Keynote Speaker Ⅰ
Dianhui (Justin) Wang
China University of Mining and Technology, Xuzhou, China
SAPI, Northeastern University, Shenyang, China
La Trobe University, Melbourne, Australia
Speech Title: Stochastic Configuration Machines: Fundamentals and Prospect
Abstract: Randomised learning techniques for training neural networks have received considerable attention in the past decades. The main reason behind this is that this class of learning algorithms can provide a faster solution with comparable modelling performance. With the best of our knowledge, all randomized algorithms from 1989 to 2017 lack basic understanding on the assignment of random weights and biases of a randomized learner model, that is, they are totally independent of the dataset. Up to our stochastic configuration networks (SCNs) published in 2017, a right and logical setting of random weights and biases drew the attention of the abused use of random parameters in learning algorithms. SCN holds the universal approximation property at algorithmic level. In another words, a SCN model can be incrementally built with guaranteed error-free learning performance. Built on SCN concept, we recently developed an advanced randomized learner model, termed Stochastic Configuration Machine (SCM), which is composed of a mechanism model (or a fuzzy system) and a lightweight SCN model. Such a milestone progress greatly contributes to both the advancement of knowledge on randomized learning theory and the development of lightweight computing units for edge-computing industrial applications. This presentation aims to introduce some fundamentals of SCM and its application prospects in process industries.
Bio: Dr. Wang was awarded his PhD degree (March 1995) in Industrial Automation from Northeastern University, China. From Sept. 1995 to June 2001, he worked as a Postdoctoral Fellow at Nanyang Technological University, Singapore and The Hong Kong Polytechnic University, Hong Kong, China. He joined La Trobe University in July 2001 and worked as a Reader and Associate Professor in the Department of Computer Science and Information Technology until the end of 2020, and with an adjunct appointment from January 2021. Since 2017, Dr Wang has been a visiting Professor at State Key Laboratory of Synthetical Automation of Process Industries, Northeastern University, China. In July 2021, He joined the Institute of Artificial Intelligence at China University of Mining and Technology. He is the Funding Director of Research Centre for Stochastic Configuration Machines. His current research focuses on Stochastic Configuration Machines (SCM) for big industrial data modelling and analytics, lightweight computing, and interpretable AI technology. Dr. Wang published more than 270 technical papers on applied mathematics, control engineering and computer sciences. He is a Senior Member of IEEE, serving as an executive Editor-in-Chief for Industrial Artificial Intelligence, Associate Editor for TCYB, TFS, INS, AIR, and WIREs Data Ming and Knowledge Discovery.
Keynote Speaker Ⅱ
Hongjing Liang
University of Electronic Science and Technology of China, China
Speech Title: Prescribed Performance Cooperative Control Research of Heterogeneous Autonomous Unmanned Systems
Abstract: In recent years, the cooperative control theory of autonomous unmanned systems has been widely applied. For example, through the cooperative operation of heterogeneous autonomous unmanned systems, functions such as information sharing, task allocation, and collaborative strikes can be achieved, thereby improving operational efficiency and capabilities. The various limitations faced by autonomous unmanned systems during task execution, such as communication bandwidth, computing power, energy supply, etc., may affect the performance and cooperative capabilities. Therefore, it is necessary to study how to achieve the prescribed performance cooperative control problem of autonomous unmanned systems. To achieve cooperative control of autonomous unmanned systems with prescribed performance in different scenarios, the consensus tracking control problem of multi-UAV systems under prescribed performance and attitude constraints, and the distributed adaptive cooperative control problem of heterogeneous UAV-UGV systems under prescribed performance are considered. Two types of prescribed performance control strategies operating in different situations are proposed, effectively improving the steady-state and transient performance of systems.
Bio: Hongjing Liang, professor of University of Electronic Science and Technology of China, Doctoral supervisor, Highly Cited Researchers in Clarivate Analytics, approved by the National Natural Science Foundation Outstanding Youth Science Fund Project, "Tianfu Emei Plan" Young Scientific and Technological Talents Project and Sichuan Natural Science Foundation Outstanding Youth Science Foundation. He has been awarded the title of provincial excellent master's thesis advisor for three consecutive years. At present, his main research direction are intelligent adaptive control of multiagent systems, collective intelligence, etc. He has presided 3 national projects such as National Natural Science Foundation of China projects, and participated in 2 National Natural Science Foundation of China projects. He has published a monograph in English. He is a member of the editorial board of international SCI journals IEEE SMCM, IEEE SMCS, FNL and IJFS. He has published (including accepted papers) more than 100 academic papers in authoritative journals, and the relevant achievements have been cited and positively evaluated by many experts and scholars at home and abroad. One paper was selected for the China's 100 Most Influential International Academic Papers, one paper was selected for the Best Paper Award of Acta Automatica Sinica, and one conference paper was selected for the Best Paper Award in Theory of ICCSS 2017. He was awarded the IEEE SMC Beijing Capital Region Chapte Young Author Prize in 2020.
Keynote Speaker Ⅲ
Guodong Guo
Ningbo Institute of Digital Twin, China
Keynote Speaker Ⅳ
Zaiqing Chen
School of Information Science and Technology, Yunnan Normal University, Kunming, China
Speech Title: Neural Representation of Binocular Color Fusion and Rivalry
Abstract: Binocular color fusion and rivalry can serve as experimental tools for investigating consciousness, attention, and how the brain processes conflicting information. This report primarily explores the neural representations of binocular color fusion and rivalry and their potential applications in cognitive science, psychology, and clinical diagnosis. By employing a comprehensive analysis of multiple biological indicators, including eye movement metrics, electroencephalographic (EEG) markers, and functional near-infrared spectroscopy (fNIRS), we attempt to uncover the physiological activity differences in the brain during the process of binocular color fusion and rivalry. Our results show that binocular color fusion and rivalry exhibit distinct characteristics in terms of eye movement indicators, EEG features, and cerebral oxygenation levels. These differences may serve as biomarkers for understanding and treating associated visual and cognitive impairments. Moreover, the report introduces a brain-computer interface (BCI) system that leverages binocular color rivalry to enhance user attention. It also looks forward to future research directions in unveiling the neural mechanisms of color perception, developing new diagnostic tools for mental health, and exploring treatments for neurological disorders.
Bio: Prof. Zaiqing Chen is with the School of Information Science and Technology, Yunnan Normal University. Honors and Titles include: Reserve Talent for Middle-aged and Young Academic and Technical Leaders in Yunnan Province, Deputy Director of the Yunnan Provincial Department of Education Engineering Research Center for Computer Vision and Intelligent Control Technology, Deputy Director of the Yuxi Mental Health Specialty Examination Key Laboratory, and Visiting Scholar at the Department of Electrical and Computer Engineering, University of Miami, USA. His research is primarily focused on the brain's mechanism for integrating perception from different information sources and related application technologies for multimodal mental health assessment. Research areas cover brain science, neuroscience, color vision, computer vision, etc., with specific content including: 1) Study on the interaction between color perception and emotion, 2) Brain-computer interface technology based on individual differences in color perception, and 3) Key technologies for applying image, sound, and bio-signals in multimodal data to the diagnosis and assessment of mental health. As a principal investigator on three projects funded by the National Natural Science Foundation of China, he published more than 50 academic papers, granted 10 invention patents and awarded the Second Prize of Yunnan Science and Technology Progress Award in 2023 (ranked 2nd).
Invited Speakers
![]() | ![]() | |
Pavel Loskot ZJU-UIUC Institute, China | Jianfeng Ren University of Nottingham Ningbo China, China | Linlin Yang Communication University of China, China |
Yang Cui University of Science and Technology Liaoning, China | Junyi Wang Northeastern University, China | Xia Yuan Chengdu University of Information Technology, China |
![]() | ![]() | ![]() |
Jing Hu Chengdu University of Information Technology, China | Jia Duan The School of Electronics and Communication Engineering, Sun Yat-sen University, China | Lei Yang Civil Aviation University of China, China |
![]() | ![]() | ![]() |
Shuai Shao Xidian University, China | Yong Wang Harbin Institute of Technology, China | Gang Xu Southeast University, China |
Copyright ©www.icvisp.org 2025-2026 All Rights Reserved.