Keynote Speakers
ISCTIS 2024 Keynote Speakers
Prof.You-Fu Li, City University of Hong Kong, China (IEEE Fellow)
You-Fu Li received the B.S. and M.S. degrees in electrical engineering from Harbin Institute of Technology, China. He obtained the PhD degree in robotics from the Department of Engineering Science, University of Oxford in 1993. From 1993 to 1995 he was a research staff in the Department of Computer Science at the University of Wales, Aberystwyth, UK. He joined City University of Hong Kong in 1995 and is currently professor in the Department of Mechanical Engineering. His research interests include robot sensing, robot vision, and visual tracking. In these areas, he has received many awards including a Second Prize of Natural Science Research Award by the Ministry of Education of China, for the work on “Active 3D Computer Vision”, and IEEE Sensors Journal Best Paper Award by IEEE Sensors Council. He has served as an Associate Editor for IEEE Transactions on Automation Science and Engineering (T-ASE), Associate Editor for IEEE Robotics and Automation Magazine (RAM), Editor for CEB, IEEE International Conference on Robotics and Automation (ICRA), and Guest Editor for IEEE Robotics and Automation Magazine (RAM). He is a fellow of IEEE.
| Title: Bio-inspired vision: calibration and tracking for machine vision systems |
| Abstract: In this talk, I will present our research to give some insights gained from our work related to robot vision, from human vision, biologically inspired vision, to machine vision systems. The focus will be on issues in 3D vision and dynamic vision as related to robotic applications. The two issues are addressed in the modeling and imaging process of a compound eye inspired vision system and an event based dynamic vision system. To overcome the limitations of traditional cameras in their low dynamic range, high power consumption, and a tendency to motion blurs, a biologically inspired vision would work asynchronously on pixel levels rather than trapping in frame-rate limitations. This gives rise to a new type of dynamic vision system with its low power consumption, high temporal resolution, and high dynamic range. To process the unconventional output of such vision systems, specific algorithms need to be developed to leverage the rich spatio-temporal information of the event data, to unlock their potential of the new dynamic vision sensors. Some illustrative examples will be presented to show the relevant robotic applications. |
Prof. Ben Niu, Shenzhen University, China
I have long been devoted to the fields of optimization and decision-making of complex management systems and has innovatively constructed a series of swarm intelligent optimization theory and data intelligent analysis methods to meet the needs of multiple scenarios and tasks, especially for health management systems and industrial service systems. I have been recognized in the “Leaders in Innovation Fellowships Programme” by the Chinese Academy of Engineering and the Royal Academy of Engineering and in the Top 100 Global AI Projects by the UNESCO International Research Center for Artificial Intelligence. Additionally, I have been named as a Life Fellow of the Royal Society for Arts, Manufactures and Commerce, and a Fellow of the International Engineering and Technology Institute. I have led 6 National Natural Science Foundation projects (1 Major Project) and published 147 papers in top journals. In recognition of these achievements, I have been ranked within the top 2% of scientists worldwide by Stanford University for 2020-2023 consecutive years.
| Title: Advances in Research on Swarm Intelligence Optimization Methods |
| Abstract: In the "New Generation Artificial Intelligence Development Plan" issued by the State Council, swarm intelligence is one of its five core elements. The fundamental idea of swarm intelligence lies in the ability of numerous simple individuals to collaborate and generate complex intelligent behaviors, thereby harnessing the strengths of the group to tackle optimization problems that traditional optimization algorithms struggle with. This report delves into the evolution of artificial intelligence, elucidating the optimization mechanisms of swarm intelligence from the perspective of complex adaptive systems. It introduces the basic principles, operational operators, fundamental processes, and algorithmic frameworks of several typical swarm intelligence optimization algorithms. Importantly, it highlights the directions for enhancing swarm intelligence optimization methods and their application domains. |
Prof. Guojian Cheng, Xi’an Shiyou University, China
He is a member of CCF of China Computer Society, a member of Microelectronics Committee of CCF of Shaanxi Province, a director of Computer Education Society of Shaanxi Province, a member of SPE of International Society of Petroleum Engineers; a member of European Geophysical Society; an editorial board member of Journal of Xi'an University of Petroleum (Natural Science Edition); and an assessor of National Natural Science Foundation of China. He has been the leader of the master's program of Software Engineering and Theory in the School of Computer Science of Xi'an Petroleum University, the director of the Institute of Intelligent Digital Oilfield, and was honored with the title of Outstanding Returned Scholar in Shaanxi Province in 2009.
| Title: Industrial Large Models and Their Application Prospects |
| Abstract: In the wave of artificial intelligence, Generative Artificial Intelligence (AIGC) and Large Language Models (LLM) are becoming key forces in driving industrial innovation. These technologies have not only caused revolutionary changes in academia but also demonstrated unprecedented application potential in the industrial field. This presentation will first outline the basic concepts of AIGC and LLM, including how they generate new data, text, images, and audio content through deep learning techniques. Then, it will delve into the specific applications of these technologies in the industrial field, such as in automated design, intelligent production processes, supply chain management, customer interaction, and predictive maintenance. These applications are gradually changing the way industrial production is carried out, improving efficiency, reducing costs, and making customized production possible. In the industrial application of large models, we will also face a series of challenges, including data privacy protection, algorithm transparency, model interpretability, and ethical issues. This evolution will analyze these issues and propose possible solutions and future research directions. In addition, it will discuss how to overcome these challenges through interdisciplinary cooperation, combining knowledge in fields such as industrial engineering, data science, and artificial intelligence. Finally, we will look forward to the future of industrial large models, predicting how they will further integrate into the Industry 4.0 ecosystem and their potential impact on intelligent manufacturing and sustainable production. Through continuous technological innovation and interdisciplinary cooperation, we can ensure that these powerful technological tools not only promote industrial development but also bring positive impacts to society. |
Prof. Zhenghao Shi, Xi’an University of Technology, China (IEEE Member)
PhD, Professor, BoD, Member of Academic Committee of Xi'an University of Technology, CCF Distinguished Member, "500 Elite Talents" of Taizhou City, Zhejiang Province, Chairman of Computer Vision Technology Committee of Shaanxi Provincial Computer Society, Vice Chairman of Biomedical Intelligent Computing Committee of Shaanxi Provincial Computer Society, Chairman of the First Branch of China Zhigong Party Committee, Head of Scientific Research Team of Intelligent Image Processing and Application of Xi'an University of Technology. China Zhigong Party Xi'an University of Science and Technology Committee of the first branch, Xi'an University of Science and Technology, "intelligent image processing and application" of the scientific research team leader, the main research direction for machine vision, medical image processing and machine learning, as the first author or corresponding author of the publication and acceptance of 60 academic papers, authorised invention patents 9 (including South Africa invention patents, 1), won the second prize of the Shaanxi Provincial Science and Technology Progress Award of the second two items ( He was awarded the second prize of Shaanxi Provincial Scientific and Technological Progress (ranked first), the second prize of Xi'an Scientific and Technological Progress (ranked first), the second prize of Shaanxi Higher Education School Science and Technology (ranked first), the second prize of Shaanxi Provincial Computer Society Scientific and Technological Progress (ranked first), and was awarded the 2022 Wiley Wiley China High Contribution Authors in Open Science Award, and was also awarded the 2022 Advanced Worker Award of the China Zhigong Party in Shaanxi Province. ).
| Title: Sleep Apnea Syndrome Detection based on Transformer |
| Abstract: Obstructive sleep apnea (OSA) is a common sleep disorder that is an important factor leading to cardiovascular diseases such as hypertension, heart failure, and stroke. Timely detection and treatment of OSA are of great significance in ensuring people's life and health. This report will introduce the research progress of this issue based on our practical experience in this field in the past two years, with a focus on reporting our work and achievements in using the Transformer method for OSA detection. |
Prof. Junzhao Du, Xidian University, China
Junchao Du, Professor of School of Computer Science and Technology at Xidian University, a leading professor of "Huashan Scholars" of Xidian University, a national talent, the executive deputy director of Engineering Research Center of Blockchain Technology Application and Evaluation，Ministry of Education, the head of the scientific and technological innovation team of Shaanxi Province, the chief scientist of the "scientist+engineer" team of QinChuangYuan, Shaanxi Province, the chairman of Yulin "Industrial Internet Association", the executive director of ACM Xi'an Branch, the organizing committee of TURC, and the deputy secretary general of the alumni association of Xdian ICT. Received the Second Prize of Technology Invention from the Ministry of Education, the Special Prize and the First Prize of Science and Technology in Higher Education in Shaanxi Province, in 2022/2021/2019 (First Completion). Publish the National Key Planning Textbook "ZigBee Technology: Principles and Practice". Undertake multiple natioanl and provincial projects, such as Key projcet of NSFC. Published multiple papers at international flagship conferences such as ACM Ubicomp, ACM Mobisys, and won the Distinguished Paper Award at the 2017 ACM Ubicomp (CCF Class A). Develop AIoT technology and systems for locatilzaiton, tracking and early warning, multimedia communication and intelligent service systems, and promote the application to important national industries. Collaborating with Wuxi Jiangnan Institute and NUDT, we have developed virtualization evaluation technology for domestically produced "Shenwei" and "Feiteng" processors, and led the development of the Chinese Electronics Society's Standard (T/CIE106-2021).
Research Fellow Yi Wang,Northwestern Polytechnical University, China
Yi Wang is a research fellow in Signal and Information Processing, School of Electronics and Information, Northwestern Polytechnical University. She was a postdoctoral fellow at the University of North Carolina at Chapel Hill, USA, in 2009-2010 and a visiting scholar at University College London, UK, in 2011. As the main technical backbone, she presided over and participated in the projects of National Natural Science Foundation of China, National High-tech R&D Program (863 Program), National Key Research and Development Program of China, the Key Research and Development Project of Shaanxi Province of China, Natural Science Basic Research Plan in Shaanxi Province of China. She has published more than 100 papers in domestic and international journals and conferences such as Expert Systems with Applications, Neuroimage, Neuroinformatics, Science Bulletin, Chinese Journal of Image and Graphics, etc., including one ESI Highly Cited, six authorized national invention patents, three software copyrights. She has been awarded the third prize of Excellent Academic Paper in Natural Science of Shaanxi Province, the first prize of Science and Technology of Shaanxi Higher Education Institutions, and the third prize of Science and Technology of Shaanxi Province, etc. She is now a member of the Chinese Society of Image and Graphics and the Chinese Society of Biomedical Engineering, the executive director and secretary-general of the Shaanxi Society of Image and Graphics, and a council member of the Shaanxi Society of Biomedical Engineering.
| Title: Neonatal White Matter Damage Analysis Using DTI Super-Resolution and Multi-Modality Image Registration |
| Abstract: Punctate White Matter Damage (PWMD) is a common neonatal brain disease, which can easily cause neurological disorder and strongly affect life quality in terms of neuromotor and cognitive performance. Especially, at the neonatal stage, the best cure time can be easily missed because PWMD is not conducive to the diagnosis based on current existing methods. The lesion of PWMD is relatively straightforward on T1-weighted Magnetic Resonance Image (T1 MRI), showing semi-oval, cluster or linear high signals. Diffusion Tensor Magnetic Resonance Image (DT-MRI, referred to as DTI) is a noninvasive technique that can be used to study brain microstructures in vivo, and provide information on movement and cognition-related nerve fiber tracts. Therefore, a new method was proposed to use T1 MRI combined with DTI for better neonatal PWMD analysis based on DTI super-resolution and multi-modality image registration. First, after preprocessing, neonatal DTI super-resolution was performed with the three times B-spline interpolation algorithm based on the Log-Euclidean space to improve DTIs' resolution to fit the T1 MRIs and facilitate nerve fiber tractography. Second, the symmetric diffeomorphic registration algorithm and inverse b0 image were selected for multi-modality image registration of DTI and T1 MRI. Finally, the 3D lesion models were combined with fiber tractography results to analyze and predict the degree of PWMD lesions affecting fiber tracts. Extensive experiments demonstrated the effectiveness and super performance of our proposed method. This streamlined technique can play an essential auxiliary role in diagnosing and treating neonatal PWMD. |
