Keynote Speech 1:
Preserving privacy in the digital age: Differential privacy and its applications


Abstract:

Over the past two decades, digital information collected by corporations, organisations and governments has created huge amount of datasets, and the speed of such data collection has increased exponentially over the last a few years because of the pervasiveness of computing devices. However, most of the collected datasets are personally related and contain private or sensitive information. Even though curators can apply several simple anonymization techniques, there is still a high probability that the sensitive information of individuals will be disclosed. Privacy-preserving has therefore become an urgent issue that needs to be addressed in the digital age.
Differential privacy is one of the most prevalent privacy models as it provides a rigorous and provable privacy notion that can be implemented in various research areas. In this presentation, we will start with privacy breaches and privacy models, and introduce the basic concept of differential privacy. We then will forcus on the applications of differential privacy in various senarios in which we have been working on, including Location privacy, Recommender systems, Tagging systems, and Correlated datasets. We will then finalise the talk by outlining the privacy challenges in the era of big data.

Professor Wanlei Zhou

Professor Wanlei Zhou

Head, School of Software, University of Technology Sydney, Australia

Professor Wanlei Zhou received the B.Eng and M.Eng degrees from Harbin Institute of Technology, Harbin, China in 1982 and 1984, respectively, and the PhD degree from The Australian National University, Canberra, Australia, in 1991, all in Computer Science and Engineering. He also received a DSc degree (a higher Doctorate degree) from Deakin University in 2002. He is currently the Head of School of Software in University of Twechnology Sydney (UTS). Before joining UTS, Professor Zhou held the positions of Alfred Deakin Professor, Chair of Information Technology, and Associate Dean (International Research Engagement) of Faculty of Science, Engineering and Built Environment, Deakin University. Professor Zhou has been the Head of School of Information Technology twice (Jan 2002-Apr 2006 and Jan 2009-Jan 2015) and Associate Dean of Faculty of Science and Technology in Deakin University (May 2006-Dec 2008). Professor Zhou also served as a lecturer in University of Electronic Science and Technology of China, a system programmer in HP at Massachusetts, USA; a lecturer in Monash University, Melbourne, Australia; and a lecturer in National University of Singapore, Singapore. His research interests include security and privacy, bioinformatics, and e-learning. Professor Zhou has published more than 400 papers in refereed international journals and refereed international conferences proceedings, including many articles in IEEE transactions and journals.

Web link
 Dr Tianqing Zhu

Dr Tianqing Zhu

School of Software, University of Technology Sydney, Australia

Dr Tianqing Zhu received her BEng and MEng degrees from Wuhan University, China, in 2000 and 2004, respectively, and a PhD degree in Computer Science from Deakin University, Australia, in 2014. Dr Tianqing Zhu is currently a Senior Lecturer in the School of Software in University of Technology Sydney, Australia (UTS). Before joining UTS, she served as a lecturer in School of Information Technology, Deakin University, Melbourne Australia from 2014 to 2018 and a lecturer in Wuhan Polytechnic University, China from 2004 to 2011. Her research interests include privacy preserving, data mining and network security. She has won the best student paper award in PAKDD 2014 and was invited to give tutorials on privacy preserving in a number of international conferences including PAKDD 2015, SociaSec 2015, GPC 2017, etc.

Web link

Plenary Speech:
Evolutionary Optimization in Algebraic Time Series Prediction � Problems and Applications


Abstract:


Time series forecasting is a challenging problem in many fields of science and engineering. In general, the main objective of any predictor is to build a model of the process and then use this model on the last values of the time series to extrapolate past behaviour into the future. A class of novel short-term time series prediction algorithms will be presented in this talk. The proposed predictors with internal, external and mixed smoothing employ target functions which help to achieve the necessary balance between the roughness of the algebraic prediction and the smoothness of the prediction based on moving averaging. Such balancing results into a difficult optimization problem which is solved using machine learning techniques.
 Prof Minvydas Ragulskis

Professor Prof Minvydas Ragulskis

Professor at Department of Mathematical Modelling, Kaunas University of Technology, Lithuania

Minvydas Ragulskis is a full professor at Department of Mathematical Modelling, Kaunas University of Technology, Lithuania. He is a Fellow of Lithuanian National Academy of Sciences and serves as an invited expert at various National and International Committees including Research Executive Agency, Brussels. M.Ragulskis takes the position of the High-end Foreign Expert of Jiangsu Province at Hohai University and the position of Honorary Professor at Jinan University, P.R. China. He has published over 100 papers in International Journals and has been invited as a Key-note speaker at a number of International Conferences.

Web Link

Keynote Speech 2:
Learning recurrent neural network architectures


Abstract:


Recurrent neural networks are a powerful means to cope with time series. The canonical approach to neural network training is to specify an architecture, and then use data to learn the parameters of the model, i.e., the strength of connections between units. We show that already linearly activated recurrent neural networks can approximate any time-dependent function f(t) given by a number of function values. The approximation can effectively be learned by simply solving a linear equation system; no backpropagation or similar methods are needed. Furthermore, the network size can be reduced by taking only the most relevant components of the network. Thus, in contrast to others, our approach not only learns network weights but also the network architecture. The networks have interesting properties: In the stationary case they end up in ellipse trajectories in the long run, and they allow the prediction of further values and compact representations of functions. We demonstrate this by several experiments, among them multiple superimposed oscillators (MSO) and robotic soccer. Predictive neural networks outperform the previous state-of-the-art for the MSO task with a minimal number of units.
 Dr Oliver Obst

Dr Oliver Obst

Associate Professor In Data Science, Deans Unit School Of Computing, Engineering & Math, Western Sydney University, Australia

Dr Oliver Obst is Associate Professor in Data Science at Western Sydney University, in Parramatta, Sydney, Australia, and the Director of Research, Quality, and Innovation for the School of Computing, Engineering, and Mathematics. Previously, he was team leader of the Data Mining Team at CSIRO (Data61), where he worked from Aug 2007 to Jan 2016, a lecturer at the University of Newcastle (2006/07), and a Post-doc at the University of Bremen, Germany (2006). He received a PhD in Artificial Intelligence (2006), and a Masters Degree in Computer Science from the University of Koblenz-Landau, in Koblenz, Germany.
Oliver's research interests include machine learning, neural networks and information theoretic approaches. He has experience in data analytics with applications in sensor networks, energy, astronomy, and robotics. He is an a member of the board of trustees of the RoboCup federation (an organisation to foster research and education in AI), and served as a PC member of scientific conferences such as NIPS, IJCAI, and AIStats.

Web Link

Keynote Speech 3:
Multimodal Medical Image Analysis Based on Machine Learning Techniques


Abstract:


Traditional approaches in biology generally look at only a few aspects of an organism at a time and try to analyse diseases, by molecularly dissecting them, and studying them part by part with the expectation, that the sum of knowledge of parts can explaining the underlying cause of disease. Seldom has this been a successful strategy to understand the causes and cures for complex diseases.
Major advances in machine learning, artificial intelligence and data engineering are beginning to have an impact on how to uncover the complex interactions between large data and information collected in medical domain, particularly in medical and radiological image analytics areas, involving multiple data sources and imaging modalities. In this presentation, I will show examples of how machine learning and deep learning, has led to major improvements in automated medical data analytics fields, using large collections of medical data and multiple modality imaging data sources, especially for computer aided diagnosis of disease.
 Dr Oliver Obst

Dr Girija Chetty

Program Director (IT) Associate Professor in Software Engineering, University of Canberra, Australia

Dr. Girija Chetty has a Bachelor’s and Master’s degree in Electrical Engineering and Computer Science from India, and PhD in Information Sciences and Engineering from Australia. She has more than 35 years of experience in Industry, Research and Teaching from Universities and Research and Development Organizations from India and Australia and has held several leadership positions including Head of Software Engineering and Computer Science, and Course Director for Master of Computing (Mainframe) Course. Currently, she is an Associate Professor, Program Director (Information Technology) and the Head of the Multimodal Systems and Information Fusion Group in HCC research Centre in Faculty of SciTech, at University of Canberra, Australia, convenes several information technology courses, and leads a research group with several PhD students, Post Docs, research assistants and regular International and National visiting researchers. She is a Senior Member of IEEE, USA, and Senior Member of Australian Computer Society, and her research interests are in the area of multimodal systems, sensor fusion, big data analytics, Internet of Things, computer vision, pattern recognition, data mining, and medical image computing. She has given several keynote and invited plenary speeches on cutting edge information technology areas related to her research interests in several International conferences and published extensively with more than 200 fully refereed publications and more than 1000 citations in several indexed research outlets, including invited book chapters, edited books, high quality conference and journals, and she is in the editorial boards, technical review committees and regular reviewer for several IEEE, Elsevier and IET journals. She actively promotes Science, Technology and Engineering careers to potential students of information technology and engineering programs.

Web Link




Proudly Sponsored by



Western Sydney University


Copyright © GCSTMR.All right reserved.Created by SBsoftcodings