Keynote Speaker
Nikola Kassabov, The University of Auckland, New Zealand
Life FIEEE, FRSNZ, FINNS College of Fellows, DVF RAE UK
Professor Nikola K Kasabov is a Life Fellow of IEEE, Fellow of the Royal Society of New Zealand, Fellow of the INNS College of Fellows, DVF of the Royal Academy of Engineering UK. He has Doctor Honoris Causa from Obuda University, Budapest. He is the Founding Director of KEDRI and Professor Emeritus at the School of Engineering, Computing and Mathematical Sciences at Auckland University of Technology, New Zealand. He is also a Visiting Professor at IICT Bulgarian Academy of Sciences and Dalian University, China and Honorary professor at the University of Auckland. Kasabov is Past President of the Asia Pacific Neural Network Society (APNNS) and the International Neural Network Society (INNS). He has been a chair and a member of several technical committees of IEEE Computational Intelligence Society and Distinguished Lecturer of IEEE (2012-2014). He is Editor of Springer Handbook of Bio-Neuroinformatics, EiC of Springer Series of Bio-and Neuro-systems and co-EiC of the Springer journal Evolving Systems. He is Associate Editor of several other journals. Kasabov holds MSc in computer engineering and PhD in mathematics from TU Sofia, Bulgaria. His main research interests are in the areas of neural networks, intelligent information systems, soft computing, bioinformatics, neuroinformatics. He has published more than 700 publications, highly cited internationally. He has extensive academic experience at various academic and research organisations in Europe and Asia, including: TU Sofia Bulgaria; University of Essex UK; University of Otago, NZ; Shanghai Jiao Tong University and CASIA Beijing; ETH/University of Zurich. Kasabov has received a number of awards, among them: INNS Ada Lovelace Meritorious Service Award; NN journal Best Paper Award for 2016; APNNA ‘Outstanding Achievements Award’; INNS Gabor Award for ‘Outstanding contributions to engineering applications of neural networks’; EU Marie Curie Fellowship; Bayer Science Innovation Award; APNNA Excellent Service Award; RSNZ Science and Technology Medal; 2015 AUT NZ Medal; Medal “Bacho Kiro” and Honorary Citizen of Pavlikeni, Bulgaria; Fellow and Honorary Member of the New Zealand-, the Bulgarian-, the Greek- and the Scottish Societies for Computer Science and Information Technologies. More information of Prof. Kasabov can be found in: https://academics.aut.ac.nz/nkasabov.
(Online Talk) Speech Title: Brain-inspired technologies for AI Applications
Abstract: The talk presents a brain-inspired AI approach for predictive and explainable modelling of multimodal data with a wider scope of applications, including: brain-machine interfaces; predicting individual health and welfare outcomes, such as dementia, stroke, mental health; predicting environmental disasters, such as floods and earthquakes. The models are based on brain inspired spiking neural neuronal network architectures (BI-SNN) that include other machine learning methods [1,2,3,4]. The inspiration comes from the brain, which can deal with multimodal sensory, emotional and other information at different and connected time scales. The talk discusses how multiple modalities of data can be integrated for a better outcome prediction and a better explainability of the models, showing the “hidden” dynamic interaction between the used modalities of data related to an individual. This approach could potentially lead to the creation of principally new “conscious” and safe decision support AI systems [5], where systems take into account holistically many aspects of an individual features across different time scales and also their consequences and relation to the environment and other individuals.
Kamal Zuhairi Zamli, Universiti Malaysia Pahang, Malaysia
Kamal Z. Zamli received the degree in electrical engineering from the Worcester Polytechnic Institute, USA, in 1992, the M.Sc. degree in real-time software engineering from Universiti Teknologi Malaysia, in 2000, and the Ph.D. degree in software engineering from the University of Newcastle upon Tyne, U.K., in 2003. He has written nearly 350 articles in journals and conferences worldwide mainly in the area of (combinatorial t-way) software testing and search-based software engineering. He is the runner up for the Q-Merit Award conferred by the Malaysian Software Testing Board, in 2011, based on his contribution to the field of software testing in Malaysia.
(Onsite Talk) Speech Title: Optimizing Multi Task Test Redundancy Reduction based on Multi Factorial Approach
Abstract: Test redundancy occurs when one requirement is requirements (i.e., large-test-to-requirement configurations covered by more than one test. Potentially affecting the testing costs while at the same time delaying the software release, test redundancy is often undesirable. Considered as an optimization explosion problem, a plethora of existing work exists typically utilizing meta-heuristic algorithms as the backbone algorithm. Although useful, much existing meta-heuristic based algorithms have focused on solving the test redundancy reduction problem as a single task problem (i.e., one-test redundancy task-at-at-time). To cater for simultaneous test redundancy reduction from multiple software development projects, our work explores the design and implementation of a multi-factorial Sine Cosine Algorithm (MF-SCA). The novelty of our work is that we integrate the multi-factorial paradigm and transfer learning algorithm to the Sine Cosine Algorithm (SCA) to achieve implicit multi-task capabilities.
Nor Ashidi Mat Isa, Universiti Sains Malaysia, Malaysia
Prof. Ir. Dr. Nor Ashidi received the B. Eng. Degree in Electrical and Electronic Engineering with First Class Honors in 1999 and the PhD degree in Electronic Engineering (majoring in Image Processing and Artificial Neural Network) in 2003 from Universiti Sains Malaysia (USM). He is currently a Professor at the School of Electrical and Electronic Engineering, USM. His research interests include intelligent systems, image processing, machine learning, deep learning and medical image processing. As of September 2024, he has published more than 195, 238 and 317 articles indexed in WoS-ISI (H-index 35), SCOPUS (H-index 42) and Google Scholar (H-Index 51) respectively. Due to his outstanding achievement in research, he gained recognition, both national and internationally. He was recognized as top 2% researcher in category – Citation Impact in Single Calendar Years 2020, 2021, 2022, 2023 and 2024 by Stanford University USA - Elsevier and Top Research Scientist Malaysia (TRSM) by Akademi Sains Malaysia (ASM) in 2020.
(Onsite Talk) Speech Title: Transforming Industry with Deep Learning: Potential of Convolutional Neural Networks for Printed Circuit Board Defect Detection
Abstract: Printed circuit boards (PCBs) are becoming more intricate, smaller, and fragile due to the continuous advancements in integrated circuit technology. As a result, accurately detecting PCB defects and components is both essential and increasingly difficult for the industry. Traditional PCB inspection techniques struggle to achieve both speed and precision simultaneously, which creates a pressing need for more advanced solutions. While automated systems have made progress, they still face challenges in handling the complexity and variability of modern PCBs. Convolutional Neural Networks (CNNs), particularly models like You Only Look Once (YOLO), are renowned for their effectiveness in real-time object detection and have shown significant promise in PCB inspections.
This presentation will explore the application of CNNs in identifying a variety of PCB issues, such as dense component placement, soldering defects, small cosmetic flaws, solder mask peel-offs (SMPO), and label printing errors. The ability of CNNs to process large amounts of visual data with high accuracy makes them an ideal tool for automating the detection of such defects. Furthermore, CNNs have the potential to reduce human error and increase the efficiency of inspections, which is critical in the fast-paced manufacturing environment.
Drawing on research conducted by the Imaging and Intelligent System Research Team (ISRT) at USM, several newly developed CNN variants have demonstrated not only outstanding performance in detecting PCB components but also remarkable ability to generalize across various PCB defect types. These advanced models have shown that, beyond simply identifying defects, they can also improve overall quality control by detecting subtle issues that might go unnoticed by traditional methods. The integration of CNNs into PCB inspection workflows could pave the way for more reliable and cost-effective production processes. This could lead to fewer faulty products reaching the market and reduced downtime in manufacturing, ultimately benefiting the entire electronics industry.
Additionally, ongoing improvements in machine learning algorithms are likely to enhance the adaptability and accuracy of these systems, ensuring that CNNs remain at the forefront of PCB inspection technology.
