Industrial Artificial Intelligence

Prof. Tianyou Chai, Northeastern University, China.

Abstract and biography


This report puts forward the necessity of developing industrial artificial intelligence, combining the role of industrial automation and information technology in the industrial revolution and the analysis of the current situation and intelligent development direction of decision-making, control and operation management of the whole process of manufacturing and production. Through the analysis of the meaning, brief history of development and development direction of artificial intelligence technology and the comparative analysis of the core objectives, realization methods, research objects and research methods of automation and artificial intelligence research and application, the meaning of industrial artificial intelligence technology and the research directions and research ideas of industrial artificial intelligence around algorithms, software and hardware platforms and AI systems that complement and enhance human capabilities are proposed. and methods.


Tianyou Chai received the Ph.D. degree in control theory and engineering in 1985 from Northeastern University, Shenyang, China, where he became a Professor in 1988. He is the founder and Director of the Center of Automation, which became a National Engineering and Technology Research Center and a State Key Laboratory. He is a member of Chinese Academy of Engineering, IFAC Fellow and IEEE Fellow. He has served as director of Department of Information Science of National Natural Science Foundation of China from 2010 to 2018.

His current research interests include modeling, control, optimization and integrated automation of complex industrial processes.

He has published 260 peer reviewed international journal papers. His paper titled Hybrid intelligent control for optimal operation of shaft furnace roasting process was selected as one of three best papers for the Control Engineering Practice Paper Prize for 2011-2013. He has developed control technologies with applications to various industrial processes. For his contributions, he has won 5 prestigious awards of National Natural Science, National Science and Technology Progress and National Technological Innovation, the 2007 Industry Award for Excellence in Transitional Control Research from IEEE Multiple-conference on Systems and Control, and the 2017 Wook Hyun Kwon Education Award from Asian Control Association.

Synergy of multi domain and large-scale systems:Take the path optimization of carbon neutralization as an example

Prof. Yusheng Xue, the Chinese Academy of Engineering, the State Grid Institute of Electric Power Science, China.

Abstract and biography


General Secretary Xi Jinping announced that China will strive to achieve peak CO2 emissions by 2030 and carbon neutrality by 2060. The "double carbon" goal has been set, but the smooth arrival from the current state to the target state with the maximum total benefit to society requires the optimization of the pathway to be formalized and grounded into feasible algorithms and procedures. For this purpose, it is necessary to model complex systems across multiple disciplines and to find optimal solutions for time-varying nonlinear systems. In order to properly describe the evolutionary process, it is necessary to consider the linkages with energy, economic, environmental and social links, and to collaboratively optimize the paths under the premise of ensuring energy security, economic security and environmental security.

The energy chain is an important support for economic and social development, and the power system is the pivotal link of the energy chain. This is the official expression of the relationship between power development and the goal of "double carbon", "a new power system with new energy as the mainstay". The report discusses the formal and quantitative analysis of a complex system composed of energy chains, carbon flows, various markets and their regulation, information systems, etc., in the process of optimizing the "carbon neutral pathway" from a systems science perspective. We review the history of the development of reductionism, holism, and the integrated approach proposed by Mr. Qian Xuesen in system science. Based on the thinking from the whole to the part and from the part to the whole as pointed out by Mr. Qian, the presentation introduces the analysis method of information-physical-social system (CPSSE) in the energy field and the framework to achieve the dual carbon goal and the optimization of energy transition path. The proposed "trajectory dynamics" establishes a reversible step-down from the "whole" to the "individual". The trajectory of all variables over time for a given scenario is obtained through a complete hybrid simulation. The trajectories of the boundary variables between the subsystem and the external environment truly reflect the interaction between them, and build a bridge between the "global" model and the "subsystem" mechanism study. This not only satisfies the global integrity, but also provides information on the co-evolution of subsystems and boundary states, which can inherit and extend the existing results of reductionism. The report also presents some of the results that the research team has achieved and the ongoing research.


Yusheng Xue, an academician of the Chinese Academy of Engineering, is currently the honorary president of the State Grid Institute of Electric Power Science. He pioneered the quantitative theory of motion stability of non-autonomous systems and quantitative algorithms of transient stability of power systems, which have been widely used at home and abroad. He designed the defense scope of the blackout defense system covering 4/5 of China's power grid. He proposed the research framework of information-physical-social system in energy field, and realized the hybrid simulation through mathematical model-multi-agent-real human to support decision making.

Towards Fully Adaptive Deep Neural Networks

Prof. Sheng Chen, School of Electronics and Computer Science, University of Southampton, UK.

Abstract and biography


The main challenge for industrial predictive models is how to effectively deal with big data from high-dimensional processes with nonstationary characteristics. Although deep networks, such as the stacked autoencoder (SAE), can learn useful features from massive data with multilevel architecture, it is difficult to adapt them online to track fast time-varying process dynamics. More specifically, it is prohibitive to adapt or optimize a large deep multi-layer network within a small sampling period, and typically, only the weights of the output regression layer of the deep network are adjusted during the online operation to provide certain adaptive capability to the model. However, this is insufficient for real-world highly time-varying industrial processes.

Recently, we have developed an adaptive gradient radial basis function (GRBF) model.Although it is a shallow network, this model is particularly suitable for online modeling and prediction of nonlinear and nonstationary processes. During the online operation, the hidden layer of the GRBF is adapted to encode the newly emerging process’s state and, moreover, this adaptation does not require any complicated online structure optimization.

In this talk, we consider the challenging task of making deep neural network models adaptive. Our approach consists of three modules, a GRBF preliminary predictor, a SAE feature extractor and an adaptive GRBF network. The GRBF predictor provides the preliminary prediction of the target output, which is offered to the SAE as the output-relevant information to enhance feature representation. The extracted features are then fed into the adaptive GRBF model as the input to produce the final prediction of the target output. During training, the three component networks can be trained one by one with the existing effective training algorithms. During online operation, the preliminary GRBF predictor and the SAE are fixed, while the adaptive GRBF model adapts its hidden-layer structure and the weights of the output layer efficiently to track the process’s fast time-varying dynamics.


Sheng Chen is Professor of Intelligent Systems and Signal Processing in School of Electronics and Computer Science, University of Southampton. He is a Fellow of the United Kingdom Royal Academy of Engineering, a fellow of IEEE, a Fellow of Asia-Pacific Artificial Intelligence Association, and a fellow of IET. He is one of the original ISI most highly cited researchers in engineering(March 2004).

He received the BEng degree from East China Petroleum Institute (now China Petroleum University), China, in January 1982, and the PhD degree from City University, London, in September 1986, both in control engineering. In 2005, he was awarded the higher doctoral degree, Doctor of Science (DSC), by the University of Southampton.

From October 1986 to August 1999, he held various research and academic posts with University of Sheffield, University of Edinburgh and University of Portsmouth, all in UK. Since September, 1999, he has been with School of Electronics and Computer Science, University of Southampton.

Professor Chen’s research interests include machine learning and neural networks, adaptive signal processing, and wireless communications. He has 16,500 plus Web of Science citations with h-index 56, and 33,100 plus Google Scholar citations with h-index 77.

Eleven researchers / doctors, including four from China who influenced 45 years of my journey on Biomedical Engineering (BME) research

Prof. Mitsuo Umezu, Waseda University, Tokyo, Japan.

Abstract and biography


After spending 45 years of fun and happy BME research, I retired from Waseda University at the age of 70 in March 2021. In 1974, I became a graduate student majoring in mechanical engineering. And I had a dream to take a job as a mechanical engineer in manufacturing high-speed trains or large motor vehicles. However, with the suggestion by Professor Kiichi TSUCHIYA(土屋喜一), I decided to participate in a joint project with the Heart Institute of Japan organized by Professor Shigeru SAKAKIBARA(榊原仟), where I learned that medical research is made up of the sacrifices of many laboratory animals. Then, I designed and developed a mechanical model (simulator) of the blood circulatory system to reduce the number of animal experiments. Fortunately, many domestic and international researchers and doctors have paid attention to our achievements. In particular, Professor Kazuhiko ATSUMI (渥美和彦)of the University of Tokyo, who was the leader of artificial hearts in Japan, especially encouraged my original research. As a result of the connections of many people, I became the first member of the National Cardiovascular Center Research Institute at Osaka in 1979, and conducted research on the development and evaluation of artificial valves and artificial hearts with President Hisao MANABE(曲直部壽夫) and Deputy Director Tetsuzo AKUTSU(阿久津哲造). Professor MANABE is the first surgeon in Japan to perform direct-view heart surgery at Cleveland Clinic in 1958. When we firstly presented our achievements in Shanghai in 1983, Professors WANG Yi-Shan(王一山)and YE Chun-Xiu(葉椿秀)of Shanghai Second Medical University, who were members of the national project for artificial organs at that time in China, were particularly interested in our achievements. At that time, Professor He Guo-Sun (何国森) of Shanghai Industrial University, currently Shanghai University, was also present there. And three Chinese professors seriously asked me how to promote medical-engineering collaboration which I have done. After that, we had a deep friendship with each other. In 1986, Dr. Victor CHANG(張任謙) from Australia asked me, if I could work at St. Vincent Hospital, Sydney, and I accepted his offer. In Sydney, based on the idea of ​​Professor YE, we developed a spiral-vortex type ventricular assisted heart in 1988 and obtained an international patent. However, it did not reach commercialization in Australia, Japan, and China. Based on this bitter experience, I came to the conclusion that learning of medical regulatory science is important for the widespread use of medical technology for the happiness of patients. Together with President Katsuhiko SHIRAI(白井克彦)of Waseda University and Vice President Teruo OKANO(岡野光夫)of the Tokyo Women's Medical University, we established the research institute (TWIns) in 2008, which has created a true medical-engineering collaboration environment, with the cooperation of Waseda University and Tokyo Women's Medical University. The Japanese government also strongly supported us. Currently, there are more than 700 residents at TWIns, including more than 300 graduate students, and we are energetically continuing our research day and night.

Throughout my lecture, I would like to introduce my 45 years of BME research with my sincere gratitude to the seniors who supported me. Finally, I would like to explain the process of how the Japanese-made implantable ventricular assisted heart, EVAHEART, was approved for clinical application in China.


Mitsuo Umezu was born in Yokosuka, kanagawa, Japan in 1951. He is a biomedical engineer in the field of cardiovascular modeling and simulation research for advanced medical application. He has two PhDs: He received a doctor of engineering from Waseda University and a doctor of medical science from Tokyo Women's Medical University.

From 1979 to 1987, he was a research associate and laboratory head of the Artificial Organ Department, National Cardiovascular Center Research Institute, Osaka, Japan. He was subsequently appointed as the first project leader of the Australian Artificial Heart Program organized at St. Vincent Hospital, Sydney, Australia.

He was a professor in the Department of Mechanical Engineering, Waseda University from April 1992 to March 2021. He is also one of the founders of "TWIns: Tokyo Women's Medical University / Waseda University Joint Institute for Advanced Biomedical Sciences". He was the Director of the Tokyo Women's Medical University-Waseda University Joint Graduate School on medical regulatory science from 2010 to 2020. This joint graduate school was the first trial to be approved by the Ministry of Education, Culture, Sports, Science and Technology of Japan.

His recent research interests include the development and evaluation of artificial organs, and regulatory science for advanced medical technologies. He is a member of the Pharmaceutical Affairs Review Board for New Medical Devices of the Japanese Ministry of Health, Labor and Welfare. He is also the chairman of the 2021 Conference of the Japanese Society for Regulatory Science of medical products.

Recent Challenges of Federated Learning, Knowledge Transfer, and Knowledge Distillation in System Modeling: An Environment of Granular Computing

Prof. Witold Pedrycz, Department of Electrical & Computer Engineering University of Alberta, Edmonton, Canada.

Abstract and biography


With the rapid progress encountered in system modeling and simulation, especially in complex architectures such as life systems, we have been witnessing important challenges. The visible requirements are inherently associated with the data and a way they are addressed in system modeling. We identify three ongoing challenges with far-reaching methodological implications, namely (i)modeling in the presence of strict constraints of privacy and security, (ii) efficient model building with limited data, and (iii) knowledge distillation.

We advocate that to conveniently address these challenges, it becomes beneficial to engage the fundamental framework of Granular Computing to enhance the existing approaches (such as e.g., federated learning in case of (i) and transfer knowledge in (ii)) or establish new directions to the problems. It is demonstrated that various ways of conceptualization of information granules as fuzzy sets, sets, rough sets, and others may lead to efficient solutions.

To establish a sound conceptual modeling framework, we include a brief discussion of information granules-oriented design of rule-based architectures. A way of forming the rules through unsupervised federated learning is discussed along with algorithmic developments. A granular characterization of the model formed by the server vis-a-vis data located at individual clients is presented. It is demonstrated that the quality of the rules at the client’s end is described in terms of granular parameters and subsequently the global model becomes represented as a granular model with parameters in the form of information granules of type-2. The roles of granular augmentations of models in the setting of transfer learning and logic-oriented knowledge distillation are discussed.

The talk is self-contained; all required prerequisites are covered in a succinct manner.


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).

Resilient Networked Microgrids Energy Management System

Prof. Mo-Yuen Chow, North Carolina State University, USA.

Abstract and biography


As technologies advances, the Networked Microgrids (NMG) is widely envisioned to be the future form of the smart grid, for its autonomy, distributed energy resources hosting capability, enhancements in reliability and resilience, etc. This presentation will dissect the NMG vision into several key technologies in the cyber (communication network) and physical (power system) layers, e.g. the needs of network/information technology to enable the resilience, reliability, and cost-effective operation of the NMG. This presentation will also highlight two of the fundamental technologies: resilient Collaborative Distributed Energy Management System (CoDEMS) and the Smart Battery Gauge (SBG) technology that have been developed in ADAC lab and FREEDM Center at NC State University and their applications for economical, reliable, resilient, and flexible energy systems.


Mo-Yuen Chow earned his degree in Electrical and Computer Engineering from the University of Wisconsin-Madison (B.S., 1982); and Cornell University (M. Eng., 1983; Ph.D., 1987). Dr. Chow is a Professor in the Department of Electrical and Computer Engineering at North Carolina State University. He was a Visiting Changjiang Scholar.

Dr. Chow is the founding director of the Advanced Diagnosis, Automation, and Control (ADAC) Laboratory. He is the founding chair of Industrial Electronics Society (IES) Energy Storage Technical Committee and the past chair of IES Resilience and Security for Industrial Applications Technical Committee. Dr. Chow has published over 350 articles and is holding 8 patents related to his research works.

Dr. Chow’s recent research focuses on distributed control and management on smart grids, batteries, and mechatronics systems. He is an IEEE Fellow, Co-Editor-in-Chief of IEEE Trans. on Industrial Informatics (2014 - 2018), Editor-in-Chief of IEEE Transactions on Industrial Electronics (2010 - 2012). He has received the IEEE IES Dr.-Ing. Eugene Mittelmann Achievement Award, the IEEE Industrial Electronics Society Anthony J Hornfeck Service Award, the IEEE Region-3 Joseph M. Biedenbach Outstanding Engineering Educator Award, the IEEE Eastern North Carolina Section (ENCS) Outstanding Engineering Educator Award, the IEEE ENCS Service Award. He is a Distinguished Lecturer of IEEE Industrial Electronics Society.

Application of computer vision in embryo surveillance, sperm discovery and AD diagnosis

Prof. Zhou Wenju, Shanghai University, China.

Abstract and biography


This report mainly introduces our team's work in the integration of automation engineering with life and medical treatment. This time mainly introduce three cases,

1. Vision-based automatic detection and evaluation of embryo development. With the postponement of people's childbearing age, the number of infertility patients has gradually increased. This brings pressure to the work of the reproductive department of the hospital, especially the daily observation and care of fertilized embryos, which is a huge workload, and the doctors are very tired every day. In this study, machine vision was used to automatically take photos, analyze and evaluate the development of fertilized embryos, and alert the doctors to promptly deal with abnormal embryos. A lot of work is reduced, and the embryonic development process is sent to the patient through the mobile phone network, so that the patient can understand the development process of their future baby (embryo), increase the trust between doctors and patients, and reduce the conflict between doctors and patients.

2. Quick search for small living objects in the surgical extracts of male infertility patients. For male patients with severe infertility, Shanghai First People's Hospital can extract the semen of the patient through surgery, and then search for the sperm under a microscope. Due to the long search process, the patient has to wait until the sperm is found before the wound can be sutured. If no sperm is found, an extended operation is needed to continue to extract new semen and continue to search. Due to the manual search, the efficiency is low and the time is long, and the patient needs to wait all the time while the wound is open. In this project, machine vision is used in conjunction with an electronic control stage to realize automatic and rapid sperm search and reduce the patient's waiting time.

3. Early diagnosis of Alzheimer's disease based on scene-inspired expression analysis. Alzheimer's disease is a common disease of the elderly. There is no effective treatment at present, but if it is detected early, early intervention can be initiated. This project realizes the recorded video image by playing, and stimulates the tester's expression response while watching the tester. Through the analysis of facial expressions, assess the risk of Alzheimer's disease, and provide help for the early screening of Alzheimer's patients.


Zhou Wenju received his Ph.D. in the field of control theory and engineering, and worked as a postdoctoral researcher at the University of Essex for two years. He is currently a distinguished researcher and doctoral supervisor of Shanghai University. He also served as the deputy director of the Center for Artificial Intelligence and Medical-Industry Intersection Research and the deputy director of the Center for Transformation and Application of Intelligent Technology Achievements of Shanghai University. He used to serve as a robotics engineer for Vitec Videocom Group Corporation in the United Kingdom. He is currently a member of the Embedded Instrument and System Technology Branch of the Chinese Instrumentation Society, a member of the Artificial Intelligence Committee of the Chinese Society of Automation, a member of the National Electrical Instrumentation Standardization Technical Committee, and a member of the American Institute of Electrical Engineers ( IEEE). He was awarded the honorary titles of "Mechatronics Engineering and Automation Scholar" of Shanghai University, "Taishan Talent" of Shandong Province, and "Double Hundred Plan" talents.

His current research interests include control theory and its application in the field of automation engineering and medical-industrial integration, machine vision and robotics, pattern recognition and intelligent manufacturing.

He has won the "Wu Wenjun" Science and Technology Progress Award, the China Innovation and Entrepreneurship Competition Award, the China Instrument and Control Society Science and Technology Award, and the Science and Technology Progress Award of Colleges and Universities in Shandong Province.

In recent years, he has been funded by 2 major R&D Projects of the Ministry of Science and Technology, 1 National Natural Science Foundation project, 1 production-university-research collaboration project of the Ministry of Education, and more than 10 enterprise science and technology research projects. He has applied for 30 patents and has obtained 10 authorized patents; he has published more than 50 SCI and EI indexed papers.

Call For Papers

The CFP of
LSMS2021 & ICSEE2021.

Keynote Speech

LSMS2021 & ICSEE2021 hold keynote speeches.


Register and submit camera-ready before 15th June 2021!

Travel & Hotel

Information about travel and accommodation in Hangzhou