Keynote
Keynote Speaker
Assoc. Prof. Mahardhika Pratama
University of South Australia, Adelaide, Australia
Title
Continual and Autonomous Machine Learning
Abstract
Although deep learning (DL) has achieved promising performances in many applications, its design principle lies in the i.i.d assumption where the learning environment is static. It does not adapt to changing learning environments without suffering from the catastrophic forgetting problem where it loses its performance to previous tasks when adapting to new tasks. In this talk, I will cover the continual learning problem including its solutions. It encompasses the problem of continual learning, few-shot learning, few-shot continual learning, cross-domain continual learning and federated continual learning.
Biography
Assoc. Prof. Mahardhika Pratama is currently an associate professor-level enterprise fellow in AI at the academic unit of STEM, University of South Australia, Adelaide, Australia. Prior to this appointment, he was an assistant professor at the school of CSE, Nanyang Technological University, Singapore from 2017 to Jan 2022, a lecturer at the department of CSIT, La Trobe University, Melbourne, Australia from 2015 to 2017 and a postdoctoral research fellow at the University of Technology Sydney, Sydney, Australia from 2014 to 2015. Mahardhika earned a PhD degree from the University of New South Wales, Australia in Nov 2014, a M.Sc degree from Nanyang Technological University, Singapore in Nov 2011 and a B.Eng degree from Institut Teknologi Sepuluh Nopember, Indonesia in Mar 2010. The research focus of Mahardhika is in deep learning where he is an active researcher in continual learning, lifelong learning, incremental learning, stream learning, fuzzy neural networks, and intelligent control systems. The goal of his study is to develop a deep learning algorithm that can learn forever as the case of biological learning. The application domain of his study includes manufacturing and satellite systems. He mainly published his works in IEEE TNNLS, IEEE TFS, IEEE TCYB, AAAI, SIGKDD, ICDM, ECML PKDD, CIKM, etc. and serves as an associate editor of IEEE TNNLS, IEEE TFS, INS, KBS, CAIS, Complexity, EVOS, JDC. His works have been recognized by several research awards such as top 2% scientists by Stanford University, 2019 IEEE TFS prestigious publication award, 2019 Amity researcher award in data streams, 2014 and 2013 UNSW high-impact publication award, and 2011 IES prestigious engineering achievement award.
Keynote Speaker
Prof. Hendrawan
Institut Teknologi Bandung, Indonesia
Title
Leveraging Machine Learning for Performance Engineering in a Sustainable Telecommunications Industry
Abstract
The telecommunications industry has become a backbone for global connectivity, linking individuals and communities across the world. However, amid rapid technological advancements, the industry faces a range of complex challenges, including the growing demand for high-speed connections, the critical need for enhanced security measures against evolving cyber threats, and increasing pressure to adopt sustainable practices that mitigate environmental and social impacts. In this context, machine learning emerges as a powerful driving force with great potential to be used as a tool for performance engineering tasks to address these challenges and support the industry’s transition toward a more sustainable and efficient future. With its advanced capabilities in data analysis, user behaviours prediction, dynamic network optimization, and proactive security enhancement, machine learning plays a significant role in modelling, planning, dimensioning, and evaluating communication networks and systems.
Biography
Hendrawan received a B.S. degree in electrical engineering from Institut Teknologi Bandung in 1985, and an M.Sc. in Telecommunication and Information Systems in 1990, followed by a Ph.D. in Electronics Systems Engineering in 1995, both from the University of Essex, United Kingdom. His research interests include queuing theory, performance engineering in communication networks and systems, and applications of Artificial Intelligence and machine learning in communication networks and systems. Currently, Hendrawan is a faculty member at the School of Electrical Engineering and Informatics ITB (SEEI – ITB) and head of the Telecommunication Engineering Group SEEI – ITB.
Keynote Speaker
Dr. Wibowo Hardjawana
The University of Sydney, Australia.
Title
AI Applications in Wireless Communication Networks
Abstract
The Internet of Things (IoT) connects a vast network of devices, transforming industries and daily life with applications in smart healthcare, cities, industries, and transportation. A critical challenge in IoT is enabling efficient multiple access: supporting massive numbers of devices while ensuring wide-area coverage, minimal resource usage, and reliable per-device throughput. Key enabling standards, such as IEEE 802.11ah and 3GPP 5G NR, provide the infrastructure for IoT wireless networks. In these networks, the multiple access bottleneck remains. Artificial Intelligence (AI) offers powerful tools to meet the challenge. Neural networks (NNs), a subset of AI, can learn complex input-output relationships, often via supervised learning, and can be tailored for site-specific requirements. AI can enhance PHY-layer signal processing and MAC-layer network resource allocation to optimise multiple access and overall network performance. This talk shares our research on AI-driven PHY-layer processing to enable efficient multiple access in 5G/6G cellular networks, and AI-based MAC resource allocation techniques to optimise multiple access in WiFi 802.11ah networks.
Biography
Wibowo Hardjawana received a PhD degree in electrical engineering from The University of Sydney, Australia. He is a Senior Lecturer in Telecommunications at the School of Electrical and Computer Engineering at the University of Sydney. Before that, he was an Australian Research Council Discovery Early Career Research Award Fellow at the same university. Before his academic career, Wibowo was with Singapore Telecom Ltd., managing core and radio access networks. His research outputs consist of publications, and patents are in AI applications for 5G/6G cellular radio access and long-range Wi-Fi networks. He focuses on system architectures, resource scheduling, interference, signal processing, and the development of wireless standard-compliant prototypes. His research is supported by Australian government as well as industry partners.
Keynote Speaker
Prof. Sung-Nien Hsieh
National Taiwan University of Science and Technology, Taipei.
Title
Millimeter Wave Radars for Micro-motion Detections and Its Applications
Abstract
Radar technology has been widely used in our daily lives, with applications ranging from automotive systems to biomedical devices. By sensing distance and other vital environmental data, radar technology offers numerous advantages, such as the ability to penetrate non-metallic materials, withstand harsh conditions like rain or fog, and provide high-precision, contactless measurements for range, motion, and presence detection. Therefore, we can utilize these benefits to find more applications of radars. In this speech, the speaker will give a brief introduction about applications of millimeter wave radars on small movement sensing or vibration detections. First, a contactless finger tapping test using a 60 GHz frequency-modulated continuous-wave (FMCW) radar will be introduced. In this study, one can utilize FMCW radar to achieve microwave interferometry to measure the phase difference between transmitted and received signals, and then to extract the movement of fingers. Based on the measured data, one can also examine if the movement is normal or abnormal with machine learning models. Second, a multi-target vibration detection for industrial applications, utilizing FMCW radar to simultaneously measure the movements of multiple vibrating objects. These data can be used to examine the operational conditions of machinery in factories. Finally, some possible applications and improvements will also be introduced.
Biography
Sung-Nien Hsieh (Member, IEEE) was born in Hualien, Taiwan. He received the B.S. degree in Electrical Engineering in 2000 and the Ph.D. degree in Communication Engineering in 2009, both from National Taiwan University. From 2009 to 2014, he was a Postdoctoral Research Fellow at the Institute of Astronomy and Astrophysics, Academia Sinica, Taipei, Taiwan. He then worked as a Deputy Engineer at Compal Electronics, Inc., Taipei, from 2014 to 2015, and as a Senior Engineer at Airoha Technology Corporation, Hsinchu, from 2015 to 2017. From 2017 to 2020, he was a Technical Manager at Wistron Corporation, Taipei, where he collaborated on the development of millimeter-wave radar systems for home healthcare applications. From May 2018 to May 2019, he was a Visiting Engineer at the Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), Cambridge, MA, USA. During this period, he was involved in a collaborative program between Wistron and Prof. Dina Katabi’s laboratory at MIT, focusing on millimeter-wave radar for healthcare applications. Since February 2020, Prof. Hsieh has been with the Department of Electronic and Computer Engineering at National Taiwan University of Science and Technology, Taipei. His research interests include microwave circuit design and measurement, radar sensors for industrial and medical applications, and antenna array technologies.