(5) Big Data and pattern recognition: Tong Zhang, South China University of Science and Engineering, China (Chair)

5.1 Speaker: Prof. Xianbing Meng, South China University of Technology, China

Talk Title: Reinforcement learning based evolutionary algorithm with applications to multi-agent systems

Abstract: As a bio-inspired algorithm, the crux of designing evolutionary algorithm is to formulate swarm intelligence. Two classic evolutionary algorithms, chicken swarm optimization and bird swarm algorithm are first used as examples to show how to extract swarm intelligence to design algorithms. Then, Reinforcement Learning based evolutionary algorithm is introduced as a framework of improving evolutionary algorithms. Finally, it will be discussed how to integrate evolutionary algorithm into multi-agent systems.

Biography: Prof. Xianbing Meng is a postdoctoral fellow with School of Computer Science and Engineering, South China University of Technology. He received the Ph. D. degree from Central South University, and severed as a senior research assistant at City University of Hong Kong. His research interests mainly include evolutionary computation, fuzzy logic systems, broad learning and their applications.

5.2 Speaker: Prof. Jiajing Wu, Sun Yat-sen University, China

Talk Title: Data Analysis and Fraud Detection on Blockchain

Abstract: Blockchain technology is a emerging technology that has the potential to revolutionize many traditional industries. Since the creation of Bitcoin, which represents blockchain 1.0, blockchain technology has been attracting extensive attention and a great amount of user transaction data has been accumulated. Furthermore, the birth of Ethereum, which represents blockchain 2.0, further enriches data type in blockchain. While the popularity of blockchain technology bringing about a lot of technical innovation, it also leads to many new problems, such as user privacy disclosure and illegal financial activities. However, the public accessible of blockchain data provides unprecedented opportunity for researchers to understand and resolve these problems through blockchain data analysis. This talk will introduce some of our recent work on data analysis and fraud detection.

Biography: Prof. Jiajing Wu is an associate professor at the School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China. She received the Ph.D. degree in Electronic and Information Engineering from The Hong Kong Polytechnic University, Hong Kong, in 2014. She was a recipient of the Hong Kong PhD Fellowship Scheme during her Ph.D. study in Hong Kong. Her research interests include theory and applications of complex networks, data mining, blockchain, and cyber-physical networks. She is a member of IEEE, a member of IEEE Technical Committee on Nonlinear Circuits and Systems, and an Associate Editor of IEEE Transactions on Circuits and Systems-II: Express Briefs.

5.3 Speaker: Prof. Yuan Zong, Southeast University, China

Talk Title: Micro-Expression Recognition Based on Group Sparse Learning

Abstract: Micro-expressions are subtle, repressed, and involuntary facial expressions and occur when people try to conceal their true emotions. Micro-expression recognition (MER) aims at accurately detecting this hidden emotion from the facial video clips. It has been one of the most attractive research issues among affective computing, pattern recognition, and computer vision. In this talk, we present a simple yet effective group sparse learning model and its several variants, which are motivated by the facial action coding system (FACS) theory, to deal with the MER problem. In addition, we would like to simply discuss the future directions of this challenging but interesting research topic.

Biography: Prof. Yuan Zong received the B.Sc. and M.Sc. degrees from Nanjing Normal University, Nanjing, China, in 2011 and 2014, respectively, and the Ph.D. degree in Biomedical Engineering from Southeast University, Nanjing, China in 2018. He is currently a Lecturer with the School of Biological Science and Medical Engineering, Southeast University. From 2016 to 2017, he worked as the Visiting Scholar with the Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland. His research interests include affective computing, pattern recognition, and computer vision, especially facial expression/micro-expression analysis. He has published over 30 papers in journals and conferences such as TIP/TCYB/TAFFC/IJCAI/ACM MM. Dr. Zong won the Video based Emotion Recognition First Runner-up Position of the EmotiW Challenge at ACM ICMI in 2019 and the Second Runner-up Position in 2016 and 2018, respectively.

5.4 Speaker: Prof. Wenxiao Zhao, Chinese Academy of Sciences, China

Talk Title: Recursive identification for Hammerstein systems with diminishing excitation signals

Abstract: In this talk, we consider the identification of Hammerstein systems where the nonlinearity is described by a combination of basis functions with unknown coefficients. The extended least squares (ELS) algorithm is applied to estimate the unknown parameters in the system. Contrary to the classical excitation signals for identification of Hammerstein systems, i.e., the periodic inputs or stationary random signals, here we choose a sequence of diminishing excitation signals as the system inputs. We prove that the strong consistency of the ELS algorithm still holds true and the convergence rate is obtained as well. A numerical example is given to verify the performance of the identification method.

Biography: Prof. Wenxiao Zhao received the B.Sc. degree from Shandong University, China in 2003 and the Ph.D. degree in operation research and cybernetics from the Institute of Systems Science (ISS), Academy of Mathematics and Systems Science (AMSS), Chinese Academy of Sciences (CAS), China, in 2008. He is currently an Associate Professor with AMSS, CAS. His research interests are mainly in identification and adaptive control, particularly, in sparse parameter estimation for stochastic systems, recursive identification of nonlinear systems, distributed optimization, etc.

5.5. Speaker: Prof. Hua Geng, Tsinghua University, China

Talk Title: Feedback limitations in nonlinear discrete-time control

Abstract: In order to cope with the worsening environmental and energy crisis, it has become an inevitable trend to replace fossil-based traditional (thermal) power generation with renewable energy such as wind power and photovoltaic power. Compared with traditional power generation, renewable energy generation has the characteristics of clustering, distribution and power electronic based, which brings many technical challenges in terms of control and optimization. This talk discusses the challenges towards safe and reliable operation of large-scale renewable energy cluster from the perspective of individual synchronization and cluster cooperation.

Biography: Prof. Hua Geng is currently a tenured associate professor in Automation Department and research professor in Energy Internet Research Institute, both of Tsinghua University. He received his Ph.D. degree in control theory and application from Tsinghua University, Beijing, China in 2008. From 2008 to 2010, he was a Postdoctoral Research Fellow with the Department of Electrical and Computer Engineering, Ryerson University, Toronto, ON, Canada. He joined Tsinghua University in June 2010. His current research interests include renewable energy conversion systems, Flexible AC transmission system (FACTS), micro-grid and digital control on power electronics. He is the Chief scientist of National Key R&D Program, principle investigator (PI) of the Excellent Youth Scholar project and one key project of National Science Foundation of China (NSFC).Dr. Geng has published more than 150 technical papers, authored a China Machine Press book, and holds more than 20 issued Chinese patents. He was granted “Delta Young Scholar Award” by Delta Environmental and Educational Foundation in 2014 and “Young Professional Award” by China Power Supply Society (CPSS) in 2013. Dr. Geng is an IET Fellow, IEEE Senior Member, Honored Chair of the Youth Working Committee of CPSS, Standing Director of CPSS, Deputy Secretary-General of the Electrical Automation Technical Committee of the China Automation Society, etc. He serves as the expert of IEC international standards, editor of IEEE Trans. on Energy Conversion, IEEE Trans. on Sustainable Energy and IEEE Power Engineering Letters, associate editor of IEEE Trans. on Industry Applications, Control Engineering Practice, Journal of control, automation and electrical systems, Chinese Journal of Electrical Engineering and CPSS trans. on Power Electronics and Applications, etc.

5.6. Speaker: Prof. Hai-Tao Zhang, Huazhong University of Science and Technology, China

Talk Title: The role of reverse edges on hierarchical networks

Abstract: Hierarchical networks widely exist in natural biological, industrial, and social networked systems. This brief explores the effects of adding a reverse edge, across a so-called stem, in a hierarchical network on consensus performance. In particular, it quantitatively reveals the effects in terms of the in-degrees of the surpassed stem nodes. The study further enriches the existing results on special chain and grid networks by accommodating more general network topologies. From the application perspective, this talk provides a guidance for an attacking (or conversely anti-attacking) strategy of injecting the most effective malicious reverse edge. It has other potential applications in regulating DAG network convergence performance with reverse edges.

Biography: Prof. Hai-Tao Zhang, Vice Dean of School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Distinguished Professor of Central China Scholar, Young Scholar of Chang Jiang Scholars’ Award Program of Minister of Education, National Young Top Talent, and Winner of National Excellent Youth Fund. Born in 1977, he received his Bachelor and Ph.D. from University of Science and Technology of China in 2000 and 2005, respectively. In 2007, he was engaged in post-doctoral research at Cambridge University in England. He was promoted to Professor in 2010. He has visited University of California, University of Virginia and other academic institutions. His research interests include swarm intelligence, cooperative control of autonomous USVs, etc. He has hosted more than 20 projects such as Joint Key Fund, Excellent Youth Fund and Major Research Plan of National Natural Science Foundation. He has published/been accepted 86 SCI journal papers, including 1 paper in Nature Communication, and 40 papers in Automatica and IEEE Trans./Mag. His collective motions’ phase-transition work was selected as research highlights in Nature Physics in 2016. He has applied or authorized 38 patents of invention (including 2 American patents). He has won the first prize of Natural Science in Hubei Province, and the gold award of Genevan International Invention Exhibition. Prof. Zhang is an IEEE Senior Member who serves/have served as Editorial Board members of several International SCI Journals such as IEEE Trans. Circuits and Systems II, Asian Journal of Control.