Professor Yun Yang
BIO: Yun Yang is a professor and doctoral supervisor of the School of Softwareof Yunnan University and a senior member of the China Computer Federation. He was selected as "Overseas High-level Talent Introduction Program", "Young and Middle-aged Academic and Technical Leaders", and "Distinguished Young Scholars" in Yunnan Province, as well as "East Land Scholars" Support Program and "Young Talents Program" of Yunnan University. He serves as a member of the Special Expert Committee of the All-China Federation of Returned Overseas Chinese, a director of the China Information Economics Society, a director of the National Alliance for Artificial Intelligence and Big Data Innovation in Colleges and Universities, an executive member of the Artificial Intelligence and Pattern Recognition Committee of China Computer Federation, an executive member of the Open Source Development Committee of China Computer Federation, and a leader of the expert group for building "Digital Yunnan". He also serves as Director of Yunnan Key Laboratory of Software Engineering, Yunnan Key Laboratory of Data Science and Intelligent Computing, and Kunming Key Laboratory of Data Science and Intelligent Computing, as well as a member of the Editorial Board of Neural Networks, Complex & Intelligent Systems,Journal of Electronic Business & Digital Economics, Journal of Yunnan University (Natural Science Edition). He is a Program Committee member of several international academic conferences, Head of the Software Engineering Discipline of Yunnan University, Head of the Artificial Intelligence Specialty of Yunnan University, and Head of the Intelligent Medical Care Innovation Team of Yunnan University. In 2011, he received his Ph.D. in Computer Science from Manchester University. During his doctoral studies, he was selected for the Overseas Research Students Awards Scheme (ORSAS) funded by the British government. After graduation, he worked as a researcher at the University of Surrey in the United Kingdom and participated in international cooperation projects funded by the Seventh Framework Plan of the European Community.
Speech Title: Research on data and knowledge driven ensemble intelligence and its applications in Smart Healthcare
Abstract: The existing intelligent computing methods can only be applied in single and static scenarios with sufficient and high-quality training samples. Without the support of domain knowledge, they can not realize intelligent activities with high accuracy and strong robustness in complex environments. This report takes ensemble learning as the research route and focuses on the key scientific issues in the field of machine learning such as deep learning, transfer learning, clustering learning, knowledge graphs, etc., to introduce the basic theoretical research findings and their applications in Smart Healthcare.
Professor Zheng'an Yao
Sun Yat-sen University
BIO: The primary research focuses on the theory and applications of partial differential equations, as well as computer science and communication. Research interests encompass fluid mechanics, numerical solutions of partial differential equations, information security, image processing, and data analysis. My previous work includes topics such as one-dimensional compressible flow and hyperbolic conservation laws, multiple solutions of nonlinear elliptic partial differential equations, global solutions of nonlinear parabolic partial differential equations, homogenization theory for evolutionary equations like semilinear parabolic, Schrodinger, and wave equations, alongside computer security and image processing. Additionally, I have made substantial contributions to the theory of reflexive spaces in the field of functional analysis.
Speech Title: The Mathematical theories,methods and systems for the automation ofpathological diagnosis
Abstract: Characteristic pathological images composed of organic combinations of differenttypes of cells are the cornerstone of pathological diagnosis, and applying mathematical theories and methods to define these characteristic images is the starting point of this research. The project intends to explore and improve key mathematical theories and methods for pathological images, including pathological image analysis based on partial differential equations; pathological image secure transmission method based on linear feedback shift registers for remote pathological diagnosis, pathological image privacy protection algorithm based on secure multi-party computation; pathological image and diagnosis report annotation method based on semantic segmentation, parallel optimization of multi-task learning and remote application; etc. In order to apply the above methods to tumor pathological diagnosis, we focus more on solving urgent medical problems such as intraoperative rapid pathological diagnosis including intelligent diagnosis system of tumor pathological images and remote intraoperative pathological image transmission and security; and establishing mathematical models of tumor evolution driven by tumor microenvironment to provide new mathematical tools and application paths for elucidating tumor evolution mechanism and disease pathological classification. The research applies mathematical theories and methods to clinical pathological diagnosis, and helps to establish a new paradigm of research and application through the combination of mathematics and medicine.
Asscociate Professor Yanyan Liang
Macau University of Science and Technology
BIO: Yanyan Liang, Ph.D., Associate Professor. He received his Ph.D. degree from Macau University of Science and Technology in 2009. Since 2009, he has successively served as a postdoctoral researcher, assistant professor and associate professor at the Macau University of Science and Technology. He is currently engaged in research in artificial intelligence, computer vision, and computer architecture. Specific research directions include: general representation learning theory and method; perpetual learning theories and methods; image understanding; abnormal pattern recognition and detection; scene understanding and reconstruction; 3D object reconstruction; deep learning compiler optimization; domain specified architecture. In recent years, he has published more than 50 papers related to the project in top journals and international conferences (including IEEE TPAMI, IEEE TIP, IEEE TITS, IEEE TIFS, IEEE TCYB, IEEE TMM, PR, AJ, MVAP, CVPR, ICCV, IJCAI, AAAI, FG, etc.), and 1 monograph. At present, he served as PI for a number of national, provincial and ministerial key research and development projects.
Speech Title: Research on intelligent diagnostic technology of endoscopic images
Abstract: At present, endoscopic screening technology is the common means of examining gastrointestinal (GI) tract diseases. The diagnostic accuracy, however, relies heavily on the clinical experience of the endoscopist. Unfortunately, cultivating an exceptional endoscopist takes a lengthy period, resulting in a serious shortage of endoscopists in China and their concentration in developed regions. Therefore, it is imperative to develop a computer-aided diagnosis technology based on deep learning to achieve automatic analysis of lesions to help endoscopists precisely judge GI tract diseases. This report will introduce our work on intelligent diagnosis technology of endoscopic images, including a multi-task model that can simultaneously achieve disease classification and segmentation, and improve the performance of the model by taking advantage of convolutional neural networks and Transformers. model performance.
Asscociate Professor Wenjian Liu
City University of Macau
BIO: Dr. Liu Wenjian received his degree in readio engineering from South China University of Technology, as well as master's degree and Ph.D degree in communication and information systems. In 2018 Dr. Liu received his second Ph.D. in applied psychology from City University of Macau. He is currently serving as Vice Dean of the Faculty of Data Science and Ph.D. supervisor. Dr. Liu's research interests in recent years include communication, cross-border applications of big data, big health, big data psychology, and intelligent healthcare.
Speech Title: Intelligent Healthcare and AIGC
Abstract: AI in Computer Vision and Multimodal Data Analysis has garnered significant attention in recent years. This field involves utilizing computer vision and machine learning techniques to analyze various forms of multimodal data, including images, videos, audios, texts, and sensory data. AI-assisted computer vision has been widely applied in object detection, image classification, semantic segmentation, and 3D reconstruction. Meanwhile, the emergence of technologies such as ChatGPT has brought new developments and possibilities to the field of intelligent healthcare, but also new uncertainties and ethical issues. How to use this technology correctly and reasonably has become one of the most urgent issues today.
Inviting & Updating