| Logout | Presenter Main Page | ||
| 2023 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE2023) - View Tentative Schedule (With YouTube Links) | ||
| This schedule may change from time to time. Please always refer here for the latest updates. | ||
| 2023-05-20 | ||
| 07:45 - 12:00 | : | Registration @ Kayu Manis Foyer |
| 08:00 - 10:15 | : | Session I-A @ Serai Room |
| Session I-B @ Kayu Manis Room | ||
| 10:15 - 10:30 | : | Morning Break @ Kayu Manis Foyer |
| 10:30 - 13:00 | : | Session II-A @ Serai Room |
| Session II-B @ Kayu Manis Room | ||
| 13:00 - 14:00 | : | Lunch @ Cinnamon Coffee House |
| 14:00 - 15:30 | : | Session III-A @ Kayu Manis Room |
| Session III-B @ Serai Room | ||
| 14:30 - 16:00 | : | Registration @ Kayu Manis Foyer |
| 15:15 - 15:30 | : | Tea Break @ Kayu Manis Foyer |
| 15:30 - 17:30 | : | Session IV-A @ Serai Room |
| Session IV-B @ Kayu Manis Room | ||
| Session IV-C: Online Presentations @ Virtual Session | ||
| 17:45 - 18:00 | : | Closing Ceremony @ Serai Room |
| 2023-05-21 | ||
| 08:00 - 18:00 | : | Networking Session & Free Activity @ N/A |
| Detailed Schedule | ||
| Date: 2023-05-20 | ||
| Session I-A (08:00 - 10:15 @ Serai Room) | ||
| Session Chair: NORAZIZAH MOHD ARIPIN | ||
| 08:00-08:15 | Validity and Reliability of Extended Technology Acceptance Model for Digital Signage Augmented Roadshow (disar) (Paper ID: 18) | |
| Yi Fan Tan (Multimedia University), Meng-chew Leow (Multimedia University), Lee-yeng Ong (Multimedia University) | ||
| 08:15-08:30 | Study On Driver Behaviour Questionnaire and Driver's Perception of Telematics Insurance in Malaysia (Paper ID: 33) | |
| Nurul Ain Mohd Rizal (Universiti Teknologi MARA), Mohd Hanif Mohd Ramli (Universiti Teknologi MARA), Ahmad Khushairy Makhtar (Universiti Teknologi MARA) | ||
| 08:30-08:45 | Classification of Hospital of The Future Applications using Machine Learning (Paper ID: 34) | |
| Izzati Thaqifah Zulkifli (Universiti Tenaga Nasional), Nurul Asyikin Mohamed Radzi (Universiti Tenaga Nasional), Norazizah Mohd Aripin (Universiti Tenaga Nasional), Kaiyisah Hanis Mohd Azmi (Universiti Tenaga Nasional), Faris Syahmi Samidi (Universiti Tenaga Nasional), Nayli Adriana Azhar (Universiti Tenaga Nasional) | ||
| 08:45-9:00 | Performance Analysis of 5g Network Slicing for Hospital of The Future (Paper ID: 37) | |
| Norazizah Mohd Aripin (UNITEN), Izzati Thaqifah Zulkifli (UNITEN), Nurul Asyikin Mohamed Radzi (UNITEN) | ||
| 9:00-9:15 | AN APPROACH TO QUALITY-MANAGED PROOFING (Paper ID: 45) | |
| Muhammad Yusuf Masod (Universiti Teknologi MARA), Aezzaddin Aisyah Zainuddin (Universiti Teknologi MARA) | ||
| 9:15-9:30 | A Systematic Literature Review in Gamification Implementation and Game Elements in Malaysia Education (Paper ID: 56) | |
| Azlimi Mazlan (Technical University Malaysia Melaka), Ibrahim Ahmad (Technical University Malaysia Melaka), Sazilah Salam (Technical University Malaysia Melaka) | ||
| 9:30-9:45 | Integrating Multimedia Learning Principle Into The Design of an Interactive Video for Low Achievers in Introductory Programming (Paper ID: 79) | |
| Mahfudzah Othman (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Perlis Branch, Arau Campus), Aznoora Osman (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Perlis Branch, Arau Campus), Siti Zulaiha Ahmad (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Perlis Branch, Arau Campus), Natrah Abdullah (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Shah Alam) | ||
| 9:45-10:00 | MCD64A1 Burnt Area Dataset Assessment using Sentinel-2 and Landsat-8 on Google Earth Engine: A Case Study in Rompin, Pahang in Malaysia (Paper ID: 109) | |
| Yee Jian Chew (Multimedia University), Shih Yin Ooi (Multimedia University), Ying Han Pang (Multimedia University) | ||
| Session I-B (08:00 - 10:15 @ Kayu Manis Room) | ||
| Session Chair: MOHD HERWAN SULAIMAN | ||
| 08:00-08:15 | Identifying Needs and Problems in Learning for Children with Autism Spectrum Disorder (asd) From a Technology Perspective (Paper ID: 3) | |
| Norshahidatul Hasana Ishak (Universiti Teknikal Malaysia Melaka), Siti Nurul Mahfuzah Mohamad (Universiti Teknikal Malaysia Melaka), Syamimi Syamsuddin (Universiti Teknikal Malaysia Melaka), Mohamad Lutfi Dolhalit (Universiti Teknikal Malaysia Melaka), Aliza Alias (Universiti Kebangsaan Malaysia), Sazilah Salam (Universiti Teknikal Malaysia Melaka) | ||
| 08:15-08:30 | Improved Barnacles Mating Optimizer for Loss Minimization Problem in Optimal Reactive Power Dispatch (Paper ID: 7) | |
| Mohd Herwan Sulaiman (Universiti Malaysia Pahang), Zuriani Mustaffa (Universiti Malaysia Pahang), Omar Aliman (Universiti Malaysia Pahang), Mohd Mawardi Saari (Universiti Malaysia Pahang) | ||
| 08:30-08:45 | Metaheuristic Approach for Optimizing Neural Networks Parameters in Battery State of Charge Estimation (Paper ID: 8) | |
| Zuriani Mustaffa (Universiti Malaysia Pahang), Mohd Herwan Sulaiman (Universiti Malaysia Pahang), Azlan Abdul Aziz (Universiti Teknologi Mara) | ||
| 08:45-9:00 | Comparison of Squeezenet and Darknet-53 Based Yolo-v3 Performance for Beehive Intelligent Monitoring System (Paper ID: 52) | |
| Sairul Safie (Universiti Kuala Lumpur), Mohd Zul-waqar Mohd Tohid (Universiti Kuala Lumpur), Ernie Mazuin Mohd Yusof (Universiti Kuala Lumpur), Noor Huda Jaafar (Universiti Kuala Lumpur) | ||
| 9:00-9:15 | Determination of Solution Concentrations using Photoacoustic Technology and Deep Learning: A comparison study (Paper ID: 72) | |
| Hui Ling Chua (Universiti Tun Hussein Onn Malaysia), Audrey Huong (Universiti Tun Hussein Onn Malaysia) | ||
| 9:15-9:30 | Clustering Mechanism in Particle Swarm Optimization Algorithm for Data Aggregation (Paper ID: 91) | |
| Sharmin Sharmin (Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya), Ismail Ahmedy (Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya), Rafidah Md Noor (Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya), Habibah Ismail (Computer Science Unit, Centre of Foundation Studies, Univesrsiti Teknologi MARA) | ||
| 9:30-9:45 | Wireless Walking Pattern Detection using Force Sensitive Resistor Pressure Sensors On Footwear (Paper ID: 100) | |
| Norul Zaharah Khairuddin (School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA), Ili Shairah Abdul Halim (School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA), Azyati Nurfaqihah Azreen (Faculty of Applied Science, Universiti Teknologi MARA), Atiyyah Musa (Faculty of Applied Science, Universiti Teknologi MARA), Siti Lailatul Mohd Hassan (School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA), Najua Tulos (Faculty of Applied Science, Universiti Teknologi MARA) | ||
| 9:45-10:00 | Application of Manta Ray Foraging Optimization with Gradient-based Mutation (cMRFO) for Solving Power System Problems (Paper ID: 115) | |
| Ahmad Azwan Abdul Razak (Universiti Malaysia Pahang), Ahmad Nor Kasruddin Nasir (Universiti Malaysia Pahang), Normaniha Abdul Ghani (Universiti Malaysia Pahang) | ||
| Session II-A (10:30 - 13:00 @ Serai Room) | ||
| Session Chair: ARI AHARARI | ||
| 10:30-10:45 | Study On Continuity of Defuzzification using Density Moment Method (Paper ID: 14) | |
| Takashi Mitsuishi (Nagano University) | ||
| 10:45-11:00 | The ontology model for selecting quality melons uses hidden semantic data based on melon knowledge domains (Paper ID: 53) | |
| Ubaidillah Umar (Department of Electrical Engineering, Faculty of Intelligent Electrical and Informatics Technology), Tri Arief Sardjono (Department of Biomedical Engineering, Faculty of Intelligent Electrical and Informatics Technology), Hendra Kusuma (Department of Electrical Engineering, Faculty of Intelligent Electrical and Informatics Technology) | ||
| 11:00-11:15 | Road Hazard Detection for The Motorcycle Based On Efficientnet-lite0 (Paper ID: 74) | |
| S. M. Najib (Universiti Teknikal Malaysia Melaka, Melaka), S. N. S. Mirin (Universiti Teknikal Malaysia Melaka, Melaka), Ahmad Irfan Harman (Universiti Teknikal Malaysia Melaka, Melaka), Muhammad Qarl Farisz Mohd Rahimi (Universiti Teknikal Malaysia Melaka, Melaka), Muhammad Daniel Rahim (Universiti Teknikal Malaysia Melaka, Melaka), Nurnajihah Hazirah Azhari (Universiti Teknikal Malaysia Melaka, Melaka), Awy Khang (Universiti Teknikal Malaysia Melaka, Melaka) | ||
| 11:15-11:30 | Sales Analytics Dashboard with Arima and Sarima Time Series Model (Paper ID: 75) | |
| Aini Fatina Mohamad (Computing Sciences Studies), Aisyah Mat Jasin (Computing Sciences Studies), Aszila Asmat (mathematical Sciences Studies), Roger Canda (Computing Sciences Studies), Juhaida Ismail (Computing Sciences Study), Afiqah Bazlla Md Soom (Computing Science Studies) | ||
| 11:30-11:45 | Detection of Cyberbullying Tweets in Twitter Media using Random Forest Classification (Paper ID: 82) | |
| Gunasekar Thangarasu (MAHSA University), Kesava Rao Alla (MAHSA University) | ||
| 11:45-12:00 | Classification of Garbage Waste in Smart Cities using Convolutional Neural Network (Paper ID: 83) | |
| Gunasekar Thangarasu (MAHSA University), Kesava Rao Alla (MAHSA University) | ||
| 12:00-12:15 | Cataract Detection using Pupil Patch Classification and Ruled-based System in Anterior Segment Photographed Images (Paper ID: 94) | |
| Laily Azyan Ramlan (Universiti Kebangsaan Malaysia), Wan Mimi Diyana Wan Zaki (Universiti Kebangsaan Malaysia), Haliza Abdul Mutalib (Universiti Kebangsaan Malaysia), Aini Hussain (Universiti Kebangsaan Malaysia), Aouache Mustapha (Division Telecom, Center for Development of Advanced Technologies (CDTA)) | ||
| 12:15-12:30 | Evaluation of K-fold value in breast cancer diagnosis technique using SVM and bio-inspired optimization algorithm (JA-ABC5) (Paper ID: 105) | |
| Ravindran Nadarajan (Universiti Malaysia Pahang), Noorazliza Sulaiman (Universiti Malaysia Pahang) | ||
| 12:30-12:45 | Development of an Artificial Intelligence (AI) Based Visual Counting System for The Food Industry (Paper ID: 113) | |
| Ari Aharari (SOJO University), Kaito Kuwaduru (SOJO University), Farhad Mehdipour (Otago Polytechnic – Auckland International Campus (OPAIC)) | ||
| 12:45-13:00 | Adaptive Levy Flight Distribution Algorithm for Solving a Dynamic Model of an Electric Heater (Paper ID: 116) | |
| Ahmad Nor Kasruddin Nasir (universiti malaysia pahang) | ||
| Session II-B (10:30 - 13:00 @ Kayu Manis Room) | ||
| Session Chair: FADHILAH NUR RANIA | ||
| 10:30-10:45 | SD-WAN as an Efficient Network Solution with IDPS (Paper ID: 4) | |
| F. N. Rania (Inti International University), J. Y. Chan (Inti International University), J. Y. Fong (Inti International University), E. S. Ng (Inti International University), S. Z. B. Zulkifli (Inti International University), P. S. Josephng (Inti International University) | ||
| 10:45-11:00 | A Case Study of Lte Coverage Extension for Rural Malaysia (Paper ID: 11) | |
| Azah Syafiah Mohd Marzuki (TM R&D), Siti Maisurah Mohd Hassan (TM R&D), Suhandi Bujang (TM R&D), Azlan Sulaiman (TM R&D), Mohd Kamarulzamin Salleh (TM R&D), Mohd Hafiz Mohamad Nor (TM R&D), Mohd Azmi Ismail (TM R&D) | ||
| 11:00-11:15 | Investigation of an Array of Dipoles in Three-dimensional Configuration (Paper ID: 25) | |
| Kiran Nadeem (universiti tunku abdul rahman), Gobi Vetharatnam (universiti tunku abdul rahman), Kim Yee Lee (universiti tunku abdul rahman), Mohammad Ghanbarisabagh (islamic azad university north tehran) | ||
| 11:15-11:30 | An Evaluation of Aco Based Approach for Network Load Balancing (Paper ID: 30) | |
| Mohd Daud Alang Hassan (Universiti Teknologi MARA (UiTM) Cawangan Pulau Pinang), Norasmah Hamzah (Kolej Komuniti Seberang Jaya), Muhammad Nur Zikri Mohamad Hafizan (Intel Technology (M)) | ||
| 11:30-11:45 | Recent Advances and Benchmarking of NewSQL for OLTP and OLAP in The Big Data Age (Paper ID: 49) | |
| Miko May Lee Chang (Swinburne University of Technology Sarawak Campus), John Zu An Chung (Swinburne University of Technology Sarawak Campus), Swee King Phang (Taylor's University) | ||
| 11:45-12:00 | Online Community Engagement: Exposing Information and Communication Technology Among Rural Learners During The Covid-19 Era (Paper ID: 69) | |
| Shahida Sulaiman (Universiti Teknologi Malaysia), Mahirah Afifah Mohd Haliza (Universiti Teknologi Malaysia), Sh. Khayulzahri Sh. A Raof (Southeast Johor Development Authority (KEJORA)) | ||
| 12:00-12:15 | Robust Text Clustering to Cluster The Text Documents in a Meta-heuristic Optimization (Paper ID: 86) | |
| Kesava Rao Alla (MAHSA University), Gunasekar Thangarasu (MAHSA University) | ||
| 12:15-12:30 | Improved Data Transmission using Noma Technology for Office Automation Application (Paper ID: 87) | |
| Kesava Rao Alla (MAHSA University), Gunasekar Thangarasu (MAHSA University) | ||
| 12:30-12:45 | Evaluating The Energy Efficiency of Noma 5g with Regard to The Capacity and Coverage (Paper ID: 112) | |
| Megat Ahmad Faiz Ahmad Shukri (Universiti Teknologi MARA), Ezmin Abdullah (Universiti Teknologi MARA), Nabil M. Hidayat (Universiti Teknologi MARA), Nurain Izzati Shuhaimi (Universiti Teknologi MARA) | ||
| Session III-A (14:00 - 15:30 @ Kayu Manis Room) | ||
| Session Chair: GUNASEKAR THANGARASU | ||
| 14:00-14:15 | Gallium Nitride Depth Porosity Using Image Processing Method (Paper ID: 17) | |
| Normasni Ad Fauzi (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang), Iza Sazanita Isa (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang), Siti Maryam Isa (School of Electrical and Electronics Engineering, Universiti Sains Malaysia, Pulau Pinang), Asrulnizam Abd Manaf (Collaborative Microelectronic Design Excellence Centre (CEDEC), Sains@USM, Universiti Sains Malaysia), Alhan Farhanah Abd Rahim (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang), Ida Rahayu Mohamed Nordin (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang) | ||
| 14:15-14:30 | Method to Validate High Speed Bit Stream Generation in Post Silicon (Paper ID: 50) | |
| Sooraj Ravindrakumar (Infineon Technologies), Jayakrishna Guddeti (Infineon Technologies), Pankaj Moharikar (Infineon Technologies) | ||
| 14:30-14:45 | Feature Extraction of Rain Cell using Weather Radar Imagery in Tropical Regions (Paper ID: 63) | |
| Noor Shazwani Osman (MARA University Technology), Wardah Tahir (MARA University Technology) | ||
| 14:45-15:00 | Video Object Detection From The Large Video Frames using Inception Networks (Paper ID: 84) | |
| Gunasekar Thangarasu (MAHSA University), Kesava Rao Alla (MAHSA University) | ||
| 15:00-15:15 | Resnet Associated Cross-layered Routing in Cognitive Radio Network (Paper ID: 85) | |
| Kesava Rao Alla (MAHSA University), Gunasekar Thangarasu (MAHSA University) | ||
| Session III-B (14:00 - 15:30 @ Serai Room) | ||
| Session Chair: SYED FARID SYED ADNAN | ||
| 14:00-14:15 | A Lightweight Microstrip Antenna Study for Wireless Application. (Paper ID: 16) | |
| Ida Rahayu Mohamed Noordin (Universiti Teknologi MARA Cawangan Pulau Pinang), Rohaiza Baharudin (Universiti Teknologi MARA Cawangan Pulau Pinang), Normasni Ad Fauzi (Universiti Teknologi MARA Cawangan Pulau Pinang), Azwati Azmin (Universiti Teknologi MARA Cawangan Pulau Pinang) | ||
| 14:15-14:30 | Detection of Ganoderma Boninense Diseases of Palm Oil Trees using Machine Learning (Paper ID: 76) | |
| Yu Hong Haw (Universiti Malaya), Zhen Zhao (Universiti malaya), Yan Chai Hum (UTAR), Joon Huang Chuah (UM), Wingates Voon (UTAR), Siti Khairunniza -bejo (UPM), Nur Azuan Husin (UPM), Por Lip Yee (UM), Khin Wee Lai (UM) | ||
| 14:30-14:45 | A Goal Programming Approach in Solving Garbage Truck Multiple Objective Problem (Paper ID: 98) | |
| Noryanti Nasir (Universiti Teknologi MARA), S. Sarifah Radiah Shariff (Universiti Teknologi MARA), Siti Sarah Januri (Universiti Teknologi MARA), Faridah Zulkipli (Universiti Teknologi MARA), Zaitul Anna Melisa Md Yasin (Universiti Teknologi MARA) | ||
| 14:45-15:00 | Domestic Garbage Target Detection Based On Improved Yolov5 Algorithm (Paper ID: 103) | |
| Ma Haohao (Universiti Putra Malaysia), Wu Xuping (Tianshui Normal University), Azizan As’arry (Universiti Putra Malaysia), Han Weiliang (Heilongjiang University), Mu Tong (Tianshui Normal University), Feng Yanwei (Tianshui Normal University) | ||
| Session IV-A (15:30 - 17:30 @ Serai Room) | ||
| Session Chair: HABIBAH HASHIM | ||
| 15:30-15:45 | Integrated Earned Value Method for It Project Cost and Duration Estimation (Paper ID: 13) | |
| Der-jiun Pang (International University of Malaya Wales (IUMW)) | ||
| 15:45-16:00 | A Novel Target Value Standardization Method Based On Cumulative Distribution Functions for Training Artificial Neural Networks (Paper ID: 23) | |
| Wai Meng Kwok (Heriot-Watt University Malaysia), George Streftaris (Heriot-Watt University Edinburgh), Sarat Chandra Dass (Heriot-Watt University Malaysia) | ||
| 16:00-16:15 | Enhancement of Low-Quality Diatom Images using Integrated Automatic Background Removal (IABR) Method from Digital Microscopic Image (Paper ID: 35) | |
| Mohd Aiman Syahmi Kamarul Baharin (Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia), Ahmad Shahrizan Abdul Ghani (Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia), Syafiq Qhushairy Syamsul Amri (Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia), Normawaty Mohammad-noor (International Islamic University Malaysia, Bandar Indera Mahkota, 25200 Kuantan, Pahang, Malaysia), Hasnun Nita Ismail (University Technology of MARA, Perak Branch, Tapah Campus, 35400 Tapah Road, Malaysia) | ||
| 16:15-16:30 | Motion Capture System Based On RGB Camera for Human Walking Recognition using Marker-based and Markerless for Kinematics of Gait (Paper ID: 44) | |
| Riky Tri Yunardi (Department of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember), Tri Arief Sardjono (Department of Biomedical Engineering , Faculty of Intelligent Electrical and Informatics Technology (F- ELECTICS) Institut Teknologi Sepuluh Nopember), Ronny Mardiyanto (Department of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember) | ||
| 16:30-16:45 | A Thorough Comparison of The Variable-sample-size Weighted-loss Cusum and Abs-sprt Control Charts (Paper ID: 59) | |
| Jing Wei Teoh (Heriot-Watt University Malaysia), Wei Lin Teoh (Heriot-Watt University Malaysia), Laila El-ghandour (Heriot-Watt University), Zhi Lin Chong (Universiti Tunku Abdul Rahman), Sin Yin Teh (Universiti Sains Malaysia) | ||
| 16:45-17:00 | Rabin-P Encryption Scheme Analysis on MQTT (Paper ID: 104) | |
| Wan Abdullah Che Izam (UiTM Shah Alam), Syed Farid Syed Adnan (UiTM Shah Alam) | ||
| 17:00-17:15 | The Impact of Track Elevations for DC Third Rail System in Malaysia (Paper ID: 106) | |
| Xin Rong Chua (Universiti Tunku Abdul Rahman), Kein Huat Chua (Universiti Tunku Abdul Rahman), Cheun Hau Lee (Universiti Tunku Abdul Rahman), Yun Seng Lim (Universiti Tunku Abdul Rahman), Li Wang (Universiti Tunku Abdul Rahman), Mohammad Babrdel (Universiti Tunku Abdul Rahman) | ||
| 17:15-17:30 | Supertwisting Sliding Mode Control for Parallel Hybrid Electric Vehicle Control Strategy (Paper ID: 111) | |
| Anith Khairunnisa Ghazali (MULTIMEDIA UNIVERSITY), Norazlina Ab. Aziz (MULTIMEDIA UNVERSITY) | ||
| Session IV-B (15:30 - 17:30 @ Kayu Manis Room) | ||
| Session Chair: ROSLINA MOHAMED | ||
| 15:30-15:45 | A Preliminary Study On Learners’ Personal Traits for Modelling Learner Profiles in Its : a Sensor-free Approach (Paper ID: 38) | |
| Mohammad Rahman (University of Tasmania), Hassan A. Al Salem (Jazan University), Soonja Yeom (University of Tasmania), Nadia Ollington (University of Tasmania), Robert Ollington (University of Tasmania), Md Mujibur Rahman (Universiti Malaya) | ||
| 15:45-16:00 | A Hybrid Wearable Technology Model for Autism Behaviour Intervention: Components and Elements Analysis (Paper ID: 55) | |
| Mohamad 'isa Ab Malik (College of Computing, Informatics and Media Universiti Teknologi MARA Perlis Branch, Arau Campus), Siti Zulaiha Ahmad (College of Computing, Informatics and Media Universiti Teknologi MARA Perlis Branch, Arau Campus), Romiza Md Nor (College of Computing, Informatics and Media Universiti Teknologi MARA Perlis Branch, Arau Campus), Nursuriati Jamil (College of Computing, Informatics and Media Universiti Teknologi MARA, Shah Alam), Sakinah Idris (Faculty of Medicine Universiti Teknologi MARA Selangor Branch, Sungai Buloh Campus), Grace Liew Bee Wah (The National Autism Society of Malaysia, Setia Alam, Shah Alam) | ||
| 16:00-16:15 | Non-fungible Token (nft) in Malaysian Creative Arts: The Status-quo of Tokenisation (Paper ID: 57) | |
| Mohammad Aaris Amirza (Universiti Teknologi MARA), Mohamed Razeef Abdul Razak (Universiti Teknologi MARA), Muhamad Fairus Kamaruzaman (Universiti Teknologi MARA), Rusmadiah Anwar (Universiti Teknologi MARA) | ||
| 16:15-16:30 | Review On Workload and Resource Allocation in Edge-based Wireless Body Area Networks (Paper ID: 58) | |
| Sachinthani Alahakoon (City University), Rajasvaran Logeswaran (City University) | ||
| 16:30-16:45 | A Framework of Quality-aware Personalized Task Matching for Mobile Crowdsensing (Paper ID: 67) | |
| Md Mujibur Rahman (University of Malaya), Mohammad Rahman (University of Tasmania), Soonja Yeom (University of Tasmania), Md Badiuzzaman (UNSW, Sydney, Australia), Hassan Salem (Department of MIS, CBA, Jazan University), Hassan A. Al Salem (Jazan University), Soo-hyeong Kim (Department of Artificial Intelligence Convergence, Chonnam National University), Umair Munir (University of Central Punjab) | ||
| 16:45-17:00 | Differences of Performance Analysis of Single Channel LoRaWAN Network for Air Pollution Monitoring System Using IoT Platform in Smart City – A Review (Paper ID: 68) | |
| Nik Farah Emmyra Nik Kamaruzaman (UNIVERSITY TEKNOLOGI MARA), Suzi Seroja Sarnin (UNIVERSITY TEKNOLOGI MARA), Nani Fadzlina Naim (UNIVERSITY TEKNOLOGI MARA) | ||
| 17:00-17:15 | Enhanced Blockchain Scalability for IoT-based Smart Devices - A Generic Model Development (Paper ID: 102) | |
| Mathuri Gurunathan (Universiti Tenaga Nasional), Moamin Mahmoud (Universiti Tenaga Nasional), Faisal Faisal (Universiti Tenaga Nasional) | ||
| 17:15-17:30 | Assessing The Importance of Browser Fingerprint Attributes Towards User Profiling Through Clustering Algorithms (Paper ID: 108) | |
| Vicki Wei Qi Lee (Multimedia University), Shih Yin Ooi (Multimedia University), Ying Han Pang (Multimedia University) | ||
| Session IV-C: Online Presentations (15:30 - 17:30 @ Virtual Session) | ||
| Session Chair: TBA | ||
| 15:30-15:45 | Paving The Way for 64 Gbps PCIe 6.0 End to End Physical Link Compliance in Multi-board Digital System (Paper ID: 15) | |
| Video Link: https://www.youtube.com/watch?v=v5L2lSiEIdI | ||
| Chang Fei Yee (Keysight Technologies) | ||
| 15:45-16:00 | Efficacy of Bidirectional LSTM Model for Network-Based Anomaly Detection (Paper ID: 21) | |
| Video Link: https://youtu.be/waLelCaAHes | ||
| Toya Acharya (Prairie View A & M University), Annamalai Annamalai (Prairie View A & M University), Mohamed F Chouikha (Prairie View A & M University) | ||
| 16:00-16:15 | On Private Server Implementations and Data Visualization for Lorawan (Paper ID: 43) | |
| Video Link: https://youtu.be/I2QI8mD8aRU | ||
| Sheikh Tareq Ahmed (Prairie View A&M University), Annamalai Annamalai (Prairie View A&M University) | ||
| 16:15-16:30 | Efficacy of Cnn-bidirectional Lstm Hybrid Model for Network-based Anomaly Detection (Paper ID: 48) | |
| Video Link: https://youtu.be/yHvQ7-olCcA | ||
| Toya Acharya (Prairie View A & M University), Annamalai Annamalai (Prairie View A & M University), Mohamed F Chouikha (Prairie View A & M University) | ||
| 16:30-16:45 | A Systematic Literature Review On Batik Image Retrieval (Paper ID: 60) | |
| Agus Eko Minarno (Universitas Gadjah Mada, Universitas Muhammadiyah Malang), Indah Soesanti (Universitas Gadjah Mada), Hanung Adi Nugroho (Universitas Gadjah Mada) | ||
| 16:45-17:00 | Visualization of Word Similarity Measurement for Messages in Sequence Diagram using Heatmap (Paper ID: 71) | |
| Video Link: https://youtu.be/piXQuNhETek | ||
| Zulhafizal Othman (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch), Aisyah Mat Jasin (Computing Sciences Centre of Studies, College of Computing, Informatics and Media, Universiti Teknologi MARA Pahang Branch, Raub Campus), Muhd Eizan Shafiq Abd Aziz (Computing Sciences Centre of Studies, College of Computing, Informatics and Media, Universiti Teknologi MARA Pahang Branch, Raub Campus), Mohd Khairul Ikhwan Zolkefley (Computing Sciences Centre of Studies, College of Computing, Informatics and Media, Universiti Teknologi MARA Pahang Branch, Raub Campus), Ainamardia Nazarudin (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch), Hamizah Mokhtar (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch), Amminudin Ab Latif (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch) | ||
| 17:00-17:15 | Air Particulate Matters Auto-rule-based Labeling to Support Long-distance Run Environment Data Classification (Paper ID: 73) | |
| Video Link: https://youtu.be/HLgD3Bq9MC0 | ||
| Wandy Wandy (Diponegoro University), Kusworo Adi (Diponegoro University), Media Anugerah Ayu (Sampoerna University) | ||
| 17:15-17:30 | Virtual Bonding in Ethernet Transmission Wireless Backhauled Links (Paper ID: 88) | |
| Video Link: https://www.youtube.com/watch?v=5dtoElwUYtc&ab_channel=puneetkumar | ||
| Puneet Kumar (IEEE), Karishma Bava (IEEE) | ||
| 17:30-17:45 | Clustering of Point-to-point Ethernet Transmission Wireless Backhaul Links (Paper ID: 90) | |
| Video Link: https://www.youtube.com/watch?v=M7P3O0PU8ik&t=277s | ||
| Puneet Kumar (IEEE), Karishma Bava (IEEE) | ||
| 17:45-18:00 | Improving Geo-location Performance of Lora with Adaptive Spreading Factor (Paper ID: 97) | |
| Video Link: https://youtu.be/I2QI8mD8aRU | ||
| Sheikh Tareq Ahmed (Prairie View A&M University), Annamalai Annamalai (Prairie View A&M University) | ||
| 18:00-18:15 | Exploring Quantum Machine Learning for Electroencephalogram Classification (Paper ID: 107) | |
| Video Link: https://youtu.be/pHcv3YC_9V4 | ||
| Raymond Ho (Hong Kong Metropolitan University), Kevin Hung (Hong Kong Metropolitan University) | ||
| Date: 2023-05-20 | ||
| Session I-A (08:00 - 10:15 @ Serai Room) | ||
| Session Chair: NORAZIZAH MOHD ARIPIN | ||
| 18. Validity and Reliability of Extended Technology Acceptance Model for Digital Signage Augmented Roadshow (disar) | ||
| Yi Fan Tan (Multimedia University), Meng-chew Leow (Multimedia University), Lee-yeng Ong (Multimedia University) | ||
| The purpose of this study was to examine the validity and reliability of the extended Technology Acceptance Model (extended TAM) questionnaire in assessing the user acceptance of DiSAR (Digital Signage Augmented Roadshow). PLS-SEM analysis is used to test the validity and reliability statistically of the 26 questions in the questionnaire. This study also serves as an exploratory study on applying PLS-SEM on the pilot study data. The result shows that the scale exhibits good reliability and convergent validity but attenuated discriminant validity. | ||
| 33. Study On Driver Behaviour Questionnaire and Driver's Perception of Telematics Insurance in Malaysia | ||
| Nurul Ain Mohd Rizal (Universiti Teknologi MARA), Mohd Hanif Mohd Ramli (Universiti Teknologi MARA), Ahmad Khushairy Makhtar (Universiti Teknologi MARA) | ||
| Every year, the number of road accidents in our country rises and Malaysia is one of the countries with the largest number of accidents caused by aggressive driving. As a result, various studies have been conducted in the transportation community to investigate and propose techniques for collecting pre-crash data. Aggressive driving increases the likelihood of drivers being involved in a traffic collision, and aggressive driving is caused by a variety of circumstances. A questionnaire is designed to present an innovative way to aid car insurance firms in estimating the annual insurance premium cost for the vehicle owner. Instead of determining insurance premiums only on the basis of an individual's demographic profile, drivers' behavior should also be taken into account. Consumers, on the other hand, may be skeptical of the availability of this behavioral data because revealing personal information could put them at risk. The purpose of this study is to learn about the demographics of the drivers, their perceptions of the present insurance rating in Malaysia, and their acceptance of the proposed approach. This self-reported driving data is important for both insurers and consumers since it allows for personalized insurance in terms of coverage and breadth of the insurance policy to meet driver profiles. | ||
| 34. Classification of Hospital of The Future Applications using Machine Learning | ||
| Izzati Thaqifah Zulkifli (Universiti Tenaga Nasional), Nurul Asyikin Mohamed Radzi (Universiti Tenaga Nasional), Norazizah Mohd Aripin (Universiti Tenaga Nasional), Kaiyisah Hanis Mohd Azmi (Universiti Tenaga Nasional), Faris Syahmi Samidi (Universiti Tenaga Nasional), Nayli Adriana Azhar (Universiti Tenaga Nasional) | ||
| Effective health management is critical to ensure that patients have access to necessary healthcare services. There are a number of challenges that can limit the provision of medical treatment, including a shortage of healthcare professionals, limited resources, and geographical barriers. Hospital of the Future (HoF) incorporates a number of technologies and innovations to improve the delivery of healthcare services and support effective health management. 5G network slicing has the potential to greatly enhance the capabilities of hospitals and the delivery of healthcare services. The network can be sliced into three main services; eMBB, mMTC and URLLC. This paper presented a comparison of various supervised machine learning models in predicting the three network services. The classification for the slices is based on HoF applications’ requirements. Deep Learning model has the highest accuracy, shortest total runtime and low standard deviation value compared to other machine learning models which conclude that deep learning is the best model in predicting 5G HoF slices. | ||
| 37. Performance Analysis of 5g Network Slicing for Hospital of The Future | ||
| Norazizah Mohd Aripin (UNITEN), Izzati Thaqifah Zulkifli (UNITEN), Nurul Asyikin Mohamed Radzi (UNITEN) | ||
| 5G network slicing is considered an efficient solution to support various applications with diverse requirements. In network slicing, each client is assigned with logical end-to end network that shares a common physical infrastructure. It allows the necessary flexibility and scalability associated with the eMBB, uRLLC and mMMTC type of traffic. Hospital of the Future (HoF) is an emerging application supporting diverse applications such as Augmented Reality (AR) controlled robotic monitoring, remote monitoring, and remote surgery. This paper envisioned exploring two network slicing strategies for HoF environment based on its dynamicity and network slicing orchestration. Their performance is evaluated in terms of the ratio of connected clients, the ratio of blockage ratio, average and total bandwidth utilization. Simulation results showed that dynamic slicing with femtocell configuration outperforms static slicing and slicing at micro BS. | ||
| 45. AN APPROACH TO QUALITY-MANAGED PROOFING | ||
| Muhammad Yusuf Masod (Universiti Teknologi MARA), Aezzaddin Aisyah Zainuddin (Universiti Teknologi MARA) | ||
| This article evaluates the factors that impact the colour consistency of a digital contract proofing system. Based on these factors, a framework towards quality-oriented proofing is presented. This approach consists of calibration, verification and proof validation steps. It is possible to ensure a specific tonal response by using a calibration step to put a proofer in a normal state. A proofer verification enables a user to monitor the output performance of the proofer. It draws attention to problems and encourages a user to take appropriate action. In the proof verification, the proof is compared to both the final print and the target, which could be an ICC profile or a standard printing procedure. | ||
| 56. A Systematic Literature Review in Gamification Implementation and Game Elements in Malaysia Education | ||
| Azlimi Mazlan (Technical University Malaysia Melaka), Ibrahim Ahmad (Technical University Malaysia Melaka), Sazilah Salam (Technical University Malaysia Melaka) | ||
| In recent years, gamification has increased a lot of interest among in both industries and academia. Gamification takes the most game elements to be applied in teaching and learning process to see the student behaviors. However, the gamification focuses mostly on game-based learning and serious game. A lot of gamification approaches has been implemented in public school compared to higher education institution. Gamification also being used in businesses. Taking this issue forward, this paper aims to explore the gamification approach in Malaysia through a systematic literature review and discussed the game elements used in the gamification context. The finding shows that there is gamification context in higher education institutions in Malaysia and the game elements used in gamification are points, badges, leader board and etc. | ||
| 79. Integrating Multimedia Learning Principle Into The Design of an Interactive Video for Low Achievers in Introductory Programming | ||
| Mahfudzah Othman (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Perlis Branch, Arau Campus), Aznoora Osman (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Perlis Branch, Arau Campus), Siti Zulaiha Ahmad (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Perlis Branch, Arau Campus), Natrah Abdullah (College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Shah Alam) | ||
| This paper discusses the design and development of an interactive video for programming fundamentals for low-achieving students. The aim is to design an interactive multimedia learning tool that is more impactful toward the low achievers’ learning requirements. Two main phases are involved in this study, where the first phase includes the selection of multimedia learning principles and usability recommendations based on Nielsen’s design guidelines. The segmenting principle is then selected and integrated into the design of the interactive video. The next phase requires an iterative design phase, which involves the design, development of the prototype, and review activities. A storyboard was designed based on the selected principle, then developed into a high-fidelity prototype. A qualitative approach through focus group discussion involving a user-centered design (UCD) session was conducted with 12 first-year students from the Diploma of Computer Science program who are also low achievers in programming to review the design of the interactive video. The scales of the usability recommendations are related to visual design, content design, navigation, interaction, and multimedia design. Results from the UCD session show that all participants agreed with the usability recommendations and segmenting principle integrated into the interactive video. | ||
| 109. MCD64A1 Burnt Area Dataset Assessment using Sentinel-2 and Landsat-8 on Google Earth Engine: A Case Study in Rompin, Pahang in Malaysia | ||
| Yee Jian Chew (Multimedia University), Shih Yin Ooi (Multimedia University), Ying Han Pang (Multimedia University) | ||
| This research paper intends to explore the suitability of adopting the MCD64A1 product to detect burnt areas using Google Earth Engine (GEE) in Peninsular Malaysia. The primary aim of this study is to find out if the MCD64A1 is adequate to identify the small-scale fire in Peninsular Malaysia. To evaluate the MCD64A1, a fire that was instigated in Rompin, a district of Pahang on March 2021 has been chosen as the case study in this work. Although several other burnt area datasets had also been made available in GEE, only MCD64A1 is selected due to its temporal availability. In the absence of validation information associated with the fire from the Malaysian government, public news sources are utilized to retrieve details related to the fire in Rompin. Additionally, the MCD64A1 is also validated with the burnt area observed from the true color imagery produced from the surface reflectance of Sentinel-2 and Landsat-8. From the burnt area assessment, we scrutinize that the MCD64A1 product is practical to be exploited to discover the historical fire in Peninsular Malaysia. However, additional case studies involving other locations in Peninsular Malaysia are advocated to be carried out to substantiate the claims discussed in this work. | ||
| Session I-B (08:00 - 10:15 @ Kayu Manis Room) | ||
| Session Chair: MOHD HERWAN SULAIMAN | ||
| 3. Identifying Needs and Problems in Learning for Children with Autism Spectrum Disorder (asd) From a Technology Perspective | ||
| Norshahidatul Hasana Ishak (Universiti Teknikal Malaysia Melaka), Siti Nurul Mahfuzah Mohamad (Universiti Teknikal Malaysia Melaka), Syamimi Syamsuddin (Universiti Teknikal Malaysia Melaka), Mohamad Lutfi Dolhalit (Universiti Teknikal Malaysia Melaka), Aliza Alias (Universiti Kebangsaan Malaysia), Sazilah Salam (Universiti Teknikal Malaysia Melaka) | ||
| Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterised by difficulties in social communication and interaction and repetitive behaviours. No scientific study has yet been able to establish the exact cause of ASD. According to statistics, an increasing number of children are diagnosed with ASD each year. Education is important for children with ASD, just like other children. The teaching techniques adopted in special education may impact the learning ability of these children with ASD. Current teaching aids sometimes cannot effectively assist children with ASD in enhancing their cognitive ability. This preliminary study is aimed to help gather data to identify and analyse current issues in teaching and learning involving children with ASD. Surveys and interviews were conducted with experts, teachers, and parents through focus group discussions to investigate the current problem of ASD in children and the impact of using the robot as a technology to deliver learning sessions for improving cognitive ability. Results show that it was challenging for the children to give attention and focus during learning. Their cognitive ability is also low. Current teaching methods sometimes cannot make them happy and interested in learning. Hence, this research proposes robots as an assistive tool to overcome the problem of teaching and learning for children with ASD. | ||
| 7. Improved Barnacles Mating Optimizer for Loss Minimization Problem in Optimal Reactive Power Dispatch | ||
| Mohd Herwan Sulaiman (Universiti Malaysia Pahang), Zuriani Mustaffa (Universiti Malaysia Pahang), Omar Aliman (Universiti Malaysia Pahang), Mohd Mawardi Saari (Universiti Malaysia Pahang) | ||
| The solution of Optimal Reactive Power Dispatch (ORPD) can be treated as one of the sub-Optimal Power Flow (OPF) problems where the loss minimization is one of the objective functions to be solved. In this paper, an improvement of recent algorithm namely Improved Barnacles Mating Optimizer (IBMO) is proposed to determine the best combination of control variables of power system’s components such as generator bus voltages, injected MVAR devices and transformer ratios so that the total transmission loss can be minimized. To assess the performance of IBMO in loss minimization of ORPD, IEEE 57-bus system will be used. The performance of IBMO will be compared with original BMO and Moth-Flame Optimizer (MFO) to show the effectiveness of proposed improvement in solving the ORPD problem. | ||
| 8. Metaheuristic Approach for Optimizing Neural Networks Parameters in Battery State of Charge Estimation | ||
| Zuriani Mustaffa (Universiti Malaysia Pahang), Mohd Herwan Sulaiman (Universiti Malaysia Pahang), Azlan Abdul Aziz (Universiti Teknologi Mara) | ||
| To accurately estimate the battery state of charge (SOC), it is vital to improve the performance of a battery-powered system. This paper employs the recent proposed Evolutionary Mating Algorithm (EMA) for optimizing the weights and biases of Feed-Forward Neural Network (FNN) in estimating the state of charge (SOC) of Lithium-ion batteries. SOC estimation is the critical aspect in battery management system (BMS) to ensure the reliable operation of electric vehicles (EV) since there are no direct way to measure it. In addition, it is very nonlinear due to variation of charge/discharge currents and temperature. EMA is the recent evolutionary algorithm based on mating theory and environmental factor will be used in this paper to optimize the weights and biases of FNN on a common Li-ion battery, multiple data measurements, drive cycles and training repetitions. The performance of EMA will be compared with other algorithms to show the effectiveness of EMA in solving the SOC estimation problem. Findings of the study demonstrate the superiority of EMA in estimating the SOC of the batteries in terms of Root Mean Square Error (RMSE), mean Absolute Error (MAE) and Standard Deviation. | ||
| 52. Comparison of Squeezenet and Darknet-53 Based Yolo-v3 Performance for Beehive Intelligent Monitoring System | ||
| Sairul Safie (Universiti Kuala Lumpur), Mohd Zul-waqar Mohd Tohid (Universiti Kuala Lumpur), Ernie Mazuin Mohd Yusof (Universiti Kuala Lumpur), Noor Huda Jaafar (Universiti Kuala Lumpur) | ||
| This paper discusses the development of a prototype to detect the activeness of stingless beehives using ‘You Only Look Once -Version 3’ (YOLO-V3) technology. A graphical user interface (GUI) was developed using MATLAB to detect, count and display the total number of bees in real-time. The developed system provides a notification alarm in the form of indicator lights and buzzers for beekeepers when the number of bees detected per frame is lower than the threshold value. The system GUI developed can operate in two modes, namely real-time and offline video modes. This paper also compares two types of deep learning architecture used with YOLO-V3, namely SqueezeNet and DarkNet-53. SqueezeNet is a CNN-based deep learning architecture with a depth of 18 layers. DarkNet-53 has a depth of 53 layers. 150 images taken from 5 beehives were used to train and test this system. The comparative performance of these two architectures is done using the precision-recall curve (PR Curve). Two performance parameters from the PR curve, namely the average precision and the area under the PR curve, are used as the selection criteria for comparison. Simulation results show that SqueezeNet can be trained in a shorter period than DarkNet-53, with 20% better performance. | ||
| 72. Determination of Solution Concentrations using Photoacoustic Technology and Deep Learning: A comparison study | ||
| Hui Ling Chua (Universiti Tun Hussein Onn Malaysia), Audrey Huong (Universiti Tun Hussein Onn Malaysia) | ||
| A medium containing different concentrations of inks can be difficult to characterize. This research studies the feasibility of an assembled multispectral photoacoustic (PA) system for this purpose using a pretrained Alexnet and Long Short-Term Memory (LSTM) network. We considered different ink concentrations, which were allowed to flow into a single translucent Poly Vinyl Chloride (PVC) hollow tube immersed in a water tank. A color-tunable light-emitting diode (LED) is used as the source of illumination, while a single-point transducer is used to detect the PA signals produced following the light absorptions. The produced PA signal is collected as the illumination wavelength varied from 450 nm to 700 nm. We discovered the best performance using the Alexnet trained using data of 550 nm with 97.6 % testing accuracy. The similar but slightly lower classification accuracy of 95.8 % achieved by the LSTM method suggests the importance of choosing the right wavelength for the given purpose. We concluded that the feasibility of the system in differentiating different ink concentrations makes it a possible technique for the characterization of hemoglobin variants in blood. | ||
| 91. Clustering Mechanism in Particle Swarm Optimization Algorithm for Data Aggregation | ||
| Sharmin Sharmin (Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya), Ismail Ahmedy (Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya), Rafidah Md Noor (Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya), Habibah Ismail (Computer Science Unit, Centre of Foundation Studies, Univesrsiti Teknologi MARA) | ||
| Wireless Sensor Networks, abbreviated as WSNs, are composed of a large number of sensor nodes, each of which is endowed with a unique set of resources, that collaborate with one another to accomplish a given task effectively. One of the most pressing issues with WSNs is enhancing network lifetime, particularly for data transfer. Sensor nodes are often equipped with self-contained battery capacity, allowing them to perform critical tasks and interact with other nodes. The longevity of a wireless sensor network (WSN) is significantly influenced by the amount of electricity conserved by each sensor, which is closely correlated with the overall energy efficiency of the network. Energy conservation per sensor in a WSN is crucial for the network's longevity. Clustering has been the most energy-efficient approach for preserving energy in wireless communications. However, it lacked a method for picking the most effective cluster head. It brings about a reduction in the efficiency of the aggregation of data. As a result of not having sufficient methods for choosing the most efficient cluster head, the sensor node's power consumption rises. The ambition of the project is to improve the energy efficiency and extend the network's service life. The Particle Swarm Optimization (PSO) will be used for clustering to reduce energy usage in WSNs. The cluster head has been elected using PSO, member node distance from the base station, and its remaining energy is determined. The improved PSO in clustering was successfully applied to aggregate data for reducing energy use and compared to Low Energy adaptive clustering hierarchy (LEACH), A stable election protocol (SEP), zonal-stable election protocol (Z-SEP) and extend zonal-stable election protocol (EZ-SEP). According to simulation outcomes, the proposed technique improved the survival time of the network and reduced energy use over existing techniques such as LEACH, SEP, Z-SEP, and EZ-SEP. | ||
| 100. Wireless Walking Pattern Detection using Force Sensitive Resistor Pressure Sensors On Footwear | ||
| Norul Zaharah Khairuddin (School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA), Ili Shairah Abdul Halim (School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA), Azyati Nurfaqihah Azreen (Faculty of Applied Science, Universiti Teknologi MARA), Atiyyah Musa (Faculty of Applied Science, Universiti Teknologi MARA), Siti Lailatul Mohd Hassan (School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA), Najua Tulos (Faculty of Applied Science, Universiti Teknologi MARA) | ||
| Previous studies on gait analysis have been conducted on various human motions, such as walking and running. These studies are mostly based on the detection of abnormalities in walking patterns and were conducted using non-wearable prototypes. This imposes measurement constraints and is unsuitable for measuring free-living subjects. Therefore, this work aims to develop a wireless walking pattern detection system using force-sensitive resistors as the sensor on footwear. The important parameter for recognizing the walking pattern, also called the gait cycle, senses pressure distribution on the feet, which is then translated into resistivity. The second aim of this work is to train and classify the walking pattern using a support vector machine (SVM) and k-nearest neighbors (KNN) classifier. As a result, the accuracy with and without principal components analysis (PCA) is compared. The system mainly detects the walking pattern through pressure sensors embedded in the footwear, and the system is controlled by an Arduino Uno. These sensors are placed on three main areas of the shoe’s insole: the toe, metatarsal, and heel. All the data obtained is transmitted wirelessly through the wireless module receiver NR24L01F and sent to the computer for further analysis. Several walking patterns were collected, such as standing still, walking, and ascending and descending stairs. The collected data is plotted into a MATLAB graph, and the gait cycle is studied. The highest accuracy of both classifiers is achieved with 73.9% for weighted KNN classifiers and 69.2% for fine Gaussian SVM classifiers. | ||
| 115. Application of Manta Ray Foraging Optimization with Gradient-based Mutation (cMRFO) for Solving Power System Problems | ||
| Ahmad Azwan Abdul Razak (Universiti Malaysia Pahang), Ahmad Nor Kasruddin Nasir (Universiti Malaysia Pahang), Normaniha Abdul Ghani (Universiti Malaysia Pahang) | ||
| This paper presents the application of a recently proposed algorithm, the Manta Ray Foraging Optimization (MRFO) algorithm, specifically the Gradient-based Mutation MRFO (cMRFO), to solve real parameter constrained optimization problems. The cMRFO algorithm is a combination of the MRFO strategy and the Gradient-based Mutation strategy, where MRFO simulates the foraging behavior of Manta Rays, and GbM is a feasibility and solution repair strategy inspired by the ε-Matrix-Adaptation Evolution Strategy (εMAgES). The effectiveness of MRFO has been demonstrated in solving artificial benchmark-function tests, while GbM has been shown to improve the feasibility of solutions during the search. The study shows that cMRFO is a competitive optimization algorithm for solving constrained optimization problems. Moreover, the algorithm was applied to a power system problem, specifically the sizing of single-phase distributed generation with reactive power support for phase balancing at the main transformer/grid. The analysis shows that cMRFO outperforms εMAgES and COLSHADE in terms of performance. | ||
| Session II-A (10:30 - 13:00 @ Serai Room) | ||
| Session Chair: ARI AHARARI | ||
| 14. Study On Continuity of Defuzzification using Density Moment Method | ||
| Takashi Mitsuishi (Nagano University) | ||
| In this study, general structure of optimal fuzzy feedback control and its mathematical consideration are proposed. Compactness of the set of membership functions which characterizes fuzzy sets in IF-THEN rules is proved for optimization. Moreover two kind of continuity of the density moment method are obtained for that purpose. Since continuity of fuzzy inference calculation on the compact set, existence of IF-THEN rules that minimize the evaluation function of fuzzy control is proved. | ||
| 53. The ontology model for selecting quality melons uses hidden semantic data based on melon knowledge domains | ||
| Ubaidillah Umar (Department of Electrical Engineering, Faculty of Intelligent Electrical and Informatics Technology), Tri Arief Sardjono (Department of Biomedical Engineering, Faculty of Intelligent Electrical and Informatics Technology), Hendra Kusuma (Department of Electrical Engineering, Faculty of Intelligent Electrical and Informatics Technology) | ||
| A quality-oriented melon selection process is an important factor in growing consumers' willingness to pay. However, unlike most fruits, melons are usually sold whole, making it difficult to choose a perfectly ripe and sweet melon, as skin color and texture play an important role in this. From a marketing perspective, the selling power of melons is influenced by demand and supply. This paper presents a new approach by utilizing hidden semantic data on melon images derived from digital images. The semantic information on the surface of the melon is described, extracted, and shared as domain knowledge using an ontology approach that allows relationships between parameters to produce descriptions and actions in the domain to determine the quality of the melon fruit, then to monitor and discover new opportunities for farmers in planning our next procurement. Using K-Nearest Neighbor (KNN) to model the data that has been obtained from the visual data extraction process. An information description approach using an ontology guided by KNN in planning the procurement of the proposed melons can assist farmers in classifying melon prices for quality melons at reasonable prices with limited human involvement. | ||
| 74. Road Hazard Detection for The Motorcycle Based On Efficientnet-lite0 | ||
| S. M. Najib (Universiti Teknikal Malaysia Melaka, Melaka), S. N. S. Mirin (Universiti Teknikal Malaysia Melaka, Melaka), Ahmad Irfan Harman (Universiti Teknikal Malaysia Melaka, Melaka), Muhammad Qarl Farisz Mohd Rahimi (Universiti Teknikal Malaysia Melaka, Melaka), Muhammad Daniel Rahim (Universiti Teknikal Malaysia Melaka, Melaka), Nurnajihah Hazirah Azhari (Universiti Teknikal Malaysia Melaka, Melaka), Awy Khang (Universiti Teknikal Malaysia Melaka, Melaka) | ||
| With the limitation of shorter stopping distance, the motorcycle needs more space to break. The existence of static road hazards has a higher potential for road crashes which leads to a higher risk of serious injury to motorcyclists. Road hazards can be identified and located using the Motorcycle Object Detection system or simply known as MOD. The MOD system has the ability to detect and classify multiple objects in real-time. It employs the TensorFlow Lite framework on edge devices i.e., Raspberry Pi 4. TensorFlow Lite is the best preference for the Raspberry Pi 4 for deploying a pre-trained neural network; EfficientNet-Lite0 model. The MOD system utilizes an 8MP camera to capture the presence of the trained objects such as potholes, cones, barriers, and branches from the opposite direction which enter the motorcyclist's Region of Interest (RoI). RoI is designed based on the motorcyclist’s point of view (30 meters ahead) which can reduce false object detection. Likewise, RoI can prevent excessive alert noise to the motorcyclist. MOD system serves to alert the motorcyclist to the presence of the trained objects and activates the audible and visual warning system through the built-in speaker in the helmet and the warning light installed on the handlebar of the motorcycle. | ||
| 75. Sales Analytics Dashboard with Arima and Sarima Time Series Model | ||
| Aini Fatina Mohamad (Computing Sciences Studies), Aisyah Mat Jasin (Computing Sciences Studies), Aszila Asmat (mathematical Sciences Studies), Roger Canda (Computing Sciences Studies), Juhaida Ismail (Computing Sciences Study), Afiqah Bazlla Md Soom (Computing Science Studies) | ||
| One of the greatest difficulties that modern companies face is keeping up with technology. The limited options available in Power BI as a dashboard for time series in business forecasting models. Hence, this paper presents the use of ARIMA and SARIMA models to forecast sales for DataCo Global Company's dataset. The results are visualized and compared in a web-based dashboard, which displays forecast graphs, density plots, residual plots, and evaluation metric results for each model. The SARIMA model with parameters of (2,1,1) (0,1,1)12 was found to be the best model based on the smallest error measurement values of AIC and BIC. The dashboard provides an effective overview of the data and presents information in a visual format, making it easier for users to understand the results of the analysis. This approach enables data analysts to quickly assess and test the efficacy of forecasting models and assist executives in making informed decisions. | ||
| 82. Detection of Cyberbullying Tweets in Twitter Media using Random Forest Classification | ||
| Gunasekar Thangarasu (MAHSA University), Kesava Rao Alla (MAHSA University) | ||
| Users of social media platforms have become more vulnerable to violent crimes, cyberbullying, and hate speech as a direct result of their increased use of online platforms, which has also contributed to this vulnerability. Another factor that has contributed to this vulnerability is the fact that users of online platforms have increased their usage of these platforms. It is of the utmost importance for the prevention of cyberbullying (CB) in smart cities to design a self-sufficient anti-cyberbullying engine that can recognise cyberbullying texts in social media posts. This is one of the most important steps that can be taken. Those who live in smart cities won't have to stress about the possibility of getting into altercations with their neighbours because of this, which will allow them to unwind and take more joy in life. In this paper, a state-of-the-art automatic classification model can recognise CB texts without requiring them to be constrained into a specific shape in high-dimensional space. This model was conceived and created. Due of these constraints, we designed a text classification engine that first pre-processes the tweets by removing noise and other background information. Then, it classifies the data without overfitting the data by extracting the necessary features and then classifying the data. The random forest classifier can obtain a higher level of accurate classification than other types of classifiers, such as conventional classifiers. The findings of the validation indicate that the random forest classifier, which has increased text classification accuracy, gives accurate classification results. | ||
| 83. Classification of Garbage Waste in Smart Cities using Convolutional Neural Network | ||
| Gunasekar Thangarasu (MAHSA University), Kesava Rao Alla (MAHSA University) | ||
| Conventional smart city management modules make use of sensors or Internet of Things (IoT) devices in conjunction with intelligent traffic systems (ITS) to either secure the routes to schedule the times at which EV charging and smart energy distribution will take place. This is done so that electric vehicles can have their charging sessions scheduled and intelligent energy distribution can take place (ITS). This research proposes a novel Smart City Management System (MS) that adopts and integrates three immersive technologies to better manage garbage disposal in electric automobiles. At the beginning, monitoring the current condition of the garbage cans was accomplished using devices that were connected to the Internet of Things. Second, the garbage payloads, weather conditions, and the distance between garbage collection and disposal are just some of the data that may be used by the ITS in conjunction with convolutional neural networks (CNNs) to manage the GDs for efficient traffic management and speed monitoring. Other data that may be used include the distance between garbage collection and disposal. The distance between the locations of waste collection and disposal is another type of data that might be employed. The experimental validation of the proposed MS with CNN-ITS and the protected blockchain architecture have both contributed to improvements in the system energy efficiency, transmission speed, and overall level of security. These improvements have been made possible because of the combination of these two factors | ||
| 94. Cataract Detection using Pupil Patch Classification and Ruled-based System in Anterior Segment Photographed Images | ||
| Laily Azyan Ramlan (Universiti Kebangsaan Malaysia), Wan Mimi Diyana Wan Zaki (Universiti Kebangsaan Malaysia), Haliza Abdul Mutalib (Universiti Kebangsaan Malaysia), Aini Hussain (Universiti Kebangsaan Malaysia), Aouache Mustapha (Division Telecom, Center for Development of Advanced Technologies (CDTA)) | ||
| A cataract is an ocular disease affecting the eye's anterior segment resulting from the lens's clouding. If left untreated, it can cause blindness or vision impairment. The current diagnosis of cataracts involves a series of manual tests that are time-consuming, subjective, and dependent on the experience of ophthalmologists. Moreover, the medical equipment used for detection and screening is costly. Recently, digital images have been used to develop healthcare applications, including anterior segment images to detect ocular diseases. Therefore, this paper presents a cataract detection method using anterior segment photographed images (ASPIs) captured with a smartphone's camera. The proposed methodology includes a pre-processing step, and cataract detection comprises patch classification and a rule-based system. Using 540 normal and cataract patches, five different pre-trained networks are employed to classify the patches. The experimental results show that the patch classification model with ResNet-50 achieves the highest accuracy, specificity, and AUC values of 98%, 98.1%, and 99.9%, respectively. Then, it is used to detect cataracts in 20 cataracts and 20 normal ASPIs using a rule-based system. The proposed method managed to achieve perfect accuracy for cataract detection. The proposed method can potentially be used for cataract detection or screening and can help optometrists or ophthalmologists, particularly in rural areas. | ||
| 105. Evaluation of K-fold value in breast cancer diagnosis technique using SVM and bio-inspired optimization algorithm (JA-ABC5) | ||
| Ravindran Nadarajan (Universiti Malaysia Pahang), Noorazliza Sulaiman (Universiti Malaysia Pahang) | ||
| Breast cancer is a deadly disease that claims thousands of lives each year, and its prevalence is rising. Early detection is critical in lowering the mortality rate associated with breast cancer. The reliance on human interpretation for screening tests such as mammography, ultrasound, and MRI, on the other hand, may result in overdiagnosis or underdiagnosis. To overcome this limitation, classification techniques can be employed to enhance the accuracy of breast cancer diagnosis. This study focuses on investigating the impact of K-fold cross validation on the performance of breast cancer classification. The K-fold value is essential in determining the appropriate value to use for reducing the evaluation time and ensuring consistent analysis. The study examines how the K-fold value affects the accuracy of breast cancer identification. Based on the Wisconsin dataset results, a K-fold value of K5 is recommended for practical classification performance analysis. This value demonstrated superior completion time and robustness, taking an average of 2677.823 seconds with 98.49% accuracy. This study emphasises the importance of K-fold cross-validation in improving breast cancer classification accuracy and emphasises the need for additional research in this area. | ||
| 113. Development of an Artificial Intelligence (AI) Based Visual Counting System for The Food Industry | ||
| Ari Aharari (SOJO University), Kaito Kuwaduru (SOJO University), Farhad Mehdipour (Otago Polytechnic – Auckland International Campus (OPAIC)) | ||
| Artificial Intelligence (AI) has revolutionized various industries, including the food industry. One of the critical tasks in the food industry is counting the products during processing, packaging, and transportation. Manual counting is tedious, time-consuming, and prone to errors, which can lead to significant losses. The development of an AI-based visual counting system for the food industry aims to automate the counting process, reduce errors, and improve efficiency. This paper discusses the development of an AI-based visual counting system for the food industry, including the challenges, advantages, and potential applications. The proposed system utilizes deep learning algorithms to analyze digital images of food products and provide accurate counts. The system's effectiveness was evaluated through various experiments, and the results indicate that it can significantly improve the accuracy and efficiency of visual counting in the food industry. | ||
| 116. Adaptive Levy Flight Distribution Algorithm for Solving a Dynamic Model of an Electric Heater | ||
| Ahmad Nor Kasruddin Nasir (Universiti Malaysia Pahang) | ||
| This paper presents an improved version of the Levy Flight Distribution (LFD) algorithm. The original LFD is formulated based on the random walk strategy. However, it suffers a premature convergence due to an imbalance of exploration and exploitation. Consequently, the algorithm produces unsatisfactory performance in terms of its final accuracy achievement. As a solution to the problem, an adaptive scheme of search agents' step size is incorporated into the original LFD algorithm. Moreover, a mating strategy is also adopted to improve its stochastic nature throughout the search process. The algorithm is applied to optimize a nonlinear dynamic model of an electric water heater. A fuzzy-based Hammerstein structure is adopted to represent the heater model. It comprises a combination of both linear and nonlinear equations so that it can capture the dynamic behavior of the heater satisfactorily. The proposed adaptive LFD algorithm is compared with the original LFD algorithm. The result shows that the proposed algorithm has attained better accuracy. It also captured the dynamic behavior of the heater more adequately. | ||
| Session II-B (10:30 - 13:00 @ Kayu Manis Room) | ||
| Session Chair: FADHILAH NUR RANIA | ||
| 4. SD-WAN as an Efficient Network Solution with IDPS | ||
| F. N. Rania (Inti International University), J. Y. Chan (Inti International University), J. Y. Fong (Inti International University), E. S. Ng (Inti International University), S. Z. B. Zulkifli (Inti International University), P. S. Josephng (Inti International University) | ||
| The Wide Area Network and firewall are the current networking technologies that are widely used in most enterprises. But due to the rapid development of new technologies, there is a rising demand for a new efficient networking solution that could overcome the current technologies' limitations and cater to the end users' new requirements. This paper focuses on investigating and finding out the contrast and comparison between old and new intranet and extranet technologies in which Software Defined-Wide Area Network with Intrusion Detection and Prevention System solution is proposed. Extensive systematic review was conducted among peer referred literatures. The proposed solution enables network performance and security improvements, resulting in an efficient network solution. | ||
| 11. A Case Study of Lte Coverage Extension for Rural Malaysia | ||
| Azah Syafiah Mohd Marzuki (TM R&D), Siti Maisurah Mohd Hassan (TM R&D), Suhandi Bujang (TM R&D), Azlan Sulaiman (TM R&D), Mohd Kamarulzamin Salleh (TM R&D), Mohd Hafiz Mohamad Nor (TM R&D), Mohd Azmi Ismail (TM R&D) | ||
| LTE service demand is increasing for the rural areas since Work from Home (WFH) and online learning becoming the norm for Malaysians. However, the LTE coverage expansion mainly focus at highly populated areas or high ROI market, leaving some rural areas under-connected. Instead of deploying a new e-NB, coverage extension method is one way forward for rural mobile connectivity. Mobile Network Operator (MNO) may benefits huge savings on the CAPEX. In this paper, a case study of LTE coverage extension for 2 rural sites is presented. Low profile pico repeater system has been deployed to prove the benefits of LTE coverage extension method. The findings from the coverage mapping and user experience test after repeater deployment are presented. From the field trial, it has been proven that coverage extension method with proper planning can provide LTE coverage with stable service. | ||
| 25. Investigation of an Array of Dipoles in Three-dimensional Configuration | ||
| Kiran Nadeem (Universiti Tunku Abdul Rahman), Gobi Vetharatnam (Universiti Tunku Abdul Rahman), Kim Yee Lee (Universiti Tunku Abdul Rahman), Mohammad Ghanbarisabagh (Islamic Azad University North Tehran) | ||
| In this paper, an array of printed dipole antenna organised in a three-dimensional (3D) configuration is investigated. The dipole is printed on a low-cost FR4 substrate, with each arm on either side, and fed by a parallel transmission line. The dipole resonates at 3.5 GHz. The dipole is organised on a 2 x 2 x 2 configuration. The array elements are fed to achieve maximum beam at the front or broadside and achieves a gain of 10.40 dBi in this direction. Beam scanning over the entire 360° is possible with this 3D configuration. In this work the gain is fairly consistent throughout the 360° scanning with a variation of only 2.2dB. This configuration looks promising for 5G and future communication system. | ||
| 30. An Evaluation of Aco Based Approach for Network Load Balancing | ||
| Mohd Daud Alang Hassan (Universiti Teknologi MARA (UiTM) Cawangan Pulau Pinang), Norasmah Hamzah (Kolej Komuniti Seberang Jaya), Muhammad Nur Zikri Mohamad Hafizan (Intel Technology (M)) | ||
| This study uses the Ant Colony Optimization (ACO) algorithm to evaluate the network load balance. The main objectives of the ACO are to decrease execution time and achieve a balanced overall distribution of workloads among the network`s nodes. There are two priorities of the ACO load balancing algorithm which is first is to ensure the number of tasks assigned to each node with the networking environment are as uniform. Next priority is to select a node with the best capabilities to execute a certain task according to the node`s current pheromone value. Furthermore, the strategy used by the ACO algorithm is to select the most capable node to execute each of the tasks submitted to the network. The simulations and output for the performance of the ACO algorithm were done in the Cloudsim Plus Toolkit. As a result, it indicates that the ACO algorithm is effective to achieve network load balancing and it is able to outperform the Randomized and Round Robin algorithm in all situations and settings. | ||
| 49. Recent Advances and Benchmarking of NewSQL for OLTP and OLAP in The Big Data Age | ||
| Miko May Lee Chang (Swinburne University of Technology Sarawak Campus), John Zu An Chung (Swinburne University of Technology Sarawak Campus), Swee King Phang (Taylor's University) | ||
| While the never-ending debate between relational and NoSQL database is ongoing, a new competitor, NewSQL, has quietly entered the field. Introduced in 2011, NewSQL is not as popular as relational or NoSQL database. The main selling point of NewSQL is its ability to scale horizontally while preserving ACID properties and thus preserving the support to handle OLTP workloads. Given the active research and evolving developments of NewSQL in the last decade, this research paper aims to identify how far has NewSQL advanced to and how comparable is it to existing database systems in terms of On-Line Transaction Processing (OLTP) and On-Line Analytics Processing (OLAP) to accommodate big data. Three research questions have been formulated as part of the systemic literature review (SLR) followed by an experimental benchmarking to validate the results from the SLR. The results show that while NewSQL still has room to improve, it is definitely ready to be used in productions, albeit having certain obstacles which may need to be addressed such as expertise in deployment and maintenance, as well as performance. One limitation of this research is that the testing was conducted on a single node and future research could include performance testing on multiple nodes. | ||
| 69. Online Community Engagement: Exposing Information and Communication Technology Among Rural Learners During The Covid-19 Era | ||
| Shahida Sulaiman (Universiti Teknologi Malaysia), Mahirah Afifah Mohd Haliza (Universiti Teknologi Malaysia), Sh. Khayulzahri Sh. A Raof (Southeast Johor Development Authority (KEJORA)) | ||
| Due to the COVID-19 pandemic in 2020, many sectors including education have been familiar with online activities. It has also affected community engagement (CE) or service learning among academicians and university students. This study reports an online intervention programme under a university community project that aims to expose Information and Communication Technology (ICT) among rural students during the COVID-19 era in 2022. It focused on the use of ICT in learning Computer Science and English subjects for the secondary level. A total of 47 secondary students from six rural schools in Southeast Johor region participated in the online programme known as e-THRiL from February to April 2022. The findings reflect positive impacts in students’ knowledge before and after joining the online programme that had also fulfilled their needs. In addition, it also accomplished both targeted changes and sustainability aspects through the activities and the exposed ICT. In brief, despite the key challenge in the Internet access, the online CE could be conducted successfully among the selected rural learners who were exposed with numerous tools, applications, and methods in using ICT for learning English and Computer Science. Students’ experience in online learning due to the COVID-19 pandemic since 2020 could have contributed to the acceptance of online CE. | ||
| 86. Robust Text Clustering to Cluster The Text Documents in a Meta-heuristic Optimization | ||
| Kesava Rao Alla (MAHSA University), Gunasekar Thangarasu (MAHSA University) | ||
| This research optimises the clustering of text documents using a meta-heuristic approach, which requires pre-processing and clustering of data. The first step in data pre-processing is a data cleaning process, which eliminates any extraneous or missing information. Selecting the most useful attribute to enhance data extraction in response to a given query is the goal of feature selection. The procedure converts the raw data (int, numeric, nominal, or text) into a more usable form. The features are broken down into discrete categories according to the input query, associations are made between them, and the relative contributions of each feature are calculated. The features with the shortest distance to the answer attribute are chosen. In this way, we may get rid of all the other features within the clusters. | ||
| 87. Improved Data Transmission using Noma Technology for Office Automation Application | ||
| Kesava Rao Alla (MAHSA University), Gunasekar Thangarasu (MAHSA University) | ||
| Many contemporary businesses view the implementation of automation in the workplace as vital for a variety of reasons, including the enhancement of safety and security. The acquisition of information, also known as the speedy gathering of data from input devices, is the primary objective of the application that is utilised for office automation. This objective is the driving force behind the application. When more and more data is communicated from devices using local wireless network management, there is an increase in the amount of data communication overhead that must be managed. This must be done since there is an increase in the amount of data being communicated. The gravity of these problems is amplified when one considers the sluggish nature of the network. To communicate data between the local wireless network management systems that are part of the Office Automation system, the proposed solution made use of the NOMA communication technology. This not only accelerated the rate at which information could be transmitted, but it also cut down on the amount of delay that was felt. Using NOMA technology and the flexibility it offers throughout the Office Automation network, the proposed study will construct a local NOMA network management framework. This will be accomplished by using NOMA technology. the operation of the network is sped up to the point where packet load balancing, energy economy, and low latency are all realized because of the research | ||
| 112. Evaluating The Energy Efficiency of Noma 5g with Regard to The Capacity and Coverage | ||
| Megat Ahmad Faiz Ahmad Shukri (Universiti Teknologi MARA), Ezmin Abdullah (Universiti Teknologi MARA), Nabil M. Hidayat (Universiti Teknologi MARA), Nurain Izzati Shuhaimi (Universiti Teknologi MARA) | ||
| The current wireless communication networks (3G and 4G) use a technology called orthogonal multiple access (OMA) to transfer information. However, for the future internet of things (IoT) with a massive number of connected devices, non-orthogonal multiple access (NOMA) is a better option to handle more users. But when connecting many devices, energy consumption becomes a concern. To investigate this, this project is carried out to simulate NOMA with successive interference cancellation (SIC) using MATLAB to find a more energy-efficient solution. The simulation uses a wireless channel model, and the study observes the trade-off between coverage distance, capacity, and energy consumption. The simulation results show that the optimum coverage distances for far and near users are 750 m and 250 m, respectively, with a reasonable power requirement of 100 W and an outage probability of 0.00001. | ||
| Session III-A (14:00 - 15:30 @ Kayu Manis Room) | ||
| Session Chair: GUNASEKAR THANGARASU | ||
| 17. Gallium Nitride Depth Porosity Using Image Processing Method | ||
| Normasni Ad Fauzi (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang), Iza Sazanita Isa (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang), Siti Maryam Isa (School of Electrical and Electronics Engineering, Universiti Sains Malaysia, Pulau Pinang), Asrulnizam Abd Manaf (Collaborative Microelectronic Design Excellence Centre (CEDEC), Sains@USM, Universiti Sains Malaysia), Alhan Farhanah Abd Rahim (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang), Ida Rahayu Mohamed Nordin (Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang) | ||
| Porous Gallium Nitride (GaN) structure is commonly prepared by using direct current photo-assisted electrochemical etching (DC-PECE) technique to generate porous structure. However, to reach a generalized pores depth porosity measured using conventional methods is impossible due to the complex and very thin layer of the GaN structure. Image processing has been widely used in validating the measurement and may be significant for this application. This study is aimed to propose a recent method to measure pores depth porosity using image processing techniques. Porosity of the structures obtained by calculating the areas occupied by the pores. To validate the method, the evaluation of porous GaN quality is performed through a non-destructive investigation of its nanostructures using adapting image analysis techniques. The quantitative results showed good agreement between measurement and calculation (percentage porosity and pore depth) based on the image-processing data with 91 % and 78 % correlation coefficient. | ||
| 50. Method to Validate High Speed Bit Stream Generation in Post Silicon | ||
| Sooraj Ravindrakumar (Infineon Technologies), Jayakrishna Guddeti (Infineon Technologies), Pankaj Moharikar (Infineon Technologies) | ||
| High Speed Pulse Density modulation (HSPDM) is a logic that generates sequence of binary logic levels or say bit-streams in the output of a microcontroller or ASIC(Application Specific Integrated Circuit). Two bit-streams generated by HSPDM are used for fine tuning and coarse tuning of Voltage Controlled Oscillator (VCO), used inside radar sensor. These bit-streams are fed to VCO through Low Pass Filters. These bit-streams are generated at a speed of 160Mbps on dedicated microcontroller output pins. High accuracy is required in generated bit-streams, as this technology is used in safety critical applications like Advance Driver Assistance System. The high speed, wide configurability, asynchronicity and lengthy sequence of bit-streams makes it difficult to detect any deviation from expected behavior. This paper presents a more reliable and controlled method of validating the HSPDM bit-stream generation. The proposed technique was deployed in validating HSPDM in next generation of automotive microcontroller | ||
| 63. Feature Extraction of Rain Cell using Weather Radar Imagery in Tropical Regions | ||
| Noor Shazwani Osman (MARA University Technology), Wardah Tahir (MARA University Technology) | ||
| In-depth metadata about the spatial characteristics of rain fields is now available from weather radar data that was previously unavailable from traditional rain gauge networks. This knowledge is crucial for improving our comprehension of hydrology and rainfall patterns systems. This study focuses on the geometric characteristics of rain cells that formed in Peninsular Malaysia's tropical climate. The center location, area, maximum rainfall intensity, mean rainfall intensity, major radius length, minor radius length, and orientation of the rain cell were all extracted. This approach for pixel-based depth characterization of radar reflectivity images, particularly under unique circumstances brought on by the influence of the tropical monsoon region, will add novelty to this research. The features that are extracted, provide information that can be incorporated into a classifier model for rainfall-based machine learning in a future study. With the help of this model, upcoming convective and stratiform rainfall types can be predicted, as these features provide the input data needed to construct the Artificial Neural Network (ANN) model for the subsequent study. | ||
| 84. Video Object Detection From The Large Video Frames using Inception Networks | ||
| Gunasekar Thangarasu (MAHSA University), Kesava Rao Alla (MAHSA University) | ||
| Finding video content that can be utilised to spark the interest of a viewer is the purpose of the procedure that is being described here. In video, frames, background occlusion, or a dynamic backdrop shift in foreground regions can also present difficulties; similarly, fuzzy-moving targets and fast-moving objects might present difficulties. In other words, the model strives to be as comprehensive as possible in terms of its optimization. The proposed approach makes use of an InceptionNet to successfully accomplish the goal of recognising significant items in dynamic films by employing a benchmark video dataset. This should allow the method to fulfill its intended purpose. The information concerning the temporal, geographical, and local limitations on the scene is collected by this network. When it comes to discovering important items in films, the suggested strategy is put up against established ways that employ benchmark datasets as a measuring stick. The results of this comparison will help determine whether a method is superior. According to the findings of the experiments, the proposed method, which makes use of a deep learning model, performs substantially better than the state-of-the-art saliency models that have been employed in the past. This is indicated by the fact that the methodology makes use of a deep-learning model | ||
| 85. Resnet Associated Cross-layered Routing in Cognitive Radio Network | ||
| Kesava Rao Alla (MAHSA University), Gunasekar Thangarasu (MAHSA University) | ||
| In this paper, we discuss a cross-layer routing protocol that is derived from machine learning and a CRN. The protocol is described in detail. This protocol was developed with the intention of enhancing the routing performance of a reconfigurable network and maximising the effective use of available bandwidth during data transfer. A distributed controller is given instructions by the system to carry out activities such as load balancing, data collection on the immediate region, and the generation of the routes that are the most efficient. This is done so that the system can achieve its intended purpose. In order to specify clustering, the CRN uses a machine-learning-assisted routing protocol. This protocol enables controllers to work together with primary or secondary users on the forwarding plane. To demonstrate that the reconfigurable CRN is more scalable and robust in terms of the amount of residual energy and resources it requires, tests are carried out using standard CRN routing models. These tests are carried out to prove the reconfigurable CRN. | ||
| Session III-B (14:00 - 15:30 @ Serai Room) | ||
| Session Chair: SYED FARID SYED ADNAN | ||
| 16. A Lightweight Microstrip Antenna Study for Wireless Application. | ||
| Ida Rahayu Mohamed Noordin (Universiti Teknologi MARA Cawangan Pulau Pinang), Rohaiza Baharudin (Universiti Teknologi MARA Cawangan Pulau Pinang), Normasni Ad Fauzi (Universiti Teknologi MARA Cawangan Pulau Pinang), Azwati Azmin (Universiti Teknologi MARA Cawangan Pulau Pinang) | ||
| A study of a lightweight microstrip antenna for wireless application is proposed in this paper. This study will discuss on the designing and simulation of a lightweight microstrip patch antenna for wireless application at 2.4 GHz. The design parameters have studied to get the best antenna performance. The simulation process was done through Computer Simulation Technology (CST) Studio Suite software. The lightweight microstrip antenna dimension is 28.9 mm x 37 mm with antenna structure consists of low-loss dielectric material, FR-4 with dielectric constant, εr is 4.3, and thickness, h is 1.6 mm. The properties of antenna such as Voltage Standing Ratio (VSWR), return loss, radiation pattern, gain and bandwidth have been analyzed. From the simulation result obtained, CST simulation computed at 2.4 GHz, VSWR value of 1.1698, antenna return loss is -22.132 dB and bandwidth below 10 dB return loss, is between 2.3602 GHz to 2.4366 GHz. The antenna radiation pattern is designed with main lobe magnitude of 2.9 dBi and gain obtained from the simulation is 2.896 dBi. | ||
| 76. Detection of Ganoderma Boninense Diseases of Palm Oil Trees using Machine Learning | ||
| Yu Hong Haw (Universiti Malaya), Zhen Zhao (Universiti malaya), Yan Chai Hum (UTAR), Joon Huang Chuah (UM), Wingates Voon (UTAR), Siti Khairunniza -bejo (UPM), Nur Azuan Husin (UPM), Por Lip Yee (UM), Khin Wee Lai (UM) | ||
| Abstract—About one-third of the world’s vegetable oil and fat supply is made up of palm oil, of which 75% is consumed as food. Palm oil is a vital economic resource for nations like Malaysia. The Basal Stem Rot disease of oil palm trees is one of many obstacles to the production of palm oil. The infection is brought on by a fungus called Ganoderma Boninense, which colonizes trees. Early detection is difficult since the symptoms of infection are sometimes mild to nonexistent. Terrestrial laser scanning was used to collect 88 photos of the oil palm tree’s greydistribution canopy. The photos gathered were pre-processed to enhance the performance of the deep learning model. To train and verify the effectiveness of disease detection, a deep learning model called convolution neural network is used. The performance of disease detection is trained and tested using a convolutional neural network deep learning model, which divides the data into two classes: the healthy class and the non-healthy class. The improved DenseNet121 model reports a Macro F1-score of 0.7983. The model could only separate the images into two classes rather than categorizing the images into distinct infection levels, which is a limitation of our work. In order to investigate the feasibility of early oil palm disease diagnosis, it is advised for future research to undertake multi-class or multi-level classification using deep learning. | ||
| 98. A Goal Programming Approach in Solving Garbage Truck Multiple Objective Problem | ||
| Noryanti Nasir (Universiti Teknologi MARA), S. Sarifah Radiah Shariff (Universiti Teknologi MARA), Siti Sarah Januri (Universiti Teknologi MARA), Faridah Zulkipli (Universiti Teknologi MARA), Zaitul Anna Melisa Md Yasin (Universiti Teknologi MARA) | ||
| Solving a single objective function is easy, however, it becomes complicated when multiple objectives are considered. Managing garbage trucks and collectors is crucial for solid waste management in sustaining a good and healthy environment such that when the cost of operations also needs to be optimised. This study has multiple objectives that need to be considered which aims to minimize the cost per area serviced to be above target, to minimize the total number of garbage collector needed in serving an area, and to minimize the number of areas that cannot be served per day. On top of these three goals, the optimum number of garbage trucks per area per day is determined. The goal programming approach is excellent for solving the multiple objectives of linear programming. The results show that two out of three objective functions achieved the goal of equations as they met all the constraints. The model shows that more than 64% of areas are able to be served daily and the number of trucks needed to serve all areas is 11, which doubles the current value by 180%. The finding gives insight and information in identifying the optimal value for the multiple objectives as well as improving the quality of a healthy environment in the future. | ||
| 103. Domestic Garbage Target Detection Based On Improved Yolov5 Algorithm | ||
| Ma Haohao (Universiti Putra Malaysia), Wu Xuping (Tianshui Normal University), Azizan As’arry (Universiti Putra Malaysia), Han Weiliang (Heilongjiang University), Mu Tong (Tianshui Normal University), Feng Yanwei (Tianshui Normal University) | ||
| With the rapid development of the economy, the improvement of the living standards of Chinese residents, and the acceleration of urbanization, the output of household garbage in China continues to rise. The process of manual garbage classification is time-consuming and laborious, and the effect is still not satisfactory. In order to reduce the intensity of manual garbage classification and improve the efficiency and accuracy of garbage classification, a new type of household garbage classification based on improved YOLOv5 algorithm visual recognition is designed. Make a data set for garbage detection, and after training on the improved YOLOv5 network framework, detect the status of garbage in real-time. Experiments have proved that the accuracy of intelligent classification reached 98.27%, which is 3.85% higher than the original algorithm. It is verified that the improved YOLOv5 algorithm is very effective when applied to garbage classification, and it has social promotion significance and value. | ||
| Session IV-A (15:30 - 17:30 @ Serai Room) | ||
| Session Chair: HABIBAH HASHIM | ||
| 13. Integrated Earned Value Method for It Project Cost and Duration Estimation | ||
| Der-jiun Pang (International University of Malaya Wales (IUMW)) | ||
| Traditional Earned Value Management technique in project planning for effort and duration remains low to medium accurate. This study seeks to develop a highly reliable and efficient Integrated Earned Value Method (IEVM) to improve cost and duration prediction accuracy. This experiment compared the performance of five machine learning models across three different datasets and six performance indicators and verified the models with three other types of live project data. The results indicated that IEVM is a highly reliable, effective, consistent, and accurate machine learning-based method with a significant increase in accuracy over the conventional Earned Value Management technique. The finding pointed out a potential gap in the relationship between dataset quality and the performance of the ML model. | ||
| 23. A Novel Target Value Standardization Method Based On Cumulative Distribution Functions for Training Artificial Neural Networks | ||
| Wai Meng Kwok (Heriot-Watt University Malaysia), George Streftaris (Heriot-Watt University Edinburgh), Sarat Chandra Dass (Heriot-Watt University Malaysia) | ||
| Function approximation by artificial neural networks (ANNs) are often carried out via a collocation grid approach. However, for certain combinations of grids and functions, the training data for the relevant ANN can be extremely skewed and hence affect training efficiency, thereby necessitating standardization or normalization techniques. The choice of collocation grids often allows uniform training features but not targets. In this paper, we contribute a comparison between methods of target standardization - the relatively common min-max, z-score, normalized log methods and the uncommon empirical cumulative distribution function (CDF) method - in terms of the resulting approximation capabilities of the ANNs using the standardized target values. We demonstrate that the empirical CDF is a general and robust standardization method that allows for efficient training and good approximations in situations of extreme target skewness. Novel modifications using a mix of true CDF and empirical CDF in standardizing targets are used to successfully reduce biases arising from the empirical CDF standardization method. | ||
| 35. Enhancement of Low-Quality Diatom Images using Integrated Automatic Background Removal (IABR) Method from Digital Microscopic Image | ||
| Mohd Aiman Syahmi Kamarul Baharin (Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia), Ahmad Shahrizan Abdul Ghani (Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia), Syafiq Qhushairy Syamsul Amri (Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia), Normawaty Mohammad-noor (International Islamic University Malaysia, Bandar Indera Mahkota, 25200 Kuantan, Pahang, Malaysia), Hasnun Nita Ismail (University Technology of MARA, Perak Branch, Tapah Campus, 35400 Tapah Road, Malaysia) | ||
| Most diatom images scanned from digital microscopes suffer from low contrast, noise, and contain unwanted floating particles and debris in a single image. Moreover, the active movement of diatom along with poor lens focusing produces a blurred image. Thus, in this paper, we introduce a new integrated automatic background removal technique (IABR) to enhance low-quality microscopic diatom images. This paper describes a two-step process of microscopic diatom image for image smoothing. First, haze removal technique is applied to the low light image to enhance and removes the image from haze and noise. Second, the background removal technique extracts the diatom cell from the background image and improves the image contrast. The output results show that the proposed IABR method has successfully enhanced and smooths low-quality diatom images by removing the image background and improving image contrast. | ||
| 44. Motion Capture System Based On RGB Camera for Human Walking Recognition using Marker-based and Markerless for Kinematics of Gait | ||
| Riky Tri Yunardi (Department of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember), Tri Arief Sardjono (Department of Biomedical Engineering , Faculty of Intelligent Electrical and Informatics Technology (F- ELECTICS) Institut Teknologi Sepuluh Nopember), Ronny Mardiyanto (Department of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember) | ||
| The motion capture system has the potential to perform kinematics of gait analysis. Gait analysis applied for human activity recognition (HAR) for human walking recognition technology. The walking recognition makes it challenging for researchers to develop a low-cost system with high accuracy. This paper compares the accuracy of vision-based motion capture based on an RGB Camera using marker-based and markerless methods. The evaluation to determine the accuracy of the proposed of both methods was compared with statistical analysis. The marker-based method uses the Kalman filter, and the markerless method uses MediaPipe to measure gait parameters. Development of motion capture that can detect joint leg positions and measure joint angles based on OpenCV. It is designed for joint trajectories and angles at the hip, knee, and ankle. The motion capture system is implemented by a Logitech C270 webcam, Intel core i5 2.1 GHz processor, 8 GB RAM, and processed by JupyterLab with Python programming. It has been tested on recorded video data containing the subject walking straight with three gait cycles: slow, fast, and zigzag. In the marker-based method, each movement's average joint position detection errors are 22 pixels, 134 pixels, and 50 pixels. The angles of the hip and knee joints have an average angle difference with a reference of ±7°. In comparison, the markerless method has an average position error are 23 pixels, 65 pixels, and 49 pixels. And markerless has an average angle difference with a reference of ±5. | ||
| 59. A Thorough Comparison of The Variable-sample-size Weighted-loss Cusum and Abs-sprt Control Charts | ||
| Jing Wei Teoh (Heriot-Watt University Malaysia), Wei Lin Teoh (Heriot-Watt University Malaysia), Laila El-ghandour (Heriot-Watt University), Zhi Lin Chong (Universiti Tunku Abdul Rahman), Sin Yin Teh (Universiti Sains Malaysia) | ||
| It is frequently documented that concurrent shifts in the mean and dispersion of a process quality characteristic carry serious consequences to a manufacturing enterprise. It is, therefore, crucial to consider the detection ability of a control scheme when monitoring simultaneous changes in the process mean and dispersion. In this article, we conduct a thorough study on the detection performances of two dynamic control schemes, i.e., the variable-sample-size weighted-loss cumulative sum (VSS WLC) chart and the absolute-value sequential probability ratio test (ABS-SPRT) chart. This article reveals that the optimal ABS-SPRT chart outperforms the optimal VSS WLC chart in terms of the average extra quadratic loss and the average time to signal over a range of shift sizes. For small process shifts, the optimal VSS WLC chart is a slightly better performer than the optimal ABS-SPRT chart in terms of the average number of observations to signal. However, for moderate and large process shifts, the optimal ABS-SPRT chart remains the most powerful scheme in all aspects. The ABS-SPRT chart is also favored due to its smaller long-run expected sample size compared to the VSS WLC chart, making it extremely promising in many industrial applications. | ||
| 104. Rabin-P Encryption Scheme Analysis on MQTT | ||
| Wan Abdullah Che Izam (UiTM Shah Alam), Syed Farid Syed Adnan (UiTM Shah Alam) | ||
| This paper presents a Rabin-P Encryption Scheme Analysis on Message Queuing Telemetry Transport (MQTT), where MQTT is one of the OASIS standard messaging protocols used for the Internet of Things (IoT). MQTT is very popular since it has a light footprint on both energy consumption and computation. MQTT payloads are not secure by default unless all the links are encrypted by Secure Sockets Layer (SSL)/Transport Layer Security (TLS). However, all client and broker must install certificates to use SSL/TLS. Another way, the payloads can be encrypted with an encryption scheme to provide end-to-end without having to configure all of the client and broker. Therefore, an encryption scheme known as Rabin-p is introduced to MQTT payloads. In this work, a microprocessor selected is Raspberry Pi 4. Then, an analysis is conducted on MQTT with the Rabin-p scheme to analyze the encryption and decryption runtime of the Rabin-p encryption scheme on MQTT as well as the energy usage of Rabin-p encryption scheme on MQTT. Asymmetric encryption even though provides higher security, requires an expensive calculation that leads to higher energy usage. However, Rabin-p offers a lower processing algorithm. A conclusion can be made that the usage of Rabin-p in MQTT can help to improve the payload security since Rabin-p offers a complex algorithm which harder to decrypt the messages when communicating between devices. Rabin-p also can be integrated with MQTT Mosquitto since it uses minimal energy usage. | ||
| 106. The Impact of Track Elevations for DC Third Rail System in Malaysia | ||
| Xin Rong Chua (Universiti Tunku Abdul Rahman), Kein Huat Chua (Universiti Tunku Abdul Rahman), Cheun Hau Lee (Universiti Tunku Abdul Rahman), Yun Seng Lim (Universiti Tunku Abdul Rahman), Li Wang (Universiti Tunku Abdul Rahman), Mohammad Babrdel (Universiti Tunku Abdul Rahman) | ||
| — Energy efficiency of electric railway system can be affected by different parameters. The focus of this study is to explore the impact of track elevations on the DC third rail system in Malaysia. A simulation model was used to analyze the electrical behavior of the electric railway system under various track elevation scenarios. An electricity power supply network was constructed based on the parameters of Malaysia’s electric railway system by using ETAP-eTraX software. The results indicate that the energy consumption for elevation of +10% is 1931.2kWh higher than that of the elevation of -10%. While the difference of power consumption of one train traveling at elevation of +10% and -10% is 1.25% and 3.5% during acceleration and deceleration phases respectively. Overall, these findings suggest that track elevation is an important factor to consider when designing and operating electric railway systems in Malaysia, and that efforts to minimize elevation changes can lead to significant energy savings. | ||
| 111. Supertwisting Sliding Mode Control for Parallel Hybrid Electric Vehicle Control Strategy | ||
| Anith Khairunnisa Ghazali (MULTIMEDIA UNIVERSITY), Norazlina Ab. Aziz (MULTIMEDIA UNVERSITY) | ||
| Control strategy for hybrid electric vehicles (HEVs) is a method of energy management that helps with production, consumption, and conservation. To successfully manage hybrid electric vehicles, the best control technique is a big challenge. This study introduces super-twisting sliding mode control (STSMC) to optimise the state of charge (SOC) in parallel HEVs to achieve optimal control. The proposed proportional gain, k, varied in three values and was verified using the ADVISOR (Advanced Vehicle Simulator) MATLAB simulation. The simulation results were used to validate the proposed design's performance in terms of SOC stored energy, overall efficiency, and fuel emission. The proposed control strategy can improve the SOC at 871 seconds, overall efficiency ratio to 0.239, stored energy 5042 kJ, and be able to lower fuel emissions, according to the results. | ||
| Session IV-B (15:30 - 17:30 @ Kayu Manis Room) | ||
| Session Chair: ROSLINA MOHAMED | ||
| 38. A Preliminary Study On Learners’ Personal Traits for Modelling Learner Profiles in Its : a Sensor-free Approach | ||
| Mohammad Rahman (University of Tasmania), Hassan A. Al Salem (Jazan University), Soonja Yeom (University of Tasmania), Nadia Ollington (University of Tasmania), Robert Ollington (University of Tasmania), Md Mujibur Rahman (Universiti Malaya) | ||
| Intelligent tutoring systems (ITS) are computer-based learning systems that use intelligent technologies to provide adaptive learning paths and contents to learners by considering their characteristics and needs. The learner model, which is a representation of different learner’s characteristics, plays a key role in this adaptation. Research on educational psychology showed that emotion and learning have a hidden mutual relationship. If a learning process involves both cognitive and affective dimensions, then learning is like to be more usable, socially appropriate, acceptable and memorable, ultimately leading to significant improvement in the learner’s performance and the learning experience. However, traditional ITS ignore emotional aspects in learner modelling mostly; instead, they focus on learners’ cognition and motivation to maximise the knowledge to be achieved. The characteristics related to cognition are not well defined and primarily sparse when modelling a learner profile tailored to the learning domains. This study attempts to investigate the most common and relevant personal traits involved in the learning process based on the domains of learning. It also explores the most adopted techniques to identify such traits from log files of learners’ interactions with ITS without using physical and physiological sensors (i.e., camera, EEG) to model characteristic learner profiles for ITS aiming to improve its adaptiveness and leverage personalised learning. | ||
| 55. A Hybrid Wearable Technology Model for Autism Behaviour Intervention: Components and Elements Analysis | ||
| Mohamad 'isa Ab Malik (College of Computing, Informatics and Media Universiti Teknologi MARA Perlis Branch, Arau Campus), Siti Zulaiha Ahmad (College of Computing, Informatics and Media Universiti Teknologi MARA Perlis Branch, Arau Campus), Romiza Md Nor (College of Computing, Informatics and Media Universiti Teknologi MARA Perlis Branch, Arau Campus), Nursuriati Jamil (College of Computing, Informatics and Media Universiti Teknologi MARA, Shah Alam), Sakinah Idris (Faculty of Medicine Universiti Teknologi MARA Selangor Branch, Sungai Buloh Campus), Grace Liew Bee Wah (The National Autism Society of Malaysia, Setia Alam, Shah Alam) | ||
| Autism spectrum disorder is a social interaction and communication problem characterized by restricted, repetitive, and stereotyped interests and behaviors. If appropriate intervention is not implemented to address the issues, these behaviors may cause significant harm to themselves and others. Technology-based interventions have a high potential for implementation and can be a useful intervention technique for children with autism spectrum disorder moreover wearable technology. However, since the characteristics of children with autism spectrum disorder vary, the practice of "one suits all" design solutions from existing WT is irrelevant to them. The specific design factors, preferences, and usability for children with autism spectrum disorder need to be considered before designing wearable technology for them to make sure it suits their needs. Therefore, the primary goal of this study is to develop a specific wearable technology model as a guideline for developers in developing wrist-worn wearable technology for autistic children with comprehensive components. Accordingly, the model is a hybrid model based on the design principles of persuasive technology, calm technology, and empathic design for autistic behavioral intervention. A critical analysis and comparative analysis of previous studies have been done to extract and mapped the components and elements that apply to the hybrid model based on persuasive, calm, and empathic design principles for autism behavior intervention. The results of the analysis are then presented as a conceptual hybrid model that consists of the implementation of persuasive, calm, and empathic design principles. | ||
| 57. Non-fungible Token (nft) in Malaysian Creative Arts: The Status-quo of Tokenisation | ||
| Mohammad Aaris Amirza (Universiti Teknologi MARA), Mohamed Razeef Abdul Razak (Universiti Teknologi MARA), Muhamad Fairus Kamaruzaman (Universiti Teknologi MARA), Rusmadiah Anwar (Universiti Teknologi MARA) | ||
| The world has been discussing non-fungible tokens (NFT) and this abbreviation is the most searched topic via Google which received widespread attention in 2021. This NFT phenomenon has made the conversion of traditional art into crypto art which also led to the emergence of marketplaces based on the NFT. Rising numbers of users and local NFT marketplaces is somehow an indication of the reception of Malaysia towards the NFT. This paper is to first identify the status-quo of NFT and tokenization in the creative arts in Malaysia since its emergence and, secondly, the potential of this emerging technology carries. The study finds that there are number of local creative talents and brands has started to tokenised their artworks and gained success with their NFT projects. Despite Malaysia having a low percentage of NFT owners, demand in NFT is increasing as the potentials of this advancement has would contribute to the encouragement towards the Metaverse. This research concludes that as more users, brands, and organisations are beginning to create their own NFT collections to not only advertise their brands but also to begin utilising this new technology as they keep pace with other international NFT users, Malaysia's NFT market is still in its infancy and must be explore. | ||
| 58. Review On Workload and Resource Allocation in Edge-based Wireless Body Area Networks | ||
| Sachinthani Alahakoon (City University), Rajasvaran Logeswaran (City University) | ||
| An emerging and novel technology known as wireless body area networks (WBANs) has proven to be promising and is now widely used in the field of human health monitoring as a result of the exponential growth in the demand for medical services. This paper reviews the edge computing-based WBAN communication architecture, resource and workload allocation, and optimization techniques widely used in edge computing applications. Most of the current works review resource and workload allocation methods for edge computing, but not specifically for the WBAN. This paper contributes to bridging the gap by highlighting the edge computing findings in relation to WBAN. | ||
| 67. A Framework of Quality-aware Personalized Task Matching for Mobile Crowdsensing | ||
| Md Mujibur Rahman (University of Malaya), Mohammad Rahman (University of Tasmania), Soonja Yeom (University of Tasmania), Md Badiuzzaman (UNSW, Sydney, Australia), Hassan Salem (Department of MIS, CBA, Jazan University), Hassan A. Al Salem (Jazan University), Soo-hyeong Kim (Department of Artificial Intelligence Convergence, Chonnam National University), Umair Munir (University of Central Punjab) | ||
| The proliferation of smartphone devices coupled with the rich development of mobile sensing technology has emerged a new form of sensing paradigm called Mobile Crowdsensing (MCS). It transforms smartphone users from passive consumers of information to producers by enabling them to contribute to various location-based sensing tasks (i.e. traffic monitoring). In MCS, task assignment is a significant issue where finding the best match between tasks and workers is crucial to ensure both the quality and effectiveness of a MCS platform. The previous studies on task assignment primarily focus on maximising the number of allocated tasks or minimising the travelling distances of the workers. However, they rarely pay attention to the credibility of the platform’s workers, which primarily depends on the careful investigation of users’ domain knowledge, trustworthiness and willingness level. To address the problem, a novel quality-aware personalised task-matching framework has been proposed in this study. The framework aims to match the right tasks to the right workers in a personalised way while workers’ credibility is taken into consideration. We conduct extensive experiments on real and synthetic datasets to evaluate the performance of our proposed model. Experimental results demonstrate the effectiveness of our proposed model in personalised task matching. | ||
| 68. Differences of Performance Analysis of Single Channel LoRaWAN Network for Air Pollution Monitoring System Using IoT Platform in Smart City – A Review | ||
| Nik Farah Emmyra Nik Kamaruzaman (UNIVERSITY TEKNOLOGI MARA), Suzi Seroja Sarnin (UNIVERSITY TEKNOLOGI MARA), Nani Fadzlina Naim (UNIVERSITY TEKNOLOGI MARA) | ||
| Cases for air pollution keep on increasing day by day. In the realm of IoT, several monitoring systems have emerged and evolved over many decades. One of the best methods proposed is LoRaWAN (Long Range Wide Area) network that has been introduced and implemented as a long range and low-cost channel to transmit data. This can be seen; the effectiveness of each performances is different for every research project conducted due to certain parameters used. This paper presented to show the differences of performance analysis of a single channel LoRaWAN network for air pollution monitoring system using IoT platform in a smart city. | ||
| 102. Enhanced Blockchain Scalability for IoT-based Smart Devices - A Generic Model Development | ||
| Mathuri Gurunathan (Universiti Tenaga Nasional), Moamin Mahmoud (Universiti Tenaga Nasional), Faisal Faisal (Universiti Tenaga Nasional) | ||
| Blockchain become well known as there is third-party contribution while doing the exchanges or transactions. Blockchain is the innovation for utilizing digital forms of money. It draws in the consideration of specialists and academicians, along with various highlights of Blockchain it is having the significant issue of versatility and scalability which can be classified into throughput, cost, limit, and systems networking. Scalability influences due to some different components like block size and block interval time which likewise may lessen the security. The system may get powerless against various attacks on the off chance that we indiscriminately change the scalability. To address these challenges, this paper con-ducts an intensive analysis of blockchain scalability challenges in the IoT context and subsequently proposes a generic model to enhance scalability. The investigation covers restrictions on different blockchain stages and how system parameters such as throughput, latency, block size, and network influence a peer-topper system’s effectiveness, security, and energy consumption. | ||
| 108. Assessing The Importance of Browser Fingerprint Attributes Towards User Profiling Through Clustering Algorithms | ||
| Vicki Wei Qi Lee (Multimedia University), Shih Yin Ooi (Multimedia University), Ying Han Pang (Multimedia University) | ||
| Browser fingerprint is often linked to privacy as it is a method to gather data about the configuration of the browser to identify a user. The browser’s configurations which are also known as attributes are the key to making the user to be identified. Web browsers explicitly disclose information about the host system to websites by making that information available to them, such as attributes like the screen resolution, local time, or OS version. Since each browser has its different attributes which make each of them unique and so it is important to understand well about the attributes. In this research, the purpose is to discover which attribute produces the highest unique value by using the clustering algorithm. Experiment results showed that if the attribute is unique, it will be hard to cluster into groups. This can be proved by using a clustering algorithm where the unique attributes will have a high value in the incorrectly clustered instances because it is harder to be clustered. | ||
| Session IV-C: Online Presentations (15:30 - 17:30 @ Virtual Session) | ||
| Session Chair: TBA | ||
| 15. Paving The Way for 64 Gbps PCIe 6.0 End to End Physical Link Compliance in Multi-board Digital System | ||
| Chang Fei Yee (Keysight Technologies) | ||
| (Video Link: https://www.youtube.com/watch?v=v5L2lSiEIdI) | ||
| This paper introduces the four-level pulse amplitude modulation (PAM-4) and its implementation in Peripheral Component Interconnect Express (PCIe) 6.0 communication protocol, to facilitate the large volume of high-resolution data traffic in multi board digital electronic system, such as computing server and modular test instrument platform. Besides that, the link loss budget of each system component, i.e., chip package, board and connector is presented. Moreover, this paper also underlines the vital pre-route consideration from signal integrity standpoint for the physical channel realization on printed wiring board (PWB), including the choice of substrate material, communication link design and the end-to-end channel analysis at 64 Gbps speed grade, to be compliant with the specification of characteristic impedance, insertion loss and eye diagram regulated by PCI-SIG. | ||
| 21. Efficacy of Bidirectional LSTM Model for Network-Based Anomaly Detection | ||
| Toya Acharya (Prairie View A & M University), Annamalai Annamalai (Prairie View A & M University), Mohamed F Chouikha (Prairie View A & M University) | ||
| (Video Link: https://youtu.be/waLelCaAHes) | ||
| The Internet is vital in daily applications such as education, health, business, etc. Increasing the usage of the Internet and technology also increases the risk. Cyber attackers can use technology to compromise the triad of the CIA (confidentiality, integrity, and confidentiality). Malicious activities occur in our surroundings without our knowing it. Cyberattacks cannot be seen physically, though occurring to our Internet of things (IoT) devices, personal computers, laptops, and even our networking devices. Network anomaly detection is an efficient way of detecting malicious activities. Network-based anomaly detection captures and analyzes attributes of abnormal behavior in a network. Machine learning and deep learning-based approach are attractive among various known methods for network anomaly detection because they can efficiently analyze big network traffic data for malicious activities and detect zero-day attacks. A Recurrent Neural Network (RNN) model is designed to recognize the sequential characteristics of data and then use the patterns to predict the coming scenario. In this research work, seven different optimizers (Nadam, Adam, RMSprop, Adamax, SGD, Adagrad, and Ftrl), epochs, batch size, and the ratio of training testing data size are analyzed for the Bidirectional Long Short Term Memory (Bi-LSTM) network anomaly detection which provides the highest anomaly detection accuracy of 98.52% on the NSL-KDD binary dataset. The performance is compared using accuracy and F1-score metrics. Performance assessment regarding the accuracy and F1-score revealed that the proposed Bi-LSTM anomaly detection model exhibited better performance than the other existing anomaly detection methods. | ||
| 43. On Private Server Implementations and Data Visualization for Lorawan | ||
| Sheikh Tareq Ahmed (Prairie View A&M University), Annamalai Annamalai (Prairie View A&M University) | ||
| (Video Link: https://youtu.be/I2QI8mD8aRU) | ||
| Monitoring and analyzing data collected from IoT devices is a very important aspect of IoT solutions. There are various types of wireless communication that can be used to collect data from edge devices. For example, Wi-Fi, LoRa, Bluetooth low energy mesh network, Zigbee, SigFox, NB-IoT, and LTE are a few technologies used in IoT. This data can be sent to public or private servers for analysis and visualization. When deciding to choose a server for IoT solutions, there are a few key factors that should be considered. For example, Coverage of your IoT product, data privacy and ownership, infrastructure requirements, and up-time of servers. In this document, we will discuss a few public and private IoT servers, their requirements, costs, and deployment | ||
| 48. Efficacy of Cnn-bidirectional Lstm Hybrid Model for Network-based Anomaly Detection | ||
| Toya Acharya (Prairie View A & M University), Annamalai Annamalai (Prairie View A & M University), Mohamed F Chouikha (Prairie View A & M University) | ||
| (Video Link: https://youtu.be/yHvQ7-olCcA) | ||
| With the development of the web and the internet, computer networks have become an important tool to transfer information digitally, that increases the system's threats and vulnerability. Cyber attackers can use the internet and tools to compromise the triad of the CIA (confidentiality, integrity, and confidentiality). Network anomaly detection is challenging while detecting anomalous behavior in a network due to the large-scale data, imbalance nature of attacks class, and huge numbers of features in the dataset. Traditional Machine learning methods are not very efficient in solving those problems. Deep learning has proven to be more efficient in detecting network-based anomalies. A Recurrent Neural Network (RNN) model is designed to recognize the sequential data characteristics to predict. We proposed a convolutional neural network with bidirectional long-short memory (CNN Bi-LSTM) model to analyze the hyperparameters, including optimizers (Nadam, Adam, RMSprop, Adamax, SGD, Adagrad, Ftrl), epochs, batch size, learning rate, and neural network model architecture of CNN-BLSTM algorithms. Those analyzed hyperparameters provide the highest anomaly detection accuracy of 98.27% and 99.87% on the NSL-KDD and UNSW-NB15, respectively. Performance assessment regarding the accuracy and F1-score revealed that the proposed CNN Bi-LSTM anomaly detection model exhibited better performance than the other existing anomaly detection methods. | ||
| 60. A Systematic Literature Review On Batik Image Retrieval | ||
| Agus Eko Minarno (Universitas Gadjah Mada, Universitas Muhammadiyah Malang), Indah Soesanti (Universitas Gadjah Mada), Hanung Adi Nugroho (Universitas Gadjah Mada) | ||
| (Video Link: Not Submitted) | ||
| Batik is a traditional textile art form that has its origins in Indonesia. The diversity of batik motifs is a result of the acculturation process, which has led to the emergence of different styles and variations in different regions. However, this diversity also poses a problem for society in terms of identifying, classifying, and locating batik based on the motifs and regions. To address this issue, researchers have been using the Content-Based Image Retrieval (CBIR) approach, which is a study field that has been around for a while and is known for its real-time retrieval capabilities. CBIR is a method that aims to minimize the gap between the image feature set and human visual understanding to recognize the pattern of batik. In this survey, we review recent instance retrieval works that have been developed based on handcrafted featured extraction and deep learning algorithms. The survey is organized by the most dataset used, the most method used and survey methods which have a best performance. This survey highlights the recent works and the potentials of using handcrafted feature extraction and deep learning algorithms in CBIR, and highlights the promising future prospects in this field. | ||
| 71. Visualization of Word Similarity Measurement for Messages in Sequence Diagram using Heatmap | ||
| Zulhafizal Othman (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch), Aisyah Mat Jasin (Computing Sciences Centre of Studies, College of Computing, Informatics and Media, Universiti Teknologi MARA Pahang Branch, Raub Campus), Muhd Eizan Shafiq Abd Aziz (Computing Sciences Centre of Studies, College of Computing, Informatics and Media, Universiti Teknologi MARA Pahang Branch, Raub Campus), Mohd Khairul Ikhwan Zolkefley (Computing Sciences Centre of Studies, College of Computing, Informatics and Media, Universiti Teknologi MARA Pahang Branch, Raub Campus), Ainamardia Nazarudin (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch), Hamizah Mokhtar (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch), Amminudin Ab Latif (Civil Engineering Studies, College of Engineering, Universiti Teknologi MARA Pahang Branch) | ||
| (Video Link: https://youtu.be/piXQuNhETek) | ||
| The problem of systematic data storage is often a problem in documentation management. Too many and crunchy documents are often an obstacle to creating good management. Apart from that, the problem of failure to monitor the operation of laboratory equipment such as equipment calibration is also a problem for the responsible officer in the laboratory. As a result of this, a management system that uses a database was created to facilitate the documentation process and help in the monitoring of instrument calibration in the laboratory. The purpose of this study is to measure similarity between 5 messages in each sequence diagram and the five messages are defined in the Table 1. Each of these messages are assigned in each object. The result of these similarity measurement will be visualized on heatmaps shown in Figure 7 to Figure 9. Heatmap is a type of plot that often used in multiple correspondence analysis. Based on the results, this study will help system analyst and system designers to refine the most similar messages in sequence diagram in analysis stage. This will effect the sequence diagram that will be enhanced in the design phase in which the system designer need to convert all these messages into technical functions in each classes. | ||
| 73. Air Particulate Matters Auto-rule-based Labeling to Support Long-distance Run Environment Data Classification | ||
| Wandy Wandy (Diponegoro University), Kusworo Adi (Diponegoro University), Media Anugerah Ayu (Sampoerna University) | ||
| (Video Link: https://youtu.be/HLgD3Bq9MC0) | ||
| Sports Science is an interdisciplinary and multidisciplinary science that strives to increase athletic performance and endurance. Sport Science recognizes and prevents injuries. Sensors and statistics formalize Sports Science. Runners need coaches and teams to support them before, during, and after the run race. Coaches generate running training plans to boost performance. Running race performances may be impacted by air pollution exposure while training, so coaches should consider limiting air pollution exposure when training. One of the external factors is Particulate Matter (PM2.5 and PM10). Sensors connecting to the Internet can record external factors and produce csv data. The foundation of supervised machine learning is the labeling process. Labeling a set of data is one of the laborious and time-consuming phases in every machine-learning application because it requires verifying the accuracy of the labels and making any necessary revisions. This research aimed to find a solution to automatically label numerous air particulate matter raw data using a rule based on parameters to reduce manual work, human errors and faster processes. This labeled data will later be used for supervised machine learning classification to support the coach in generating training programs for the runners in a Sports Information System. Based on Indonesia Air Quality index rule-based approach, labeled text data in csv has been generated and tested with PM2.5 and PM10 parameters in three scenarios with a 100% success rate. It was possible to automate the labeling process, and it explained how automation results in fast and accurate results. | ||
| 88. Virtual Bonding in Ethernet Transmission Wireless Backhauled Links | ||
| Puneet Kumar (IEEE), Karishma Bava (IEEE) | ||
| (Video Link: https://www.youtube.com/watch?v=5dtoElwUYtc&ab_channel=puneetkumar) | ||
| In order to achieve higher throughput and robust redundancy, bonding ports has been a widely-used technique in wired networking since a long time. With the evolution of 5G, deployment of wireless backhaul links are on the rise, since they require less infrastructure. A single wireless link throughput is limited due to its hardware capabilities, therefore bonded links can be a suitable alternative to provide higher throughput, while keeping same infrastructure. Radios in wireless backhaul links may not be present in the same premises, which demands smart techniques to bond the wireless backhaul links. This paper presents a novel approach of virtually bonding different wireless backhaul links to provide a single control plane for the north and south bound devices for control plane, Management and Data Plane Protocols. Additionally, this approach will scale the extension of Layer 2 and Layer 3 domains of a network, along with a reduction in the manual configuration. Our simulation results show that our approach increased \gls{TCP} throughput by 59.5\% and 61.29\% in one and two links scenarios respectively. | ||
| 90. Clustering of Point-to-point Ethernet Transmission Wireless Backhaul Links | ||
| Puneet Kumar (IEEE), Karishma Bava (IEEE) | ||
| (Video Link: https://www.youtube.com/watch?v=M7P3O0PU8ik&t=277s) | ||
| Clustering is bundling physical links to construct a single logical link between peers to increase bandwidth and overcome failover issues. While this definition holds true, it is imperative to know that its implementation is hard with certain key factors to maintain those links along with a single control and data plane. With 5G becomes more ubiquitous, \gls{P2P} wireless Ethernet transmission backhaul links play a vital role in backbone networks, it is essential to make data rates capability of Ethernet transmission links as high as possible. Presently, backhaul links suffers from poor resiliency, performance, scalability, maintainability, and manageability. This paper proposed a stateful clustering algorithm, which improves the failover mechanism, increase bandwidth, and maintains a single control and data plane for upstream and downstream devices for the aggregated links. According to our best knowledge this is the first comprehensive, stateful, and failover resilience protocol for clustering wireless backhaul links. | ||
| 97. Improving Geo-location Performance of Lora with Adaptive Spreading Factor | ||
| Sheikh Tareq Ahmed (Prairie View A&M University), Annamalai Annamalai (Prairie View A&M University) | ||
| (Video Link: https://youtu.be/I2QI8mD8aRU) | ||
| The Low-Power Long-Range Wide Area Network (LoRaWAN) technology has received considerable attention in recent years with a wide-range of emerging applications such as precision agriculture, tracking, home security, water, and air pollution monitoring, among many others. One of the potential use cases of the LoRa technology is the geo-location of people with cognitive problems (autism spectrum disorder, Down syndrome, dementia) that could alleviate one of the biggest concerns of caregivers on how to prevent their patients wandering from their safe settings. While existing commercially available personal tracking devices can help locate missing persons, most of them are expensive (cellular subscriptions and/or high monthly service fees associated with one-to-one communication between child/patient and parent/provider), rely solely on global positioning system that does not work well in indoors, have limited coverage (if based on Bluetooth or Wi-Fi access) as well as poor battery life (require frequent recharging). Moreover, current LoRaWAN solutions also suffer from coverage and packet loss issues in dense environments (e.g., indoors, or outdoors with dense buildings or blockages). While a higher spreading factor can improve the communication range, but it will also result in a lower transmission bit rate which is a critical design consideration owing to the over-the-airtime restrictions of such LoRa networks. In this work, we propose and implement an adaptive algorithm in a LoRaWAN testbed that will dynamically change the spreading factor based on the received signal strength indicator (RSSI), packet SNR, and/or packet success rate to improve the overall coverage and throughput of the network. This in turn will translate into a better and economically feasible tracking/geo-location solution. Our proposed solution will give a peace of mind to caregivers at an affordable price aside from mitigating “caregiver burnout syndrome” and/or preventing the need for resource-intensive search-and-rescue efforts. | ||
| 107. Exploring Quantum Machine Learning for Electroencephalogram Classification | ||
| Raymond Ho (Hong Kong Metropolitan University), Kevin Hung (Hong Kong Metropolitan University) | ||
| (Video Link: https://youtu.be/pHcv3YC_9V4) | ||
| Quantum machine learning (QML) is a relatively new discipline emerging from the concepts of machine learning and quantum computing, whereby quantum algorithms are used to solve machine learning tasks. This paper explores the use of quantum machine learning for electroencephalogram (EEG) classification. In particular, a previously proposed EEG feature extraction method and classification framework for classifying dementia subjects were followed in this study. A quantum classifier replaced the classical classifier component of the framework, and the classification accuracies between the quantum and classical classifiers were compared. This study has demonstrated that applying QML in healthy-dementia classification can be implemented using near-term quantum devices or quantum simulators with moderate performance. The quantum classifier achieved an overall classification accuracy of 81.67% and 79.17% in a train-test split performance test and an n×k-fold cross-validation test, respectively. However, the quantum approach did not produce higher classification accuracies than the classical classifier. Despite the promise of quantum advantages, further investigation and optimization are required to improve its effectiveness. | ||
Conference Registration System v3.41, (c) Ihsan Mohd Yassin | ||