Keynote Speakers

Big Data Privacy Protection

Prof. Jinjun Chen
Swinburne University of Technology, Australia

Abstract:
While more and more data is being hosted on cloud, privacy protection is becoming increasingly worrying to the community. How to protect personal privacy in a timely manner and in an effective way is challenging given that there is huge amount of data records, data is transferred between different domains as well as different types of data is being hosted together. Especially, data privacy needs to be protected before data can be analyzed. In this talk, we will highlight our research in this area and main challenges we are trying to address.

Short Bio:

0Dr Jinjun Chen is a Professor from Swinburne University of Technology, Australia. He is Deputy Director of Swinburne Data Science Research Institute, and Director of Data Systems and Advanced Analytics. He holds a PhD in Information Technology from Swinburne University of Technology, Australia. His research interests include scalability, big data, data science, data systems, cloud computing, data privacy and security, health data analytics and related various research topics. His research results have been published in more than 140 papers in international journals and conferences, including various IEEE/ACM Transactions.

He received UTS Vice-Chancellor's Awards for Research Excellence Highly Commended (2014), UTS Vice-Chancellor's Awards for Research Excellence Finalist (2013), Swinburne Vice-Chancellor¡¯s Research Award (ECR) (2008), IEEE Computer Society Outstanding Leadership Award (2008-2009) and (2010-2011), IEEE Computer Society Service Award (2007), Swinburne Faculty of ICT Research Thesis Excellence Award (2007). He is an Associate Editor for ACM Computing Surveys, IEEE Transactions on Big Data, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Cloud Computing, as well as other journals such as Journal of Computer and System Sciences.

Personal data meets blockchain: the key to privacy-enhanced sustainable use of our own data

Prof. Qun Jin
Waseda University, Japan

Abstract:
In recent years, blockchain has received a lot of attention as one of the most promising technologies for changing our human society. Big data, particularly, personal big data, is regarded to be of great value. However, use of personal data may pose a critical risk to privacy. In this talk, we discuss the potentials and challenges to use blockchain to protect privacy while unlocking the value toward privacy-enhanced sustainable use of personal data.

Short Bio:
0Qun Jin is a professor at the Networked Information Systems Laboratory, Department of Human Informatics and Cognitive Sciences, Faculty of Human Sciences, Waseda University, Japan. Dr. Jin has been extensively engaged in research works in the fields of computer science, information systems, and social and human informatics. He seeks to exploit the rich interdependence between theory and practice in his work with interdisciplinary and integrated approaches. His recent research interests cover human-centric ubiquitous computing, behavior and cognitive informatics, big data, data quality assurance and sustainable use, personal analytics and individual modeling, intelligence computing, blockchain, cyber security, cyber-enabled applications in healthcare, and computing for well-being. He has published more than 200 refereed papers in the world-renowned academic journals, such as ACM Transactions on Intelligent Systems and Technology, IEEE Transactions on Human-Machine Systems, IEEE Transactions on Systems, Man and Cybernetics: Systems, IEEE Transactions on Learning Technologies, IEEE Systems Journal, and Information Sciences (Elsevier), and international conference proceedings in the related research areas. Dr. Jin has been a general chair, program chair, and keynote speaker for a number of international conferences. He served as editor-in-chief, associate editor, editorial board member, and guest editor for many scientific journals, such as IEEE Transactions on Emerging Topics in Computing, IEEE MultiMedia, IEEE Cloud Computing, Information Sciences (Elsevier), and Future Generation Computer Systems (Elsevier). Dr. Jin is a senior member of Association of Computing Machinery (ACM), Institute of Electrical and Electronics Engineers (IEEE), and Information Processing Society of Japan (IPSJ).

Deep Mixture for Large-Scale Visual Recognition

Jianping Fan
Department of Computer Science
University of North Carolina ¨C Charlotte, USA

Abstract:
In this talk, I will introduce our recent work published on PAMI, which is called deep mixture of diverse experts. First, a two-layer ontology is constructed to assign large numbers of atomic object classes into a set of task groups according to the similarities of their learning complexities, where certain degrees of inter-group task overlapping are allowed to enable sufficient inter-group message passing. Second, one particular base deep CNNs with M outputs is learned for each task group to recognize its M atomic object classes and identify one special class of ¡°not-in-group¡±, where the network structure (numbers of layers and units in each layer) of the well-designed deep CNNs (such as AlexNet, VGG, GoogleNet, ResNet) is directly used to configure such base deep CNNs. For enhancing the separability of the atomic object classes in the same task group, two approaches are developed to learn more discriminative base deep CNNs: (a) our deep multi-task learning algorithm that can effectively exploit the inter-class visual similarities; (b) our two-layer network cascade approach that can improve the accuracy rates for the hard object classes at certain degrees while effectively maintaining the high accuracy rates for the easy ones. Finally, all these complementary base deep CNNs with diverse but overlapped outputs are seamlessly combined to generate a mixture network with larger outputs for recognizing tens of thousands of atomic object classes.

Short Bio:
0Jianping Fan received the MS degree in theory physics from Northwestern University, Xian, China, in 1994 and the PhD degree in computer science from the Chinese Academy of Sciences, China, in 1997. He is now a professor with the UNC-Charlotte. From 1999 to 2001, he was a postdoc researcher with the Department of Computer Science, Purdue University. His research interests include image/video privacy protection, automatic image/video understanding, and large-scale deep learning.

 

1 International Conference on Information Science and Control Engineering