Nanyang Technological University, Singapore
A Potential Paradigm Shift for Visual Signal Processing on the Rise of Machine Intelligence
With the development of AI technology, increasingly more visual signals are intended for machines (rather than humans) as the ultimate users. What challenges and opportunities may this shift bring for visual signal representation, e.g., to address the requirements of Video Coding for Machines (VCM), JPEG AI and other issues beyond compression? In this talk, we will first discuss how to determine visual signal sensitivity toward machine intelligence (MI). MI-oriented models can be also developed for identity/privacy protection. Secondly, a possible change of visual representation is explored: intermediate, deep-learnt visual features (instead of a whole image) can be the basic unit of representation for MI. This brings intelligence to the edge, facilitates edge-cloud collaboration and green computing, and leads to integration of signal representation and computer vision which have been separate processes for long. Finally, possible new research thinking, and potential technical directions and topics will be discussed.
Weisi Lin researches in intelligent image and video processing, computational perceptual signal assessment, and multi-modality/media modelling. He is currently a Professor in School of Computer Science and Engineering, Nanyang Technological University, Singapore, where he also serves as the Associate Chair (Research). He is a Fellow of IEEE and IET, and has been a Highly Cited Researcher 2019, 2020 , 2021 and 2022. He has elected as a Distinguished Lecturer in both IEEE Circuits and Systems Society (2016-17) and Asia-Pacific Signal and Information Processing Association (2012-13) and given keynote/invited/tutorial/panel talks in 40+ international conferences. He has been an Associate Editor for IEEE Trans. Neural Networks and Learning Syst., IEEE Trans. Image Process., IEEE Trans. Circuits Syst. Video Technol., IEEE Trans. Multimedia, IEEE Signal Process. Lett., Quality and User Experience, and J. Visual Commun. Image Represent., and a Senior Editor in APSIPA Trans. Info. and Signal Process, as well as a Guest Editor for 7 special issues in different journals. He also chaired the IEEE MMTC QoE Interest Group (2012-2014); he has been a Technical Program Chair for IEEE ICME 2013, QoMEX 2014, PV 2015, PCM 2012 and IEEE VCIP 2017. He leads the Temasek Foundation Programme for AI Research, Education & Innovation in Asia, 2020-2025. He believes that good theory is practical and has delivered 10+ major systems for industrial deployment with the technology developed.
Dr. Jiashen Teh
School of Electrical & Electronic Engineering,
Universiti Sains Malaysia (USM)
Flexible Thermal Line Rating for Reliable Power Systems
Flexible thermal line rating (FTLR) has been proposed as a technique to improve power system reliability by increasing transmission line capacity based on real-time weather and ambient conditions. This paper presents the benefits of FTLR for power system reliability, including enhanced transmission capacity, reduced congestion, improved system utilization, and increased economic benefits. FTLR utilizes online monitoring and dynamic thermal rating models to calculate real-time transmission line capacity based on current weather conditions, such as wind speed, temperature, and solar radiation. By dynamically adjusting transmission line capacity, FTLR can improve power system reliability by reducing the risk of transmission line overload and associated power outages. FTLR also has economic benefits, including the potential to defer transmission line upgrades and reduce transmission losses. Moreover, FTLR can support the integration of renewable energy sources by enabling the efficient transmission of variable power outputs. Overall, FTLR provides an innovative solution to enhance power system reliability, promote renewable energy integration, and improve economic efficiency. Its benefits can be leveraged by utilities and grid operators to improve power system reliability and resilience in the face of increasing climate variability and renewable energy penetration.
Dr. Teh demonstrates the advantages of flexible transmission line rating on high voltage (138-400kV) power grids to enhance the integration of solar and wind energies. The research is state-of-the-art because the new relationships of the flexible line rating technology with existing conditions and legacy technologies are investigated. The research enables the optimal enhancements of line ratings while preserving the life-cycle of transmission lines, and thereby improving the reliability of transmission grids. With this new discovery, electric utilities worldwide can safely increase the power capacity of their existing grids, which can enhance the integration of renewable energy and improves the delivery of clean energy to consumers at a minimal cost. Consequently, the dependency on traditional, carbon-emitting fuels is reduced. This assists electric utilities to reduce carbon emissions and, enable them to commit to higher level of ESG standard. Dr. Teh is also a Technical Director of UPE-Power in Taiwan, which he has implemented his research findings on line sensor products developed for applications in Taiwan and Japan. He has published more than 50 journal articles indexed in the globally recognized SCIE database, which he is the first/corresponding author in 34 (>70%) of them, and 30 (>65%) of the articles are ranked in the database’s first quarter. His publications have attracted 2085 citations and 28 h-index on Google Scholar. He has secured around RM800k of research funding, where more than 40% of the amount was obtained abroad (Taiwan, Saudi). He has accumulated RM30k of local consultancy projects. He has 1 pending patent filed in Malaysia. He is the main supervisor of 4 graduated PhD students, and another on-going 9 PhD students. For three consecutive years in 2019, 2020 and 2021 he was the top 2% world-most-cited-researchers according to field by Stanford University. He was the 2021 Outstanding Engineer by the IEEE Power & Energy Malaysia and the 2022 Outstanding Young Professional by the IET Malaysia.
Dr. Fei Xue
Department of Electrical & Electronic Engineering,
Xi’an Jiaotong–Liverpool University, Suzhou, China
Active Distribution Networks based on Virtual Microgrid Technology
The Virtual Microgrid (VM) method is a solution for addressing challenges in Conventional Distribution Network (CDN) by actively partitioning the CDN into interconnected Microgrid-style VMs. A novel framework for Active Distribution Networks (ADN) with active planning, active management and active defense will be discussed. Different models and methodologies in developing VMs will be analyzed and compared. Critical technologies for VMs, i.e. network partitioning, resources allocations and optimal operation will be introduced.
Dr. Fei Xue was born in Tonghua, Jilin, China, in 1977. He received the bachelor’s and master’s degrees in power system and its automation from Wuhan University, Wuhan, China, in 1999 and 2002, respectively, and the Ph.D. degree in electrical engineering from the Politecnico di Torino, Turin, Italy, 2009. He was the Deputy Chief Engineer of Beijing XJ Electric Company, Ltd., Beijing, China, and a Lead Research Scientist with Siemens Eco-City Innovation Technologies (Tianjin) Company, Ltd., Tianjin, China. He is currently a Senior Associate Professor and the Head of the Department of Electrical and Electronic Engineering, Xi’an Jiaotong–Liverpool University, Suzhou, China. His research interests include power system security, virtual microgrids, electric vehicle, and transactive energy control.