Prof. Chee Peng Lim
Lim Chee Peng completed his Ph.D. degree at the Department of Automatic Control and Systems Engineering, University of Sheffield, UK, in 1997. His research focuses on the design and development of machine learning-based models for data analytics and decision support, with application to medical prognosis and diagnosis, fault detection and classification, and manufacturing process optimisation. He has published over 450 technical articles in journals, conference proceedings, and books, and received 8 best paper awards in international conferences. He has also received many prestigious fellowships for international research collaboration, viz., Australia-India Senior Visiting Fellowship (by Australian Academy of Science), Australia-Japan Emerging Research Leaders Exchange Program (by Australian Academy of Technology and Engineering), Commonwealth Fellowship (at University of Cambridge), Fulbright Fellowship (at University of California, Berkeley), and Visiting Scientists Program of Office of Naval Research Global, USA (at Harvard University and Stanford University). In collaboration with co-workers, he has developed innovative software systems that have won various awards, which include Gold Medal at Pittsburgh Invention and New Product Exposition, USA, Gold Medal and Special Award at British Innovation Show, UK, Gold Medal at Geneva International Exhibition of Inventions, Switzerland, and Silver Prize at Open Source Software World Challenge, South Korea.
Speech Title: "Machine Learning for Signals Analytics: Principles and Applications"
Abstract: Machine learning (ML) is a broad discipline that encompasses a variety of methodologies inspired by human and/or animal intelligence. In this talk, research on the design, development, and application of ML-based models for data and signals analytics will be presented. Specifically, various ML-based models, which include artificial neural networks, fuzzy systems, evolutionary algorithms, and decision trees will be explained. Several essential principles and properties of ML-based models for applications, which include knowledge elicitation and trust measurement, will be exemplified. Real-world applications ranging from healthcare to industrial domains to ascertain the efficacy of ML-based models for decision support utilising data and signals analytics will be demonstrated.
Prof. Kurban Ubul
Kurban Ubul is a Professor at School of Information Science and Engingeering, Xinjiang University, China where he conducts research in pattern recognition, computer vision, and biometrics recognition. He is a member of several professional committees of China Computer Federation(CCF), Chinese Association for Artificial Intelligence(CAAI), China society of Image and Graphcis(CSIG) and Chinese Association of Automation(CAA), and he is a member of IEEE, IAPR and IAENG. He is a reviewer of IEEE THMs, IET biometrics, IJITM and other magazines. He was a TPC chair of CCBR2018, and area chair of PRCV2019. He is a TPC member or reviewer of many conference such as ICPR, ICDAR, CCFAI, CCBR and so on.
Speech Title: "Recent Advance in Script Identification of Central Asian Multi-script Document Images"
Abstract: With the widespread of Internet and digitized processing of various script documents worldwide, multi-script document images must be identified and processed in today's globalization environment. As the front-end technology of Optical Character Recognition (OCR), script identification concerns methods for identifying different scripts in multi-lingual, multi-script documents. In this report, the writing systems and the vital processes in script identification are addressed firstly. Then our work for script identification of Central Asian printed document images is summarized. Finally, it is concluded the problems to be solved and future work trends in script identification of multi-script document images.