Speakers

Prof. Witold Pedrycz，IEEE Life Fellow

Department of Electrical & Computer Engineering University of Alberta, Edmonton, Canada

Biography: 

Dr. Witold Pedrycz (IEEE Life Fellow) is Professor and Canada Research Chair (CRC) in Computational Intelligence in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland. Dr. Pedrycz is a foreign member of the Polish Academy of Sciences and a Fellow of the Royal Society of Canada. He is a recipient of several awards including Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society, IEEE Canada Computer Engineering Medal, a Cajastur Prize for Soft Computing from the European Centre for Soft Computing, a Killam Prize, a Fuzzy Pioneer Award from the IEEE Computational Intelligence Society, and 2019 Meritorious Service Award from the IEEE Systems Man and Cybernetics Society.,His main research directions involve Computational Intelligence, fuzzy modeling and Granular Computing, knowledge discovery, pattern recognition, data science, knowledge-based neural networks among others. Dr. Pedrycz is involved in editorial activities. He is an Editor-in-Chief of Information Sciences, Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley), and Co-editor-in-Chief of Int. J. of Granular Computing (Springer) and J. of Data Information and Management (Springer).

Title: Data Privacy, Energy Awareness and Credibility: Challenges in Machine Learning

Abract:                

Over the recent years, we have been witnessing spectacular achievements of Machine Learning with highly visible accomplishments encountered, in particular, in natural language processing and computer vision impacting numerous areas of human endeavours. Driven inherently by the technologically advanced learning and architectural developments, Machine Learning constructs are highly impactful coming with far reaching consequences; just to mention autonomous vehicles, control, health care imaging, decision-making in critical areas, among others.

We advocate that the design and analysis of ML constructs have to be carried out in a holistic manner by identifying and addressing a series of central and unavoidable quests coming from industrial environments and implied by a plethora of requirements of  interpretability, energy awareness (being also lucidly identified on the agenda of green AI), efficient quantification of quality of ML constructs, their brittleness and conceptual stability coming hand in hand with the varying levels of abstraction.  They are highly intertwined and exhibit relationships with the technological end of ML. As such, they deserve prudent attention, in particular when a multicriterial facet of the problem is considered.

The talk elaborates on the above challenges, offers definitions and identifies the linkages among them. In the pursuit of coping with such quests, we advocate that Granular Computing can play a pivotal role offering a conceptual environment and realizing algorithmic development. As a detailed study, we discuss the ideas of knowledge transfer showing how a thoughtful and prudently arranged knowledge reuse to support energy-aware ML computing. We discuss passive and active modes of knowledge transfer. In both modes, the essential role of information granularity is identified. In the passive approach, information granularity serves as a vehicle to quantify the credibility of the transferred knowledge. In the active approach, a new model is constructed in the target domain whereas the design is guided by the loss function, which involves granular regularization produced by the granular model transferred from the source domain. A generalized scenario of multi-source domains is discussed. Knowledge distillation leading to model compression is also studied in the context of transfer learning.

Prof. Tao Zhang

North China University of Technology, NCUT, China

Biography: 

Zhang Tao, professor, doctoral tutor, "Distinguished Expert" of overseas high-level talents introduced by the Central Organization Department, Chief Scientist of Aerospace Changfeng of Aerospace Science and Industry Group, Vice President of Beijing European and American Alumni Association, President of Electronic Branch of Beijing Expert Association, Distinguished Expert of Beijing Overseas High-level Talents "Haiju Project", "High-end Leading Talent" of National Zhongguancun Science and Technology Demonstration and Entrepreneurship Base, Beijing International "High-end Business Talent" Award, and Chief Technical Expert of National Golden Shield Project. Expert leader of key R&D projects of informatization construction of National Development and Reform Commission, expert of national informatization projects, member of National Science and Technology Award Expert Committee, special expert of key R&D of Ministry of Science and Technology, and expert of National Natural Science Foundation of China. He used to be the chief architect of the German Volkswagen Computer Expert System, the senior consultant of the banking business of IBM Corporation of America, and the vice president of the technology and operation department of Bank of America. Engaged in the research and application of big data core algorithms, data integration and data governance, the design and construction of powerful intelligent engine middle and back-office architecture, providing 360-dimensional support for applications in various fields of foreground application scenarios, and leading the design, development and implementation of 28 intelligent application systems: 1. Smart financial risk prevention and control, 2. Smart city, 3. Safe city, 4. Intelligent transportation, 5. Smart medical care, 6. Wisdom.

Prof. Yang Han, IEEE Senior Member

School of Mechanical and Electrical Engineering, UESTC, China

Biography:

Yang Han (S’08-M’10-SM’17) received the Ph.D. degree in Electrical Engineering from Shanghai Jiaotong University (SJTU), Shanghai, China, in 2010. In 2010, he joined the University of Electronic Science and Technology of China (UESTC), Chengdu, China, where he has been an Associate Professor in 2013, and Full professor in 2021. From March 2014 to March 2015, he was a Visiting Scholar with the Department of Energy Technology, Aalborg University, Aalborg, Denmark. He is currently with the School of Mechanical and Electrical Engineering, UESTC. His research interests include the ac/dc microgrids, active distribution networks, power quality, grid-connected converters for renewable energy systems, active power filters, multilevel converters, and static synchronous compensators (STATCOMs).        

Dr. Han has received several national and provincial projects, and more than 30 industrial projects in the area of power electronics, smart grid, microgrid, and power quality analysis and compensation. He holds more than 40 issued and pending patents. Dr. Han was listed as “World’s Top 2% Scientist 2022” by Stanford University in 2022, and the recipient of the Young Scientist Award in CPESE 2021, the Provincial Science and Technology Award in 2020 and 2022, Science and Technology Award from Sichuan Electric Power Company in 2019, Academic Talent Award by UESTC, in 2017, Baekhyun Award by the Korean Institute of Power Electronics, in 2016. He has published a book “Modeling and Control of Power Electronic Converters for Microgrid Applications”, ISBN: 978-3-030-74512-7, Springer. He served as an Associate Editor of Journal of Power Electronics and IEEE ACCESS (2019-2020).

Personal Website: Click here

Title: Recent Progress on Modeling and Control of Power Electronic Converters for Microgrid Applications

Abract:  

This presentation introduces the fundamental ideas of power electronic converter modeling and control, digital simulation, and experimental studies in the renewable energy systems and AC/DC microgrid. Recent advanced control methods for voltage source inverters (VSIs) and the hierarchical controlled islanded microgrid would be presented, including the mathematical modeling, controller synthesis, parameter selection and multi-time scale stability analysis, as well as the consensus-based control strategies for the microgrid and microgrid clusters. This topic would be an invaluable technical reference for practicing engineers and researchers working in the areas of renewable energy, power electronics, energy internet, and smart grid. This topic has been published in the recent book “Modeling and Control of Power Electronic Converters for Microgrid Applications” by Springer: https://www.springer.com/gp/book/9783030745127.