Prof. Shengli Xie

Foreign member of the Russian Academy of Engineering, IEEE Fellow, Winner of the National Outstanding Youth Science Foundation, GuangdongUniversity

Bio: Shengli Xie (Fellow, IEEE) received the M.S. degree in mathematics from Central China Normal University, Wuhan, China, in 1992, and the Ph.D. degree in control theory and applications from the South China University of Technology, Guangzhou, China, in 1997.,He is currently the Director of the Laboratory for Intelligent Information Processing (LIIP) and a Full Professor with the Guangdong University of Technology, Guangzhou. He has authored or coauthored two monographs and more than 100 scientific articles published in journals and conference proceedings. His current research interests include automatic control and signal processing, especially blind signal processing and image processing.

Title:A Novel Method for High-Precision Deformation Measurement Using Optical Coherence Tomography Integrated with Artificial Intelligence

Abstract: Composite materials are widely used in the production of load-bearing components for high-end aviation equipment due to their excellent properties such as high strength, high-temperature resistance, and low density. To ensure more complex loads, larger carrying capacity, longer service life, and higher safety, scientific research on the mechanical properties and failure mechanisms of materials is needed. To address these issues, tomographic deformation measurement technology is used to depict the strength and damage evolution of composite materials, spanning from surface characteristics to the material's interior. Phase-contrast optical coherence tomography stands as a state-of-the-art international technique for chromatographic deformation measurement, boasting nanometer-scale sensitivity in its measurements. However, it faces challenges marked by limited resolution, low measurement accuracy, and a diminished signal-to-noise ratio. Overcoming these three key bottlenecks is imperative for further advancements in this area. Currently, the international mainstream solution is to enhance hardware equipment such as expanding the bandwidth of the light source. However, this solution evolves intricate hardware integration and cannot address the underlying bottlenecks. Therefore, a novel method for phase-contrast optical coherence tomography measurement is urgently needed.

Tomography measurement based on artificial intelligence algorithms integrates extensive experimental and simulation data, enabling accurate learning of the time-frequency domain characteristics of signals obtained through tomography interferometry. This approach eliminates the need for complex physical modeling and holds the potential to overcome the limitations mentioned before. To this end, this report includes discussions on data perception, cognitive analysis, and software-hardware integration. Furthermore, it introduces novel intelligent tomography measurement methods such as high-resolution tomography reconstruction using deep convolutional neural networks, high-precision phase computation employing composite deep neural networks, and high signal-to-noise ratio strain imaging utilizing Bayesian neural network. Moreover, a new generation of tomography measurement instrumentation systems that incorporate AI technology has been developed.

Prof. Yang Tang

IEEE Fellow, High-Level Talents, East China University ofScience and Technology, China

Bio: Dr. Yang Tang is now a Professor at Department of Automation, and the Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China. He was a Research Associate with the Hong Kong Polytechnic University, Hong Kong, from 2008 to 2010. From 2011 to 2015, he conducted his postdoctoral research with the Humboldt University of Berlin, Berlin, Germany, and the Potsdam Institute for Climate Impact Research, Potsdam, Germany. He is now a Professor with the East China University of Science and Technology, Shanghai, China. He has published over 100 refereed papers in international journals such as Nature Communications, Patterns (Cell Press), Automatica, IEEE Transactions, SIAM Journals and APS journals (including more than 20 papers in IEEE TAC and Automatica). His current research interests include multi-agent systems/complex networks, cyber-physical systems, artificial intelligence, autonomous systems, hybrid dynamical systems, and their applications. Dr. Tang was a recipient of the Alexander von Humboldt Fellowship in 2011 and he got the National Young Distinguished Professor and National Distinguished Professor of 2015 and 2020, respectively. He is a Senior Board Member of Scientific Reports, an Associate Editor of IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, IEEE Transactions on Circuits and Systems I: Regular Papers, IEEE Transactions on Cognitive and Developmental Systems, IEEE Transactions on Emerging Topics in Computational Intelligence, IEEE Systems Journal and Engineering Applications of Artificial Intelligence (IFAC Journal) and Science China Information Sciences, etc. He is also a Leading Guest Editor for several special issues in IEEE Transactions on Circuits and Systems I: Regular Papers, IEEE Transactions on Emerging Topics in Computational Intelligence, IEEE Transactions on Cognitive and Developmental Systems, CHAOS, the Journal of the Franklin Institute. He is a Guest Editor for topics like industrial metaverse, large language models in IEEE Transactions on Neural Networks and Learning systems, IEEE Transactions on Cybernetics and Science China Information Sciences. He is a Vice Chair of Technical Committee on Big Data, Vice Chair of Technical Committee on Networked Intelligence, Chinese Association of Automation (CAA), a technical committee of Complex Systems and Complex Networks (CSIAM, China) and a member of Young Working Committee in Chinese Association of Automation. He is an IEEE Fellow.

Tilte: Distributed Optimization, Decision Making, and Game Theory in Clustered Systems

Abstract: Currently, intelligent unmanned clusters are developing rapidly and showing great potential in areas such as energy economic dispatch, machine learning, and collaborative operation of complex systems. Consequently, this report introduces distributed optimization, decision-making, and game theory in cluster systems. This report discusses how to reduce the communication volume of distributed optimization through various event-triggered mechanisms while considering privacy protection and asynchronous computation. Additionally, in light of the inherent uncertainty within the system and the challenge of interpreting decision models, this report delves into the exploration of optimizing strategies driven by data. Notably, cluster games encompass both analytic games and games based on reinforcement learning. In the analytic game, the game model among cluster members is constructed through mathematical analysis to complete decision making. On the other hand, reinforcement learning-based games leverage reinforcement learning techniques to make decisions through a series of trials. At the end of the report, the future outlook is made.

Prof. Dongrui Wu

IEEE Fellow, Huazhong University of Science and Technology,China

Bio: Dongrui Wu (IEEE Fellow) received a B.E in Automatic Control from the University of Science and Technology of China, Hefei, China, in 2003, an M.Eng in Electrical and Computer Engineering from the National University of Singapore in 2006, and a PhD in Electrical Engineering from the University of Southern California, Los Angeles, CA, in 2009. He is now Professor and Deputy Director of the Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China.

Prof. Wu's research interests include brain-computer interface, machine learning, computational intelligence, and affective computing. He has more than 200 publications (11000+ Google Scholar citations; h=55). He received the IEEE Computational Intelligence Society (CIS) Outstanding PhD Dissertation Award in 2012, the IEEE Transactions on Fuzzy Systems Outstanding Paper Award in 2014, the IEEE Systems, Man and Cybernetics (SMC) Society Early Career Award in 2017, the USERN Prize in Formal Sciences in 2020, the IEEE Transactions on Neural Systems and Rehabilitation Engineering Best Paper Award in 2021, the Chinese Association of Automation Early Career Award in 2021, and the Ministry of Education Young Scientist Award in 2022. His team won the First Prize of the China Brain-Computer Interface Competition in four successive years (2019-2022). Prof. Wu is the Editor-in-Chief of IEEE Transactions on Fuzzy Systems.

Prof. Wu is a Board of Governors (BoG) member and Associate Vice President for Human-Machine Systems of the IEEE SMC Society. He will be Editor-in-Chief of IEEE Transactions on Fuzzy Systems in 2023.

Tilte: Machine Learning in Brain-Computer Interfaces

Abstract: A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. Electroencephalograms (EEGs) used in BCIs are weak, easily contaminated by interference and noise, non-stationary for the same subject, and varying across different subjects and sessions. Thus, sophisticated machine learning approaches are needed for accurate and reliable EEG-based BCIs. This talk will introduce the basic concepts of BCIs, review the latest progress, and describe several newly proposed machine learning approaches for BCIs.

Prof. Xi Xie

Winner of theNational Outstanding Youth Science Foundation, SunYat-sen University, China

Bio: Prof. Xi Xie is currently a full professor in the School of Electronics and Information Technology at Sun Yat-sen University, and was awarded by the National Science Fund for Distinguished Young Scholars (国家杰青). He is also an adjunct professor in the First Affiliated Hospital of Sun Yat-sen University. He graduated from Stanford University in USA with PhD degree on 2014, and then worked as a postdoc researcher in the Prof. Robert Langer’s lab at Massachusetts Institute of Technology. On 2016, he started his own research lab at Sun Yat-sen University. Prof. Xi Xie has been focusing on the research on minimally invasive biosensing technologies. In specific, he has been working on microneedles or nanoneedles technologies for detection of biological information in vivo or even inside cells. He has published >100 manuscripts. As corresponding author or first authors, 60 manuscripts have been published on journals including Nature Biomedical Engineering, Nature Nanotechnology, Nature Protocols, Nature Communications, Science Advances and et al. He has applied for >80 patents. He was also awarded by “MIT Technology Reviews Innovators Under 35 China”, the “Outstanding Scientific Award of Chinese Institute of Electronics”, and the “Microsystems & Nanoengineering Summit 2019 Young Scientist Award”. He serves as Associate editor in Microsystems & Nanoengineering (Nature Publishing Group, JCR Q1) and Bio-designs and Manufacturing (JCR Q1). He also served as the editorial board member in two core journals including Life Science Instruments, and served as the academic members in three academic associations in China. 

Tilte: Minimally Invasive Bioelectronics

Abstract: Biomedical sensing is the key to access biological information. In recent years. The development of biosensing has gradually evolved from detection from blood detection level to in situ detection on tissue or cellular level. The technology of detection has also evolved from single point detection, to in situ sensing for long time or even sensing with high resolution. Among the existing in situ biosensing technologies, non-invasive sensing does not reach the detection target in the tissue, making it difficult to accurately reflect the real situation. Invasive sensing through implanted devices, on the other hand, has safety concerns. Therefore, how to balance safety and accuracy has been challenging in the field of biosensing. Microneedle arrays, as a minimally invasive technology, can balance the accuracy of invasive sensing with the safety of non-invasive sensing. Our research of minimally invasive biosensing technology employs microneedle arrays as the core structure to penetrate skin layers or cell membranes minimally invasively to detect information in tissues or cells in vivo. The key technologies we have developed for minimally invasive devices consist of three aspects: first, the delicate preparation of microneedle arrays and the preparation of highly sensitive sensing modules on the surface of microneedles; second, the development of technologies for efficient and safe penetration of microneedle arrays through tissue mucosa and cell membranes. The third is the design and development of miniaturized multifunctional circuit systems to support the functions of minimally invasive devices. The minimally invasive biosensing technologies we have developed have been validated and applied in penetrating cell membranes to record intracellular physiological signals, penetrating organ mucosa layers to measure biochemical signals in tissues, and penetrating skin layers to measure in vivo physiological signals, respectively. These minimally invasive biosensing technologies are expected to provide new tools and solutions for the diagnosis and treatment of major diseases.

Prof. Jiawen Kang

Guangdong University of Technology, China

Bio: Jiawen Kang is a Full Professor at Guangdong University of Technology. His research interests mainly focus on blockchain, metaverse, edge intelligence, etc. He has published more than 150 research papers in leading journals and flagship conferences including 12 ESI highly cited papers and 3 ESI hot papers （Google Scholar: 10600 citations）. He is the co-inventor of 16 granted patents and has won the IEEE VTS Best Paper Award,  IEEE Communications Society CSIM Technical Committee Best Journal Paper Award, IEEE Best Land Transportation Paper Award, IEEE HITC Award for Excellence in Hyper-Intelligence Systems (Early Career Researcher award), IEEE Computer Society Smart Computing Special Technical Community Early-Career Award，and 13 best paper awards of international conferences as well. He is an IEEE Senior Member and is listed in the World’s Top 2% of Scientists identified by Stanford University. He is now serving as the editor or guest editor for 11 leading journals including IEEE JSAC, TVT, TNSE and IEEE Systems Journal. He has also served as 15 Conference Co-chairs including ICDCS, IEEE WCNC, IEEE ICC, IEEE Globecom, etc. He received the IEEE Outstanding Leadership Award for 2022 EUC Conference (Program Chair) and the IEEE Distinguished Services Award for the 16th IEEE iThings Conference (Program Chair). He is a vice-chair of the IEEE Technical Committee on Cognitive Networks Special Interest Group on "Wireless Blockchain Networks.

Tilte: Efficient Vehicle Twins Migration for Vehicular Metaverses

Abstract: Vehicle Twins, as promising digital assistants in Vehicular Metaverses, can enable drivers and passengers to immerse in 3D virtual spaces, serving as a practical emerging example in intelligent vehicular environments. However, the high mobility of vehicles, the dynamic workload of RSUs, and the heterogeneity of RSUs pose novel challenges to making twins migration decisions. To address these challenges, in this talk, we propose a model to predict the future trajectories of intelligent vehicles based on their historical data, indicating the future workloads of RSUs. Based on the expected workloads of RSUs, we formulate the twins task migration problem as a long-term mixed integer programming problem. To tackle this problem efficiently, the problem is transformed into a Partially Observable Markov Decision Process (POMDP) and solved by multiple DRL agents with hybrid continuous and discrete actions in decentralized. Furthermore, we design an efficient incentive mechanism framework for VT migrations by using a novel metric named Age of Migration Task (AoMT). To incentivize the contribution of bandwidth resources among the next RSUs, we propose an AoMT-based contract model to improve metaverse service quality.

Prof. Shiling Zhang

State Grid Chongqing Electric Power CompanyChongqing Electric Power Research Institute, China

Bio: Zhang Shiling, PhD, professor level senior engineer, technical expert. Engaged in the optimization design of ultra-high voltage insulation structures, as well as the operation status detection and life assessment of ultra-high voltage power equipment. Published over 38 SCI/EI search papers as the first author in domestic and foreign publications, 28 Chinese core journals of Peking University, and won 9 provincial and ministerial awards such as the first prize for scientific and technological progress in Chongqing and the special first prize of the China Water Resources and Power Quality Management Association for innovative achievements. Accepted 1 international invention patent, authorized more than 30 national invention patents and utility models, authorized 18 software copyrights, and reported more than 20 international and domestic conferences, As the project leader, I presided over 2 provincial and ministerial level projects at the forefront of the foundation, and 6 science and technology projects at the headquarters of State Grid Corporation of China.

Tilte: Research on the Application of Large Model and Parallel Computing Technology in the Design and Operation of ±800kV Ultra High Voltage Power Equipment

Abstract:  (1) From the perspective of high-voltage power equipment operation, this paper introduces the typical structure of high-voltage power equipment under high-order harmonic loads, actual valve chamber operating environment, and heating theoretical model for the output device and bushing structure of converter transformers. By optimizing the design using artificial intelligence algorithms, the structural dimensions of the high-voltage bushing and outgoing device are obtained.

(2) The proposed operation detection strategy and method for ultra-high voltage converter transformers and their accessories can intelligently determine their operating status based on the type and content of micro decomposed gases in oil chromatography. The developed defect simulation device hardware platform can effectively collect raw classification data and form a defect sample library; The proposed intelligent simulation algorithm is easy to program and can be used for the diagnosis and evaluation of potential defects in transformers in practical engineering.

This speech provides new ideas for the establishment of a three-dimensional digital model of converter transformers and the practical application of artificial intelligence technology in the structural design and operation of converter accessories.

Dr. Vishnu Pendyala

San Jose State University, USA

Bio: Vishnu Pendyala is an assistant professor in the Department of Applied Data Science at the College of Professional and Global Education and was an Association for Computing Machinery (ACM) distinguished speaker.  He is the current chair of the IEEE Computer Society Silicon Valley chapter, and IEEE Computer Society Distinguished Contributor. He teaches and conducts research in artificial intelligence, machine learning and data science. He gave numerous (50+) invited talks in conferences, faculty development programs, and other forums. He has more than two decades of experience in the software industry in Silicon Valley. His book, "Veracity of Big Data," is available in several libraries, including those of MIT, Stanford, CMU, and internationally. He holds an MBA in finance from Osmania University, India and a doctoral degree in computer engineering from Santa Clara University.

Tilte: The Crossroads of Intelligence: Responsible use of AI as it reshapes humanity

Abstract: Artificial intelligence (AI) is at a pivotal juncture, poised to fundamentally reshape our world. Its immense potential, from revolutionizing healthcare in unforeseen ways to automating driving, is obvious. Yet, alongside this dazzling future lies a darker possibility, where biases creep into algorithms, ethical lines blur, and the very essence of humanity is threatened. This talk delves into the critical discourse surrounding the responsible use of AI. The speaker will explore the challenges, from algorithmic bias and impact on environment to privacy concerns arising from the limitations of Machine Learning (ML) that is becoming increasingly synonymous with AI. Through a lens of ethical frameworks and policy considerations, the talk will navigate the delicate balance between harnessing AI's power and safeguarding our humanity. Ultimately, this is not merely a technological challenge, but a profound human one, demanding nuanced discourse, thoughtful collaboration, and an unwavering commitment to ensuring AI serves the values and aspirations that define humanity.

Prof. Li Chen

IEEE Senior Member

Sun Yat-sen University, China

Bio: Li was awarded his PhD in Communication Engineering by Newcastle University of United Kingdom in 2008. Previously, he was awarded a BSc in Applied Physics by Jinan University and MSc in Communication and Signal Processing (with distinction) by Newcastle University in 2003 and 2004, respectively. His PhD thesis title is 'Design of an efficient list decoding system for Reed-Solomon and algebraic-geometric codes'. He was a UK government Overseas Research Scholarship (ORS) recipient for his PhD engagement. After his PhD, he worked as a Research Associate for an EPSRC project collaborated with Cambridge University.

After completing his post-doc engagement in Jan. 2010, he returned to China as a Lecturer with the School of Electronics and Information Technology (then School of Information Science and Technology, SIST), Sun Yat-sen University (SYSU). From 2011 and 2016, he became an Associate Professor and a Professor of the University, respectively. From 2013, he became the Associate Head of Department of Electronic and Communication Engineering (ECE). From 2017 - 2020, he was the Deputy Dean of the School of Electronics and Communication Engineering. During 2011 - 2012, he was a visiting researcher with the Institute of Network Coding, the Chinese University of Hong Kong. From Jul. - Oct. 2015, he was visitor to the Institute of Communications Engineering, Ulm University, Germany. From Oct. 2015 - Jun. 2016, he was a visiting Associate Professor of the Department of Electrical Engineering, University of Notre Dame, U.S. Now, he is the Chair of IEEE Information Theory Society Guangzhou Chapter and IEEE Information Theory Society Board of Governors Conference Committee. He is a member of IEEE Information Theory Society Board of Governors External Nominations Committee and CIE Information Theory Society. He is serving as an Associate Editor of IEEE Transactions on Communications. His research interests include information theory, error-correction codes and data communications. He likes reading and photography.

Tilte: Low-latency Ordered Statistics Decoding of BCH Codes

Abstract: Ordered statistics decoding (OSD) can achieve a near maximum likelihood (ML) decoding performance for BCH codes. However, Gaussian elimination (GE) that delivers the systematic generator matrix of the code has an uncompromised latency. Addressing this challenge, this talk introduces a low-latency OSD (LLOSD). Since BCH codes are binary subcodes of Reed-Solomon (RS) codes, its codeword candidates can be produced using the RS systematic generator matrix, where its entries can be generated in parallel through the Lagrange interpolation. By eliminating the non-binary codeword candidates and identifying the ML codeword, the LLOSD also has a low complexity. Decoding complexity can be further reduced by its segmented variant. This talk also shows the LLOSD can be interpreted as systematic RS encoding of a punctured BCH codeword. Such a concatenated perspective unveils the valid BCH codeword candidates are far fewer than TEPs, validating its low complexity feature. Finally, a hybrid soft decoding (HSD) that integrates the LLOSD and the algebraic Chase decoding is proposed. The latter can effectively provide extra TEPs for the LLOSD, enhancing the decoding performance. This is an effective approach for decoding longer BCH codes.

Dr. Linqing Feng

Zhejiang Lab, China

Bio: Linqing Feng, PhD in Biomedical Engineering, Zhejiang University, Postdoctoral Fellow, Korea Institute of Science and Technology (KIST), Visiting Scholar, Janelia Farm Research Park, Howard Hughes Medical Institute (HHMI), Senior Research Fellow, Institute of Brain Science, KIST (Tenured PI), After returning to China, he served as a research expert of Zhijiang Laboratory Artificial Intelligence Research Institute Mixed Enhanced Intelligence Center. Engaged in the research of biological image informatics and brain microscopic/mesoscopic connectivity atlas, developed a series of algorithms and software platforms for the reconstruction of microscopic connectivity atlas from optical microscopic images. The open source cross-platform software neuTube (neutracing.com) forms a good ecology and is widely used in the field. Published papers in journals such as Nature Protocols.

Tilte: Research on Multi-scale Brain Atlas Reconstruction and Visualization Platform and Optical Brain-Computer Interface System

Abstract: Investigating the intricate structure and connectivity patterns of neurons within the brain, as well as deciphering the relationship between structure and function, are crucial steps toward comprehending the cognitive functions of the brain. The high-resolution brain microscopy images present great challenges for data visualization and efficient information extraction. Consequently, this report introduces a series of bioimage informatics software developed by our team and their applications in constructing multi-scale brain atlases. In recent years, implantable microscopes and calcium imaging techniques have made remarkable progress in deciphering neuronal function. Utilizing the cellular identity information obtained through registration, these techniques enable long-term and stable localization of single-neuron activity and its correlation with behavior or memory. In summary, this report introduces the brain-computer interface software system based on implantable optical imaging that we have developed, along with the validation of the prototype system.