CSIS-IAC 2023 Plenary Speakers

Speaker	Affiliation	Title
Zeng-Guang Hou	CASIA	BCI Based Intelligent Control Methods for Rehabilitation Robots
Guo-Ping Liu	SUSTech	Cloud Predictive Control for Networked Multi-agent Systems
Jun-Fei Qiao	BJUT	Intelligent Optimal Control for Municipal Solid Waste Incineration Processes
Fei-Yue Wang	CASIA	The Complexity Science and Parallel Intelligence for the New Generation: A Foundation Thinking for Being, Becoming, and Believing
Shengli Xie	GDUT	A New Approach for Optical Coherence Tomography Signal Processing and the Corresponding Instrument System
Qin Zhang	Tsinghua U	Dynamic Uncertain Causality Graph for Clinical Diagnosis in General Practice Applied in Real World

Zeng-Guang Hou

Zeng-Guang Hou is a Professor and Deputy Director of the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences (CAS). He is a VP of Chinese Association of Automation (CAA), VP of the Asia Pacific Neural Network Society (APNNS). Dr. Hou is a CAA Fellow and an IEEE Fellow. He also serves as an AE of IEEE Transactions on Cybernetics, and an Editorial Board Member of Neural Networks. Dr. Hou was a recipient of the Dennis Gabor Award of the International Neural Network Society (INNS) in 2023, the Outstanding Achievement Award of Asia Pacific Neural Network Society (APNNS) in 2017, and IEEE Transactions on Neural Networks Outstanding Paper Award in 2013, etc. His research interests include computational intelligence, robotics and intelligent systems.

BCI Based Intelligent Control Methods for Rehabilitation Robots

We are facing increasingly serious issues due to aging population, such as stroke and Alzheimer's disease, which require accurate evaluation and efficient rehabilitation, but we are short of rehabilitation therapists. Rehabilitation robots are expected to provide a possible technical solution helping to solve these issues and provide more efficient rehabilitation services for patients and therapists. However, applications of rehabilitation robots also have many challenges, such as efficiency, reliability and safety for human-robot interactions. And intelligent control is an important issue hindering its development. In this talk, we will discuss the recent developments and challenges of multi-modal biological signal acquisition and processing, brain-computer interface and intelligent control methods, and prospects for the future development.

Guo-Ping Liu

Professor Guo-Ping Liu received the BEng degree in industrial automation and MEng degree in control engineering from the Central South University of Technology, China (now Central South University) and the PhD degree in control systems from the University of Manchester in the UK. He was a professor with the Institute of Automation of the Chinese Academy of Sciences, University of South Wales, Harbin Institute of Technology, and Wuhan University. He is now a chair professor with the Southern University of Science and Technology. Prof Liu’s research interests include networked control systems, multi-objective optimal control and intelligent decision, nonlinear identification and intelligent control, and industrial advanced control applications. He was named a highly cited researcher by Thomson Reuters, Clarivate Analytics, and Elsevier. He was awarded the Alexander von Humboldt research fellowship. He received the second prize of Chinese National Science and Technology Awards twice. Prof. Liu was the general chair of the 2007 IEEE International Conference on Networking, Sensing and Control, 2011 International Conference on Intelligent Control and Information Processing, and 2012 UKACC International Conference on Control. He is a member of the Academy of Europe and a fellow of IEEE, IET and CAA.

Cloud Predictive Control for Networked Multi-agent Systems

With the rapid development of communication network technology, cloud computing technology and control system technology, there are more and more networked multi-agent control systems via cloud computing, such as industrial internet control systems and smart grids. This talk mainly discusses the coordinated control problem of networked multi-agent systems based on cloud computing. For complex large-scale networked multi-agent systems, utilizing the advantages of cloud computing, a cloud predictive control strategy is introduced to compensate for communication constraints actively, execute control algorithms fast and achieve desired coordination performance of the systems. A multi-step learning predictor is discussed to predict the future outputs of unknown nonlinear multi-agents. The coordinated control optimization design is adopted to have the expected dynamic and static coordination performance between individual agents. The consensus and stability of networked multi-agent systems are analysed, which is controlled employing the cloud predictive control method. The simulation and experimental results demonstrate the advantages of the cloud predictive control of networked multi-agent systems.

Jun-Fei Qiao

Jun-Fei Qiao is a Professor and the Vice President of Beijing University of Technology. He is the Director of Beijing Laboratory of Smart Environmental Protection, Director of Engineering Research Center of Intelligent Perception and Autonomous Control, Ministry of Education. He also serves as a member of the discipline appraisal group of the Academic Degrees Committee of the State Council, and a member of the Teaching Steering Committee of the Ministry of Education. He is a Distinguished Professor of the "Changjiang Scholar Award Program", and a recipient of the National Science Fund for Distinguished Young Scholars from the National Natural Science Foundation. He is also a winner of the New Century Ten Million Talents Project, and an expert enjoying the Special Government Allowance from the State Council. Prof. Qiao’s research focuses on computational intelligence and intelligent optimal control, and smart environmental protection. He has published more than 200 papers on prestigious journals, and more than 100 invention patents have been authorized by U.S. and China respectively. He has won several awards, including 1 second prize of National Science and Technology Progress Award, and 1 first prize of Science and Technology Progress Award by the Ministry of Education.

Intelligent Optimal Control for Municipal Solid Waste Incineration Processes

Municipal solid waste incineration (MSWI) provides an effective and promising approach for managing municipal solid waste (MSW) due to the fact that it can reduce waste volume and recover energy. MSWI has become an important support for the ecological civilization construction and dual carbon target. The MSWI process is a complex dynamic system with multiple elements in space and time, involving various physical and chemical reactions, with strong nonlinearity, high coupling, etc. Hence, it is difficult to realize the optimal control of MSWI processes. This talk will discuss the challenges faced by realizing the optimal control, and then introduce the recent developments of real-time measurement, adaptive control, and multi-objective dynamic optimization.

Fei-Yue Wang

Fei-Yue Wang received his Ph.D. degree in computer and systems engineering from the Rensselaer Polytechnic Institute, Troy, NY, USA, in 1990. He joined The University of Arizona in 1990 and became a Professor and the Director of the Robotics and Automation Laboratory and the Program in Advanced Research for Complex Systems. In 1999, he founded the Intelligent Control and Systems Engineering Center at the Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China, under the support of the Outstanding Chinese Talents Program from the State Planning Council, and in 2002, was appointed as the Director of the Key Laboratory of Complex Systems and Intelligence Science, CAS, and Vice President of Institute of Automation, CAS in 2006. He found CAS Center for Social Computing and Parallel Management in 2008, and became the State Specially Appointed Expert and the Founding Director of the State Key Laboratory for Management and Control of Complex Systems in 2011. His current research focuses on methods and applications for parallel intelligence, social computing, and knowledge automation. He is a Fellow of INCOSE, IFAC, ASME, and AAAS. In 2007, he received the National Prize in Natural Sciences of China, numerous best papers awards from IEEE Transactions, and became an Outstanding Scientist of ACM for his work in intelligent control and social computing. He received the IEEE ITS Outstanding Application and Research Awards in 2009, 2011, and 2015, respectively, the IEEE SMC Norbert Wiener Award in 2014, and became the IFAC Pavel J. Nowacki Distinguished Lecturer in 2021. Since 1997, he has been serving as the General or Program Chair of over 30 IEEE, INFORMS, IFAC, ACM, and ASME conferences. He was the President of the IEEE ITS Society from 2005 to 2007, the IEEE Council of RFID from 2019 to 2021, the Chinese Association for Science and Technology, USA, in 2005, the American Zhu Kezhen Education Foundation from 2007 to 2008, the Vice President of the ACM China Council from 2010 to 2011, the Vice President and the Secretary General of the Chinese Association of Automation from 2008 to 2018, the Vice President of IEEE Systems, Man, and Cybernetics Society from 2019 to 2021. He was the Founding Editor-in-Chief (EiC) of the International Journal of Intelligent Control and Systems from 1995 to 2000, IEEE ITS Magazine from 2006 to 2007, IEEE/CAA Journal of Automatica Sinica from 2014 to 2017, China's Journal of Command and Control from 2015 to 2021, and China's Journal of Intelligent Science and Technology from 2019 to 2021. He was the EiC of the IEEE Intelligent Systems from 2009 to 2012, IEEE Transactions on Intelligent Transportation Systems from 2009 to 2016, IEEE Transactions on Computational Social Systems from 2017 to 2020. Currently, he is the President of CAA's Supervision Council, and the EiC of IEEE Transactions on Intelligent Vehicles.

The Complexity Science and Parallel Intelligence for the New Generation: A Foundation Thinking for Being, Becoming, and Believing（第三轴心时代的复杂性科学与平行智能：面向必映，必明，必曞的基础认知）

The lecture explores the synergistic potential of parallel intelligence, Industry 5.0 in the context of radio-frequency identification (RFID) and smart sensing technologies. As Industry 4.0 transitions to the next phase of industrial revolution, Industry 5.0 emphasizes the harmonious coexistence between humans and machines, promoting human-centered approaches to technological advancements. Parallel intelligence, a concept leveraging Artificial systems (A), Computational experiments (C), and Parallel execution (P) to enable novel solutions and insights that address complex problems and achieve superior outcomes. By combining RFID and smart sensing technologies with decentralized autonomous organizations (DAOs) and decentralized science (DeSci), new possibilities emerge. The collective intelligence of multiple RFID systems and smart sensors can be harnessed to optimize supply chain operations, enhance asset tracking accuracy, and enable predictive maintenance. The integration of DAOs further enhances this collaborative ecosystem by facilitating decentralized decision-making and resource allocation. DeSci emphasizes open collaboration, data sharing, and reproducibility, facilitating scientific progress and innovation in a decentralized manner, and empowers collaborative frameworks for RFID and smart sensing the potential to revolutionize industries, drive efficiency, and foster innovation in a human-centered and decentralized manner, paving the way for a more sustainable and smart future.

Shengli Xie

Shengli Xie received the B.S. degree in mathematics from Jilin University, Changchun, China, in 1983, the M.S. degree in mathematics from Central China Normal University, Wuhan, China, in 1995, and the Ph.D. degree in control theory and applications from South China University of Technology, Guangzhou, China, in 1997. He is currently a Full Professor and the Head of the Institute of Intelligent Information Processing, Guangdong University of Technology, Guangzhou. He was awarded Highly Cited Researcher. His research interests include blind signal processing, machine learning, and Internet of Things. He was an Associate Editor for IEEE Transactions on Neural Networks and Learning Systems, and is an Associate Editor for IEEE Transactions on Systems, Man, and Cybernetics: Systems. He received the Second Prize of National Natural Science Award of China in 2009. He is a Foreign Full Member (Academician) of the Russian Academy of Engineering. He is a winner of the Science and Technology Progress Award 2022 of the Ho Leung Ho Lee Foundation.

A New Approach for Optical Coherence Tomography Signal Processing and the Corresponding Instrument System

Resin composite materials possess several advantages, including high strength, resistance to high temperatures, and low density. These materials find extensive applications in the construction of high-end aviation equipments. To fulfill the demands for complicate equipment loads, increased carrying capacity, extended service life, and enhanced safety, it is imperative to conduct scientific research on the mechanical properties and failure mechanisms of materials. Therefore, the development of tomographic deformation measurement techniques is crucial in accurately capturing the strength and damage evolution of composite materials, both externally and internally. Optical coherence tomography (OCT) is an advanced method that offers nanometer-level measurement sensitivity for tomographic deformation analysis, positioning it at the forefront of international research. However, resolution limitations, inadequate measurement accuracy, and low signal-to-noise ratio (SNR) of imaging pose significant challenges within this field, necessitating substantial advancements. The commonly accepted solution entails utilizing hardware techniques, such as expanding the bandwidth of the light source. Unfortunately, this strategy can increase the complexity of integrating hardware and therefore is difficult to fundamentally resolve the aforementioned bottleneck issues. As a result, it is imperative to investigate a novel approach for OCT signal processing, as well as the development of associated instrument systems. This lecture introduces novel techniques in OCT signal processing, including sparse blind separation for estimating interferometric spectra, underdetermined blind separation for unmixing interlayer phases, and spatial spectral separation for compensating phase errors. A state-of-the-art tomographic measurement instrument system has been developed. The detailed content includes:
(1) Considering the issue of restricted resolution resulting from narrow bandwidth, we uncover the consistent occurrence of sparse interference spectrum as a crucial parameter for characterizing axial resolution. Building upon this finding, we propose the "sparse blind separation model for OCT" and the "interference spectrum sparsity optimization method for multi-layer underdetermined systems", which effectively overcomes the bottleneck of axial resolution limitations.
(2) To address the challenge of inadequate measurement accuracy resulting from spectral leakage, we establish the “underdetermined blind separation (UBS) model for OCT phase” in the wavenumber domain. Furthermore, we present the “OCT phase spectrum optimization method” to solve the UBS model and finally, the solution can enable precise reconstruction of topography and deformation measurements without the need for prior information.
(3) To solve the challenge of low SNR arising from speckle decorrelation, we investigate a phase noise localization method based on binary maps. Additionally, we present new OCT image processing techniques, specifically “spatio-temporal adaptive differential phase calculation" and "interference spatial spectrum separation phase error compensation," leading to a 137% improvement in SNR in strain imaging.
(4) Building upon the innovative techniques for processing OCT signals mentioned earlier, we develop a new OCT system that is capable of measuring surface topography and internal deformation with high precision. Notably, the system offers an axial resolution of 1 micron, a cross-sectional measurement speed of 20 frames per second, and a measurement accuracy within ±20 nanometers, showing a superior performance in comparations to current mainstream OCT systems.

Qin Zhang

Qin Zhang is a member of the Standing Committee of the 13th Chinese People’s Political Consultative Conference, emeritus member of China Association for Science and Technology, member of International Nuclear Energy Academy, head of the strategic advisory expert team for China National Key Project of Nuclear Power, Fellow of Chinese Association for Artificial Intelligence (CAAI), Chair of the Technical Committee for Uncertainty in AI of CAAI, Director of the Academic Advisory Committee of China Intellectual Property Society, and Professor of Institute of Nuclear and New Energy Technology and Department of Computer Science and Technology, Tsinghua University.

Dynamic Uncertain Causality Graph for Clinical Diagnosis in General Practice Applied in Real World

DUCG (Dynamic Uncertain Causality Graph) is a newly developed medical AI model that graphically represents domain uncertain causal knowledge and makes probabilistic reasoning with penetrative explainability and inherent invariance in different application scenarios. The "independent and identically distributed" assumption is not needed in DUCG, because DUCG is causality-driven instead of data-driven. Therefore, DUCG does not have problems such as data collecting, labeling, fitting, privacy, bias, generalization, high cost and high energy consumption, etc. This presentation will show online how DUCG works to guide general practitioners to make clinical diagnoses under more than 50 chief complaints covering more than 1,000 diseases, including how to collect clinical information and what medical checks to make, step by step according to the conditions of primary hospitals or clinics. The chief complaints include: Cough sputum, dyspnea, abdominal pain, diarrhea, hematemesis, nasal congestion, nasal bleeding, blood in the stool, nausea and vomiting, joint pain, hemoptysis, fever, chest pain, jaundice, anemia, edema, obesity, emaciation, sore throat, palpitation, fever in children, dizziness, headache, constipation, rash, difficulty swallowing, enlargement of lymph nodes, cyanosis, limb numbness, vaginal bleeding, abnormal vaginal discharge, pruritus vulvae, reduced menstruation or amenorrhea, abdominal distension, syncopation, tinnitus, deafness, earache, acid reflux, heartburn, hiccup, belching, mass, oliguria or no uria, lower urinary tract symptoms (frequent urination, urgency of urination, pain in urine, dysuria, polyuria, gross hematuria, and urine leakage), neck and low back pain (neck pain, waist pain and back pain). In total, the diagnostic precision verified by third-party hospitals for every chief complaint is more than 95%, in which the diagnostic precision for every disease (including uncommon disease) is no less than 80%, which is most needed by general practitioners. More than 650,000 cases were performed in real world in China. In which, only 17 diagnoses were determined as incorrect and the mistakes in DUCG were found and fixed afterward. Statistics in the real-world applications show that DUCG can increase the ability of general practitioners to diagnose diseases several times more than without DUCG.