Biography: MengChu Zhou received his B.S. degree in Control Engineering from Nanjing University of Science and Technology, Nanjing, China in 1983, M.S. degree in Automatic Control from Beijing Institute of Technology, Beijing, China in 1986, and Ph. D. degree in Computer and Systems Engineering from Rensselaer Polytechnic Institute, Troy, NY in 1990. He joined New Jersey Institute of Technology (NJIT), Newark, NJ in 1990, and is a Distinguished Professor of Electrical and Computer Engineering and the Director of Discrete-Event Systems Laboratory. His research interests are in intelligent automation, Petri nets, Internet of Things, Web service, workflow, big data, transportation and energy systems. He has over 800 publications including 12 books, 500 journal papers (over 400 in IEEE transactions), and 29 book-chapters. He holds 14 patents and several pending ones.
He is the founding Editor of IEEE Press Book Series on Systems Science and Engineering and Editor-in-Chief of IEEE/CAA Journal of Automatica Sinica. He served as Associate Editor of IEEE Transactions on Robotics and Automation, IEEE Transactions on Automation Science and Engineering, and IEEE Transactions on Industrial Informatics, and Editor of IEEE Transactions on Automation Science and Engineering. He served as a Guest-Editor for many journals including IEEE Internet of Things Journal, IEEE Transactions on Industrial Electronics, and IEEE Transactions on Semiconductor Manufacturing. He is presently Associate Editor of IEEE Transactions on Intelligent Transportation Systems, IEEE Internet of Things Journal, IEEE Transactions on Systems, Man, and Cybernetics: Systems, and Frontiers of Information Technology & Electronic Engineering. He was General Chair of IEEE Conf. on Automation Science and Engineering, Washington D.C., August 23-26, 2008, General Co-Chair of 2003 IEEE International Conference on System, Man and Cybernetics (SMC), Washington DC, October 5-8, 2003 and 2019 IEEE International Conference on SMC, Bari, Italy, Oct. 6-9, 2019, Founding General Co-Chair of 2004 IEEE Int. Conf. on Networking, Sensing and Control, Taipei, March 21-23, 2004, and General Chair of 2006 IEEE Int. Conf. on Networking, Sensing and Control, Ft. Lauderdale, Florida, U.S.A. April 23-25, 2006. He was Program Chair of 2010 IEEE International Conference on Mechatronics and Automation, August 4-7, 2010, Xi’an, China, 1998 and 2001 IEEE International Conference on SMC and 1997 IEEE International Conference on Emerging Technologies and Factory Automation. Dr. Zhou has led or participated in over 50 research and education projects with total budget over $12M, funded by National Science Foundation, Department of Defense, NIST, New Jersey Science and Technology Commission, and industry. He was a recipient of Excellence in Research Prize and Medal from NJIT, Humboldt Research Award for US Senior Scientists from Alexander von Humboldt Foundation, and Franklin V. Taylor Memorial Award and the Norbert Wiener Award from IEEE SMC Society. He has been among most highly cited scholars for years and ranked top one in the field of engineering worldwide in 2012 by Web of Science. He is Fellow of IEEE, International Federation of Automatic Control (IFAC), American Association for the Advancement of Science (AAAS) and Chinese Association of Automation (CAA).
Speech Title: Dendritic Neuron Models, Learning Algorithms and Applications
Abstract: An artificial neural network (ANN) that mimics the information processing mechanisms and procedures of neurons in human brains has achieved great success in many fields, e.g., classification, prediction and control. However, traditional ANNs suffer from many problems, such as the hard understanding problem, the slow and difficult training problem and the difficulty to scale them up. These drawbacks motivate us to develop a new dendritic neuron model (DNM) by considering the nonlinearity of synapses, not only for a better understanding of a biological neural system, but also for providing a more useful method for solving practical problems. To achieve its better performance for solving problems, six learning algorithms including biogeography-based optimization, particle swarm optimization, genetic algorithm, ant colony optimization, evolutionary strategy and population-based incremental learning are used to train it instead of the traditional backpropagation algorithm. The best combination of its user-defined parameters has been systematically investigated by using the Taguchi’s experimental design method. The experiments on fourteen different problems involving classification, approximation and prediction are conducted by various neural networks. The results answer which one is the most effective in training them and prove the outstanding performance of DNM over other neural networks in solving classification, approximation and prediction problems. This talk will also reveal the novel combination of DNM and a decision-tree-based initialization method and its application to semiconductor manufacturing equipment’s fault diagnosis.
Biography: Prof. TAN Kay Chen received the B.Eng. degree (First Class Hons.) and the Ph.D. degree from the University of Glasgow, U.K., in 1994 and 1997, respectively. He is a Professor with the Department of Computer Science, City University of Hong Kong, Hong Kong. He has published over 130 journal papers and over 130 papers in conference proceedings, and co-authored six books. His current research interests include artificial/computational intelligence and machine learning, with applications to evolutionary multi-objective optimization, data analytics, prognostics, BCI, and operational research etc.
He is the Editor-in-Chief of IEEE Transactions on Evolutionary Computation (IF: 10.629), was the EiC of IEEE Computational Intelligence Magazine (2010-2013), and currently serves on the Editorial Board of over 10 international journals such as IEEE Transactions on Cybernetics, IEEE Transactions on Computational Intelligence and AI in Games, Evolutionary Computation (MIT Press) etc. He has been an invited Keynote/Plenary speaker for over 60 international conferences and was the General Co-Chair for IEEE World Congress on Computational Intelligence (WCCI) 2016 in Vancouver, Canada. He also serves as the General Co-Chair for IEEE Congress on Evolutionary Computation (CEC) 2019 in Wellington, New Zealand.
He is a Fellow of IEEE, an elected AdCom member of IEEE Computational Intelligence Society (2014-2019), and an IEEE Distinguished Lecturer (2011-2013; 2015-2017). He received the 2016 IEEE Transactions on Neural Networks and Learning Systems Outstanding Paper Award. He was the awardee of the 2012 IEEE Computational Intelligence Society Outstanding Early Career Award for his contributions to evolutionary computation in multi-objective optimization. He also received the Recognition Award (2008) from the International Network for Engineering Education & Research (iNEER) for his outstanding contributions to engineering education and research.
Speech Title: Evolutionary Transfer Optimization
Abstract: It is known that the processes of learning and the transfer of what has been learned are central to humans in problem-solving. Within the context of computational intelligence, several core learning technologies in neural and cognitive systems, fuzzy systems, probabilistic reasoning have been notable for their ability in emulating some of human’s cultural and generalization capabilities. In spite of the accomplishments made in computational intelligence, the attempts to emulate the cultural intelligence of human in search, evolutionary optimization in particular, have to date received less attention. Particularly, the study of optimization methodology which learns from the problem solved and transfer what have been learned to help problem-solving on unseen problems, has been under-explored in the context of evolutionary computation. However, it is believed that real-world problems seldom exist in isolation, and related problems encountered may yield useful information for more effective and efficient problem-solving on new encountered problems, when properly harnessed.
This talk will touch upon the topic of evolutionary transfer optimization (ETO), which focus on knowledge learning and transfer across problems towards enhanced evolutionary optimization performance. In particular, I will first present an overview of existing ETO approaches for enhanced problem-solving in evolutionary computation. I will then introduce our recent progresses on ETO for evolutionary multitasking which is an emerging search paradigm in the realm of evolutionary computation that conducts evolutionary search concurrently on multiple search spaces corresponding to different tasks or optimization problems. Next, I will present our recent work on ETO for solving dynamic multi-objective optimization problems with enhanced performance. As problems at two consecutive time instances of a given dynamic optimization problem usually share great similarity, the optimized solutions obtained at a time instance are thus able to help the prediction of the moving optima of the next time instance. I will end my talk with discussions on potential research directions of ETO, which will cover fertile research topics ranging from theoretical analysis to real-world complex applications.
Biography: Jinliang Ding received the Bachelor, Master and Ph.D degrees in control theory and control engineering from Northeastern University, Shenyang, China. He is currently a Professor with the State Key Laboratory of Synthetical Automation for Process Industry, Northeastern University. He has authored or coauthored over 100 refereed journal articles and refereed articles at international conferences. He is also the inventor or co-inventor of 17 patents. His current research interests include modeling, plant-wide control, and optimization for the complex industrial systems, machine learning, industrial artificial intelligence, and computational intelligence and application. Dr. Ding was a recipient of the Young Scholars Science and Technology Award of China in 2016, the National Science Fund for Distinguished Young Scholars in 2015, the National Technological Invention Award in 2013, and three First-Prize of Science and Technology Awards of the Ministry of Education in 2006, 2012, and 2018, respectively. One of his articles published on Control Engineering Practice was selected for the Best Paper Award of 2011–2013.
Speech Title: Data-driven Operational Optimization of Complex Industrial Processes and Its Application
Abstract: With ever increased needs for an improved product quality, production efficiency, and cost in today’s globalized world market, advanced process control should not only realize the accuracy of each control loops, but also has the ability to achieve an optimization control of production indices that are closely related to the improved product quality, enhanced production efficiency and reduced consumption. As a result, the operational optimization of complex industrial process has attracted an increased attention of various process industries. The challenging issue is how the automation systems can be integrated to realize optimal control of the global production indices (i.e., the product quality, yield, cost and profit, etc.). This talk provides the problem description and challenges of operational optimization for the whole plant. The proposed strategy and design methods based on AI technology are presented, where optimization and adaptation, prediction and adjusting are adopted to realize the operational optimization. Our group has focus on the problem for ten years and the recent progress will be presented in this talk.
Biography: Jianhua Zhang has been a full Professor and Deputy Head of OsloMet AI Lab, Department of Computer Science, Oslo Metropolitan University, Norway, since 2018.
Dr Zhang received his PhD from Ruhr University Bochum, Germany and did postdoctoral research at University of Sheffield, UK. From 2007 to 2017 Dr Zhang was full Professor and Head of Intelligent Systems Group at East China University of Science and Technology, Shanghai, China. Between 2017 and 2018 he was Scientific Director and Head of Machine Learning Research Lab at VEKIA, Lille, France. He also held visiting positions as Guest Scientist at Dresden University of Technology, Germany from 2002 to 2003 (for a year) and Visiting Professor at Technical University of Berlin during 2008-2015 (for a year in total).
Dr Zhang’s current research interests include computational intelligence and artificial intelligence, machine learning and deep learning, intelligent systems and control, human-machine systems, brain signal processing, and brain-machine interaction. In those areas, he has published 4 books, 11 invited book chapters, and more than 150 technical papers in journals and conference proceedings.
Dr Zhang serves as Chair of IFAC (International Federation of Automatic Control) Technical Committee on Human-Machine Systems (2017-), Vice-Chair of IEEE CIS (Computational Intelligence Society) Norway Chapter (2018-), Vice-Chair of IEEE Norway Section (2019-), and is on editorial board of four international journals, such as Frontiers in Neuroscience, Cognitive Neurodynamics (Springer), and Cognition, Technology & Work (Springer). He served as IPC Co-Chair for IFAC LSS'13 (Shanghai) and HMS'16 (Kyoto), IPC Chair for IFAC HMS'19 (Tallinn), Technical Associate Editor for 19th and 20th IFAC World Congress (Cape Town, Toulouse), Editor for 21st IFAC World Congress (Berlin), and Conference Co-Chair for IEEE Int. Conf. on Big Data Analytics (ICBDA2019 (Suzhou), ICBDA2020 (Xiamen)). He was an invited keynote speaker or IPC member for a number of international scientific conferences.
Speech Title: EEG-based Human Emotion Recognition Using Machine Learning
Abstract: In this work, we investigate emotion recognition problem using the standard DEAP datasets. Firstly we use clustering technique to identify four target classes of human emotions. Then we compare two feature extraction methods, namely wavelet transform and nonlinear dynamics. Furthermore, we examine the impact of feature reduction methods on emotion classification performance. Finally, we empirically compare the affective classification performance of four types of classifiers, namely k-nearest neighbor, naïve Bayesian, support vector machine, and random forest. The data analysis results are presented to show the effectiveness of the combination of Kernel Spectral Regression (for feature dimensionality reduction) and random forest (as classifier) for emotion recognition.
Copyright © 2020 3rd International Conference on Big Data and Artificial Intelligence. All rights reserved.