Road Travel
.
.
 |
Prof. Dr. Ir. Suwarno, Institut Teknologi Bandung, Indonesia |
|
SUWARNO (Senior Member, IEEE) received the B.Sc. and M.Sc. degrees from the Department of Electrical Engineering, Institut Teknologi Bandung, Indonesia, in 1988 and 1991, respectively, and the Ph.D. degree from Nagoya University, Japan, in 1996. Senior Member of IEEE. He is currently a Professor and the Emeritus Dean of the School of Electrical Engineering and Informatics, Institut Teknologi Bandung. He is also the Head of the Electrical Power Engineering Research Group. He has published more than 300 international journal articles and conference papers. His research interests include high voltage insulating materials and technology and diagnostics and asessment of HV equipment and renewable energy systems, and asset management. He was the General Chairperson of several international conferences, such as ICPADM 2006, ICEEI 2007, CMD 2012, ICHVEPS 2017, and ICHVEPS 2019-2025. He is the Editor-in-Chief of International Journal on Electrical Engineering and Informatics.
Speech Title: Artificial Intelligence Application for Condition Assessment of High Voltage Power Transformer using Health Index |
||
 |
Assoc. Prof. Shuang Du, the University of Electronic Science and Technology of China, China |
|
Shuang Du, a native of Sichuan, China, was born in 1983. He completed his undergraduate studies in Electronic Engineering at Beijing University of Posts and Telecommunications (BUPT) in 2005. He then pursued graduate education at the University of Calgary, Canada, receiving his M.Sc. in 2010 and his Ph.D. in 2015, both in Geomatics Engineering. Dr. Du embarked on his professional career at the University of Electronic Science and Technology of China (UESTC) in 2015, and he is serving as an associate professor at the School of Aeronautics and Astronautics. He is also recognized as an expert committee member of both the China BeiDou Open Laboratory and the Sichuan Provincial Department of Science and Technology. His primary research and teaching activities focus on autonomous navigation and route planning for unmanned systems, as well as the field of embodied intelligent robots. Dr. Du has presided over or led a series of research projects including the Key R&D Program of China's Ministry of Science and Technology, projects from National Natural Science Foundation of China, and Key R&D program of Sichuan Provincial Department of Science and Technology, achieving a series of innovative research outcomes. He was the recipient of the 2018 Second Prize of the Surveying and Mapping Science and Technology Progress Award (China) and the 2024 Third Prize of the Sichuan Provincial Science and Technology Progress Award. He has published more than 20 peer-reviewed articles in reputable journals and conferences, and granted more than 10 invention patents, five of which have been commercialized, generating significant economic benefits. Dr. Du pioneered the use of rotational modulation to suppress random error drift in inertial devices, effectively solving the key challenge of error divergence in long-term autonomous navigation. Building upon this foundational technology, he led his team in the development of an autonomous navigation system for ground wheeled vehicles, which has now entered the commercialization phase.
Speech Title: MAPSE: A Decoupled Planning and Execution Framework for Robust Vision-Language-Action Robots Abstract： Vision-Language-Action (VLA) models show great promise for multi-task robotic manipulation, but their real-world deployment is hindered by limited out-of-distribution (OOD) robustness, a lack of hierarchical task decomposition for long-horizon reasoning, and insufficient fault tolerance. To address these challenges, this paper proposes MAPSE, a decoupled planning-execution framework designed to achieve modular generalizability and execution recoverability. At the planning level, MAPSE utilizes a multimodal episodic memory hub, employing a Pareto multi-objective retrieval mechanism and task skeleton re-ranking to ensure candidate diversity and structural alignment. Furthermore, an adaptive threshold-gated strategy dynamically balances efficiency and generalization by toggling between semantic mapping transfer and retrieval-augmented MLLM planning. For robust execution, any VLA policy can be integrated as a plug-and-play action expert, monitored by a SAFE-driven closed-loop failure detection mechanism at the sub-task level. Upon identifying a failure trend, a spatial-aware MLLM synthesizes geometric correction prompts to trigger targeted recovery trajectories. Crucially, to prevent control stagnation during MLLM inference, we introduce a latency aware asynchronous parallel recovery mechanism. Extensive evaluations demonstrate that MAPSE significantly improves both the success rate and closed-loop robustness of existing VLA policies. Notably, our framework achieves state-of-theart mean success rates of 97.9% on the LIBERO simulation benchmark and 79.7% on SimplerEnv-WidowX, alongside superior continuous performance in complex, multi-stage real-world manipulation tasks.
|
||
 |
Associate Professor Ir. Ts. Dr. Mohamad Nur Khairul Hafizi Rohani, Universiti Malaysia Perlis, Malaysia |
|
Associate Professor Ir. Ts. Dr. Mohamad Nur Khairul Hafizi bin Rohani is a distinguished scholar and professional engineer at Universiti Malaysia Perlis (UniMAP), Malaysia, where he serves as Associate Professor in High Voltage Engineering and Director of the Centre for Alumni Relations. A registered Professional Engineer (BEM) and Professional Technologist (MBOT), he is internationally recognized for his expertise in partial discharge diagnostics, condition monitoring of high-voltage assets and artificial intelligence–driven signal and image analysis.
Speech Title: Benchmarking CNN and Vision Transformer Models for Small-Dataset PRPD Classification in High-Voltage Rotating Machines Abstract： Partial discharge (PD) analysis plays a critical role in assessing insulation condition in high-voltage rotating machines. Phase-Resolved Partial Discharge (PRPD) pattern classification enables early fault detection and condition-based maintenance. Recently, Vision Transformers (ViTs) have demonstrated superior performance in various computer vision tasks; however, their effectiveness on small industrial diagnostic datasets remains uncertain. This paper presents a comparative evaluation of convolutional neural networks (CNNs) and Vision Transformer architectures for multi-class PRPD pattern classification. Five-fold stratified cross-validation was conducted on a six-class industrial PRPD image dataset. We evaluated ResNet18, EfficientNet-B0, DeiT-Tiny (head-only fine-tuning), and ViT-Base with LoRA adaptation. Experimental results show that CNN-based models significantly outperform transformer-based architectures on limited-data PRPD scenarios. ResNet18 achieved the highest mean performance (Accuracy: 89.6%, F1-score: 85.6%), whereas transformer models exhibited unstable convergence and poor generalization. The findings indicate that CNN inductive biases remain advantageous for small-scale industrial diagnostic datasets.
|
||
 |
Dr. Mohammad Hafiz Mohd Yusof, Universiti Teknologi MARA, Malaysia |
|
| Dr. Mohammad Hafiz Mohd Yusof is a Senior Lecturer and Researcher at the Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA (UiTM), Perak Branch, Tapah Campus, Malaysia. He holds a PhD from Universiti Kebangsaan Malaysia (UKM), an MSc from UiTM, and a B.Tech (Hons) from Universiti Teknologi PETRONAS (UTP). He is also a recipient of a professional certificate from the Massachusetts Institute of Technology (MIT). He is also a registered member of the Malaysia Board of Technologists (MBOT) and holds the professional title of Professional Technologist (Ts.). His primary research interests lie within the Machine Learning & Interactive Visualization (MaLIV) Research Interest Group (RIG). Dr. Hafiz has extensive experience in academic instruction and has contributed significantly to Cybersecurity research (Intrusion Prediction and Detection Model) in machine learning and data visualization. Beyond academia, Dr. Hafiz possesses over 12 years of extensive industrial experience working with multinational corporations, including IBM and ENI. His research focuses on bridging advanced computational techniques with practical industrial applications, contributing significantly to both academic discourse and technological innovation in his field.
Speech Title: Visualizing Realistic Benchmarked IDS Dataset: CIRA-CIC-DoHBrw-2020 Abstract： Intrusion Detection System (IDS) dataset is crucial to detect lateral movement of cyber-attacks. IDS dataset will help to train the IDS classifier model to achieve earliest detection. A good near-realism public dataset is essential to assist the development of advanced IDS classifier models. However, the available public IDS dataset has long been under scrutiny for its practicality to reflect real low-footprint cyber threats, render real-time network scenario, reflect recent malware attack over newly developed DoH protocol, disregard layer 3 information and finally publish contradictory results of classification and analysis between various studies which makes it non-reproducible and without shareable results. This problem can be resolved by sophisticatedly visualizing a new realistic, real-time, low footprint and up-to-date benchmarked dataset. Visualization helps to detect data deformation before designing the optimized and highly accurate classifier model. Therefore, this study aims to review a new realistic benchmarked IDS dataset and apply sophisticated technique to visualize them. The review starts by carefully examining production network features. These are then compared with various well-established public IDS datasets. Many of them are static, unrealistic meta-features and disregard source and destination Internet Protocol (IP) information except CIRA-CIC-DoHBrw-2020 dataset. The study then applies Eigen Centrality (EC) technique from the graph theory to visualize this layer 3 (L3) information. Finally, using various visualization techniques such as Principal Component Analysis (PCA) and Gaussian Mixture Model (GMM), the study further analyzes and subsequently visualizes the data. Results show that the CIRA-CIC-DoHBrw-2020 simulated recent malware attack and has a very imbalanced dataset which reflects the realistic low-footprint cyber-attacks. The centrality graph clearly visualizes IPs that are compromised by recent DoH attack in real-time, and the study concludes decisively that smaller packet length of size 1000 to 2000 bytes is to fit an attack trait.
|
||
 |
Senior Lecturer Dr. Siti Nabila Aidit, Universiti Malaya, Malaysia |
|
Dr. Siti Nabila binti Aidit is a Senior Lecturer at Universiti Malaya, Malaysia where her research sits at the forefront of emerging wearable electronics and printed flexible technologies. Her expertise focuses on the synthesis and application of 2D materials and functionalized MXenes for the development of high-performance sensing systems. A prolific researcher with an H-index of 20, Dr. Nabila has authored over 50 ISI-ranked journal articles and currently leads several high-impact research projects in the field of advanced materials. Her contributions to flexible electronics and sensing technology have been recognized with numerous prestigious innovation awards. Beyond her research, Dr. Nabila is committed to academic leadership through the supervision of doctoral researchers and her service as an examiner for leading universities, playing a key role in maintaining the academic rigor and global advancement of flexible sensing technologies.
Speech Title: Next-Generation Wearable Electronics: Advancing Healthcare through Flexible and Printable Technologies Abstract： The transition toward personalized, continuous healthcare requires a new generation of electronic systems that are not only high-performing but also mechanically flexible and cost-effective to produce. This presentation explores recent advancements in the field of printable electronics, focusing on the synergy between innovative nanomaterials and scalable additive manufacturing techniques. The research examines the development of various sensing platforms including biochemical, thermal, and physiological monitors. Central to this work is the application of low-cost printing methods, such as dispense and screen printing, to create high-resolution electrode arrays on flexible substrates. By functionalizing these platforms with advanced nanohybrids and biopolymer-based electrolytes, the study demonstrates significant improvements in sensitivity, response time, and mechanical durability. The discussion highlights how these technological pillars, material innovation and rapid fabrication enable the creation of robust, degradable, and stretchable wearable devices. These advancements provide a foundation for non-invasive, real-time diagnostic tools that bridge the gap between traditional clinical settings and proactive mobile healthcare.
|
||