahaan (Institut Teknologi Sepuluh Nopember Surabaya), Ahmad Saikhu (Institut Teknologi Sepuluh Nopember Surabaya) | ||
| 12:00-12:15 | Text Segmentation Methods for Annotation on eHealth Consultation with Interview Function Labels: A Comparative Study (Paper ID: 33) | |
| Presenter: Yunianita Rahmawati - Bio | ||
| Yunianita Rahmawati (Institut Teknologi Sepuluh Nopember), Daniel Siahaan (Institut Teknologi Sepuluh Nopember), Diana Purwitasari (Institut Teknologi Sepuluh Nopember) | ||
| 12:15-12:30 | An Overview of Part-of-Speech Tagging Methods and Datasets for Malay Language (Paper ID: 37) | |
| Presenter: Chua Chi Log - Bio | ||
| Chi Log Chua (Tunku Abdul Rahman University of Management and Technology), Tong Ming Lim (Tunku Abdul Rahman University of Management and Technology), Kwee Teck See (Tunku Abdul Rahman University of Management and Technology) | ||
| 12:30-12:45 | Investigation on Insurance Purchase Classification for Insurance Recommendation using Deep Learning and Class Propagation (Paper ID: 54) | |
| Presenter: Jasmin Chu Ze Kee - Bio | ||
| Jasmin Z. K. Chu (Swinburne University of Technology), Joel C. M. Than (Swinburne University of Technology), Pun Liang Thon (Swinburne University of Technology), Hudyjaya Siswoyo Jo (Swinburne University of Technology) | ||
| 12:45-13:00 | Priority Based Fair Scheduling: Enhancing Efficiency in Cloud Job Distribution (Paper ID: 61) | |
| Presenter: Saydul Akbar Murad - Bio | ||
| Video Link: https://www.youtube.com/watch?v=sEYmue9-NrM | ||
| Saydul Akbar Murad (Universiti Malaysia Pahang Al-Sultan Abdullah), Zafril Rizal M Azmi (Universiti Malaysia Pahang Al-Sultan Abdullah), Faria Jerin Brishti (International Islamic University Chittagong), Md Saib (South China University of Technology), Anupam Kumar Bairagi (Khulna University) | ||
| Session I-C (11:15 - 13:00 @ Lada Room) | ||
| Session Chair: SYAHRUL NIZAM JUNAINI | ||
| 11:15-11:30 | A Comprehensive Ensemble Deep Learning Method for Identifying Native Advertising in News Articles (Paper ID: 58) | |
| Presenter: Brian Rizqi Paradisiaca Darnoto - Bio | ||
| Brian Rizqi Paradisiaca Darnoto (Institut Teknologi Sepuluh Nopember), Daniel Siahaan (Institut Teknologi Sepuluh Nopember), Diana Purwitasari (Institut Teknologi Sepuluh Nopember) | ||
| 11:30-11:45 | Machine Learning Regression Models for Real-time Touchless Interaction Applications (Paper ID: 68) | |
| Presenter: Hadyan Hafizh - Bio | ||
| Qinyan Gong (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Hadyan Hafizh (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Muhammad Ateeq (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Anwar Pp Abdul Majeed (School of Robotics, Xi'an Jiaotong-Liverpool University), Matilda Isaac (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Bintao Hu (School of Internet of Things, Xi'an Jiaotong-Liverpool University) | ||
| 11:45-12:00 | Shaping the Digital Future of Civil Service: An Assessment of Digital Transformation and Data Science Competencies (Paper ID: 83) | |
| Presenter: Syahrul Nizam Junaini - Bio | ||
| Syahrul Nizam Junaini (Universiti Malaysia Sarawak), Sopian Bujang (Universiti Malaysia Sarawak), Nadri Aetis Basmawi (Leadership Institute of Sarawak Civil Service), Jusmawati Fauzaman (International Islamic University Malaysia) | ||
| 12:00-12:15 | Deep Learning-based Classification Approach for Wire Bonding Defects Inspection (Paper ID: 101) | |
| Presenter: Nur Ayuni Mohamed - Bio | ||
| Nur Ayuni Mohamed (Infineon Technologies Sdn. Bhd.), Fock Lin Mok (Infineon Technologies Sdn. Bhd.), Qing Zhe Loong (Infineon Technologies Sdn. Bhd.) | ||
| 12:15-12:30 | ARIMA-LP: A Hybrid Model for Air Pollution Forecasting with Uncertainty Data (Paper ID: 117) | |
| Presenter: Muhammad Shukri Che Lah - Bio | ||
| Muhammad Shukri Che Lah (Universiti Tun Hussein Onn Malaysia Malaysia), Nureize Arbaiy (Universiti Tun Hussein Onn Malaysia Malaysia), Pei-chun Lin (Feng Chia University Taiwan) | ||
| 12:30-12:45 | Enhancing Autism Screening Classification using Feature Selection and Stacking Classifier (Paper ID: 129) | |
| Presenter: Ainie Hayati Noruzman - Bio | ||
| Ainie Hayati Noruzman (Faculty of Computing, University Malaysia Pahang Sultan Al-Abdullah,26600 Pekan, Pahang, Malaysia), Ngahzaifa Abd Ghani (Faculty of Computing, University Malaysia Pahang Sultan Al-Abdullah,26600 Pekan, Pahang, Malaysia), Nor Saradatulakmar Zulkifli (Faculty of Computing, University Malaysia Pahang Sultan Al-Abdullah,26600 Pekan, Pahang, Malaysia) | ||
| 12:45-13:00 | Machine Learning Classification to Detect Unattended Child in Vehicle Using Sensor Signal : A Review (Paper ID: 130) | |
| Presenter: Ida Fadliza Abu Zarin - Bio | ||
| Ida Fadliza Abu Zarin (University Malaysia Pahang), Ngahzaifa Abd Ghani (University Malaysia Pahang), Syafiq Fauzi Kamarulzaman (University Malaysia Pahang) | ||
| Session I-B (11:15 - 13:00 @ Halia Room) | ||
| Session Chair: SYAFIQ FAUZI BIN KAMARULZAMAN | ||
| 11:15-11:30 | Crow Search Freeman Chain Code (CS-FCC) Feature Extraction Algorithm for Handwritten Character Recognition (Paper ID: 91) | |
| Presenter: Muhammad 'arif Bin Mohamad - Bio | ||
| Muhammad Arif Mohamad (Universiti Malaysia Pahang Al-Sultan Abdullah), Zalili Musa (Universiti Malaysia Pahang Al-Sultan Abdullah), Amelia Ritahani Ismail (International Islamic Universiti Malaysia) | ||
| 11:30-11:45 | Internet of Things Intercommunication Using SocketIO and WebSocket with WebRTC in Local Area Network as Emergency Communication Devices (Paper ID: 96) | |
| Presenter: Syafiq Fauzi Bin Kamarulzaman - Bio | ||
| Nur Izzaty Ariffin (Ascenity Solutions Enterprise), Muhd. Aidil Syazwan Hamdan (Ascenity Solutions Enterprise), Syafiq Fauzi Kamarulzaman (University Malaysia Pahang) | ||
| 11:45-12:00 | Intelligent Humanoid Emotion Response based on Human Emotion Recognition for Virtual Intercommunication Simulator (Paper ID: 97) | |
| Presenter: Syafiq Fauzi Bin Kamarulzaman - Bio | ||
| Andrew Lim Wei Chin (Universiti Malaysia Pahang), Lim Gim Wen (Universiti Malaysia Pahang), Syafiq Fauzi Kamarulzaman (Universiti Malaysia Pahang) | ||
| 12:00-12:15 | Hop Restricted-AODV (HR-AODV) Routing and Its Applicability on Different Wireless Channels for Vehicular Network (Paper ID: 104) | |
| Presenter: Quadri Wassem - Bio | ||
| Tanvir Ahmad (University Malaysia Pahang (UMP)), Nor Syahidatul Nadiah Binti Ismail (University Malaysia Pahang (UMP)), Md Arafatur Rahman (University of Wolverhampton), Abdullah Mat Safri (University Malaysia Pahang (UMP)), Waseem Quadri (University Malaysia Pahang (UMP)) | ||
| 12:15-12:30 | An improvement of Interactive Prioritization Technique for Requirements Interdependency in prioritization process (Paper ID: 109) | |
| Presenter: Siti Nursyafiqah Binti Rusli - Bio | ||
| Siti Nursyafiqah Rusli (UNIVERSITI MALAYSIA PAHANG), Rohani Abu Bakar (UNIVERSITI MALAYSIA PAHANG), Siti Suhaila Abdul Hamid (UNIVERSITI MALAYSIA PAHANG) | ||
| 12:30-12:45 | QSroute : A QoS aware routing scheme for Software Defined Networking (Paper ID: 124) | |
| Presenter: Imran Edzereiq Bin Kamarudin - Bio | ||
| Imran Edzereiq Kamarudin (Universiti Malaysia Pahang), Mohamed Ariff Ameedeen (Universiti Malaysia Pahang), Muhamad Idaham Umar Ong (Universiti Malaysia Pahang), Azlee Zabidi (Universiti Malaysia Pahang) | ||
| 12:45-13:00 | Robust Image Watermarking using Hessenberg Decomposition and SVD with Integer Wavelet Transform (Paper ID: 143) | |
| Presenter: Ferda Ernawan - Bio | ||
| Ahmad Hisyam (Faculty of Computing Universiti Malaysia Pahang Pekan), Ferda Ernawan (Faculty of Computing Universiti Malaysia Pahang Pekan), Prajanto Wahyu Adi (Faculty of Science and Mathematics Universitas Diponegoro), Zuriani Mustaffa (Faculty of Computing Universiti Malaysia Pahang Pekan), Mohd Faizal Ab Razak (Faculty of Computing Universiti Malaysia Pahang Pekan) | ||
| Session II-A (14:00 - 16:00 @ Pandan Room) | ||
| Session Chair: AZMA BINTI ABDULLAH | ||
| 14:00-14:15 | PERFORMANCE EVALUATION OF DETECTION MECHANISMS TOWARDS THE SLOW DDOS ATTACK OF EDGE COMPUTING (Paper ID: 8) | |
| Presenter: Leau Yu Beng - Bio | ||
| Yu Beng Leau (Universiti Malaysia Sabah), Xue Yi Lee (Universiti Malaysia Sabah) | ||
| 14:15-14:30 | Customizing of ERP In Microservice SaaS Architecture: An Overview of Intrusive & Non-intrusive Approach (Paper ID: 47) | |
| Presenter: Ding Ying Hong - Bio | ||
| Ying Hong Ding (Tunku Abdul Rahman University of Management and Technology), Kwee Teck See (Tunku Abdul Rahman University of Management and Technology), Tong Ming Lim (Tunku Abdul Rahman University of Management and Technology), Hoong Jack Chang (Tunku Abdul Rahman University of Management and Technology) | ||
| 14:30-14:45 | High Performance Business Intelligence Dashboard (Paper ID: 56) | |
| Presenter: Harvindran Chandrasekaran - Bio | ||
| Harvindran Chandrasekaran (Intel Technology Sdn. Bhd), Yu Xuan Tan (Intel Technology Sdn. Bhd), Kok Mang Tang (Intel Technology Sdn. Bhd) | ||
| 14:45-15:00 | Exploring Cryptographic Techniques for Data security in Resource-Constrained Wireless Sensor Networks:Performance Evaluation and Considerations (Paper ID: 66) | |
| Presenter: Dharshika Singarathnam - Bio | ||
| Video Link: https://youtu.be/wHDQ3OnwmCw | ||
| Dharshika Singarathnam (York St John University), Swathi Ganesan (York St John University), Sangita Pokhrel (York St John University), Nalinda Somasiri (York St John University) | ||
| 15:00-15:15 | Effects of the GDPR in South East Asia vs. Europe - A Large-scale Analysis of IoT Devices (Paper ID: 70) | |
| Presenter: Frank Ebbers - Bio | ||
| Frank Ebbers (Fraunhofer Institute for Systems and Innovation Research ISI) | ||
| 15:15-15:30 | User Stories in Requirements Elicitation: A Systematic Literature Review (Paper ID: 79) | |
| Presenter: Yanche Ari Kustiawan - Bio | ||
| Yanche Ari Kustiawan (Multimedia University), Tek Yong Lim (Multimedia University) | ||
| 15:30-15:45 | Effective Visualization Electrification System via PSCADA Event Log in Railway Industry (Paper ID: 82) | |
| Presenter: Syamsul Azrin Bin Kamaruddin - Bio | ||
| Syamsul Azrin Kamaruddin (Universiti Tun Hussein Onn Malaysia (UTHM)), Ts. Dr. Hairulazwan Hashim (Universiti Tun Hussein Onn Malaysia (UTHM)), Prof. Madya Ts. Dr. Elmy Johana Mohamad (Universiti Tun Hussein Onn Malaysia (UTHM)), Nazwa Hidayah Mohamad (Pestech Technology Sdn Bhd), Halim Mamat (Department of Electrification, Keretapi Tanah Melayu Berhad) | ||
| 15:45-16:00 | Safety Property Attributes in Critical Systems for Requirement Specification: A Review (Paper ID: 144) | |
| Presenter: Azma Binti Abdullah - Bio | ||
| Azma Abdullah (Faculty of Computing University Malaysia Pahang Al-Sultan Abdullah (UMPSA) Pahang), Rohani Abu Bakar (Faculty of Computing University Malaysia Pahang Al-Sultan Abdullah (UMPSA) Pahang), Kiriyadhatshini Gunaratnam (Faculty of Computing University Malaysia Pahang Al-Sultan Abdullah (UMPSA) Pahang), Fadhl Hujainah (Volvo Car Corporation), Mohd Fairus Abdul Farid (Malaysia Nuclear Agency) | ||
| Session II-C (14:00 - 16:00 @ Lada Room) | ||
| Session Chair: CHANG HOONG JACK | ||
| 14:00-14:15 | An Ensemble-Based Framework to Estimate Software Project Effort (Paper ID: 29) | |
| Presenter: Mohammad Haris - Bio | ||
| Mohammad Haris (Multimedia University), Fang-fang Chua (Multimedia University), Amy Hui-lan Lim (Multimedia University) | ||
| 14:15-14:30 | A Systematic Literature Review on Solutions of Mutation Testing Problems (Paper ID: 32) | |
| Presenter: Loh Zheung Yik - Bio | ||
| Zheung Yik Loh (Faculty of Computing, Universiti Teknologi Malaysia), Wan Mohd Nasir Wan Kadir (Faculty of Computing, Universiti Teknologi Malaysia), Noraini Ibrahim (Faculty of Computing, Universiti Teknologi Malaysia) | ||
| 14:30-14:45 | Security Requirements Assurance: An Assurance Case Perspective (Paper ID: 35) | |
| Presenter: Aftab Alam Janisar - Bio | ||
| Aftab Alam Janisar (Department of computer and information science Universiti Teknologi Petronas 32610 Seri Iskandar Perak, Malaysia.), Khairul Shafee Bin Kalid (Department of computer and information science Universiti Teknologi Petronas 32610 Seri Iskandar Perak, Malaysia.), Aliza Bt Sarlan (Department of computer and information science Universiti Teknologi Petronas 32610 Seri Iskandar Perak, Malaysia.) | ||
| 14:45-15:00 | Parking Space Detection in Different Weather Conditions Based on YOLOv5 Method (Paper ID: 38) | |
| Presenter: Misbachul Falach Asy'ari - Bio | ||
| Misbachul Falach Asy'ari (Department of Informatics, Institut Teknologi Sepuluh Nopember), Chastine Fatichah (Department of Informatics, Institut Teknologi Sepuluh Nopember), Nanik Suciati (Department of Informatics, Institut Teknologi Sepuluh Nopember) | ||
| 15:00-15:15 | Comparative Analysis of Convnext and Mobilenet on Traffic Vehicle Detection (Paper ID: 39) | |
| Presenter: Yusuf Gladiensyah Bihanda - Bio | ||
| Yusuf Gladiensyah Bihanda (Institut Teknologi Sepuluh Nopember), Chastine Fatichah (Institut Teknologi Sepuluh Nopember), Anny Yuniarti (Institut Teknologi Sepuluh Nopember) | ||
| 15:15-15:30 | An Overview Analysis of Authentication Mechanism in Microservices-based Software Architecture: A Discussion Paper (Paper ID: 46) | |
| Presenter: Chang Hoong Jack - Bio | ||
| Hoong Jack Chang (Tunku Abdul Rahman University of Management and Technology), Kwee Teck See (Tunku Abdul Rahman University of Management and Technology), Tong Ming Lim (Tunku Abdul Rahman University of Management and Technology), Ying Hong Ding (Tunku Abdul Rahman University of Management and Technology) | ||
| 15:30-15:45 | Monocular Camera Free Region Detection Method of Obstacle Avoidance for Micro - Sized UAV (Paper ID: 78) | |
| Presenter: Muhamad Wafi Bin Abdul Aziz - Bio | ||
| Muhamad Wafi Bin Abdul Aziz (Universiti Tun Hussein Onn Malaysia), Muhammad Faiz Bin Ramli (Universiti Tun Hussein Onn Malaysia) | ||
| 15:45-16:00 | SODIBOT: A TWO in ONE Real-Time Human Monitoring System using YOLO algorithms (Paper ID: 116) | |
| Presenter: Azim Zaliha Binti Abd Aziz - Bio | ||
| Azim Zaliha Abd Aziz (Universiti Sultan Zainal Abidin), Nurul Nadzirah Adnan (Universiti Sultan Zainal Abidin), Nur Farraliza Mansor (Universiti Sultan Zainal Abidin), Wan Suryani Wan Awang (Universiti Sultan Zainal Abidin), Ida Nurhaida (Universitas Pembangunan Jaya), Safitri Jaya (Universitas Pembangunan Jaya) | ||
| Session II-B (14:00 - 16:00 @ Halia Room) | ||
| Session Chair: MUHAMAD IDAHAM BIN UMAR ONG | ||
| 14:00-14:15 | A Meta-Requirement Approach to Validate User Requirement Specification: Threshold Definition (Paper ID: 6) | |
| Presenter: Muhamad Idaham Umar Ong - Bio | ||
| Muhamad Idaham Umar Ong (Universiti Malaysia Pahang), Mohamed Ariff Ameedeen (Universiti Malaysia Pahang) | ||
| 14:15-14:30 | A Visualized Hybrid Keyword-cluster Approach for Extractive Text Summarizer Tool for STEM Education in Malaysia (Paper ID: 49) | |
| Presenter: Suraya Alias - Bio | ||
| Suraya Alias (UMS), Mazliah Majalin (UMS), Nur Hayatin Nur Hayatin (UMS) | ||
| 14:30-14:45 | Phishing Website Detection Technique Using Machine Learning (Paper ID: 84) | |
| Presenter: Mohd Faizal Ab Razak - Bio | ||
| Nurul Amira Mohd Zin (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Mohd Faizal Ab Razak (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Ahmad Firdaus (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Ferda Ernawan (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Nor Saradatul Akmar Zulkifli (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,) | ||
| 14:45-15:00 | Enhancing Chiller Plant Modelling Performance Through NARX-Based Feature Optimization (Paper ID: 106) | |
| Presenter: Azlee Bin Zabidi - Bio | ||
| Azlee Zabidi (Universiti Malaysia Pahang Al-Sultan Abdullah), Mohd Izham Mohd Jaya (Universiti Malaysia Pahang Al-Sultan Abdullah), Hasliza Abu Hassan (Universiti Industri Selangor), Ahmad Ihsan Mohd Yassin (Universiti teknologi Mara) | ||
| 15:00-15:15 | A New SVM-STEG Embedding Model In Steganography (Paper ID: 114) | |
| Presenter: Hanizan Hussain - Bio | ||
| Hanizan Shaker Hussain (Quest International University), Fazali Ghazali (Universiti Islam Antarabangsa Sultan Abdul Halim Mu'adzam Shah), Hafiza Abdul Samad (Universiti Poly-Tech Malaysia, Malaysia), Hanif Mohd Ali (Universiti Islam Antarabangsa Sultan Abdul Halim Mu'adzam Shah), Anbuselvan Sangodiah (Quest International University), Kante Koli Oumar (Quest International University) | ||
| 15:15-15:30 | A Comparative Analysis on Three Duplication Elements in Copy-Move Forgery Using PatchMatch-based Detection Method (Paper ID: 119) | |
| Presenter: Nor Bakiah Abd Warif - Bio | ||
| Nur Izzati Nor Azaimi (Universiti Tun Hussein Onn Malaysia), Nor Bakiah Abd Warif (Universiti Tun Hussein Onn Malaysia), Nor-syahidatul N Ismail (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| 15:30-15:45 | Designing an E-voting Framework Using Blockchain: A Secure and Transparent Approach (Paper ID: 121) | |
| Presenter: Syarifah Bahiyah Rahayu - Bio | ||
| Syarifah Bahiyah Rahayu (Universiti Pertahanan Nasional Malaysia), Andrianto Arfan Wardhana (Microsoft Indonesia), Moon-gul Lee (Korea National Defense University) | ||
| 15:45-16:00 | A Survey on Supervised Machine Learning in Intrusion Detection Systems for Internet of Things (Paper ID: 131) | |
| Presenter: Shakirah Binti Saidin - Bio | ||
| Shakirah Saidin (Universiti Malaysia Pahang Al-Sultan Abdullah), Syifak Izhar Hisham (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| 16:00-16:15 | CHARITY AND DONATION TRACKING SYSTEM USING QUEUE STRUCTURE (Paper ID: 141) | |
| Presenter: Manea Abdullah - Bio | ||
| Manea Abdullah Badheyba (Faculty of Computer Science Universiti Malaysia Pahang Al-Sultan Abdullah), Ldr. Rozlina Bt Mohamed (Faculty of Computer Science Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| Session II-D (Virtual) (14:00 - 16:00 @ Online) | ||
| Session Chair: TBA | ||
| 14:00-14:15 | Real-Time Data Visualization and Analysis using ASP.NET Core's Tag Helpers in Business Intelligence Applications (Paper ID: 30) | |
| Presenter: Safaa Bataieneh - Bio | ||
| Video Link: https://youtu.be/JCAFvH6D82E | ||
| Safa'a Bataieneh (Philadelphia University), Samer Hanna (Philadelphia University) | ||
| 14:15-14:30 | A Supervised Machine Learning Method for Predicting the Employees Turnover Decisions (Paper ID: 44) | |
| Presenter: Trirat Arromrit - Bio | ||
| Video Link: https://youtu.be/6Zx1blyevaA | ||
| Trirat Arromrit (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy), Korrapin Srisakaew (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy), Napatsakorn Roswhan (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy), Wiriya Mahikul (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy) | ||
| 14:30-14:45 | Analysis of Sentiment Towards Artificial Intelligent Industry Using Hybrid Natural Language Processing Technique (Paper ID: 120) | |
| Presenter: Hong Chang - Bio | ||
| Video Link: https://youtu.be/lHrLFiV3dZ8 | ||
| Chang Hong (Xiamen University Malaysia) | ||
| 14:45-15:00 | Optimized Energy Distribution in Smart Grid System Using Hybrid Machine Learning Techniques (Paper ID: 122) | |
| Presenter: Ding Daorui - Bio | ||
| Video Link: https://youtu.be/cUuuxdfL6H4 | ||
| Daorui Ding (Xiamen University Malaysia), Chang Hong (Xiamen University Malaysia), Venkata Durga Kumar Burra (Xiamen University Malaysia) | ||
| 15:00-15:15 | EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification (Paper ID: 134) | |
| Presenter: Emam Hasan - Bio | ||
| Video Link: https://www.youtube.com/watch?v=ttFtoSR89tw | ||
| Niful Islam (Department of Computer Science and Engineering, United International University), Md. Mehedi Hasan Jony (Department of Computer Science and Engineering, United International University), Emam Hasan (Department of Computer Science and Engineering, United International University), Sunny Sutradhar (Department of Computer Science and Engineering, United International University), Atikur Rahman (Department of Computer Science and Engineering, United International University), Md. Motaharul Islam (Department of Computer Science and Engineering, United International University) | ||
| 15:15-15:30 | Improving Data Security in IoT Cloud Computing via Compiler-Supported Homomorphic and Symmetric Encryption Techniques (Paper ID: 136) | |
| Presenter: Huang - Bio | ||
| Video Link: https://youtu.be/CHh5T9fneyg | ||
| Jingjia Huang (Xiamen University Malaysia Sepang, Malaysia), Xincheng Huang (Xiamen University Malaysia Sepang, Malaysia) | ||
| 15:30-15:45 | A Comprehensive Approach to Mitigate Return-Oriented Programming Attacks: Combining Operating System Protection Mechanisms and Hardware-Assisted Techniques (Paper ID: 137) | |
| Presenter: Zhang Xingnan - Bio | ||
| Video Link: https://youtu.be/vxPyE9IsqdI | ||
| Xingnan Zhang (Program in Computer Science & Technology, Xiamen University Malaysia), Jingjia Huang (Program in Computer Science & Technology, Xiamen University Malaysia), Yue Feng (Program in Computer Science & Technology, Xiamen University Malaysia) | ||
| 15:45-16:00 | Enhancing Subcluster Identification in IoT Sensor Networks with Hierarchical Clustering Algorithms and Dendrograms (Paper ID: 140) | |
| Presenter: Fuad Bajaber - Bio | ||
| Video Link: https://youtu.be/PpL9hNrst0c | ||
| Fuad Bajaber (King Abdulaziz University) | ||
| Date: 2023-08-27 | ||
| Session III-A (08:30 - 10:00 @ Pandan Room) | ||
| Session Chair: SHAZWANI BINTI KAMARUDIN | ||
| 08:30-08:45 | Fintech future business & Cyber vulnerabilities and challenges (Paper ID: 5) | |
| Presenter: Ts Dr Venkata Venugopal Rao Gudlur - Bio | ||
| Dr Venkata Venugopal Rao Gudlur (Veritas University College) | ||
| 08:45-9:00 | PREDICTING MENTAL HEALTH DISORDER ON TWITTER USING MACHINE LEARNING TECHNIQUES (Paper ID: 12) | |
| Presenter: Nur Shazwani Kamarudin - Bio | ||
| Shi Ru Lim (UNIVERSITI MALAYSIA PAHANG), Nur Shazwani Binti Kamarudin (UNIVERSITI MALAYSIA PAHANG), Nur Hafieza Binti Ismail (UNIVERSITI MALAYSIA PAHANG), Nik Ahmad Hisham Ismail (INTERNATION ISLAMIC UNIVERSITY MALAYSIA), Nor Ashikin Mohamad Kamal (UNIVERSITI TEKNOLOGI MARA) | ||
| 9:00-9:15 | Metaverse in Education: Insights from South Korea and Potentials for Malaysia (Paper ID: 36) | |
| Presenter: Najihah Binti Nasir - Bio | ||
| Najihah Binti Nasir (Jeju National University), Jiyong Moon (Jeju National University), Seong Baeg Kim (Jeju National University) | ||
| 9:15-9:30 | RSSI-Guided Cluster Head Selection for Optimal Optimization in IoT-Enabled WSNs (Paper ID: 72) | |
| Presenter: Azamuddin Bin Ab. Rahman - Bio | ||
| Azamuddin Ab. Rahman (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| 9:30-9:45 | Knowledge of the Utilization of Telegram for Learning Among Primary Students in Kuantan (Paper ID: 146) | |
| Presenter: Noor Azida Binti Sahabudin - Bio | ||
| Saadiah Awang Salim (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Noor Azida Sahabudin (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Gausallyaa Murugiah (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Nur Shamsiah Abdul Rahman (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Norhasyimah Hamzah (Department of Vocational Education Faculty of Technical and Vocational Education Universiti Tun Hussein Onn Malaysia) | ||
| Session III-B (08:30 - 10:00 @ Halia Room) | ||
| Session Chair: MOHD IZHAM BIN MOHD JAYA | ||
| 08:30-08:45 | Real-time Fault Diagnostic in Rotating Shaft using IoT-based Architecture and Fuzzy Logic Analysis (Paper ID: 86) | |
| Presenter: Mohd Izham Mohd Jaya - Bio | ||
| Nur Afiqah Mohd Azman (Universiti Malaysia Pahang), M. Izham Jaya (Universiti Malaysia Pahang), Azlee Zabidi (Universiti Malaysia Pahang) | ||
| 08:45-9:00 | SAISMS: Transforming Ammunition Management Through IoT-Enabled Inventory and Safety Monitoring System (Paper ID: 88) | |
| Presenter: Mohammad Faris Bin Mahdir - Bio | ||
| Mohammad Faris Bin Mahdhir (UNIVERSITI MALAYSIA PAHANG), Nor Saradatul Akmar Binti Zulkifli (UNIVERSITI MALAYSIA PAHANG), Mohd Zamri Bin Osman (UNIVERSITI MALAYSIA PAHANG), Azlee Bin Zabidi (UNIVERSITI MALAYSIA PAHANG), Mohd Izham Bin Mohd Jaya (UNIVERSITI MALAYSIA PAHANG) | ||
| 9:00-9:15 | Exploring Machine Learning in IoT Smart Home Automation (Paper ID: 90) | |
| Presenter: Quadri Waseem - Bio | ||
| Quadri Waseem (Universiti Malaysia Pahang; AnalytiCray), Wan Isni Sofiah Wan Din (Universiti Malaysia Pahang), Azamuddin Bin Ab Rahman (Universiti Malaysia Pahang), Kashif Nisar (Swinburne University of Technology, Sydney) | ||
| 9:15-9:30 | Examining the Correlations Between Teacher Profiling, ICT Skills, and the Readiness of Integrating Augmented Reality in Education (Paper ID: 105) | |
| Presenter: Danakorn Nincarean Eh Phon - Bio | ||
| Azrie Salleh (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Danakorn Nincarean Eh Phon (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Nur Shamsiah Abdul Rahman (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Suhaizal Hashim (Universiti Tun Hussien Onn Malaysia), Noor Hidayah Che Lah (Faculty of Computing & Meta Technology, Universiti Pendidikan Sultan Idris) | ||
| 9:30-9:45 | Factors Affecting Cyber Bullying Behaviours Among University Students: A review on Conceptual Framework (Paper ID: 115) | |
| Presenter: Nur Shamsiah Abdul Rahman - Bio | ||
| Nur Shamsiah Abdul Rahman (Universiti Malaysia Pahang Al-Sultan Abdullah), Noor Azida Sahabudin (Universiti Malaysia Pahang Al-Sultan Abdullah), Danakorn Nincarean Eh Phon (Universiti Malaysia Pahang Al-Sultan Abdullah), Mohd Faizal Ab Razak (Universiti Malaysia Pahang Al-Sultan Abdullah), Anis Farihan Mat Raffei (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| Session IV-A (10:15 - 12:45 @ Pandan Room) | ||
| Session Chair: SALWANA BINTI MOHAMAD @ ASMARA | ||
| 10:15-10:30 | chatGPT vs Mentor : Programming Language Learning Assistance System for Beginners (Paper ID: 40) | |
| Presenter: Junseong Moon - Bio | ||
| Junseong Moon (Jeju National University), Raeeun Yang (Jeju National University), Somin Cha (Jeju National University), Seong Baeg Kim (Jeju National University) | ||
| 10:30-10:45 | SDN enabled Big Data Analytics and Framework for sensor data of Vehicle Health, Safety and Monitoring System (Paper ID: 43) | |
| Presenter: Mohammad Sojon Beg - Bio | ||
| Tanvir Ahmad (University Malaysia Pahang (UMP)), Nor Syahidatul Nadiah Binti Ismail (University Malaysia Pahang (UMP)), Abdullah Mat Safri (University Malaysia Pahang (UMP)), Md Arafatur Rahman (University of Wolverhampton), Mohammad Sojon Beg (University Malaysia Pahang (UMP)), M. Taher Bin Bakhtiar (International Islamic University Malaysia (IIUM)) | ||
| 10:45-11:00 | Cloud of Word vs DroidKungfu: Performance Evaluation in Detecting Root Exploit Malware with Deep Learning Approach (Paper ID: 80) | |
| Presenter: Che Akmal Che Yahaya - Bio | ||
| Che Akmal Che Yahaya (Tunku Abdul Rahman University of Management and Technology), Ahmad Firdaus Zainal Abidin (Universiti Malaysia Pahang), Mohd Azlee Zabidi (Universiti Malaysia Pahang), Noor Akma Abu Bakar (Universiti Malaysia Pahang), Mukrimah Nawir (Tunku Abdul Rahman University of Management and Technology), Philimal Normelissa Ani Abdul Malek (Tunku Abdul Rahman University of Management and Technology) | ||
| 11:00-11:15 | Product Recommendation using Deep Learning in Computer Vision (Paper ID: 92) | |
| Presenter: Zuriani Mustaffa - Bio | ||
| Zuriani Mustaffa (Universiti Malaysia Pahang), Sharvinteraan A/l C. Mogan (Universiti Malaysia Pahang), Mohd Herwan Sulaiman (Universiti Malaysia Pahang), Ferda Ernawan (Universiti Malaysia Pahang) | ||
| 11:15-11:30 | Determining the Best Weightage Feature in Parameterization Process of GCCD Model for Clone Detection In C-based Applications (Paper ID: 99) | |
| Presenter: Al-fahim Mubarak Ali - Bio | ||
| Nurul Syafiqah Zaidi (Universiti Malaysia Pahang), Al-fahim Mubarak-ali (Universiti Malaysia Pahang), Abdul Sahli Fakharudin (Universiti Malaysia Pahang), Rahiwan Nazar Romli (Universiti Malaysia Pahang) | ||
| 11:30-11:45 | Taxonomy of SQL Injection: ML Trends & Open Challenges (Paper ID: 123) | |
| Presenter: Raed Abdullah Abobakr Busaeed - Bio | ||
| Raed Abdullah Abobakr Busaeed (University Malaysia Pahang AL-Sultan Abdullah), Wan Isni Sofiah Wan Din Wan Din (University Malaysia Pahang AL-Sultan Abdullah), Quadri Waseem Waseem (University Malaysia Pahang AL-Sultan Abdullah), Azlee Bin Zabidi (University Malaysia Pahang AL-Sultan Abdullah) | ||
| 11:45-12:00 | Identifying PTSD Symptoms using Machine Learning Techniques on Social Media (Paper ID: 125) | |
| Presenter: Nur Hafieza Ismail - Bio | ||
| Muhamad Aiman Ibrahim (University Malaysia Pahang Al-Sultan Abdullah), Nur Hafieza Ismail (University Malaysia Pahang Al-Sultan Abdullah), Nur Shazwani Kamarudin (University Malaysia Pahang Al-Sultan Abdullah), Nur Syafiqah Mohd Nafis (University Malaysia Pahang Al-Sultan Abdullah), Ahmad Fakhri Ab. Nasir (University Malaysia Pahang Al-Sultan Abdullah) | ||
| 12:00-12:15 | Development of Light Energy Harvesting for Wearable IoT (Paper ID: 128) | |
| Presenter: Micheal Drieberg - Bio | ||
| Eisyah Hanun Zawawi (Universiti Teknologi PETRONAS), Micheal Drieberg (Universiti Teknologi PETRONAS), Azrina Abd Aziz (Universiti Teknologi PETRONAS), Patrick Sebastian (Universiti Teknologi PETRONAS), Hai Hiung Lo (Universiti Teknologi PETRONAS) | ||
| 12:15-12:30 | A Review of Knowledge Graph Embedding Methods of TransE, TransH and TransR for Missing Links (Paper ID: 142) | |
| Presenter: Salwana Mohamad @ Asmara - Bio | ||
| Salwana Mohamad @ Asmara (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang,), Noor Azida Sahabudin (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang,), Nor Syahidatul Nadiah Ismail (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang,), Ily Amalina Ahmad Sabri (Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu) | ||
| 12:30-12:45 | AN AUTOMATED STRABISMUS CLASSIFICATION USING MACHINE LEARNING ALGORITHM FOR BINOCULAR VISION MANAGEMENT SYSTEM (Paper ID: 145) | |
| Presenter: Anis Farihan Mat Raffei - Bio | ||
| Muhammad Amirul Isyraf Rohismadi (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Anis Farihan Mat Raffei (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Nor Saradatul Akmar Zulkifli (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Mohd. Hafidz Ithnin (Kulliyah of Medicine, International Islamic University Malaysia, Pahang), Shah Farez Othman (Kulliyah of Medicine, International Islamic University Malaysia, Pahang) | ||
| Session IV-B (10:15 - 12:45 @ Halia Room) | ||
| Session Chair: NURUL IZZATI | ||
| 10:15-10:30 | COVID-19 FAKE NEWS DETECTION MODEL ON SOCIAL MEDIA DATA USING MACHINE LEARNING TECHNIQUES (Paper ID: 13) | |
| Presenter: Nur Shazwani Kamarudin - Bio | ||
| Kai Xuan Kelvin Liew (UNIVERSITI MALAYSIA PAHANG), Mohaiminul Islam Bhuiyan (UNIVERSITI MALAYSIA PAHANG), Nur Shazwani Kamarudin (UNIVERSITI MALAYSIA PAHANG), Ahmad Fakhri Ab. Nasir (UNIVERSITI MALAYSIA PAHANG), Muhammad Zulfahmi Toh Abdullah (UNIVERSITI MALAYSIA PAHANG) | ||
| 10:30-10:45 | Feature Selection Using Law of Total Variance with Fast Correlation-Based Filter (Paper ID: 14) | |
| Presenter: Azlyna Senawi - Bio | ||
| Azlyna Senawi (Universiti Malaysia Pahang), Nur Atiqah Mustapa (Universiti Malaysia Pahang), Zun Liang Chuan (Universiti Malaysia Pahang) | ||
| 10:45-11:00 | Hand Calibration with Limited Data As The Initial Step Towards System Dynamics Model Validation For The COVID-19 Case In Malaysia. (Paper ID: 77) | |
| Presenter: Aisyah Ibrahim - Bio | ||
| Aisyah Ibrahim (Faculty of Computing, Universiti Malaysia Pahang, Al-Sultan Abdullah, Malaysia), Tuty Asmawaty Abdul Kadir (Faculty of Computing, Universiti Malaysia Al-Sultan Abdullah Pahang, Malaysia), Roderick H. Macdonald (School of Integrated Sciences, James Madison University, Virginia), Hamdan Daniyal (Faculty of Electrical and Electronic Engineering Technology, Universiti Malaysia Pahang, Malaysia) | ||
| 11:00-11:15 | AI-Generated CT Scan Image for Improving Colorectal Cancer Classification (Paper ID: 102) | |
| Presenter: Syafie Bin Nizam - Bio | ||
| Syafie Nizam (Department of Physics, Kulliyyah of Science, IIUM), Mohd Adli Md Ali (Department of Physics, Kulliyyah of Science, IIUM), Mohd Radhwan Abidin (Department of Radiology, Kulliyyah of Medicine, IIUM) | ||
| 11:15-11:30 | Loan Eligibility Classification Using Logistic Regression (Paper ID: 112) | |
| Presenter: Mohd Arfian Ismail - Bio | ||
| Paul Law Lik Pao (Universiti Malaysia Pahang), Mohd Arfian Ismail (Universiti Malaysia Pahang) | ||
| 11:30-11:45 | Implementation of Serious Games for Data Privacy and Protection Awareness in Cybersecurity (Paper ID: 113) | |
| Presenter: Siti Normaziah Ihsan - Bio | ||
| Siti Normaziah Ihsan (UMP), Tuty Asmawaty Abd Kadir (UMP), Nurul Ishafira Binti Ismail (Universiti Malaysia Pahang), Kerk Zhi Yuan (Teleperformance Malaysia), Yeow Song Jie (SIM IT SDN BHD) | ||
| 11:45-12:00 | CAGDEEP: Mobile Malware Analysis Using Force Atlas 2 with Strong Gravity and Deep Learning (Paper ID: 127) | |
| Presenter: Nur Khairani Kamarudin - Bio | ||
| Video Link: https://youtu.be/mHKTMj4yfqE | ||
| Nur Khairani Kamarudin (Universiti Malaysia Pahang), Ahmad Firdaus (Universiti Malaysia Pahang), Azlee Zabidi (Universiti Malaysia Pahang), Mohd Faizal Ab Razak (Universiti Malaysia Pahang) | ||
| 12:00-12:15 | Inertia Weight Strategies in GbLN-PSO for Optimum Solution (Paper ID: 132) | |
| Presenter: Nurul Izzatie Husna - Bio | ||
| Nurul Izzatie Husna Fauzi (Universiti Malaysia Pahang), Zalili Musa (Universiti Malaysia Pahang) | ||
| 12:15-12:30 | A New Approach of Midrange Exploration Exploitation Searching Particle Swarm Optimization for Optimal Solution (Paper ID: 133) | |
| Presenter: Nurul Izzatie Husna - Bio | ||
| Nurul Izzatie Husna Fauzi (Universiti Malaysia Pahang), Zalili Musa (Universiti Malaysia Pahang) | ||
| 12:30-12:45 | Review on Serious-Education Games for Slow Learners (Paper ID: 135) | |
| Presenter: Siti Nuraishah Binti Nazri - Bio | ||
| Siti Nuraishah Binti Nazri (Universiti Malaysia Pahang Al-Sultan Abdullah), Tuty Asmawaty Binti Abdul Kadir (Universiti Malaysia Pahang Al-Sultan Abdullah), Siti Normaziah Binti Ihsan (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| Session IV-C (Virtual) (10:15 - 12:45 @ Online) | ||
| Session Chair: TBA | ||
| 10:15-10:30 | Determining the Optimal Number of GAT and GCN Layers for Node Classification in Graph Neural Networks (Paper ID: 42) | |
| Presenter: Humaira Noor - Bio | ||
| Video Link: https://www.youtube.com/watch?v=MRGMYQnvchQ | ||
| Humaira Noor (United International University), Niful Islam (United International University), Md. Saddam Hossain Mukta (United International University), Nur Shazwani Binti Kamarudin (Universiti Malaysia Pahang), Mohaimenul Azam Khan Raiaan (United International University), Sami Azam (Charles Darwin University) | ||
| 10:30-10:45 | Design and Implementation of a LCDP with Enhanced Functionality (Paper ID: 53) | |
| Presenter: Rattakorn Poonsuph - Bio | ||
| Video Link: https://www.youtube.com/watch?v=rZZIFkw0mfk | ||
| Rattakorn Poonsuph (Graduated School of Applied Statistics) | ||
| 10:45-11:00 | Emotional Analysis Based On LSTM-CNN Hybrid Neural Network Model (Paper ID: 107) | |
| Presenter: Wu You - Bio | ||
| Video Link: https://youtu.be/rkfd0ZrB5nI | ||
| You Wu (Xiamen University Malaysia), Muataz Al-daweri (University of Nizwa), Venkata Durga Kumar Burra (Xiamen University Malaysia) | ||
| Date: 2023-08-26 | ||
| Session I-A (11:15 - 13:00 @ Pandan Room) | ||
| Session Chair: ANIS FARIHAN BINTI MAT RAFFEI | ||
| 11. Project Cost’s Early Warning Analysis via Microsoft Power BI (Business Intelligence) | ||
| Farah Aini Amin Nordin (PETRONAS) | ||
| This paper aims to briefly explain the development and application of project cost’s early warning indicator for data and performance analytics via Microsoft Power BI. This Microsoft Power BI acts as both the visualization and analysis platform. It will also briefly discuss the typical analysis being done using these indicators and how that can assist towards better cost control performance in project delivery. | ||
| 27. Recognition Textual Entailment on Bahasa using Biplet Individual Comparison and BiLSTM | ||
| I Made Suwija Putra (Department of Informatics, Institut Teknologi Sepuluh Nopember Surabaya), Daniel Siahaan (Department of Informatics, Institut Teknologi Sepuluh Nopember Surabaya), Ahmad Saikhu (Department of Informatics, Institut Teknologi Sepuluh Nopember Surabaya) | ||
| Recognizing Textual Entailment (RTE) is one of the important tasks in Natural Language Processing (NLP). Various approaches have been taken, starting from a simple statistical framework to the neural network (NN) that is currently the mainstay, including RTE in Bahasa Indonesia. Currently, RTE in Bahasa Indonesia has started using the neural network approach, but the value of the resulting accuracy is still less than 77%. This is because the new NN architecture has just accommodated the lexical elements and not yet the syntactical elements of sentences. Syntactical elements in sentences are important components in obtaining the local information contained therein. In RTE, local information is useful for determining how closely related text fragments are. This study proposes a new approach to NN-based Bahasa Indonesia RTE using the Biplet (head-dependency) individual comparison technique. Biplet is generated from the process of word pair dependency. The concept of word pair dependency is used to improve alignment and inference assessment that is optimized by adjusting the weight of the phrase using an attention mechanism. From experiments conducted using the SNLI dataset that has been translated into Bahasa Indonesia (SNLI Indo), it was obtained that the highest training accuracy value is 83.56% with the validation accuracy value is 64.61% for the number of pairs of sentences of 100k. | ||
| 31. Improving Sarcasm Detection in Mash-Up Language Through Hybrid Pretrained Word Embedding | ||
| Mochamad Alfan Rosid (Institut Teknologi Sepuluh Nopember Surabaya), Daniel Siahaan (Institut Teknologi Sepuluh Nopember Surabaya), Ahmad Saikhu (Institut Teknologi Sepuluh Nopember Surabaya) | ||
| Sarcasm detection is an imperative undertaking within the realm of natural language processing, albeit one that poses considerable challenges when confronted with mash-up languages, characterized by the amalgamation of multiple distinct languages. In response to the intricacies of sarcasm detection in mash-up languages, with a specific focus on the Indonesian-English language mash-up, this study introduces the Hybrid Pretrained Word Embedding approach as a means to enhance sarcasm detection. The primary objective of this research is to augment the precision of sarcasm detection in mash-up languages by amalgamating suitable word embeddings tailored to the employed terms. The present study combines two prevalent pre-trained word embeddings, i.e. Glove and Fasttext, wherein Glove is utilized to extract semantic context vectors for English words. At the same time, Fasttext is employed to extract semantic context vectors for Indonesian words. The classification process in this research leverages the deep learning methodology known as Bidirectional Gated Recurrent Unit (BiGRU). To assess the efficacy of the proposed approach, an extensive dataset comprising sarcastic and non-sarcastic tweets, written in a hybrid language of Indonesian and English, is acquired from the Twitter platform. The results unequivocally demonstrate that the Hybrid Pretrained Word Embedding approach significantly enhances sarcasm detection in mash-up languages, attaining a commendable classification accuracy of 93.57% and an F-measure of 97.94%. By offering an effective methodology to identify sarcasm in mash-up languages, this study yields a substantive contribution to natural language processing. | ||
| 33. Text Segmentation Methods for Annotation on eHealth Consultation with Interview Function Labels: A Comparative Study | ||
| Yunianita Rahmawati (Institut Teknologi Sepuluh Nopember), Daniel Siahaan (Institut Teknologi Sepuluh Nopember), Diana Purwitasari (Institut Teknologi Sepuluh Nopember) | ||
| There have been several existing text segmentation methods. Nevertheless, no study has provided the experimental result on the performance of those methods in segmenting text of health consultation data based on sentence context and provided automatic annotation on the segmented results in the form of interview function labels. This study compares four methods with different text segmentation approaches and analyzes their performances based on their reliability concerning human expert judgment. The methods are Content Vector Segmentation (CVS), GraphSeg, K-Means, and Latent Dirichlet Allocation (LDA). This study used a greedy similarity approach to perform automatic annotation by selecting candidate labels based on the maximum value. The annotation results were evaluated using Gwet's AC1 method to assess the integrity among evaluators in clinical research. The evaluation results indicate that the CVS method outperforms other methods and has a substantial level of agreement (0.67). It is also relatively stable, with a standard deviation of 0.12. | ||
| 37. An Overview of Part-of-Speech Tagging Methods and Datasets for Malay Language | ||
| Chi Log Chua (Tunku Abdul Rahman University of Management and Technology), Tong Ming Lim (Tunku Abdul Rahman University of Management and Technology), Kwee Teck See (Tunku Abdul Rahman University of Management and Technology) | ||
| The purpose of this review is to summarise the knowledge about Malay Part-of-Speech (POS) training methods and datasets, and to identify its future research directions. A total of ten research papers related to Malay POS model training methods has been reviewed and five datasets were found from online resources. Two major issues were identified – first, all the ten papers reviewed, it was found that dataset used to train Malay POS were not standardized. Second, limited dataset was found from online resources – only five datasets were available, and only three were annotated. This review highlights two directions worth future investigation: how to train a high- performance POS model using only a small amount of annotated data, and how to utilize existing high-performance POS models to reduce the burden of annotating data. | ||
| 54. Investigation on Insurance Purchase Classification for Insurance Recommendation using Deep Learning and Class Propagation | ||
| Jasmin Z. K. Chu (Swinburne University of Technology), Joel C. M. Than (Swinburne University of Technology), Pun Liang Thon (Swinburne University of Technology), Hudyjaya Siswoyo Jo (Swinburne University of Technology) | ||
| A majority of insurers are in the opinion that Artificial Intelligence (AI) has potential to create a better customer experience, improve direction-making and achieve cost savings. One area of interest for AI in insurance is in the area of recommendation of on-demand insurance policies. This automated recommendation can expedite the process of insurance recommendation as it does not involve any agents. This research involves the utilization of insurance dataset, comprising 9422 records and 86 customer features related to social-demographics and insurance purchases. The data is transformed into a graph-based representation using Stellar Graph to capture the interrelationships between features and fit into a Graph Convolutional Network (GCN). Additionally, other AI techniques such as Long Short-term Memory Networks (LSTM), Decision Tree (DT), and Support Vector Machines (SVM) were also considered. To address the issue of imbalanced data in the dataset, various class propagation techniques such as Borderline-SMOTE, Adaptive Synthetic Sampling Approach (ADASYN), and Gaussian Copula were employed with different data size ratio distributions. Overall, GCN performs well with 50:50 ratio distribution in three of the different oversampling techniques, indicating that the graph-based structure and processing algorithm of GCN are suitable for recommendation systems. | ||
| 61. Priority Based Fair Scheduling: Enhancing Efficiency in Cloud Job Distribution | ||
| Saydul Akbar Murad (Universiti Malaysia Pahang Al-Sultan Abdullah), Zafril Rizal M Azmi (Universiti Malaysia Pahang Al-Sultan Abdullah), Faria Jerin Brishti (International Islamic University Chittagong), Md Saib (South China University of Technology), Anupam Kumar Bairagi (Khulna University) | ||
| (Video Link: https://www.youtube.com/watch?v=sEYmue9-NrM) | ||
| In recent years, there has been a growing interest in cloud computing as a means to enhance user access to shared computing resources, including software and hardware, through the internet. However, the efficient utilization of these cloud resources has been a challenge, often resulting in wastage or degraded service performance due to inadequate scheduling. To overcome this challenge, numerous researchers have focused on improving existing Priority Rule (PR) cloud schedulers by developing dynamic scheduling algorithms, but they have fallen short of meeting user satisfaction. In this study, we introduce a new PR scheduler called Priority Based Fair Scheduling (PBFS), which takes into account key parameters such as CPU Time, Job Arrival Time, and Job Length. We evaluate the performance of PBFS by comparing it with five existing algorithms, and the results demonstrate that PBFS surpasses the performance of the other algorithms. The experiment was conducted using the CloudSim simulator, utilizing a dataset of 300 and 400 jobs. In order to assess the performance, three key metrics were employed: flow time, makespan time, and total tardiness. These metrics were chosen to evaluate and analyze the effectiveness of the proposed scheduling algorithm. | ||
| Session I-C (11:15 - 13:00 @ Lada Room) | ||
| Session Chair: SYAHRUL NIZAM JUNAINI | ||
| 58. A Comprehensive Ensemble Deep Learning Method for Identifying Native Advertising in News Articles | ||
| Brian Rizqi Paradisiaca Darnoto (Institut Teknologi Sepuluh Nopember), Daniel Siahaan (Institut Teknologi Sepuluh Nopember), Diana Purwitasari (Institut Teknologi Sepuluh Nopember) | ||
| Native ads are a popular form of online advertisement that has a similar style and function to that of the original content of the platform they are displayed on. There are several problems in the sponsorship disclosure of native ads, namely their positioning, eminence, and lucidity of meaning, causing readers to not recognize them as advertisement. Unlike the selling message of traditional ads that are explicit, the selling message of native ads are implicit. This study aims to carry out the detection of native ads using deep ensemble-based models. The ensemble learning approach is adopted by combining two deep learning models using dense layers. Furthermore, to overcome the overfitting problem, an attention mechanism using a dense layer is implemented within the model. The experimental results show that the BiLSTM-CNN model with attention mechanism and parameter tuning was able to overcome the overfitting problem and achieve the highest accuracy of 95% for the detection of native ads. | ||
| 68. Machine Learning Regression Models for Real-time Touchless Interaction Applications | ||
| Qinyan Gong (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Hadyan Hafizh (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Muhammad Ateeq (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Anwar Pp Abdul Majeed (School of Robotics, Xi'an Jiaotong-Liverpool University), Matilda Isaac (School of Internet of Things, Xi'an Jiaotong-Liverpool University), Bintao Hu (School of Internet of Things, Xi'an Jiaotong-Liverpool University) | ||
| Touchless technologies have gained significant popularity, particularly amidst the COVID-19 pandemic, as they addressed concerns related to germ transmission and hygiene during human-device interactions. This study aimed to develop an intuitive and user-friendly touchless system by combining eye gaze and hand gesture methods. Four regression machine learning models, namely Ridge regression, Lasso regression, Linear regression, and Gradient-boosting regressor, were trained and tested using standard metrics such as coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE). The results indicated that Ridge regression outperformed the other models, demonstrating a high R2 value of 0.98. Leveraging this model, a simulation was conducted to evaluate the effectiveness of integrating eye gaze and hand gestures in real-time touchless interactions. The simulation demonstrated the successful integration of these modalities in the item selection process, providing users with a seamless and intuitive interaction method. This touchless interaction technology enabled effortless and accurate navigation of screens and facilitated item selections. The promising results highlighted the potential of this technology, presenting exciting opportunities for its integration with actuators. By incorporating actuators, touchless interaction systems could revolutionize various industries, including retail, healthcare, hospitality, and smart home automation. | ||
| 83. Shaping the Digital Future of Civil Service: An Assessment of Digital Transformation and Data Science Competencies | ||
| Syahrul Nizam Junaini (Universiti Malaysia Sarawak), Sopian Bujang (Universiti Malaysia Sarawak), Nadri Aetis Basmawi (Leadership Institute of Sarawak Civil Service), Jusmawati Fauzaman (International Islamic University Malaysia) | ||
| In the era of digital transformation and data proliferation, the need for effective digital competency assessment is increasingly critical. However, existing frameworks often lack comprehensive integration of key digital transformation and data science competencies necessary for roles within the civil service sector. This study introduces a robust instrument to profile competency domains critical to digital transformation and data science roles in the civil service. Leveraging a four-phase mixed method methodology, including brainstorming, external validation, and a pilot study, the instrument was developed, validated, and tested among 30 state government servants. The reliability of the domains—Data Analytics, Data Science Management, Data & Digital Architecture, and Digital Transformation—was confirmed by excellent Cronbach’s Alpha values ( 0.9). Content validity was evaluated using Lawshe’s Content Validity Ratio (CVR) and Index (CVI), indicating strong validity for Digital Transformation and Data & Digital Architecture domains, while suggesting refinement for Data Analytics and Data Science Management. The proposed instrument, validated through self-evaluation scores, illustrates potential for career and organizational development within the civil service, emphasizing its practical value and feasibility. | ||
| 101. Deep Learning-based Classification Approach for Wire Bonding Defects Inspection | ||
| Nur Ayuni Mohamed (Infineon Technologies Sdn. Bhd.), Fock Lin Mok (Infineon Technologies Sdn. Bhd.), Qing Zhe Loong (Infineon Technologies Sdn. Bhd.) | ||
| The wire bonding process is one of the most vital processes in semiconductor manufacturing. Therefore, defect detection is needed to ensure the quality of the produced integrated circuits (ICs), in which poor quality wire bonding can prevent it from functioning effectively. An automatic optical inspection (AOI) system is commonly used for defect inspection in fabrication mode. However, the AOI system suffers from a lot of challenges that require human assistance in the event of uncertain defect classification. In consequence, manual inspection leads to low productivity and can be influenced by human errors. Therefore, it is necessary to integrate the AOI with artificial intelligence (AI) technology to replace human assist for productivity and quality improvement. Hence, the main focus of this paper is to find the best deep learning model suitable to be used for wire bonding defect classification. Various deep learning models have been tested using the original images collected from semiconductor fabrication. From the experimental results, EfficientNetB0 V2 is selected as the best model to be used for defect inspection by considering the accuracy and processing speed with the best results of 98% and 0.045 seconds, respectively. Moreover, the model also retains its lightweight nature with model size of 29 MB which is tolerable to be deployed in the real-world application. | ||
| 117. ARIMA-LP: A Hybrid Model for Air Pollution Forecasting with Uncertainty Data | ||
| Muhammad Shukri Che Lah (Universiti Tun Hussein Onn Malaysia Malaysia), Nureize Arbaiy (Universiti Tun Hussein Onn Malaysia Malaysia), Pei-chun Lin (Feng Chia University Taiwan) | ||
| Public health is seriously threatened by air pollution. Systems for early warning are crucial for preventing its negative impacts on humans. But predicting air quality is difficult because it needs precise data from time series gathered at air monitoring sites. Due to things like measurement mistakes, this data may be ambiguous. Using fuzzy symmetry triangular fuzzy numbers, we suggest a strategy in this study for preparing data that contains uncertain information. Linear programming is utilized to obtain the midpoint value for defuzzification. The fuzzy pre-processed data is then used to build a predictive model using ARIMA. Our findings imply that the linear program can greatly lower prediction errors, resulting in more precise predictions. | ||
| 129. Enhancing Autism Screening Classification using Feature Selection and Stacking Classifier | ||
| Ainie Hayati Noruzman (Faculty of Computing, University Malaysia Pahang Sultan Al-Abdullah,26600 Pekan, Pahang, Malaysia), Ngahzaifa Abd Ghani (Faculty of Computing, University Malaysia Pahang Sultan Al-Abdullah,26600 Pekan, Pahang, Malaysia), Nor Saradatulakmar Zulkifli (Faculty of Computing, University Malaysia Pahang Sultan Al-Abdullah,26600 Pekan, Pahang, Malaysia) | ||
| The current screening process for early detection of autism spectrum disorders (ASD) is time-consuming and costly, requiring numerous questions about various aspects of a child's development. To address this issue, this study integrates the Recursive Feature Elimination (RFE) method into a stacking ensemble classifier, allowing to identify the most important and effective features from the autism screening tool. This approach is aimed to create a simplified version of the autism screening and to make the screening process faster and more efficient by reducing the number of questions in autism screening tool. The proposed model provides a more efficient and simplified alternative for autism screening, allowing for early decision-making based on consistent and precise results. With 0.9760% accuracy results in predicting ASD traits, it is hoped that these findings will be an alternative option to make the screening questions much simpler while also providing an alternative to parents in predicting autism earlier and with less time. | ||
| 130. Machine Learning Classification to Detect Unattended Child in Vehicle Using Sensor Signal : A Review | ||
| Ida Fadliza Abu Zarin (University Malaysia Pahang), Ngahzaifa Abd Ghani (University Malaysia Pahang), Syafiq Fauzi Kamarulzaman (University Malaysia Pahang) | ||
| A significant number of children die each year in the United States and around the world as a result of being left in hot vehicles. Numerous studies aimed at reducing the number of unattended children in vehicles have employed a variety of strategies. The majority of studies use sensors to detect unattended children, while only a few integrate machine learning with the sensors. The efficacy of a sensor's system is improved by machine learning. This paper reviews the implementation of machine learning classification in child detection systems and reviews the research conducted to detect unattended children. For the majority of the research, the machine learning algorithms SVM, KNN, and Random Forest effectively classified the occupants into a few classifications with accuracies greater than 90%. | ||
| Session I-B (11:15 - 13:00 @ Halia Room) | ||
| Session Chair: SYAFIQ FAUZI BIN KAMARULZAMAN | ||
| 91. Crow Search Freeman Chain Code (CS-FCC) Feature Extraction Algorithm for Handwritten Character Recognition | ||
| Muhammad Arif Mohamad (Universiti Malaysia Pahang Al-Sultan Abdullah), Zalili Musa (Universiti Malaysia Pahang Al-Sultan Abdullah), Amelia Ritahani Ismail (International Islamic Universiti Malaysia) | ||
| With so many algorithms developed to improve classification accuracy, interest in feature extraction in Handwritten Character Recognition (HCR) has increased. In this research, a Crow Search Algorithm (CSA)-based metaheuristic strategy for feature extraction in HCR was developed. The data representation method employed was Freeman Chain Code (FCC). The fundamental issue with using FCC to represent a character is that the outcomes of the extractions depend on the starting points that changed the chain code's route length. The shortest route length and least amount of computational time for HCR were found using the metaheuristic technique via CSA, which was suggested as a solution to this issue. The suggested CS-FCC extraction algorithm's computation durations and route lengths serve as performance indicators. The research. The algorithm experiments are carried out using the chain code representation created from previous research of the Centre of Excellence for Document Analysis and Recognition (CEDAR) dataset, which consists of 126 upper-case letter characters. According to the results, the proposed CS-FCC has a route length of 1880.28 and only takes 1.10 seconds to solve the entire set of character images. | ||
| 96. Internet of Things Intercommunication Using SocketIO and WebSocket with WebRTC in Local Area Network as Emergency Communication Devices | ||
| Nur Izzaty Ariffin (Ascenity Solutions Enterprise), Muhd. Aidil Syazwan Hamdan (Ascenity Solutions Enterprise), Syafiq Fauzi Kamarulzaman (University Malaysia Pahang) | ||
| The Emergency Intercom System (EIS) is a communication and video conferencing system designed to enhance emergency response in areas, such as malfunctioning lifts. This paper presents a feasibility analysis of EIS as internet of things device, focusing on the utilization of WebRTC over WebSocket, Socket.io, and LAN device hostname assignment. The study evaluates performance metrics including latency, throughput, dropped calls, lost packets, audio and video quality, resource utilization, and network bandwidth. The results indicate that EIS offers acceptable latency, sufficient throughput for simultaneous calls, minimal dropped calls and lost packets, and satisfactory audio and video quality. The system demonstrates effective communication and video conferencing capabilities, making it a promising solution for improving emergency response in areas. The findings highlight the potential for further research to optimize performance, address security considerations, and extend the system's applicability in diverse emergency scenarios. | ||
| 97. Intelligent Humanoid Emotion Response based on Human Emotion Recognition for Virtual Intercommunication Simulator | ||
| Andrew Lim Wei Chin (Universiti Malaysia Pahang), Lim Gim Wen (Universiti Malaysia Pahang), Syafiq Fauzi Kamarulzaman (Universiti Malaysia Pahang) | ||
| Emotion is one of the key factors that humans use to communicate with each other. It will also affect the behavior of humans such as our moods, feeling and reaction. A deep study of emotion of human will be conducted in this research. This research will be covering basic knowledge of emotion, computational emotion model, face detection algorithm, fuzzy logic inference system. Then, a computational emotion model Fuzzy Artificial Intelligent Human Emotion Response (FATHER) was proposed and implemented into a 3D humanoid named Umar. The responses of humanoid are presented by using virtual humanoid is a 3D human face model. By animating the 3D model, humanoid’s emotion can be expressed through facial expression animation. | ||
| 104. Hop Restricted-AODV (HR-AODV) Routing and Its Applicability on Different Wireless Channels for Vehicular Network | ||
| Tanvir Ahmad (University Malaysia Pahang (UMP)), Nor Syahidatul Nadiah Binti Ismail (University Malaysia Pahang (UMP)), Md Arafatur Rahman (University of Wolverhampton), Abdullah Mat Safri (University Malaysia Pahang (UMP)), Waseem Quadri (University Malaysia Pahang (UMP)) | ||
| Routing is considered the most significant part of any wireless system, and vehicular network depends on Ad-hoc On-demand Distance Vector (AODV) routing mostly for routing purposes. To adapt to the dynamic topology of the vehicular network, different variations of AODV routing are adopted, and there have some event-driven limitations considering different performance metrics. In this paper, we propose a variant of AODV routing hop restricted-AODV (HR-AODV) that limit searching for receiver up to a maximum of four hops and completes data transmission. We simulate the protocol on two channels; LOS-driven two-ray ground and Non-LOS multipath fading channel Rayleigh channel. We found acceptable results that constitute its usability in vehicular networks. | ||
| 109. An improvement of Interactive Prioritization Technique for Requirements Interdependency in prioritization process | ||
| Siti Nursyafiqah Rusli (UNIVERSITI MALAYSIA PAHANG), Rohani Abu Bakar (UNIVERSITI MALAYSIA PAHANG), Siti Suhaila Abdul Hamid (UNIVERSITI MALAYSIA PAHANG) | ||
| Requirement Prioritization (RP) was introduced as a solution to the project with huge number of requirements by eliminating some of the requirements based on fair judgement in terms of priority value or rank made by expertise or stakeholder or both parties depending on the technique's specific operation. Along with the RP concept, there is another concept that must be deeply understood, which is Requirement Interdependencies (RI), which describes the interdependencies of requirements with each other. However, not many RP techniques involve the RI element during the RP process, citing complexity as the key reason for this, even though the RI element plays a critical role in determining the most important requirement for improving the project success rate. This paper describes the propose technique, which improves the RP process while considering the RI element. Two conventional RP techniques, Three-level Scale and Rank Ordering. Each RP technique plays an important part in producing high accuracy results while improving the impact of RI element during the RP process. | ||
| 124. QSroute : A QoS aware routing scheme for Software Defined Networking | ||
| Imran Edzereiq Kamarudin (Universiti Malaysia Pahang), Mohamed Ariff Ameedeen (Universiti Malaysia Pahang), Muhamad Idaham Umar Ong (Universiti Malaysia Pahang), Azlee Zabidi (Universiti Malaysia Pahang) | ||
| The increasing demand for bandwidth-intensive network applications, such as video streaming, multimedia, and Internet of Things (IoT) applications, necessitates improved resource management to protect the network without compromising Quality of Service (QoS). Meeting these challenges requires a centralized view of all available network resources. Software Defined Networking (SDN), an emerging technology, provides a centralized view and control of network resources. This feature enables administrators to programmatically define and manage network behavior, including routing, making it more flexible and adaptable. This study proposes a QoS-aware routing scheme for SDN that considers available bandwidth, packet delay, and packet loss to determine the optimal routing path. Optimal paths are selected based on meeting predefined threshold criteria. The study concludes by discussing potential directions for future research in this field. | ||
| 143. Robust Image Watermarking using Hessenberg Decomposition and SVD with Integer Wavelet Transform | ||
| Ahmad Hisyam (Faculty of Computing Universiti Malaysia Pahang Pekan), Ferda Ernawan (Faculty of Computing Universiti Malaysia Pahang Pekan), Prajanto Wahyu Adi (Faculty of Science and Mathematics Universitas Diponegoro), Zuriani Mustaffa (Faculty of Computing Universiti Malaysia Pahang Pekan), Mohd Faizal Ab Razak (Faculty of Computing Universiti Malaysia Pahang Pekan) | ||
| Preventing unauthorized use and distribution has grown more difficult as a result of the extensive usage of the internet and the simplicity of duplicating and distributing digital media. Watermarking has come to be recognized as a successful remedy for this issue. Image watermarking is the process of adding a distinctive identifier to an image so that it is hidden from view but can still be read to establish ownership. This research proposes Hessenberg Decomposition (HD) and Singular Value Decomposition (SVD) in the Integer Wavelet Transform (IWT) domain to achieve high robustness. The proposed method utilizes the HD feature of the image to enhance the robustness of the watermark against attacks, while the SVD technique is used to achieve high invisibility and security. The IWT domain is employed to make the watermarking process more efficient, leading to a faster and more reliable watermarking algorithm. The results of the experiments demonstrate that the proposed scheme provides a high level of robustness for preserving the ownership of multimedia content and resistant to various image processing attacks. The outcomes demonstrate that, in terms of robustness and invisibility, the suggested approach performs better than the existing watermarking schemes. | ||
| Session II-A (14:00 - 16:00 @ Pandan Room) | ||
| Session Chair: AZMA BINTI ABDULLAH | ||
| 8. PERFORMANCE EVALUATION OF DETECTION MECHANISMS TOWARDS THE SLOW DDOS ATTACK OF EDGE COMPUTING | ||
| Yu Beng Leau (Universiti Malaysia Sabah), Xue Yi Lee (Universiti Malaysia Sabah) | ||
| Edge computing is a network topology composed of three layers: the cloud server layer (CSL), the edge server layer (ESL), and the edge device layer (EDL). It is vulnerable because the processing capacity of IoT devices or mobile devices is not sufficient to withstand it, and they are not able to implement high-level security measures such as HTTP/HTTPS, FTP, or SMTP on this layer, which poses significant security risks, especially slow Distributed Denial of Service (DDoS) attacks. In this study, three machine learning algorithms classified as anomaly-based detection techniques were chosen, including CDAAE (Conditional Denoising Adversarial AutoEncoder), CNN (Convolutional Neural Network), and deep learning using 'relu' and'softmax' to detect Slow DDoS attacks. These models were tested on the CICIDS2017 dataset, and the results show that CNN achieved better overall performance with a shorter training time and high detection accuracy. | ||
| 47. Customizing of ERP In Microservice SaaS Architecture: An Overview of Intrusive & Non-intrusive Approach | ||
| Ying Hong Ding (Tunku Abdul Rahman University of Management and Technology), Kwee Teck See (Tunku Abdul Rahman University of Management and Technology), Tong Ming Lim (Tunku Abdul Rahman University of Management and Technology), Hoong Jack Chang (Tunku Abdul Rahman University of Management and Technology) | ||
| In Industry Revolution 4.0, industries are aiming towards a direction of digitalization whereby enterprise system will need to be adopted widely in Small Medium Enterprise to improve their competitive power. Customization of enterprise system is commonly adopted as it is necessary to meet the specific needs of the organization. However, customization for enterprise system would take a large effort for modifying underlying code without affecting the original codebase and with the increasing adoption of microservice-based Software-as-a-Service (SaaS) architectures, the process of customization has become even more complicated. In this particular paper, the authors will be discussing on the approaches to customize Enterprise Resource Planning system in microservice SaaS architecture. The authors of this paper will be discussing on the two approaches namely, intrusive approach and non-intrusive approach including the advantages and the disadvantages of each approach. By understanding the trade-offs between these approaches and carefully evaluating their customization needs, organizations can make informed decisions that meet their unique business requirements while minimizing the risks associated with customization. | ||
| 56. High Performance Business Intelligence Dashboard | ||
| Harvindran Chandrasekaran (Intel Technology Sdn. Bhd), Yu Xuan Tan (Intel Technology Sdn. Bhd), Kok Mang Tang (Intel Technology Sdn. Bhd) | ||
| Intel software development ecosystem is complex, consisting of components produced in-house, third-party vendors and open-source community. Different tools and processes are being used to manage individual deliverables throughout the whole software product life cycle. Managing the release of such complex software solution is very competitive, especially when dealing with the dependencies of many moving pieces across different department which contribute to an array of products releases with different requirements and schedule. This paper describes Owl’s View, high performance and scalable personalized dashboard’s architecture which enables very fast data lookup from multiple sources; it also explains how productivity gains can be achieved through eliminating unnecessary waste and summarizing day to day top priority tasks in single dashboard; as well as revealing the impacts that Owl’s View brings to the organization, especially in productivity gains and Intel Software Quality compliance. | ||
| 66. Exploring Cryptographic Techniques for Data security in Resource-Constrained Wireless Sensor Networks:Performance Evaluation and Considerations | ||
| Dharshika Singarathnam (York St John University), Swathi Ganesan (York St John University), Sangita Pokhrel (York St John University), Nalinda Somasiri (York St John University) | ||
| (Video Link: https://youtu.be/wHDQ3OnwmCw) | ||
| Wireless sensor networks (WSNs) play a crucial role in environmental monitoring and data collection. However, ensuring data security in WSNs poses challenges due to the vulnerabilities of wireless communication channels. In this paper, we address this concern by exploring the application of cryptographic techniques to enhance data security in WSNs. Considering the limited sensor power, computing power, and storage resources, we propose a novel approach that evaluates the suitability of symmetric and asymmetric cryptographic algorithms in WSNs. Through performance comparisons based on computation power and storage capacity requirements, we identify key insights for selecting appropriate encryption algorithms in WSNs. Our findings emphasize the importance of considering the specific requirements and constraints of WSN applications, highlighting the efficiency of symmetric key-based encryption algorithms in resource-constrained environments and the stronger security and key distribution mechanisms provided by ECC-based asymmetric encryption algorithms for secure communication among multiple nodes. This research contributes to the existing knowledge by offering an effective solution to enhance data security in WSNs while considering computational and storage limitations | ||
| 70. Effects of the GDPR in South East Asia vs. Europe - A Large-scale Analysis of IoT Devices | ||
| Frank Ebbers (Fraunhofer Institute for Systems and Innovation Research ISI) | ||
| Ever more IoT devices and services find their way into private homes and industry, coming along with a plethora of risks to users’ privacy. The General Data Protection Regulation (GDPR) became effective in 2018 and protects rights of IoT (and other) users. Manufacturers can address these rights, for example, with firmware updates. In this paper, we conduct a large-scale analysis that identifies changes in the age of the installed firmware and general device age after the GDPR went into effect. We utilize a set of 400 terabytes of real-world IoT data from Censys.io dating from 2015 until the end of 2021. Based on grouped mean age values, we conduct difference-in-differences analyses for devices deployed in the EU, compared to Malaysia (MY), Indonesia (ID), Singapore (SG) and USA. The results show unexpected insights. For a majority of European Union (EU) member states, the GDPR leads to an increase of the devices’ mean age by 101 days compared to non-EU states. Compared to ID it increases by 201 days, SG by 11 days, MY+ID+SG by 89 days and USA by 194 days. Results for MY are not significant, however. This work offers first insights into effects of the GDPR in the IoT ecosystem and highlights the need for more research for sense-making. | ||
| 79. User Stories in Requirements Elicitation: A Systematic Literature Review | ||
| Yanche Ari Kustiawan (Multimedia University), Tek Yong Lim (Multimedia University) | ||
| A user story is commonly applied in requirement elicitation, particularly in agile software development. User story is typically composed in semi-formal natural language, and often follow a predefined template. The user story is used to elicit requirements from the users’ perspective, emphasizing who requires the system, what they expect from it, and why it is important. This study aims to acquire a comprehensive understanding of user stories in requirement elicitation. To achieve this aim, this systematic review merged an electronic search of four databases related to computer science. 40 papers were chosen and examined. The majority of selected papers were published through conference channels which comprising 75% of total publications. This study identified 24 problems in user stories related to requirements elicitation, with ambiguity or vagueness being the most frequently occurring problem reported 18 times, followed by incompleteness reported 11 times. Finally, the model approach was the most popular approach reported in the research paper, accounting for 30% of the total approaches reported. | ||
| 82. Effective Visualization Electrification System via PSCADA Event Log in Railway Industry | ||
| Syamsul Azrin Kamaruddin (Universiti Tun Hussein Onn Malaysia (UTHM)), Ts. Dr. Hairulazwan Hashim (Universiti Tun Hussein Onn Malaysia (UTHM)), Prof. Madya Ts. Dr. Elmy Johana Mohamad (Universiti Tun Hussein Onn Malaysia (UTHM)), Nazwa Hidayah Mohamad (Pestech Technology Sdn Bhd), Halim Mamat (Department of Electrification, Keretapi Tanah Melayu Berhad) | ||
| Rail transport has been one of the main intercity passenger train operators in Malaysia. The Electrification Department is the most important department to make sure the trains have enough power to operate and responsible for the maintenance of the power supply infrastructure and SCADA system to ensure the Electrification System accurately monitored and controlled and assure the Reliability, Availability and Safety of the system. The key issue faced by this department is related to reporting for maintenance. The report was very time-consuming to prepare because it was on paper-based method, and information was presented badly due to the lack of a visualization tool and being vulnerable to data quality problems. To address this issue, the current study aims to propose a tool that provides screening and detecting of device fault status using a dashboard developed using Microsoft Power BI by extracting the raw data log from the Power SCADA. We demonstrate the process of adopting the cloud-based dashboard using Power BI at the strategic management level. The development of the dashboard system is adopting from the previous research framework, consisting of four main stages which are designing, data analyzing process (ETL), visualizing, and validating. One of the findings is that the data cleansing process is the most important stage to produce the right information. This interactive tool made instant visibility of device status and assist the maintenance team to capture the status trends. The study benefits to the organization are to reduce 86% of the time and cost to prepare the maintenance reporting and planning | ||
| 144. Safety Property Attributes in Critical Systems for Requirement Specification: A Review | ||
| Azma Abdullah (Faculty of Computing University Malaysia Pahang Al-Sultan Abdullah (UMPSA) Pahang), Rohani Abu Bakar (Faculty of Computing University Malaysia Pahang Al-Sultan Abdullah (UMPSA) Pahang), Kiriyadhatshini Gunaratnam (Faculty of Computing University Malaysia Pahang Al-Sultan Abdullah (UMPSA) Pahang), Fadhl Hujainah (Volvo Car Corporation), Mohd Fairus Abdul Farid (Malaysia Nuclear Agency) | ||
| The integration of critical system components, requirement specification, and safety properties plays a crucial role in advancing the development and verification processes of critical systems. This integration enables effective analysis, management of safety requirements, and identification of potential risks. Although several studies have explored safety properties in safety analysis (SA), they often lack a comprehensive presentation of all possible safety properties with proper categorization. This paper aims to address this gap by analyzing a comprehensive list of possible safety properties in requirement specification. The list is derived through an extensive analysis of studies published between 2019 and 2023, with a focus on past researchers' contributions. Additionally, our future work includes a systematic literature review encompassing a broader range of studies to further enhance the analysis. By providing a structured approach for addressing safety aspects, this paper contributes valuable insights into the significance of safety properties in ensuring the safety and reliability of critical systems. It lays the foundation for improved safety analysis (SA) practices and strengthens the overall development process of critical systems. | ||
| Session II-C (14:00 - 16:00 @ Lada Room) | ||
| Session Chair: CHANG HOONG JACK | ||
| 29. An Ensemble-Based Framework to Estimate Software Project Effort | ||
| Mohammad Haris (Multimedia University), Fang-fang Chua (Multimedia University), Amy Hui-lan Lim (Multimedia University) | ||
| Effort estimation is essential for successful software project planning, budgeting, and risk identification. However, the techniques used to estimate effort are often inaccurate, outdated, and only consider technical factors while neglecting project management or stakeholder engagement. Expert estimation remains an important technique for leveraging human expertise in software estimation, but solely relying on this technique causes biased and subjective predictions. Machine learning (ML) techniques have shifted the direction of software project effort estimation towards computational intelligence. Nonetheless, there is a lack of deployment due to ambiguous outcomes and ineffective model-building approaches. This study presents an ensemble-based framework that can estimate software project effort more accurately with the incorporation of domain knowledge and experiences. To achieve this, six homogeneous classifier ensembles will be constructed using six distinct classifiers on the proposed USP05-FT dataset. The collected expert estimations will be integrated into the proposed dataset as an additional feature in the form of numerical values such as expert-provided software project effort estimations (in person hours) that provide additional insight and knowledge. Subsequently, the predictions of all six homogeneous classifier ensembles will be combined through majority voting to obtain a more accurate and reliable prediction with increased robustness against errors and uncertainties. The performance of the proposed framework will be evaluated using Recall, F-measure, Precision, and Accuracy. It is expected that the proposed ensemble-based framework for software project effort estimation will lead to more efficient and effective software project management, an improvement in resource allocation, empowering informed decision-making, and timely project delivery. | ||
| 32. A Systematic Literature Review on Solutions of Mutation Testing Problems | ||
| Zheung Yik Loh (Faculty of Computing, Universiti Teknologi Malaysia), Wan Mohd Nasir Wan Kadir (Faculty of Computing, Universiti Teknologi Malaysia), Noraini Ibrahim (Faculty of Computing, Universiti Teknologi Malaysia) | ||
| Mutation testing (MT) is regarded as a gold standard way to assess test suite (TS) fault finding capability and to verify the effectiveness of software testing methodologies. However, the adoption of MT in the software industry remains uncommon due to various problems. In this systematic literature review, we investigate the recent solutions of MT problems. Our review involves a comprehensive analysis of relevant research papers published from 2017 to 2022, indexed in reputable databases such as Scopus, WoS, IEEE, and ACM. After we synthesized our findings, we identified the potential research direction which can increase the adoption of MT in the software industry. | ||
| 35. Security Requirements Assurance: An Assurance Case Perspective | ||
| Aftab Alam Janisar (Department of computer and information science Universiti Teknologi Petronas 32610 Seri Iskandar Perak, Malaysia.), Khairul Shafee Bin Kalid (Department of computer and information science Universiti Teknologi Petronas 32610 Seri Iskandar Perak, Malaysia.), Aliza Bt Sarlan (Department of computer and information science Universiti Teknologi Petronas 32610 Seri Iskandar Perak, Malaysia.) | ||
| In current era, software security requirements domain has changed thoroughly, and has been considered an essential aspects for software quality in recent times. Machine learning and artificial intelligence have become the emerging trends to automate the identification and specification of security requirements. As an active research area, security requirements specifications are recognized and persuaded in software engineering and security assurance communities. Overfitting of security requirements after system design can result in security issues in current system architecture. Consistency, completeness, and correctness are critical requirements for ensuring the effectiveness of systems architecture. However, without these security requirements, the system is vulnerable to attacks and organization’s assts, and reputation is at risk. Moreover, it increases the cost and time to fix the security problem. Therefore, to avoid such problems security requirements need to be identified more precisely and consistently. Realizing the benefits of assurance case, A conceptual framework is proposed for security requirements using assurance case. Objective of the proposed conceptual framework is to assist the security engineer to identify the security requirements using assurance case during requirement phase i.e., the security requirements are correct, complete, and consistent. The proposed conceptual framework involves five phases : (1)assets identification, (2) threat identification, (3) security objectives, (4) security requirements and (5) security requirement assurance. | ||
| 38. Parking Space Detection in Different Weather Conditions Based on YOLOv5 Method | ||
| Misbachul Falach Asy'ari (Department of Informatics, Institut Teknologi Sepuluh Nopember), Chastine Fatichah (Department of Informatics, Institut Teknologi Sepuluh Nopember), Nanik Suciati (Department of Informatics, Institut Teknologi Sepuluh Nopember) | ||
| The increasing number of vehicles on the road has led to a serious problem of finding available parking spaces during rush hour. Previous works used the classifier method to classify empty or occupied parking spaces. Other studies used object detection algorithms to detect the parking spaces and show their location. However, prior studies have not demonstrated the efficiency of parking space detection in various weather conditions. In this paper, we experiment with an object detection method to detect parking space using the You Only Look Once version 5 (YOLOv5). This study used four out of nine cameras in the CNRPark dataset that include different weather conditions (overcast, rainy, and sunny). After splitting the datasets, the training and validation data were trained using six configurations of YOLOv5 architecture. We evaluated the result of testing data using six weights from the training process. The results show that the method achieved the best mean average precision (mAP0.5) score of 0.969 in rainy weather using the best model of YOLOv5 configurations. Furthermore, this study compared the accuracy of parking slot detection with previous studies. Our experiment provides an effective solution for parking space detection in various weather circumstances. | ||
| 39. Comparative Analysis of Convnext and Mobilenet on Traffic Vehicle Detection | ||
| Yusuf Gladiensyah Bihanda (Institut Teknologi Sepuluh Nopember), Chastine Fatichah (Institut Teknologi Sepuluh Nopember), Anny Yuniarti (Institut Teknologi Sepuluh Nopember) | ||
| Traffic vehicle detection plays important role in making decision about maintenance of a road section. However, the method to conduct it still used traditional approach, by means of surveyors being on the road and identifying vehicles for 40 hours, so it takes quite a long time and has the potential for human error to occur when identifying vehicles. In this research, a solution is formulated to identify vehicles using closed-circuit television (CCTV) and object detection methods based on deep learning. The dataset that used to train deep learning model were recorded in some of road section by our CCTV. Then, we annotate each object from given video frame based on defined classes. Then, all of the annotated frame divided in train and validation with percentage of 80% and 20% respectively. Train and validation dataset used for model training and test dataset used for evaluating best model weight and produce Average Precision, while best model weight also tested for show model performance and its Frame Per Second. We then compared the application of Faster-RCNN method with ConvNext v1 and Mobilenet v3 backbone in carrying out vehicle detection. Using 12 classes of vehicle in training and testing phase, test results based on evaluation dataset showed that ConvNext v1 backbone produced an average precision value of 0.81 while Mobilenet v3 backbone obtained a result of 0.3. As for the results of the Frame per Second (FPS) test, Mobilenet v3 backbone obtained an average FPS of 18 while Convnext v1 obtain 7. The results obtained indicated Faster R-CNN backbone ConvNext v1 was an effective approach to obtain robust object detection while Faster R-CNN Mobilenet v3 backbone is effective for object detection in real time. | ||
| 46. An Overview Analysis of Authentication Mechanism in Microservices-based Software Architecture: A Discussion Paper | ||
| Hoong Jack Chang (Tunku Abdul Rahman University of Management and Technology), Kwee Teck See (Tunku Abdul Rahman University of Management and Technology), Tong Ming Lim (Tunku Abdul Rahman University of Management and Technology), Ying Hong Ding (Tunku Abdul Rahman University of Management and Technology) | ||
| Microservices-based software architecture promotes scalability and flexibility by breaking down a software application into smaller modules and making it more independent and loosely coupled services compared to monolith systems. However, securing microservices in a distributed nature has become one of the challenges. Authentication is one of the most critical components that should be focused in the microservices security measures. It helps to identify that only authenticated personnel and services can access sensitive information and secure the trust between microservices. This discussion paper aims to provide an overview analysis and extensive understanding on the authentication mechanism in microservices-based software architecture. In this study, we explore different authentication mechanisms including Mutual Transport Layer Security (mTLS), Token-based authentication and API Gateway authentication. This study examines the strengths and limitations of different authentication mechanisms in microservices-based software architecture. It also emphasizes the importance of authentication and the need for having a well-designed authentication mechanism to ensure the integrity and security of microservices-based software architecture is crucial. | ||
| 78. Monocular Camera Free Region Detection Method of Obstacle Avoidance for Micro - Sized UAV | ||
| Muhamad Wafi Bin Abdul Aziz (Universiti Tun Hussein Onn Malaysia), Muhammad Faiz Bin Ramli (Universiti Tun Hussein Onn Malaysia) | ||
| Robustness of the UAV depends on the ability to detect upcoming obstacles. Dependency on range sensor is only able to detect the distance of the object from the UAV however, restricted to the robustness of UAV especially Micro -Sized UAV (MAV) that are limited in terms of payload and energy consumption. On other hand, certain range sensors are expensive and sensitive to surroundings. Hence, implementing simple LIDAR and lightweight monocular camera sensor with appropriate free region detection method will give better combination to overcome previous problems as camera sensors will provide various of surrounding inputs related to the obstacles. This method will segmentized input image of first and second frame via K – Means. Then the second image frame will be subtracted by the first image frame. Next the subtracted image frame will be divided into 12 regions. Then, the least pixel expansion will be selected from the regions. Finally further sub regions to find least pixel expansion will be executed from the previously selected free region. The method is tested with experiment for texture and texture-less obstacles for free region detection. The method successfully obtained the best free region area for the MAV to avoid the obstacle. | ||
| 116. SODIBOT: A TWO in ONE Real-Time Human Monitoring System using YOLO algorithms | ||
| Azim Zaliha Abd Aziz (Universiti Sultan Zainal Abidin), Nurul Nadzirah Adnan (Universiti Sultan Zainal Abidin), Nur Farraliza Mansor (Universiti Sultan Zainal Abidin), Wan Suryani Wan Awang (Universiti Sultan Zainal Abidin), Ida Nurhaida (Universitas Pembangunan Jaya), Safitri Jaya (Universitas Pembangunan Jaya) | ||
| COVID-19 primarily spreads through direct physical contact. As a precaution, it is recommended that each individual to keep the distance of at least one meter between one to another. This study proposes a real-time system named as SODIBOT for monitoring physical distancing compliance and body temperature measurement in indoor spaces during this endemic using computer vision and deep learning techniques. The method suggested in the study utilizes the YOLO object detection algorithm to detect individuals and promptly estimate their physical distance in real-time using a high-end thermal camera. Every identified human is assigned a color-coded bounding box with a distinct significance. Simultaneously, body temperature is also recorded and displayed at the top of each bounding box. The effectiveness of the proposed system was measured by the number of people detected in frame per second. Furthermore, the system's ability to measure and display individual body temperatures at the top of the bounding boxes adds additional value to SODIBOT. The outcomes illustrate the potential of SODIBOT in effectively monitoring compliance with physical distancing in indoor environments, offering valuable insights for potential application in other public health scenarios. | ||
| Session II-B (14:00 - 16:00 @ Halia Room) | ||
| Session Chair: MUHAMAD IDAHAM BIN UMAR ONG | ||
| 6. A Meta-Requirement Approach to Validate User Requirement Specification: Threshold Definition | ||
| Muhamad Idaham Umar Ong (Universiti Malaysia Pahang), Mohamed Ariff Ameedeen (Universiti Malaysia Pahang) | ||
| The software requirement specification document is critical for ensuring that software development projects are completed on time, within budget, and meet the needs of all stakeholders. User requirement completeness refers to the extent to which user requirements accurately and fully capture the needs and expectations of stakeholders for a given system or application. The completeness of user requirements is critical for the successful design and implementation of information systems, as incomplete requirements can lead to a range of issues, including system failure, delays, and cost overruns. The author has developed a meta-requirement validation approach to validate the completeness of a set of requirements. Based on a numerical reading, the user of the approach will be able to determine the completeness of the requirement. This publication's main objective is to identify the threshold value through a method of literature search. The identified threshold value will be used to determine the minimum reading for the result to be deemed complete. The result of a 70% value has been identified to be suitable for the use of the validation approach. | ||
| 49. A Visualized Hybrid Keyword-cluster Approach for Extractive Text Summarizer Tool for STEM Education in Malaysia | ||
| Suraya Alias (UMS), Mazliah Majalin (UMS), Nur Hayatin Nur Hayatin (UMS) | ||
| Summarization tool has become increasingly relevant due to the shift towards online learning caused by the Covid-19 pandemic. In this paper, we present an extractive educational text summarizer tool with a focus on Science, Technology, Engineering, and Mathematics (STEM) subjects specifically designed for secondary school students in Malaysia. The tool addresses the challenge of understanding complex STEM concepts from lengthy explanations and problem-solving scenarios. We propose a new hybrid method for scoring the keywords by leveraging the word embeddings technique to improve the keyword extraction cluster approach. The generated summaries are displayed with highlighted cluster of keywords and illustrated using word clouds to attract students' interest and engage them with the subject matter. We compare our proposed method to the benchmark and baseline Malay text summarizer using random STEM articles. The ROUGE-1 results produced an average F-Score of 56.8%, precision of 56.3% and recall of 58.1%. We also conducted a System Usability Testing with teachers and secondary school students, obtaining high ratings for system simplicity, pleasant interface, and ease of information retrieval. Our study demonstrates the potential of educational text summarization tools to enhance student learning experiences in diverse contexts. | ||
| 84. Phishing Website Detection Technique Using Machine Learning | ||
| Nurul Amira Mohd Zin (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Mohd Faizal Ab Razak (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Ahmad Firdaus (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Ferda Ernawan (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,), Nor Saradatul Akmar Zulkifli (Faculty of Computing College of Computing and Applied Science, Universiti Malaysia Pahang,) | ||
| The Internet has emerged as an indispensable tool in both our personal and professional life in our modern day. As a direct consequence of this, the number of customers who make their purchases over the Internet is quickly increasing. Internet users may be vulnerable to a wide variety of web threats because of this fact. These threats may result in monetary loss, fraudulent use of credit cards, loss of personal data, potential damage to a brand's reputation, and customer mistrust in e-commerce and online banking. Phishing is a sort of cyber threat that may be defined as the practice of imitating a genuine website for the purpose of stealing sensitive information such as usernames, passwords, and credit card numbers. This research focuses on strategies for detecting phishing attacks. This study apply a machine learning approach to detect a phishing attack. As a result, this study able to detect phishing with accuracy 94%. | ||
| 106. Enhancing Chiller Plant Modelling Performance Through NARX-Based Feature Optimization | ||
| Azlee Zabidi (Universiti Malaysia Pahang Al-Sultan Abdullah), Mohd Izham Mohd Jaya (Universiti Malaysia Pahang Al-Sultan Abdullah), Hasliza Abu Hassan (Universiti Industri Selangor), Ahmad Ihsan Mohd Yassin (Universiti teknologi Mara) | ||
| The research focuses on the modelling chiller plants in air cooling systems of large buildings. The existing evaluation of prediction efficiency and identification of efficient components in chiller plants has been limited. The goal of this research is to develop a methodology for modeling chiller plants by utilizing key parameters from their components. The resulting model accurately simulates the actual chiller plant system and can be used by organizations to predict future events, aiding in preventative maintenance and reducing maintenance costs, especially in critical buildings like hospitals. The research process include compiling the chiller plant's history, simulating the machinery using a regression technique called NARX, selecting crucial parameters using an optimization technique (BPSO), and validating the model. This study enhances our understanding and management capabilities of these important cooling systems by addressing the challenges of efficient modeling and prediction accuracy in chiller plant systems. | ||
| 114. A New SVM-STEG Embedding Model In Steganography | ||
| Hanizan Shaker Hussain (Quest International University), Fazali Ghazali (Universiti Islam Antarabangsa Sultan Abdul Halim Mu'adzam Shah), Hafiza Abdul Samad (Universiti Poly-Tech Malaysia, Malaysia), Hanif Mohd Ali (Universiti Islam Antarabangsa Sultan Abdul Halim Mu'adzam Shah), Anbuselvan Sangodiah (Quest International University), Kante Koli Oumar (Quest International University) | ||
| One of the sub-fields in information security is called information hiding and can be applied to protect data and information nowadays. Indeed, this is a method in which secret-messages are hidden in an image file. This method has been used in various fields especially in digital image steganography. Most of the techniques proposed to date have various problems i.e., non-random changes will obviously occur especially when the secret message is embedded in an inappropriate area and when the load capacity exceeds the number of bits allowed. This paper proposes a machine learning steganographic method called SVM-Steg model that uses embedding and extracting algorithms by exploiting SVM classification and SVM-Steg embedding to achieve good performance. In addition, the distance of the embedding location is also taken into account so that more pixels can be embedded at more distance locations. The results show a quality cover-image when high peak signal-to-noise ratio (PSNR) values are recorded greater for all types of cover images. In comparison to the other technique, all PSNRs for the proposed technique, SVM-Steg Method achieved 40 or higher. It is not only succeeding in providing a secure embedding position, but also increases the number of secret-bits embedded. | ||
| 119. A Comparative Analysis on Three Duplication Elements in Copy-Move Forgery Using PatchMatch-based Detection Method | ||
| Nur Izzati Nor Azaimi (Universiti Tun Hussein Onn Malaysia), Nor Bakiah Abd Warif (Universiti Tun Hussein Onn Malaysia), Nor-syahidatul N Ismail (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| Image forgery is the alteration of a digital image to hide some of the important and useful information. Copy-move forgery (CMF) is one of the most difficult to detect because the copied part of the image has the same characteristics as the original image. Most of the existing datasets only highlight additional attacks in the copied part. Since there are no categories of duplication elements in the datasets, this research analyzed three categories of duplication elements in CMF which are animals, food and non-living things using DEFACTO and CoMo3Dataset. The analysis is performed on PatchMatch-based detection method and the results show that the method able to maintain at least 83% for all duplication elements in both DEFACTO and CoMo3Dataset. Furthermore, the method is able to detect a minimum 92% score for the food category in both datasets. | ||
| 121. Designing an E-voting Framework Using Blockchain: A Secure and Transparent Approach | ||
| Syarifah Bahiyah Rahayu (Universiti Pertahanan Nasional Malaysia), Andrianto Arfan Wardhana (Microsoft Indonesia), Moon-gul Lee (Korea National Defense University) | ||
| With the increasing demand for secure, trustworthy, and transparent voting systems, electronic voting (e-voting) has emerged as a promising solution to address the shortcomings of traditional methods. However, traditional e-voting systems face numerous challenges in ensuring integrity, privacy, and auditability such as paper-based ballots and electronic voting machines. These traditional systems are susceptible to issues such as voter fraud, coercion, and a lack of transparency, undermining the democratic process. This paper proposes a novel approach to designing an e-voting framework using blockchain technology. By leveraging the distributed ledger and consensus mechanisms of blockchain, our framework aims to provide a secure, transparent, and tamper-resistant voting system. These features enable the creation of a secure and transparent voting system that ensures the integrity of votes, protects voter privacy, and enables verifiability and auditability of the entire voting process. The paper presents the key components, design considerations, and benefits of the proposed framework, along with an analysis of its potential challenges and future directions for research and development. The system architecture of the proposed framework establishes communication channels, data flows, and interfaces that facilitate voters’ attendance, secure interactions, and information exchange within the voting system. The use of smart contracts helps enforce the rules and conditions of the voting process on the blockchain, ensuring the accuracy and fairness of the electoral outcome. In conclusion, the proposed e-voting framework using blockchain technology has the potential to revolutionize the electoral process by providing a secure, transparent, and tamper-resistant voting system. By addressing the challenges of traditional e-voting systems and leveraging the inherent features of blockchain technology, we can enhance the integrity, privacy, and trustworthiness of the voting process. | ||
| 131. A Survey on Supervised Machine Learning in Intrusion Detection Systems for Internet of Things | ||
| Shakirah Saidin (Universiti Malaysia Pahang Al-Sultan Abdullah), Syifak Izhar Hisham (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| The Internet of Things (IoT) is expanding exponentially, increasing network traffic flow. This trend causes network security vulnerabilities and draws the attention of cybercriminals. Consequently, an intrusion detection system is designed to identify various network attacks and provide network resource protection. On the other hand, building a steadfast intrusion detection system is difficult since there are numerous flaws to address, such as the presence of supernumerary and irrelevant features in the dataset, leading to low detection accuracy and a high false alarm rate. To address these flaws, researchers are attempting to research on applying supervised machine learning techniques in intrusion detection systems for IoT. Therefore, this paper explores the prevailing machine learning techniques utilized in the intrusion detection system research area to provide better insight in this field. | ||
| 141. CHARITY AND DONATION TRACKING SYSTEM USING QUEUE STRUCTURE | ||
| Manea Abdullah Badheyba (Faculty of Computer Science Universiti Malaysia Pahang Al-Sultan Abdullah), Ldr. Rozlina Bt Mohamed (Faculty of Computer Science Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| With the advent of new technology and online payment systems, acquiring donors for charitable causes has become easier. However, the donation process often ends for donors once they have made their contribution, leaving the remaining work to the charity. This lack of visibility and involvement can lead to donor disengagement and hinder future contributions. To address this problem, we propose implementing a comprehensive donor tracking system that uses the queue which operates on a first-in, first-out (FIFO) basis. This system ensures that the first donor's donation is prioritized and fulfilled before the second donor can utilize and benefit from their donation. This system aims to provide real-time updates on the progress and impact of donations, bridging the gap between donors and beneficiaries. Existing online donation platforms often focus solely on facilitating payments, neglecting post-donation tracking. This lack of transparency leaves donors unaware of how their contributions are utilized and whether they reach the intended beneficiaries, potentially affecting donor trust and confidence. By implementing the queue method, charities can streamline donation workflows, track, and acknowledge donations, and provide transparency to donors. When we examine the current tracking methods used in the donation field, it becomes evident that only a limited number of methods, and only blockchain-based systems are in use. Unfortunately, these systems tend to escalate costs significantly. This paper highlights the how and what are the benefits of adopting the queue method for donor tracking, including improved donor engagement and trust. Ultimately, the proposed system enhances donor satisfaction and maximizes the impact of charitable giving. | ||
| Session II-D (Virtual) (14:00 - 16:00 @ Online) | ||
| Session Chair: TBA | ||
| 30. Real-Time Data Visualization and Analysis using ASP.NET Core's Tag Helpers in Business Intelligence Applications | ||
| Safa'a Bataieneh (Philadelphia University), Samer Hanna (Philadelphia University) | ||
| (Video Link: https://youtu.be/JCAFvH6D82E) | ||
| In today's fast-paced corporate environment, real-time data was essential for making educated decisions, but it was challenging to create dynamic dashboards with drill-down capabilities. This study investigated how Tag Helpers in ASP.NET Core improved maintainability, simplified HTML creation, and enhanced the user experience for real-time data visualization and analysis in business intelligence applications. The researchers demonstrated the power of Tag Helpers in visualizing key metrics and providing real-time insights to businesses. The findings suggested that Tag Helpers offered a powerful tool for creating dynamic web content and facilitating data analysis in real time. | ||
| 44. A Supervised Machine Learning Method for Predicting the Employees Turnover Decisions | ||
| Trirat Arromrit (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy), Korrapin Srisakaew (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy), Napatsakorn Roswhan (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy), Wiriya Mahikul (Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy) | ||
| (Video Link: https://youtu.be/6Zx1blyevaA) | ||
| Human resource management is a crucial component for the smooth operation of business organizations. However, changing perspectives and values among different age groups present significant challenges for organizations. Resignation and quick job changes can lead to huge budgetary and manpower issues. This research aims to develop and compare machine learning algorithms for predicting employees’ turnover decisions using a public dataset on Kaggle.com The dataset includes performance data for 15,000 employees. The eight features and five algorithms, including Random Forest, Support vector machine, Logistic Regression, K-Nearest Neighbor, and Gaussian Naïve Bayes classifier, were employed to develop the model. The results showed that the Random Forest Classifier was the most efficient model with Geometric Mean, F1-score and AUC which are 0.995, 0.995, and 0.999, respectively when evaluated with stratified K-fold cross-validation. Moreover, using the SHapley Additive exPlanations method, five important factors for predicting employee turnover were identified. These factors include satisfaction level, average working hours in a month, number of responsibility projects, time spent with the company and salary level. These features enable the Human Resources department to gain valuable insights, facilitating strategic planning and proactive measures to prevent employee resignations. By doing so, businesses can achieve smoother and more efficient operations. | ||
| 120. Analysis of Sentiment Towards Artificial Intelligent Industry Using Hybrid Natural Language Processing Technique | ||
| Chang Hong (Xiamen University Malaysia) | ||
| (Video Link: https://youtu.be/lHrLFiV3dZ8) | ||
| Artificial Intelligence (AI) has revolutionized various aspects of human life and transformed how people live, work, and interact. However, the development of AI also poses potential risks and ethical concerns. In this report, we aim to analyze the sentiment towards the AI industry using hybrid natural language processing techniques. To achieve our aim, we propose a model that draws upon a survey of related work. Data collection involves gathering user-generated data from social media platforms. We then use hybrid natural language processing techniques to analyze the sentiment towards the AI industry. Our analysis reveals that the sentiment towards the AI industry is generally positive, with many people recognizing its potential benefits. However, there are also concerns about the potential risks and ethical implications of AI development. Some leading figures in the AI industry have expressed concerns about the potential misuse of AI and the need for ethical guidelines. In conclusion, our analysis highlights the transformative effects of AI on various industries and the potential risks associated with its development. We recommend that policymakers and industry leaders work together to develop ethical guidelines for the development and use of AI. This will help to ensure that the benefits of AI are maximized while minimizing the potential risks and ethical concerns. | ||
| 122. Optimized Energy Distribution in Smart Grid System Using Hybrid Machine Learning Techniques | ||
| Daorui Ding (Xiamen University Malaysia), Chang Hong (Xiamen University Malaysia), Venkata Durga Kumar Burra (Xiamen University Malaysia) | ||
| (Video Link: https://youtu.be/cUuuxdfL6H4) | ||
| Smart Grid systems are becoming increasingly important with the rapid advent of industrial parks and residential areas. The aim of the Smart Grid system is to modernize and enhance the efficiency, reliability, and flexibility of electrical power grids. It integrates network, smart sensors, and time series prediction machine learning algorithms into the existing grid transmission system to collect the data and make predictions for optimizing decisions. With the help of big data techniques, Smart Grid systems can provide on-demand power supplies. However, most of the proposed prediction algorithms for Smart Grid system highly rely on pre-defined parameters and influential factors, such kind of models fail to dynamically update themselves to cater to the changing world especially when emergencies happen. In this paper, we introduce Dynamic Bayesian Network (DBN) concept and propose a new prediction architecture Smart Grid+ to improve the systems’ self-adaptability and resilience to power outages, faults, and disruptions. Because of DBN’s ability of dynamical expansion and posterior probability calculation from prior data, our proposed Smart Grid+ responds to emergencies more quickly and predicts the electricity load more precisely. And we believe it can better apply to the requirements of Smart Grid system and has a promising future. | ||
| 134. EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification | ||
| Niful Islam (Department of Computer Science and Engineering, United International University), Md. Mehedi Hasan Jony (Department of Computer Science and Engineering, United International University), Emam Hasan (Department of Computer Science and Engineering, United International University), Sunny Sutradhar (Department of Computer Science and Engineering, United International University), Atikur Rahman (Department of Computer Science and Engineering, United International University), Md. Motaharul Islam (Department of Computer Science and Engineering, United International University) | ||
| (Video Link: https://www.youtube.com/watch?v=ttFtoSR89tw) | ||
| Improper disposal of e-waste poses global environmental and health risks, raising serious concerns. The accurate classification of e-waste images is critical for efficient management and recycling. In this paper, we have presented a comprehensive dataset comprised of eight different classes of images of electronic devices named the E-Waste Vision Dataset. We have also presented EWasteNet, a novel two-stream approach for precise e-waste image classification based on a data-efficient image transformer (DeiT). The first stream of EWasteNet passes through a sobel operator that detects the edges while the second stream is directed through an Atrous Spatial Pyramid Pooling and attention block where multi-scale contextual information is captured. We train both of the streams simultaneously and their features are merged at the decision level. The DeiT is used as the backbone of both streams. Extensive analysis of the e-waste dataset indicates the usefulness of our method, providing 96% accuracy in e-waste classification. The proposed approach demonstrates significant usefulness in addressing the global concern of e-waste management. It facilitates efficient waste management and recycling by accurately classifying e-waste images, reducing health and safety hazards associated with improper disposal. | ||
| 136. Improving Data Security in IoT Cloud Computing via Compiler-Supported Homomorphic and Symmetric Encryption Techniques | ||
| Jingjia Huang (Xiamen University Malaysia Sepang, Malaysia), Xincheng Huang (Xiamen University Malaysia Sepang, Malaysia) | ||
| (Video Link: https://youtu.be/CHh5T9fneyg) | ||
| In traditional cloud storage and cloud computing systems, symmetric encryption is typically employed by service providers to convert data into cipher text. This methodology requires the user to trust the service provider with their data, as any modifications necessitate the conversion of cipher text back into original data. Homophobic Encryption (HE), which enables computations on encrypted data without revealing the original content, presents a solution to this privacy challenge. However, its application is limited due to performance overheads and programmability challenges. This paper aims to enhance cloud computing security and mitigate privacy risks by investigating optimized compiler models. Through extensive literature review and analysis, we have selected a compiler model based on the Porcupine privacy computing approach and a component called Quill, which translates plain text specifications into equivalent implementations in homomorphic cryptography. Concurrently, we propose additional optimization strategies that improve the efficiency and cost-effectiveness of homophobic encryption. Our work signifies a step forward in the realm of secure, private cloud computing. | ||
| 137. A Comprehensive Approach to Mitigate Return-Oriented Programming Attacks: Combining Operating System Protection Mechanisms and Hardware-Assisted Techniques | ||
| Xingnan Zhang (Program in Computer Science & Technology, Xiamen University Malaysia), Jingjia Huang (Program in Computer Science & Technology, Xiamen University Malaysia), Yue Feng (Program in Computer Science & Technology, Xiamen University Malaysia) | ||
| (Video Link: https://youtu.be/vxPyE9IsqdI) | ||
| This paper proposes a comprehensive approach to mitigate ROP (Return-Oriented Programming) attacks by combining internal operating system protection mechanisms and hardware-assisted techniques. Through extensive literature review, we identify the effectiveness of ASLR (Address Space Layout Randomization) and LBR (Last Branch Record) in preventing ROP attacks. We present a process involving buffer overflow detection, hardware-assisted ROP attack detection, and the use of Turing detection technology to monitor control flow behavior. We envision a specialized tool that views and analyzes the last branch record, compares control flow with a baseline, and outputs differences in natural language. This tool offers a graphical interface, facilitating the prevention and detection of ROP attacks. The proposed approach and tool provide practical solutions for enhancing software security. | ||
| 140. Enhancing Subcluster Identification in IoT Sensor Networks with Hierarchical Clustering Algorithms and Dendrograms | ||
| Fuad Bajaber (King Abdulaziz University) | ||
| (Video Link: https://youtu.be/PpL9hNrst0c) | ||
| IoT sensor networks (ISNs) have gained significant attention due to their broad applicability in various fields. One crucial aspect in ISNs is the efficient utilization of network resources, including energy, latency, and scalability. In this paper, we propose a hierarchical clustering-based approach to improve energy efficiency, latency reduction, and scalability in ISNs. By employing complete-linkage hierarchical clustering, the network is divided into clusters, and dendrograms are utilized to further partition clusters into subclusters. The objective is to optimize network performance with respect to energy efficiency, latency, and scalability. Extensive simulations and performance evaluations are conducted to assess the effectiveness of the approach. The results demonstrate that the hierarchical clustering approach offers improved energy efficiency, reduced latency, and enhanced scalability in ISNs, making it a promising solution for resource optimization in these networks. | ||
| Date: 2023-08-27 | ||
| Session III-A (08:30 - 10:00 @ Pandan Room) | ||
| Session Chair: SHAZWANI BINTI KAMARUDIN | ||
| 5. Fintech future business & Cyber vulnerabilities and challenges | ||
| Dr Venkata Venugopal Rao Gudlur (Veritas University College) | ||
| Financial applications and business processes require a secure environment to have safe transactions. But today, new start-up companies and business entities are unable to understand the importance of secure transactions. Therefore, cyber vulnerabilities are unstoppable and have greater impact on current and future financial transactions. Technology based financial transactions and process are advanced terms to be applied to many business entities in the current world. Most of the transactions are done via internet and mobile based applications. The users are exposed to various issues related to data security or translation security. In this paper the researcher is explaining various vulnerabilities related to fintech for future business and financial transactions and explained prevention methods with a proposed model. | ||
| 12. PREDICTING MENTAL HEALTH DISORDER ON TWITTER USING MACHINE LEARNING TECHNIQUES | ||
| Shi Ru Lim (UNIVERSITI MALAYSIA PAHANG), Nur Shazwani Binti Kamarudin (UNIVERSITI MALAYSIA PAHANG), Nur Hafieza Binti Ismail (UNIVERSITI MALAYSIA PAHANG), Nik Ahmad Hisham Ismail (INTERNATION ISLAMIC UNIVERSITY MALAYSIA), Nor Ashikin Mohamad Kamal (UNIVERSITI TEKNOLOGI MARA) | ||
| Social media gives young people a place to voice their difficulties and trade opinions on current events in the digital era. Therefore, it is possible to analyze human behavior using internet media. However, the illness of mental disorder is common yet often ignored. Social media makes it possible to identify mental health disorders in large populations. Many efforts have been made to evaluate individual postings using machine-learning techniques to identify people with mental health conditions on social media. This study attempted to predict mental health disorders among Twitter users using machine learning techniques. Sentiment analysis was used in this study to identify people with mental health disorders by focusing entirely on tweets on such conditions on Twitter. Support Vector Machine (SVM), Decision Tree, and Nave Bayes are three examples of machine learning approaches applied in this study. To assess the algorithms, the performance and accuracy of these three algorithms are compared. After the study, the performance of the support vector machine classifier shows outstanding results compare to others with an accuracy of 97.23% and precision of 98.38%. | ||
| 36. Metaverse in Education: Insights from South Korea and Potentials for Malaysia | ||
| Najihah Binti Nasir (Jeju National University), Jiyong Moon (Jeju National University), Seong Baeg Kim (Jeju National University) | ||
| Metaverse, a cutting-edge technology offering immersive and engaging educational experiences, is revolutionizing learning by enabling real-world users to interact and collaborate with others in a virtual space. South Korea is one of leading countries in this field, with extensive research and application at various levels of education and across disciplines. Beyond enhancing teaching and learning, the metaverse also supports non-academic educational experiences. In Malaysia, various educational technology been employed in response to limitation of conducting face-to-face class during Covid-19 era. However, metaverse remains underutilized and under-discussed within the Malaysian school educational context. Consequently, this study aims to inform potential metaverse usage for Malaysia school education by specifically investigates the application of metaverse technology in South Korea education and reviewing existing research of metaverse education in Malaysia. As a result, we propose potential utilization and challenges of metaverse in Malaysia's school educational environment. The findings of this article are expected to pave the way for more promising metaverse research within the Malaysian education system. | ||
| 72. RSSI-Guided Cluster Head Selection for Optimal Optimization in IoT-Enabled WSNs | ||
| Azamuddin Ab. Rahman (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| The Internet of Things (IoT) relies on Wireless Sensor Networks (WSN) to collect physical data from the environment. Sensor nodes in WSN have limited resources such as memory, energy, and processing power, and data transmission consumes the most energy. Therefore, clustering and data aggregation techniques are designed to achieve energy efficiency in WSN. This research paper proposes a new method, called Energy Efficient of Cluster Head and Relay Node (EECR), which selects Cluster Heads (CH) based on residual energy, distance to the Base Station (BS), and RSSI. The EECR technique, which uses fuzzy logic for cluster head selection. The aggregated data of the cluster head is then transmitted to the BS to achieve energy efficiency. The EECR technique was tested under three different scenarios and achieved better results in terms of energy efficiency and network lifetime compared to SEP, MAP and EECR 1. | ||
| 146. Knowledge of the Utilization of Telegram for Learning Among Primary Students in Kuantan | ||
| Saadiah Awang Salim (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Noor Azida Sahabudin (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Gausallyaa Murugiah (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Nur Shamsiah Abdul Rahman (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang), Norhasyimah Hamzah (Department of Vocational Education Faculty of Technical and Vocational Education Universiti Tun Hussein Onn Malaysia) | ||
| There are various online learning platforms already available such as Google Classroom, Coursera, Skillshare and Udemy. In this regard, the Ministry of Education Malaysia (MOE) has launched a learning platform, Digital Educational Learning Initiative Malaysia (Delima). This platform offers all the digital applications and services needed by teachers, and students in the Malaysian school system. However, the use of Delima did not get the response as expected. However, the use of Delima did not get the response as expected. Telegram can be seen as one of the effective platforms for students in online learning to support these efforts. The focus of this study is to identify the utilization of Telegram for learning among primary students, to determine the factors that influence the utilization of Telegram among primary students and determine students' perceptions of Telegram as a learning platform. This quantitative study was conducted by conducting a questionnaire to 361 primary students aged 11 to 12 years around Kuantan, Pahang. The TAM model was used in this study. The study results show nine factors influence students' utilization of Telegram in learning: usefulness, usability, accessibility, ELearning Attitude, functionality, enjoyment, subjective norms, behavioral intentions, and actual use. The results showed that the utilization of Telegram for learning based on the factors that have been identified is in the range of 57% to 72%. With this, the utilization of Telegram as a learning tool can increase productivity, performance, and thus motivation to primary school students. | ||
| Session III-B (08:30 - 10:00 @ Halia Room) | ||
| Session Chair: MOHD IZHAM BIN MOHD JAYA | ||
| 86. Real-time Fault Diagnostic in Rotating Shaft using IoT-based Architecture and Fuzzy Logic Analysis | ||
| Nur Afiqah Mohd Azman (Universiti Malaysia Pahang), M. Izham Jaya (Universiti Malaysia Pahang), Azlee Zabidi (Universiti Malaysia Pahang) | ||
| The rotating shaft, commonly known as an axle, plays a crucial role in enabling rotational motion and power transmission within industrial rotating machines. However, assessing the condition of a rotating shaft presents a significant challenge due to its concealed nature. Traditionally, manual inspections by technicians have been relied upon to detect potential damage, resulting in time-consuming processes and potential delays in fault diagnostic. To address this issue, this paper proposes an IoT-based architecture integrated with fuzzy logic to enable real-time fault diagnostic in rotating shaft. By employing fuzzy logic classification based on vibration frequency and noise analysis, the system accurately determines the condition of the rotating shaft. Experimental results confirm the successful implementation of the proposed system, providing valuable insights into the current condition of the rotating shaft. This real-time approach enables proactive maintenance strategies and mitigates the risk of unexpected industrial machine failures. | ||
| 88. SAISMS: Transforming Ammunition Management Through IoT-Enabled Inventory and Safety Monitoring System | ||
| Mohammad Faris Bin Mahdhir (UNIVERSITI MALAYSIA PAHANG), Nor Saradatul Akmar Binti Zulkifli (UNIVERSITI MALAYSIA PAHANG), Mohd Zamri Bin Osman (UNIVERSITI MALAYSIA PAHANG), Azlee Bin Zabidi (UNIVERSITI MALAYSIA PAHANG), Mohd Izham Bin Mohd Jaya (UNIVERSITI MALAYSIA PAHANG) | ||
| Ammunition plays a crucial role in military and defense operations, requiring significant investments to arm military forces adequately. However, ammunition is susceptible to environmental factors that can degrade its quality, leading to defects or even accidental explosions. To ensure constant combat readiness, it is vital to maintain secure storage facilities with sufficient ammunition supplies. This project aims to enhance ammunition inventory and safety management procedures by leveraging IoT technologies. This project proposed the implementation of an IoT-powered web application dashboard that utilizes weight measurements to provide real-time inventory tracking and monitors environmental conditions such as temperature and humidity for quality control. Additionally, the system can predict ammunition condition outcomes. By adopting this IoT-based solution, ammunition management processes will be streamlined, resulting in improved efficiency and effectiveness. | ||
| 90. Exploring Machine Learning in IoT Smart Home Automation | ||
| Quadri Waseem (Universiti Malaysia Pahang; AnalytiCray), Wan Isni Sofiah Wan Din (Universiti Malaysia Pahang), Azamuddin Bin Ab Rahman (Universiti Malaysia Pahang), Kashif Nisar (Swinburne University of Technology, Sydney) | ||
| The Internet of Things (IoT) is used in a variety of industries such as industrial automation, mobility, healthcare, agriculture, etc. IoT has caught the interest of various organizations and researchers in every field of life. There are many applications of IoT, such as smart cities, smart communities, smart homes and many more. "Smart Homes” has emerged as one the latest Internet of Things (IoT) applications known to automate household equipment’s using remote or automated functioning from remote locations to improve the quality of life for its inhabitants. For a smart home system to function effectively, the machine learning (ML) implementation must go beyond basic remote control and simple automation. The most advanced and useful smart home research must focus on scientific implementation instead. To enhance user interactions, boost security, and save energy, such value must be distributed throughout the IoT Smart Home systems effectively and efficiently. Thus, only then the smart system must be able to recognize user behavior and anticipate user activities expertly. To fully realize its potential and provide homeowners with the tremendous and unexpected benefits, more research and development in the fields of machine intelligence and smart home automation are required. In this research work, we explore the overall domain of IoT smart homes using ML for automation purposes. | ||
| 105. Examining the Correlations Between Teacher Profiling, ICT Skills, and the Readiness of Integrating Augmented Reality in Education | ||
| Azrie Salleh (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Danakorn Nincarean Eh Phon (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Nur Shamsiah Abdul Rahman (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Suhaizal Hashim (Universiti Tun Hussien Onn Malaysia), Noor Hidayah Che Lah (Faculty of Computing & Meta Technology, Universiti Pendidikan Sultan Idris) | ||
| This study explores the relationship between respondent demographic profiling and the factors affecting teachers' readiness in adopting augmented reality (AR) for teaching and learning. While AR holds promise for transforming educational practices, the readiness of teachers to adopt this technology remains a critical factor for successful implementation. However, there is a lack of research examining the specific relationship between respondent demographics and the factors influencing teachers' readiness in AR adoption. This study aims to fill this gap by employing a quantitative research approach and survey methodology. By analyzing the data collected from primary school teachers, including demographic information and factors affecting readiness, the study seeks to identify any significant correlations or patterns. The findings will contribute to a better understanding of how respondent demographics influence teachers' readiness in AR integration, addressing a crucial problem in the field of educational technology. The insights gained from this study will inform policymakers and educational institutions in developing targeted strategies to enhance teachers' readiness and support the successful integration of AR in primary school classrooms. | ||
| 115. Factors Affecting Cyber Bullying Behaviours Among University Students: A review on Conceptual Framework | ||
| Nur Shamsiah Abdul Rahman (Universiti Malaysia Pahang Al-Sultan Abdullah), Noor Azida Sahabudin (Universiti Malaysia Pahang Al-Sultan Abdullah), Danakorn Nincarean Eh Phon (Universiti Malaysia Pahang Al-Sultan Abdullah), Mohd Faizal Ab Razak (Universiti Malaysia Pahang Al-Sultan Abdullah), Anis Farihan Mat Raffei (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| The conceptual framework that was utilized to pinpoint the factors influencing university students' cyberbullying behaviours was examined in this study. According to a systematic screening of recent research articles (from 2013 to 2023) pertaining to online bullying behaviours among university students, the findings were given. After evaluating theoretical models and associated concepts, we suggest using the Theory of Planned Behaviour to evaluate factors influencing cyberbullying behaviours among university students. The findings of this study are discussed, and it is concluded that subjective norms, attitude, perceived behavioural control, social media use, and intentions all have the ability to influence university students' cyberbullying behaviours. | ||
| Session IV-A (10:15 - 12:45 @ Pandan Room) | ||
| Session Chair: SALWANA BINTI MOHAMAD @ ASMARA | ||
| 40. chatGPT vs Mentor : Programming Language Learning Assistance System for Beginners | ||
| Junseong Moon (Jeju National University), Raeeun Yang (Jeju National University), Somin Cha (Jeju National University), Seong Baeg Kim (Jeju National University) | ||
| With the recent rise of large language models, learning assistance systems that utilize natural language processing capabilities are gaining attention. However, existing learning assistance systems mainly aim to provide answers to learners' questions, and have limitations in accurately identifying individual learning needs and analyzing questions to provide customized answers. Therefore, In this study, we compare chatGPT and mentor responses in the process of learning a programming language and find out the limitations of each and develop a system to assist programming language learning using chatGPT. The developed system allows learners to get real-time answers from chatGPT immediately, and can also provide additional personalized guidance and answers based on the mentor's judgment. In addition, through the analysis of learners' responses and chatGPT's answers, we aim to evaluate the appropriateness and accuracy of the answers and explore and suggest technical limitations and improvement measures of chatGPT. By analyzing and discussing the differences between the traditional mentoring method and the learning assist method using chatGPT, we aim to diagnose the limitations of chatGPT in programming language learning. Through this study, we expect to develop an effective programming language learning assistance system by integrating the advantages of chatGPT and mentoring to improve learners' understanding and learning efficiency. | ||
| 43. SDN enabled Big Data Analytics and Framework for sensor data of Vehicle Health, Safety and Monitoring System | ||
| Tanvir Ahmad (University Malaysia Pahang (UMP)), Nor Syahidatul Nadiah Binti Ismail (University Malaysia Pahang (UMP)), Abdullah Mat Safri (University Malaysia Pahang (UMP)), Md Arafatur Rahman (University of Wolverhampton), Mohammad Sojon Beg (University Malaysia Pahang (UMP)), M. Taher Bin Bakhtiar (International Islamic University Malaysia (IIUM)) | ||
| Vehicular network enabled vehicle health, safety and monitoring system is gaining attention for its potential application while software defined network (SDN) is supporting vehicular communication for designing core of the network. Vehicular network emits enormous amount of data where most of them are sensor data and that amount of data required to undergo analyzed for productive output. There are two types of sensor data are used in vehicular network, vehicle sensor data (VSD) and roadside sensor data (RSD). Flow based SDN controller examines every packet of the network which is responsible of engagement of resources gravely. For vehicular health monitoring and safety applications, SDN doesn’t required to check and analyze RSD. In this paper, a framework is proposed that promises to ignore RSD and only consider VSD for vehicle health, safety and monitoring applications. With this connections, this paper proposes big data module along with SDN controller and inside the big data module, a partitioner program is designed. The partitioner program categorize VSD and RSD on the basis of certain parameters like data payload, technology used, packet header and restrict RSD to be processed by SDN controller. A combiner program is designed that bind both VSD and RSD to fed to the application plane of system. Additionally, a big data analytics for vehicle health, safety and monitoring application is derived. | ||
| 80. Cloud of Word vs DroidKungfu: Performance Evaluation in Detecting Root Exploit Malware with Deep Learning Approach | ||
| Che Akmal Che Yahaya (Tunku Abdul Rahman University of Management and Technology), Ahmad Firdaus Zainal Abidin (Universiti Malaysia Pahang), Mohd Azlee Zabidi (Universiti Malaysia Pahang), Noor Akma Abu Bakar (Universiti Malaysia Pahang), Mukrimah Nawir (Tunku Abdul Rahman University of Management and Technology), Philimal Normelissa Ani Abdul Malek (Tunku Abdul Rahman University of Management and Technology) | ||
| Android mobile malware is a type of malware that execute malicious activities (stealing and collecting data and running programs without the user’s knowledge) in victims’ Android mobile device. There are several types of malware, for instance; 1) Root exploit; 2) Botnet; 3) Trojan; and 4) Ransomware. Among these, root exploit is the most dangerous as it is able to gain control over the root privileges of an operating system (OS) stealthily, avoids security software scanning, and further installs other types of malware. Moreover, there are multiple types of root exploit families that attack Android, such as Droidkungfu, Droiddream, and Asroot. However, Droidkungfu possesses the highest number of samples among other families and able to survive with updated versions (version one until six). Therefore, the updated version could be increasing in the future. Furthermore, finding the best features in detecting root exploit is challenging, as the categories (permission, system calls, and intent) are many to choose from. Moreover, finding the ideal number of features is challenging as well, as it is able to affect machine learning detection. Thus, this study focuses to develop a solid model to predict undiscovered Droidkungfu by converting all the codes in images and adopted a Convolutional neural network (CNN) with Word of Cloud (WoC) to discover features automatically without considering the categories and number of features in the code. Among all parameters in evaluation, the highest result is 96 % accuracy in predicting unknown Droidkungfu and proved to detect new versions of this family in the future | ||
| 92. Product Recommendation using Deep Learning in Computer Vision | ||
| Zuriani Mustaffa (Universiti Malaysia Pahang), Sharvinteraan A/l C. Mogan (Universiti Malaysia Pahang), Mohd Herwan Sulaiman (Universiti Malaysia Pahang), Ferda Ernawan (Universiti Malaysia Pahang) | ||
| Recently, recommendation models have gained popularity due to their effectiveness in improving customer satisfaction and deriving sales. However, current product recommendation models have a drawback: they lack personalized and targeted advertisements for individual users. Consequently, the recommendations provided are random and not tailored to users’ preferences. This limitation negatively impacts the system’s ability to deliver relevant and personalized advertisements, leading to reduced user engagement and potentially lower conversion rates. Moreover, the absence of personalized advertisements can result in user dissatisfaction as they may receive recommendations that are irrelevant or not aligned with their interests and needs. To address these challenges, this study proposed a targeted product recommendation model using Deep Learning (DL) techniques in computer vision. The study utilizes the dataset of human images obtained from the Kaggle website, which includes details such as gender, class, and age. Findings of the study demonstrated a high level of accuracy in product recommendations, indicating the potential for significant improvements in addressing the issues. In conclusion, the proposed method achieves good accuracy in predicting the gender and age, and provides appropriate product recommendations based on these features. | ||
| 99. Determining the Best Weightage Feature in Parameterization Process of GCCD Model for Clone Detection In C-based Applications | ||
| Nurul Syafiqah Zaidi (Universiti Malaysia Pahang), Al-fahim Mubarak-ali (Universiti Malaysia Pahang), Abdul Sahli Fakharudin (Universiti Malaysia Pahang), Rahiwan Nazar Romli (Universiti Malaysia Pahang) | ||
| The term "code clone" relates to code that has been replicated many times in a program. Primarily, Type-1, Type-2, Type-3, and Type-4 serve as the four distinct categories for the classification of code clones. Distinct code clone approaches and tools have been implemented for identifying code clones over the years. To overcome the limitation of generalization in recognizing all types of clones, Generic Code Clone Detection (GCCD) model is developed. The five procedures that make up the GCCD model's foundational structure are pre-processing, transformation, parameterization, categorization, and match detection. However, the preceding GCCD model can only detect all types of code clone in Java applications. Based on this limitation, it is important to propose a code clone detection model which can support other programming language in different applications. The primary objective of this proposed research is to enhance the process in Generic Code Clone Detection (GCCD) model that can improve the code clone detection result, specifically in C based applications. To achieve the desired objective, some enhancements in the GCCD model have been recommended which are to propose a constant and weightage for Pre-processing and Parameterization process in GCCD model. The proposed work will be tested in a case study involving four C applications. As determined by the code clone detection results from the proposed enhancement, void with its weightage is the preeminent constant and weightage for the Generic Code Clone Detection Model in C based applications. | ||
| 123. Taxonomy of SQL Injection: ML Trends & Open Challenges | ||
| Raed Abdullah Abobakr Busaeed (University Malaysia Pahang AL-Sultan Abdullah), Wan Isni Sofiah Wan Din Wan Din (University Malaysia Pahang AL-Sultan Abdullah), Quadri Waseem Waseem (University Malaysia Pahang AL-Sultan Abdullah), Azlee Bin Zabidi (University Malaysia Pahang AL-Sultan Abdullah) | ||
| Abstract— A significant and ever-present threat to web applications and database security is SQL injections. During these attacks, malicious SQL statements are injected into input fields of data-driven systems, leading to unauthorized access and data breaches. Consequently, a need is generated to understand the nature of the attacks, detection, and effective prevention techniques. This research paper focuses on providing a taxonomy and comprehensive survey of SQL injection attacks, detection and prevention including their various types and techniques. Additionally, it explores the current state-of-the-art and evaluation for attacks, detection, and prevention techniques. This research paper also discusses and provides a taxonomy of current machine learning (ML) trends and their open challenges for detection purpose. Finally, this paper ends with discussion aiming to equip system administrators, researchers, scientists and practitioners with the knowledge and strategies required to effectively mitigate the risks associated with SQL injection attacks. Eventually, this will help to enhance the security and resilience of web applications and databases in the face of this significant threat. | ||
| 125. Identifying PTSD Symptoms using Machine Learning Techniques on Social Media | ||
| Muhamad Aiman Ibrahim (University Malaysia Pahang Al-Sultan Abdullah), Nur Hafieza Ismail (University Malaysia Pahang Al-Sultan Abdullah), Nur Shazwani Kamarudin (University Malaysia Pahang Al-Sultan Abdullah), Nur Syafiqah Mohd Nafis (University Malaysia Pahang Al-Sultan Abdullah), Ahmad Fakhri Ab. Nasir (University Malaysia Pahang Al-Sultan Abdullah) | ||
| Post-traumatic stress disorder (PTSD) is a mental health illness brought on by watching or experiencing a horrific incident. Flashbacks, nightmares, acute anxiety, and uncontrolled thoughts about the unforgettable incident are the possible symptoms faced by PTSD sufferers. The PTSD diagnosis is usually done by a mental health specialist based on the symptoms that the person has, and the task is very time-consuming. Due to the widespread use of social media in recent years, it has opened up the opportunity to explore PTSD signs in users’ postings on Twitter. The content-sharing feature available on this platform has allowed its users to share personal experiences, thoughts, and feelings that could reflect their psychological status. Thus, the goal of this work is to identify the PTSD symptom from text posting on Twitter. The crawled text posting is filtered and trained on selected machine learning and deep learning methods. The experiment results show that the support vector machine performed the best with 91% accuracy compared to others. This extracted model could be used in identifying PTSD symptoms on social media. | ||
| 128. Development of Light Energy Harvesting for Wearable IoT | ||
| Eisyah Hanun Zawawi (Universiti Teknologi PETRONAS), Micheal Drieberg (Universiti Teknologi PETRONAS), Azrina Abd Aziz (Universiti Teknologi PETRONAS), Patrick Sebastian (Universiti Teknologi PETRONAS), Hai Hiung Lo (Universiti Teknologi PETRONAS) | ||
| In recent times, wearables internet of things (IoT) devices has gained popularity due to their ability to improve many facets of our daily lives. This innovative technology is equipped with sensors, processors, and other electronic components to collect and transmit data to the cloud for processing important insights. However, the limited power supply, frequent recharging, and user inconvenience, are some of the critical barriers to their widespread adoption. To circumvent these constraints, effective energy harvesters are essential. This paper proposes light energy harvesting to power up wearable IoT devices. It consists of a small photovoltaic (PV) panel, energy management IC and lithium polymer (LiPo) rechargeable battery. The experiments include a baseline system, LiPo charging and discharging, and the light energy harvesting system under natural sunlight. Experimental results show that the light energy harvesting enabled wearable IoT system can provide an increase in lifetime of more than 300% when compared to the baseline system. This shows that light energy harvesting is a reliable and efficient option to power a wearable IoT device, making it a promising option for self-powered, and sustainable wearables IoT. | ||
| 142. A Review of Knowledge Graph Embedding Methods of TransE, TransH and TransR for Missing Links | ||
| Salwana Mohamad @ Asmara (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang,), Noor Azida Sahabudin (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang,), Nor Syahidatul Nadiah Ismail (Faculty of Computing Universiti Malaysia Pahang Pekan, Pahang,), Ily Amalina Ahmad Sabri (Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu) | ||
| Knowledge representation and reasoning require knowledge graph embedding as it is crucial in the area. It involves mapping entities and relationships from a knowledge graph into vectors of lower dimensions that are continuous in nature. This encoding enables machine learning algorithms to effectively reason and make predictions on graph-structured data. This review article offers an overview and critical analysis specifically about the methods of knowledge graph embedding which are TransE, TransH, and TransR. The key concepts, methodologies, strengths, and limitations of these methods, along with examining their applications and experiments conducted by existing researchers have been studied. The motivation to conduct this study is to review the well-known and most applied knowledge embedding methods and compare the features of those methods so that a comprehensive resource for researchers and practitioners interested in delving into knowledge graph embedding techniques is delivered. | ||
| 145. AN AUTOMATED STRABISMUS CLASSIFICATION USING MACHINE LEARNING ALGORITHM FOR BINOCULAR VISION MANAGEMENT SYSTEM | ||
| Muhammad Amirul Isyraf Rohismadi (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Anis Farihan Mat Raffei (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Nor Saradatul Akmar Zulkifli (Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah), Mohd. Hafidz Ithnin (Kulliyah of Medicine, International Islamic University Malaysia, Pahang), Shah Farez Othman (Kulliyah of Medicine, International Islamic University Malaysia, Pahang) | ||
| Binocular vision is a type of vision that allows an individual to perceive depth and distance using both eyes to create a single image of their environment. However, there is an illness called strabismus, where it is difficult for some people to focus on seeing things clearly at a time. There are many diagnoses that need to be done for doctors to diagnose whether patients suffer from strabismus or not. Besides, a new practitioner could lead to misdiagnosis due to lack of professional experience and knowledge. To overcome these limitations, a machine learning algorithm, which is a case-based reasoning, is developed to automate the strabismus classification. The results showed that the case-based reasoning algorithm provides 91.8% accuracy, 89.29% precision, 92.59% recall and 90.91% F1-Score. This shows that using the case-based reasoning algorithm can give better performance in classifying the class. | ||
| Session IV-B (10:15 - 12:45 @ Halia Room) | ||
| Session Chair: NURUL IZZATI | ||
| 13. COVID-19 FAKE NEWS DETECTION MODEL ON SOCIAL MEDIA DATA USING MACHINE LEARNING TECHNIQUES | ||
| Kai Xuan Kelvin Liew (UNIVERSITI MALAYSIA PAHANG), Mohaiminul Islam Bhuiyan (UNIVERSITI MALAYSIA PAHANG), Nur Shazwani Kamarudin (UNIVERSITI MALAYSIA PAHANG), Ahmad Fakhri Ab. Nasir (UNIVERSITI MALAYSIA PAHANG), Muhammad Zulfahmi Toh Abdullah (UNIVERSITI MALAYSIA PAHANG) | ||
| Social media sites like Instagram, Twitter, and Facebook have become indispensable parts of the daily routine. These social media sites are powerful instruments for spreading the news, photographs, and other sorts of information. However, since the emergence of the COVID-19 pandemic in December 2019, many articles and headlines concerning the COVID-19 epidemic have surfaced on social media. Social media is frequently used to disseminate fraudulent material or information. This disinformation may confuse consumers, perhaps causing worry. It is hard to counter the widespread dissemination of disinformation. As a result, it is critical to develop a model for recognizing fake news in the news stream. The dataset, which would be a synthesis of COVID-19-related news from numerous social media and news sources, is utilized for categorization in this work. Markers are retrieved from unstructured textual data gathered from a variety of sources. Then, to eliminate the computational burden of analyzing all of the features in the dataset, feature selection is done. Finally, to categorize the covid -19 related dataset, multiple cutting-edge machine-learning algorithms were trained. Support Vector Machine (SVM), Naïve Bayes (NB), and Decision Tree (DT) are the machine learning models presented. Finally, numerous measures are used to evaluate these algorithms such as accuracy, precision, recall, and F1 score. The Decision Tress algorithm reported the highest accuracy of 100% compared to the Support Vector Machine 98.7% and Naïve Bayes 96.3%. | ||
| 14. Feature Selection Using Law of Total Variance with Fast Correlation-Based Filter | ||
| Azlyna Senawi (Universiti Malaysia Pahang), Nur Atiqah Mustapa (Universiti Malaysia Pahang), Zun Liang Chuan (Universiti Malaysia Pahang) | ||
| The increased dimensionality of data poses a formidable obstacle to completing data mining tasks. Due to the extraneous features associated with high-dimensional data, processing and analysis took longer and were less precise. As a pre-processing phase in the analysis of data mining tasks, feature selection is effective at reducing dimensionality, removing irrelevant characteristics, increasing accuracy, and enhancing the readability of the results. This research proposes the law of total variance with fast correlation-based filter (LTVFCBF) as a new filtering method for handling feature selection with data of varying dimensionalities. LTVFCBF chose the significant features by recognizing the relevant features and redundancy among the relevant features. The analysis is conducted with ten datasets of varied dimensionality to evaluate the performance of the proposed LTVFCBF and validated by four classifiers: KNN, NB, SVM, and BG. The LTVFCBF and LTV methods have been compared regarding the number of selected features, classification accuracy, and execution time. Overall, the suggested LTVFCBF has the potential to minimize the dimensionality of data by selecting a lesser significant feature with better accuracy. However, it required a slightly higher execution time compared to LTV. Aside from that, LTVFCBF can achieve comparable accuracy with a faster execution time when less than half of the original features are maintained, regardless of the dimensional size of the dataset. The proposed method can produce a promising outcome and may be regarded as an effective filter method for the feature selection domain. | ||
| 77. Hand Calibration with Limited Data As The Initial Step Towards System Dynamics Model Validation For The COVID-19 Case In Malaysia. | ||
| Aisyah Ibrahim (Faculty of Computing, Universiti Malaysia Pahang, Al-Sultan Abdullah, Malaysia), Tuty Asmawaty Abdul Kadir (Faculty of Computing, Universiti Malaysia Al-Sultan Abdullah Pahang, Malaysia), Roderick H. Macdonald (School of Integrated Sciences, James Madison University, Virginia), Hamdan Daniyal (Faculty of Electrical and Electronic Engineering Technology, Universiti Malaysia Pahang, Malaysia) | ||
| This paper presents the manual calibration effort for the System Dynamics (SD) COVID-19 model for Malaysia. This study aims to develop a COVID-19 SD model based on the COVID-19 scenario in Malaysia. The SD model consisted of nine compartments and was adapted based on a standard disease SEIR model using Vensim DSS. While the development of the model is still ongoing, an initial validation was carried out between ‘Actively Infected’ and the case data gathered from the Malaysia Ministry of Health's official COVID-19 websites. During this period, the parameters were manually adjusted by hand to align the model's output with the actual data. Despite the challenges encountered during the manual calibration process, the expected outcome was not easy to achieve, but the result was acceptable. It is important to note that the lack of such strategies may compromise the model’s validity. This paper also discusses the challenges posed by hand calibration, the lesson learned during this work, and the potential future implications of this work. | ||
| 102. AI-Generated CT Scan Image for Improving Colorectal Cancer Classification | ||
| Syafie Nizam (Department of Physics, Kulliyyah of Science, IIUM), Mohd Adli Md Ali (Department of Physics, Kulliyyah of Science, IIUM), Mohd Radhwan Abidin (Department of Radiology, Kulliyyah of Medicine, IIUM) | ||
| This research focuses on the improvement of classification of abnormal and normal CT scan images in the context of colorectal cancer by using generated CT scan images. Limited data availability poses a challenge as classification models, particularly deep learning models, require substantial amounts of data to achieve optimal performance. To address this issue, we employ a Generative Adversarial Networks (GANs) based model to generate additional data using the existing dataset. Subsequently, we retrain the classification model to assess any improvements resulting from the augmented data. Our findings indicate that StyleGAN2-ADA effectively generates synthetic CT scan images of colorectal cancer patients. Leveraging the generated images, we observe an enhancement in the classification performance. These results suggest the potential of data augmentation using GAN-based models to improve the accuracy and efficacy of classification models in the field of medical imaging analysis. | ||
| 112. Loan Eligibility Classification Using Logistic Regression | ||
| Paul Law Lik Pao (Universiti Malaysia Pahang), Mohd Arfian Ismail (Universiti Malaysia Pahang) | ||
| Machine learning is becoming increasingly vital in various domains, including loan eligibility classification, due to its ability to analyze large amounts of data, develop predictive models, adapt to new information, and automate processes. This research paper presents a study on loan eligibility classification using a machine learning approach by comparing the performance of three Machine Learning algorithms which were Logistic Regression, Random Forest, and Decision Tree. This research was conducted using Python and Jupyter Notebook for data analysis and model development. The models were then evaluated on the testing set using evaluation metrics such as Accuracy, Precision, Recall, And F1-Score. The performance of the models was compared to identify the most effective algorithm for loan eligibility classification. Among the three ML approach, the LR model appears to be the most effective at classify loan eligibility, with the 82% accuracy score, 82% recall score, 81% precision score and 79% F1 score. | ||
| 113. Implementation of Serious Games for Data Privacy and Protection Awareness in Cybersecurity | ||
| Siti Normaziah Ihsan (UMP), Tuty Asmawaty Abd Kadir (UMP), Nurul Ishafira Binti Ismail (Universiti Malaysia Pahang), Kerk Zhi Yuan (Teleperformance Malaysia), Yeow Song Jie (SIM IT SDN BHD) | ||
| Information security and privacy are big issues in today's digital world, and people should be aware of the risks that come with using their personal information online. There are many things that can be done to make people more aware of the importance of keeping personal information safe from attacks, such as an educational campaign, workshops and training sessions, public service announcements, and events in the community. Serious games, which are also called educational games, are a type of educational campaign activity that is meant to teach or train players about a certain subject or skill. They can play an important role in raising awareness of data privacy and information security by providing an engaging and interactive way for players to learn about these important topics. In this study, we suggest a game design architecture for protecting and keeping data private in cybersecurity. In order to validate the architecture, Datanion, a platform game, was created to educate the public on maintaining data privacy over the internet. This lack of awareness will have negative effects on mental health, private information, and computer equipment. Through these games, players can learn the basics of cybersecurity in a fun way, such as how to use strong passwords, recognize and avoid phishing websites, and how firewalls work. The advantage of playing these games is that they can help non-expert end users improve their knowledge and awareness of cybersecurity and also increase a player’s motivation, engagement, and comprehension of cybersecurity knowledge. | ||
| 127. CAGDEEP: Mobile Malware Analysis Using Force Atlas 2 with Strong Gravity and Deep Learning | ||
| Nur Khairani Kamarudin (Universiti Malaysia Pahang), Ahmad Firdaus (Universiti Malaysia Pahang), Azlee Zabidi (Universiti Malaysia Pahang), Mohd Faizal Ab Razak (Universiti Malaysia Pahang) | ||
| (Video Link: https://youtu.be/mHKTMj4yfqE) | ||
| Today many smart devices are running on Android systems. With the increasing popularity of Android, mobile malware continuously evolves as well, and further attacks Android operating systems. To address these shortcoming issues many security practitioners adopt different approaches to detect malware based on various static features. However, by considering only the statistical features, the potential semantic information such as the behavioral feature of the code is overlooked. To leverage the existing static analysis techniques, this study proposes CAGDeep, to reflect deep semantic information of malware samples. The novelty of our study lies in the Force Atlas 2 call graph development to capture malware behavior patterns. Afterwards, this study adopts Convolutional Neural Network (CNN) for malware detection and classification algorithm. We compare CAGDeep with a state-of-the-art Android malware detection approach. Our evaluation results demonstrate that CAGDeep can achieve 80% accuracy for detecting malware. | ||
| 132. Inertia Weight Strategies in GbLN-PSO for Optimum Solution | ||
| Nurul Izzatie Husna Fauzi (Universiti Malaysia Pahang), Zalili Musa (Universiti Malaysia Pahang) | ||
| Particle Swarm Optimization (PSO) is the popular metaheuristic search algorithm that is inspired by the social learning of birds and fish. In the PSO algorithm, inertia weight is an important parameter to determine the searching ability of each particle. When the selected inertia weight is not suitable, the searching particles are more focused on one direction or area nearest to the local best. Therefore, the movement of the particles is limited and not spreading during the search process. Thus, this will cause the particles fast to converge. As the result, the particle is trapped in local optimal. To overcome this problem, we used three different inertia weight strategies such as Constant Inertia Weight (CIW), Random Inertia Weight (RIW), and Linear Decreasing Inertia Weight (LDIW) to analyze the impact of inertia weight on the performance of Conventional PSO and the enhancement of PSO called Global Best Local Neighborhood-PSO (GbLN-PSO) algorithm. In order to test the performance of the three different inertia weight strategies, we test these algorithms in different sizes of search space with random values. Based on the comparison result of 30 simulations, it shows that GbLN-PSO using RIW was producing a better search result compared to CIW and LDIW. Furthermore, the result shows an improvement in GbLN-PSO searching ability. | ||
| 133. A New Approach of Midrange Exploration Exploitation Searching Particle Swarm Optimization for Optimal Solution | ||
| Nurul Izzatie Husna Fauzi (Universiti Malaysia Pahang), Zalili Musa (Universiti Malaysia Pahang) | ||
| The conventional Particle Swarm Optimization (PSO) was introduced as an optimization technique for real applications such as image processing, tracking, localization, and scheduling. However, conventional PSO still has its limitation in finding optimal solutions and is always trapped in the local optima. Therefore, the concept of conventional PSO was unsuitable to be used in dynamic problems. In order to address these issues, we have introduced a novel enhancement approach known as Midrange Exploration Exploitation Searching Particle Swarm Optimization (MEESPSO) to categorize the particle into resident particles and migrant particles according to midrange value. A migrant particle will execute the process of exploration to other search spaces, meanwhile resident particles went through the process of exploitation accordingly to the best solution. The comparison result shows that MEESPSO has the talent to increase the accuracy in a real application. | ||
| 135. Review on Serious-Education Games for Slow Learners | ||
| Siti Nuraishah Binti Nazri (Universiti Malaysia Pahang Al-Sultan Abdullah), Tuty Asmawaty Binti Abdul Kadir (Universiti Malaysia Pahang Al-Sultan Abdullah), Siti Normaziah Binti Ihsan (Universiti Malaysia Pahang Al-Sultan Abdullah) | ||
| Serious education games are popular as they engage and educate more learners, including slow learners who are normal students but have difficulty meeting academic standards. Having a game that targets a child's struggles can make a significant difference, helping them feel more confident. Our goal is to increase awareness of slow learners in the classroom and stimulate discussion about this population. This review identifies slow learners and examines serious games' advantages and features designed for them. The paper findings also explore whether these technologies can be more effective than traditional methods. Slow learners struggle with traditional teaching methods, so it's essential to find ways to make learning fun and exciting. This study shows that games designed for education provide children with a great learning experience. This is especially helpful for students who struggle with traditional education methods, especially slow learners. Serious games have been shown to benefit slow learners in a variety of ways. These include developing problem-solving skills, improving motivation and engagement, and increasing academic performance. Therefore, serious gaming strategies may be more effective than traditional methods of engaging slow learners. Research using serious games for slow learners should yield promising results. | ||
| Session IV-C (Virtual) (10:15 - 12:45 @ Online) | ||
| Session Chair: TBA | ||
| 42. Determining the Optimal Number of GAT and GCN Layers for Node Classification in Graph Neural Networks | ||
| Humaira Noor (United International University), Niful Islam (United International University), Md. Saddam Hossain Mukta (United International University), Nur Shazwani Binti Kamarudin (Universiti Malaysia Pahang), Mohaimenul Azam Khan Raiaan (United International University), Sami Azam (Charles Darwin University) | ||
| (Video Link: https://www.youtube.com/watch?v=MRGMYQnvchQ) | ||
| Node classification in complex networks plays an important role including social network analysis and recommendation systems. Some graph neural networks such as Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) have emerged as effective approaches for achieving high-performance classification in such tasks. However, constructing a graph neural network architecture is challenging particularly due to the complex task of determining the optimal number of layers. This study presents a mathematical formula for determining the optimal number of GCN and GAT hidden layers. The experiment was conducted on ten benchmark datasets, evaluating performance metrices such as accuracy, precision, recall, F1-score, and MCC for identifying the best estimation of number of hidden layers. According to the experimental findings, the number of GAT and GCN layers selected has a substantial impact on classification accuracy. Studies show that adding extra layers after the optimum number of layers has a negative or no impact on the classification performance. Our proposed approximation technique may provide valuable insights for enhancing efficiency and accuracy of the Graph Neural Network algorithms. | ||
| 53. Design and Implementation of a LCDP with Enhanced Functionality | ||
| Rattakorn Poonsuph (Graduated School of Applied Statistics) | ||
| (Video Link: https://www.youtube.com/watch?v=rZZIFkw0mfk) | ||
| Low-code application development platforms (LCDPs) have been widely used recently to replace typical application development with lower development costs and speed up application delivery. However, LCDP in the market is still evolving, with several limitations. This research aims to demonstrate a new LCDP implementation that can generate an application with improved functionality practically used in real-world business applications. The invention starts from the concept of model-driven engineering (MDE) theory and designs an intelligent code generator engine. This LCDP implementation is a software-as-a-service platform allowing users to design their custom applications with the visualized designer. The output of the design then is to generate an executable source code that enables to build of the software applications with minimum limitation, less code for development, future extensibility, and unleash from vendor locked-in of a proprietary platform. The research has also extended the study by comparing functionality with benchmark commercial applications so that the generated software applications from this LCDP research can perform similarly. | ||
| 107. Emotional Analysis Based On LSTM-CNN Hybrid Neural Network Model | ||
| You Wu (Xiamen University Malaysia), Muataz Al-daweri (University of Nizwa), Venkata Durga Kumar Burra (Xiamen University Malaysia) | ||
| (Video Link: https://youtu.be/rkfd0ZrB5nI) | ||
| —In the realm of natural language processing (NLP), text classification is an important task. Current techniques for text classification tasks still need development, however, because of the complex abstraction of text semantic information and the considerable impact of context. This research synthesises the strengths of the Bidirectional Long Short-Term Memory (Bi-LSTM) and the Convolutional Neural Network (CNN) models of neural networks. The LSTM-CNN hybrid model is a combination of the two models: the LSTM- generated text feature vector is then extracted using the CNN structure. The Bi-LSTM can retain long text sequences while taking into account the importance of the whole text, and it can subsequently use the organisational principles of the CNN to extract local text features. The research’s experiment compares the effectiveness of the LSTM-CNN, the Bi-LSTM, and the random forest in a sentiment analysis project based on the ternary classification (Neutral, Positive and Negative) of metaverse, which can be described as a virtual reality space where individuals can interact with a computer-generated environment and other users in real-time, related topics. From what can be gathered from this research experiments, the LSTM-CNN outperforms other models when it comes to boosting text classification accuracy and achieving lower loss. | ||
Conference Registration System v3.48, (c) Ihsan Mohd Yassin | ||