Professor Jiankun Hu

School of Engineering and Information Technology, UNSW Canberra (Australian Defence Force Academy), Australia

Dr. Jiankun Hu is a full professor at the School of Engineering and IT, University of New South Wales (UNSW) Canberra (also named UNSW at the Australian Defence Force Academy (UNSW@ADFA), Canberra, Australia. He is the invited expert of Australia Attorney-Generals Office. Prof. Hu has served at the Panel of Mathematics, Information and Computing Sciences (MIC), ARC ERA (The Excellence in Research for Australia) Evaluation Committee 2014. Prof. Hu's research interest is in the field of cyber security covering intrusion detection, sensor key management, and biometrics authentication. He has many publications in top venues including IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Computers, IEEE Transactions on Parallel and Distributed Systems (TPDS), IEEE Transactions on Information Forensics & Security (TIFS), Pattern Recognition, and IEEE Transactions on Industrial Informatics. He is currently the Editor of the following international journals: (1) IEEE Transactions on Information Forensics and Security, (2) Journal of Security and Communication Networks, John Wiley; (3) Security and Privacy, Wiley. (4) IET Cyber-Physical Systems: theory & applications. (5) Area Editor for KSII Transactions on Internet and Information Systems.

Speech Title: Privacy-preserving Big data Analytics: A Comprehensive Survey

Abstract: With the emergence of social network, Internet of Things (IoTs), and outsourced cloud computing, we are embracing an era of big data. Big data analytics can bring huge cost savings, and identify hidden patterns in the big data. However, big data also has a big issue of privacy concern as big data analytics can reveal individual’s personal behaviour, and other sensitive information. Therefore, it is vital to have suitable techniques for privacy-preserving big data analytics. In this talk, we will report on the latest developments in this field and discuss open challenges for future research.


Professor Yizhou Yu

Department of Computer Science, The University of Hong Kong, Hong Kong

Yizhou Yu is a full professor in the Department of Computer Science at the University of Hong Kong. He was first a tenure-track and then a tenured professor at University of Illinois, Urbana-Champaign (UIUC) for 12 years. He has also collaborated with Google Brain and Microsoft Research in the past. He received his PhD degree in computer science from the computer vision group at University of California, Berkeley. He also holds a MS degree in applied mathematics and a BE degree in computer science and engineering from Zhejiang University.

Prof Yu has made many important contributions to AI and visual computing, including deep learning, computer vision, image processing, and computer graphics. He is a recipient of 2002 US National Science Foundation CAREER Award, 2007 NNSF China Overseas Distinguished Young Investigator Award, ACCV 2018 Best Application Paper Award, ACM SCA 2011 and 2005 Best Paper Awards, and 1998 Microsoft Graduate Fellowship. Innovative technologies co-invented by him has been frequently adopted by the film and special effects industry. He has more than 150 publications in international conferences and journals. His current research interests include deep learning, computer vision, biomedical data analysis, computational visual media, and geometric computing. He is an IEEE fellow and ACM distinguished member.,

Speech Title: Machine Learning for Image Understanding and Medical Image Analysis

Abstract: In recent years, we have witnessed technological breakthroughs in the fields of deep learning and image understanding. In this talk, I share a few examples of my recent work on machine learning based image understanding and medical image analysis. In the first part on image understanding, I present projects on fine-grained image classification based on either transfer learning or weakly supervised learning, large-scale hierarchical image classification, language-guided object identification in images as well as weakly supervised learning for object detection and semantic segmentation. In the second part on medical image analysis, I present projects on 3D medical volume segmentation based on global guidance and progressive fusion as well as automated chest X-ray interpretation using mixed supervised learning

Professor En-Bing Lin

Central Michigan University, USA

Dr. En-Bing Lin is a full Professor of Mathematics at Central Michigan University, USA. He is a former mathematics department chair at the University of Toledo and Central Michigan University. He has taught and visited at several institutions including Massachusetts Institute of Technology, University of Wisconsin-Milwaukee, University of California, Riverside, University of Toledo, UCLA, and University of Illinois at Chicago. He received his Ph. D. in Mathematics from Johns Hopkins University. His research interests include Data Analysis, Image Processing, Information Theory, Bioinformatics, Applied and Computational Mathematics, Wavelet Analysis and Applications, and Mathematical Physics. He has supervised a number of graduate and undergraduate students. Dr. Lin serves on the editorial boards of several mathematics and computational journals. He has served on several academic committees of regional and national associations. He has organized several special sessions at regional IEEE conference and American Mathematical Society national and regional meetings. He received many honors and awards including Central Michigan University Distinguished Service Award as well as many research, travel and education grants.

Speech Title: Big Data Analytics, Generalized Fuzzy Rough Approximations and Comparisons of Gene Variants

Abstract: We begin with a brief survey of current trends of big data analytics and present some applications in biology, business and industry. As a powerful artificial intelligence tool, rough set theory (RST) is of fundamental importance in dealing with many aspects of processing information systems and problem solving in big data analytics. We represent a data set of an information system as a table and show how we pass from classical RST to variable precision generalized rough set theory (VPGRS). We use minimal neighborhood systems to characterize lower and upper approximations for VPGRS-model. Furthermore, we extend RST to fuzzy rough set theory via a general approach to the fuzzification of rough sets. We develop a generalized fuzzy rough approximation by incorporating VPGRS with fuzzy rough sets and show how to determine the discernibility threshold for a reflexive relational decision system in the variable precision generalized fuzzy rough set model. As applications, we propose some parallel distributed computations to analyze the systems. It has many applications in a number of different areas, such as engineering, environment, banking, medicine, bioinformatics, pattern recognition, data mining, machine learning and others. We also use different techniques to compare some gene variants and obtain approximation and detail information of the numerical representations of gene variants.




© Copyright 2017-2019 ICCTS All rights reserved.