Keynote & Plenary Speakers


The Hong Kong Polytechnic University, Hong Kong (香港理工大学)  

Biography: Professor Jiannong Cao is a chair professor of the Department of Computing at The Hong Kong Polytechnic University. He is also the director of the Internet and Mobile Computing Lab in the department. Before joined The Hong Kong Polytechnic University in 1997, he has been on faculty of computer science in James Cook University and The University of Adelaide in Australia, and the City University of Hong Kong. Professor Cao is currently an adjunct professor ofSun Yat-Sen University. He also held several adjunct and visiting positions, including an adjunct chair professor of Central South University; an adjunct professor of National University of Defense Technology, Northeastern University, Shanghai Jiao Tong University, Northwest Polytechnic University, and Beijing Jiaotong University; a guest professor of Shenzhen University; a visiting research professor in the National Key Lab for Novel Software Technology, Nanjing University of China; a visiting fellow in the School of Computer Science and Engineering, Nanyang Technological University of Singapore; a visiting scholar of the Institute of Software at Chinese Academy of Science, and Peking University Overseas Scholar Lecture Program.
Professor Cao’s research interests include parallel and distributed computing, wireless networks and mobile computing, big data and cloud computing, pervasive computing, and fault tolerant computing. He has co-authored 5 books in Mobile Computing, co-edited 9 books, and published over 500 papers in major international journals and conference proceedings (including top journals IEEE Network, TC, TMC, TPDS, TWC, TDSC, JSAC, TCOM, TSE; ACM TOSN, TOIT, TAAS; and PMCJ, TON, JPDC, and top conferences INFOCOM, ICNP, PERCOM, WWW, DSN, ICDCS, SRDS).  

Title of Speech: Cross-domain Big Data Processing and Analytics 

Abstract: Big data analytics using cross-domain datasets allow us to study phenomena by fusing views from multiple angles, facilitating identifying meaningful problems and discovering new insights. However, we need methods and techniques to solve the challenges like heterogeneity, uncertainty and high dimensionality in analyzing cross-domain datasets. In this talk, I will share our work of analyzing datasets from multiple domains to uncover the underlying patterns, correlations and interactions to address human and urban dynamics issues like predict traffic congestions, optimize demand dispatching in emerging on-demand services, and designing wireless networks.  


Prof. Hayato YAMANA

Waseda University, JAPAN 

Biography: Hayato YAMANA received his Dr. Eng. degree at Waseda University in 1993. He began his career at the Electrotechnical Laboratory (ETL) of the former Ministry of International Trade and Industry (MITI), and was seconded to MITI's Machinery and Information Industries Bureau for a year in 1996. He was subsequently appointed Associate Professor of Computer Science at Waseda University in 2000, and has been a professor since 2005. From 2003 to 2004, he was IEEE Computer Society Japan Chapter Chair. Since 2015, he has been director of IPSJ (Information Processing Society of Japan) and vice chairman of information and communication society of IEICE (the institute of electronics, information and communication engineers). At Waseda University, he has been deputy Deputy Chief Information Officer and WasedaX project director since 2015. His research area is big data analysis. Currently, his group engages in Japanese government funded project called “Secure Data Sharing and Distribution Platform for Integrated Big Data Utilization - Handling all data with encryption.” For more information, please refer to  

Title of Speech: Fully Homomorphic Encryption in Cloud Computing  

Abstract: In this talk, I will pick up a privacy issue that effects to our society followed by introducing secure computation using fully homomorphic encryption (FHE) in cloud computing. IDC reported that “At least 40 percent of big data requires some level of security, from privacy protection to full-encryption.” Especially, medical information should be kept strictly secured. To handle such sensitive data, FHE is one of the key technology to realize secure computation, i.e., handling all data with encryption throughout the data life cycle. Curranty, we are engaged in Japanese government awarded project called “Secure Data Sharing and Distribution Platform for Integrated Big Data Utilization” which continues until March, 2021. Our final goal is to speed-up encrypted calculation over 1,000 times over current methods by theoretical and computer architecture optimization-approaches. Although the bottleneck of FHE is large time and space complexity, we have successfully achieved over 400 times speed-up for data mining in comparison with the state-of-the-art method. Besides, we have implemented a secure search technique without leaking any information to cloud servers. In this talk, we will introduce its current status and the future direction of secure computation. 


Prof. Hongwei Du

California State University, East Bay, USA (加州州立大学东湾校区)  

Biography: Professor Hongwei Du is the Coordinator of Information Technology Management Program in the College of Business and Economics at California State University, East Bay. He holds a Ph.D. in Operations Research from Florida Institute of Technology, a M.S. in Computer Science from Bowling Green State University and a M.S. in System Engineering from Beijing Institute of Automation. His works have been published in the California Journal of Operations Management, the European Journal of Information Systems, the International Journal of Innovation and Learning, the International Journal of Intercultural Information Management, the International Journal of Information and Decision Science, the International Journal of Electronic Healthcare, the Journal of Economic Studies, and the International Review of Business Research Papers.  

Title of Speech: Professional Sports meet Big Data 

Abstract: Analytics and Big Data have been started their journey in many industries, and now they are on the edge of scoring major points in professional sports. Over the past few years, the world of sports has experienced an explosion in the use of analytics and Big Data. Today, every major professional sports team either has an analytics department or analytics experts on staff. From coaches and players to front offices and businesses, analytics can make a difference in improving their team, signing contracts, understanding fans behavior, preventing injuries and gaining competitive advantages. It has impacted both players’ performance and viewers’ experience in more ways than we can imagine, and it has taken the field of professional sports to a new level.
Big data is already revolutionizing the National Basketball Association (NBA). The rise of big data is pitting the old school against the new school as the NBA undergoes its analytics revolution. The NBA’s new camera system, SportVu, is only the latest example of the power and pervasiveness of big data. This presentation mainly focuses on the NBA’s best team, the Golden State Warriors. Some specific talks are players analytics of their offensive/defensive rebounds, two-point and three-point shooting, steals and fouls per game. More talk also on how big data help owners and coaches recruit players, improve new training and practice methods, and execute game plans.
In short, big data and analytics is the ultimate weapon in the field of sports that has the power to enhance professionalism, and to make it more enjoyable than before.  

Prof. Neil Bergmann

University of Queensland, Australia  

Biography: Neil W. Bergmann has been Professor of Embedded Systems in the School of Information technology and Electrical Engineering at the University of Queensland, Brisbane, Australia since 2001. He has bachelor degrees in electrical engineering and computer science from University of Queensland, and a PhD in Computer Science from University of Edinburgh, UK, in 1984. His research interests are in computer systems, wireless sensor networks, and in understanding the data streams that those sensors collect. He is a member of IEEE, and a Fellow of the Institution of Engineers, Australia.  

Title of Speech: Location, Location, Location: Understanding human mobility through data analytics 

Abstract: Technology trends such as Internet-of-Things, Cloud Computing, Big Data, Machine Learning and Data Analytics all affect our understanding of the world. These trends mean that an enormous amount of data is captured from people’s everyday interactions with digital systems, a proportion of that data is stored, and an even smaller amount of that data is analysed to gain useful social insights.
Human mobility within cities and between cities is an area of increasing interest. People follow regular patterns of movement from home to work, home to shopping, home to school, etc. However human mobility also includes aspects of randomness, as people visit new locations, attend special events or simply explore their environment. Understanding both the regularity and randomness of movement can provide insights that are useful for transport planning, infrastructure management, disease control, and emergency responses.
This talk will look at some of the data sources that can be used for monitoring location and mobility, and also some of the insights that can be gained from analysis of this data. This work will include a summary of some of the work done in this area by our research students at University of Queensland.  


Invited Speaker 

Prof. Changxu (Sean) Wu

University of Arizona, USA  

Biography: Dr. Changxu (Sean) Wu received his Ph.D. degree in Industrial and Operational Engineering from the University of Michigan-Ann Arbor (2007). He is currently a tenured full professor of Department of Systems and Industrial Engineering University of Arizona, starting from August 2017. Dr. Wu directs the Cognitive System Lab and he is interested in integrating cognitive science and engineering system design, especially modeling human cognition system with its applications in system design, improving transportation safety, promoting human performance in human-computer interaction, and inventing innovative sustainable and smart energy systems with human in the loop.
Dr. Wu has published 116 papers in the field including 80 journal papers, 36 conference papers, 1 book chapter, and 2 patents in intelligent system design authorized. The journal papers include IEEE Transactions on Systems, Man, and Cybernetics (Part A), IEEE Transactions on Intelligent Transportations Systems, Psychological Review (Impact Factor: 9.02), ACM Transactions on Computer-Human Interaction, International Journal of Human-Computer Studies, as well as several other journals. He was the Chair of Human Performance Modeling Technical Group of Human Factors and Ergonomics Society (HFES) in USA. He is also Associate Editors for IEEE Transactions on Intelligent Transportations Systems, IEEE Transaction on Human-Machine Systems, and Behaviour & Information Technology. He received the Senior Researcher of the Year Award from the Dean of School the Engineering & Applied Sciences at SUNY Buffalo and Outstanding Student Instructor Award from the American Society of Engineering Education (ASEE).  

Title of Speech: An Innovative Computer Vision System for Drunk Driving Detection 

Abstract: A pressing public health concern world-wide, drunk driving has persistently caused great losses of lives each year, despite recent advancements in sensor technology put forth to deter this criminal behavior. In this paper, we present an innovative surveillance system for drunk driving detection. Making use of a stereo camera as the sole sensing device, it employs a 2D-3D hybrid approach for accurate vehicle detection in both day and night scenarios. Elaborate experimental results from our field study confirm the effectiveness of this system and its potential application in the transportation safety domain. Not only is our system able to detect, track, and accurately estimate the speeds of vehicles, but it is also capable of identifying at a reasonable rate drivers that might be under the influence. The driving features indicative of drunk driving were determined by analyzing data collected from our in-lab driving simulator STISIM. Subsequently, the system was modified to be able to extract those features, namely vehicle lateral deviation, headlights, turning radius, following distance, as well as instantaneous and average speeds.