Tel: +86-28-86528758
9:30--18:00, Monday to Friday (GMT+8 Time Zone)
The 8th International Conference on Intelligent Computing and Applications (ICICA 2019)
Swinburne University of Technology     January 16-18, 2019

Keynote Speakers of ICICA 2018


Prof. Ghassan Beydoun
University of Technology Sydney, Australia

Professor Ghassan Beydoun is currently based at the Faculty of Engineering and Information Technology in University of Technology Sydney, where he is also deputy Head of School (Research) Systems, Management and Leadership at the University of Technology Sydney. He is also an adjunct senior research fellow at the School of Information Systems, Management and Technology at the University of New South Wales, an associate editor of the International Journal of Intelligent Information Technologies (IJIIT) and an Editorial member of the Journal of Software. He received a degree in computer science and a PhD degree in knowledge systems from the University of New South Wales in 2000. His research interests include multi agent systems applications, ontologies and their applications, and knowledge acquisition. He is currently working on a project sponsored by an Australian Research Council Discovery Grant to investigate the best uses of ontologies in developing methodologies for complex systems and another project with SES on exploring the use of ontologies for flood management decision support. He has authored more than 100 journal and conference papers in these areas over the past 15 years. His most recent publication appeared in IEEE Transactions of Software Engineering, Information Systems journal, Information and Management, International Journal of Human Computer Studies, Information Processing and management and others.


Using Agent Based Analysis to Manage Complexity in Disaster Management Planning

Abstract: Over the past eight years, we have undertaken research to enable the unification of DM knowledge across various disaster types and jurdisctions. In this talk, I will describe our approach which enables partitioning a DM problem into sub-problems. To partition the problem, an agent based modelling process is applied in combination with a DM metamodel. Decision makers can then develop a variety of domain solutions models based on mixing and matching solutions for sub-problems indentified using the metamodel. In developed countries, for recurring disasters (e.g. floods), there are dedicated document repositories of Disaster Management Plans (DMP) that can be accessed as needs arise. I will describe an agent-based knowledge analysis method to convert DMPs into a collection of knowledge units that can be stored into a unified repository based on the unifiying metamodel. The repository of DM actions then enables the mixing and matching knowledge between different plans. We use the flood management plans used by SES (State Emergency Service), an authoritative DM agency in NSW (New State Wales) State of Australia to illustrate and give a preliminary validation of the approach. It is illustrated using DMPs along the flood prone Murrumbidgee River in central NSW. I will also conclude by examining the opportunities to generalise the approach to various knowledge integration and sharing in complex domains.


Prof. William Guo
Central Queensland University, Australia

Professor William Guo teaches and researches in computation and applied mathematics at Central Queensland University Australia (CQU). He was the Dean of the School of Engineering and Technology at CQU from Jan 2014-Jan 2015, and the Deputy Dean of the School from Feb 2013-Jan 2014. He has significant experience in academic governance through his services in various committees and boards since 2009, including CQU Education Committee (2011-2012), CQU Academic Board (2013-2014), and Australian Council of Deans of ICT (2013-), and as an Executive Member of Australian Council of Professors and Heads of IS (2012-). His teaching over the past 13 years has covered data structures and algorithms analysis, computational intelligence, systems analysis and architecture, IT/IS project management, e-Business, digital forensics, information security, research methods, and engineering mathematics. He was the recipient of CQU Vice-Chancellor’s Award for Good Practice in Learning and Teaching (2012) and Commendation in Student Voice Awards (2014). His research interests include computational intelligence, image processing, bioinformatics, big data modelling and simulation. He has published more than seventy papers in international journals and conference proceedings, and a new text (published by Pearson) in advanced engineering mathematics in 2014. He has supervised research higher degree students to completion. He is a member of IEEE, ACM, ACS, and Australian Mathematics Society (AUSTMS).


What can a reviewer do on your academic work?

Abstract: In anyone’s academic life, you will definitely serve as the two roles in research domain, either as an author who receives comments from reviewers on your work, or as a reviewer who provides comments on other’s work in the same discipline. Although it is debatable on what is meant to be a good, a fair, or a bad reviewer, this presentation shares personal experiences in this important peer reviewing process as either an author or a reviewer. This including examples from magnificent comments from good reviewers who helped significantly improved the quality of the work, to insane comments from pretended experts who made all nonsenses on the work.


Prof. Girija Chetty
University of Canberra, Australia

Dr. Girija Chetty has a Bachelors and Masters degree in Electrical Engineering and Computer Science, and PhD in Information Sciences and Engineering from Australia. She has more than 25 years of experience in Industry, Research and Teaching from Universities and Research and Development Companies 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 Course. Currently, she is the Head of Multimodal Systems and Information Fusion Group in University of Canberra, Australia, 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, computer vision, pattern recognition and image processing. She has published extensively with more than 120 fully refereed publications in several 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 in Computer Vision, Pattern Recognition and Image Processing.


Towards A Global Collective Intelligence - Leveraging Advances in AI, Big Data and Multimodal Science

Abstract: We are currently living in a complex world, with increasing concerns about future of humanity due to several threats of environmental problems, resource shortage, ethnic conflicts, terrorism, natural disasters and many other uncertainties. To address these potentially disastrous consequences , humans and machines need to work collectively at the global level to change our ways of interacting with one another and with the nature and the other living species around us. Technology can come to the rescus, and by using advances in cutting edge information and communication technologies, such as AI, Big Data, Machine Learning and Information Fusion, it is possible to develop computational collective intelligence framework for an improved global collective intelligence and better strategies for solving the complex problems, the humanity is facing.
Recently, in last few years, we have witnessed some progress in developing collective intelligence systems as a response to the potential global threats, particularly in fighting disease, terrorism and natural calamities and disasters. But the scale of these isolated efforts, do not quite commensurate with large complex problems we face as humanity. What is needed is an integrated approach, at a global level, by exploiting the benefits of advancements in information and communication technologies and systems. However, this is easier said than done. Due to the complex nature of real world phenomena associated with above mentioned threats, it is often difficult to extract complete knowledge about the physical process of interest, from one singe modality or information channel.
This is due to multiple layers of complex information and knowledge hidden and embedded within this natural phenomena, A detailed understanding and characterization of the such processes is needed, with input from different types of human as well as machine based sensors, systems and computational intelligence frameworks, providing high quality, efficient and timely support to humans in dealing with these challenges The concept of 'multi-modality' can often be leveraged in in this context, which in general refers to information acquisition about the process or phenomena, from multiple information sources or channels By utilizing multiple different modalities to inform about the same process or phenomena, it is possible to gain more intelligence, and more degrees of freedom, with better solutions to complex and challenging problems. However, this has a downside, with massive data deluge with important information getting buried within the big data stores, and difficulties in making sense out of it.
The two key questions that need to be addressed in these situations are: “Is it possible to exploit the complementary, competitive and collective information available from multiple modalities and sources, and if yes, " how do exploit this rich information synergistically", so as to solve the complex and difficult problems we face as humanity.
In this talk, a novel computational collective intelligence framework being developed, based on integration of multisensory fusion, AI and Big Data Science technologies will be presented. The experimental validation of the proposed algorithmic framework and its implementation as an open source technology platform, for several publicly available benchmark datasets, that represent several real world problem scenarios, has resulted in promising outcomes, leading toward the vision of achieving global collective intelligence, and improved ability to solve complex challenges we face as humanity.


Plenary Speakers



Prof. Jun Shen
University of Wollongong, Australia

Dr. Jun Shen was awarded PhD in 2001 at Southeast University, China. He held positions at Swinburne University of Technology in Melbourne and University of South Australia in Adelaide before 2006. He is an Associate Professor in School of Computing and Information Technology at University of Wollongong in Wollongong, NSW of Australia. He is a Senior Member of three institutions: IEEE, ACM and ACS. He has published more than 120 papers in prestigious journals (including IEEE Transactions) and conferences (for example, IEEE Big Data) in CS/IT areas, in particular on computational intelligence topics. His expertise includes Web services, Cloud computing and learning technologies including MOOC. He has been Editor, PC Chair, Guest Editor, PC Member for numerous journals and conferences published by IEEE, ACM, Elsevier and Springer. A/Prof Shen is also a current member of ACM/AIS Task Force on Curriculum MSIS 2016.


MLaaS(Micro Learning as a Service): taking advantage of fragmented time for fragmented knowledge

Abstract: Open learning is a rising trend in the educational sector and it attracts millions of learners to be engaged to enjoy massive latest and free open education resources (OERs). Through the use of mobile devices, open learning is often carried out in a micro learning mode, where each unit of learning activity is commonly shorter than 15 minutes. Learners are often at a loss in the process of choosing OER leading to their long term objectives and short term demands. MLaaS is a smart system to deliver personalized OER with micro learning to satisfy their real-time needs, while its decision-making process is scarcely supported due to the lack of historical data. Inspired by this, MLaaS embeds a new solution to tackle the cold start problem, by opening up a brand new profile for each learner and delivering them the first resources in their fresh start learning journey. In this work, we also propose an ontology-based mechanism for learning prediction and recommendation.


Prof. Wernhuar Tarng
National Tsing Hua University, Taiwan

Wernhuar Tarng is currently a professor at the Institute of Learning Science and Technology, National Tsing Hua University, Hsinchu, Taiwan. He was the director of Computing and Networking Center, National Hsinchu University of Education, Taiwan from 1993 to 2004 and the chairman of the Graduate Institute of Computer Science from 2008 to 2012. From 1980, Prof. Tarng conducted his undergraduate study at National Chiao Tung University, Hsinchu, Taiwan and he was graduated from the Department of Control Engineering in 1984. He received his M.S. degree (1987) and Ph.D. degree (1992) from the Department of Electrical and Computer Engineering, State University of New York at Buffalo, USA. Prof. Tarng has received more than 20 grant projects funded by Ministry of Science and Technology (MOST), Taiwan and published over 100 research papers in the field of computer science, engineering, networking, and learning technologies. Prof. Tarng was a visiting professor of Distant and Online Learning Center, Oxford University, UK in 2002 and a visiting scholar at Hear and Say Centre, Brisbane, Australia from 2014 to 2015. His current research interests include: e-Learning technologies, virtual reality, augmented reality, game-based learning, image processing, pattern recognition, computer architecture, and computer networking.


Applications of Virtual Reality and Gamification in Learning Nanotechnology

Abstract: Nanotechnology is one of the most advanced technologies in 21st century, and its  applicaitons promote the development of related industries and the global economy. To increase the national competitiveness, Ministry of Science and Technology (MOST), Taiwan initiated "National Science and Technology Program for Nanoscience and Nanotechnology" in 2002. The goal is to establish an effective mechanism for training personnel  with special skills in nanotechnology as well as promoting the development of nanotechnology industry. Ministry of Education started "Nanotechnology Human Resource Development Program" in 2003 wiht the objective of training talented personnel in all categories to achieve the popular science education and enhance the technological literacy of the entire people. With the efforts in recent years, schools at all levels have a variety of teaching materials in nanotechnology as well as the realted cirriculums. Because nannostructures cannot be seen with naked eyes or by using general microscopes, it is not an easy task for students to observe microscopic phenomena in  natural environments to understand their principles. In recent years, many high-tech instruments have been developped for investigating the nanostructures of materials. However, they are very expensive and not easy to operate such that most schools cannot provide students with this kind of equipments for teaching purposes. Based on the research results of advanced nanotechnology and basic concepts of new scientific knowledge, this study combines the virtual reality technology and the game-based learning theory to develop course modules for applications in learning nanotechnology by concretizing and simplifying the abstract and complex knowledge and making them more interesting. Users can enter the microscopic world to observe nanoscale phenomena with the apps on mobile devices to enhance their learning motivation and learning effectiveness through motion-sensing operation and 3D interaction. Therefore, they are suitable assistant tools for nanotechnology curriculums in elementary and secondary schools. This study uses innovative learning technologies to cultivate students' scientific spirits and attitudes as well as their explorative and problem-solving abilities. They can practice repeatedly anytime and anywhere in learning nanotechnology to understand its concepts through 3D immersive interaction, and thus very helpful for enhancing the related knowledge and scientific literacy.


Invited Speaker


Prof. Eric Jiang
University of San Diego, USA

Eric Jiang is currently a professor of computer science in the school of engineering at University of San Diego, USA. He served as head of mathematics and computer science of USD from 2014 to 2016. His research interests include parallel and distributed computing, information retrieval, data analytics and machine learning. Professor Jiang has published research papers in edited books and journals. He has also given presentations at international conferences, workshops and invited seminars. Since 2010, he has been serving on the editorial board of International Journal of Intelligent Data Analysis.


Integrating Labeled and Unlabeled Data for Classification

Abstract: Automatic classification is a process of assigning data objects into one or more predefined categories or classes, based on their contents. It is typically carried out by applying machine learning algorithms to build models from pre-labeled training samples and then by deploying the models to classify previously unseen data. In this talk, we discuss a classification framework for incorporating a clustering based EM algorithm into machine learning paradigms such as artificial neural networks, which can learn for classification effectively from both labeled and unlabeled data. The framework involves a procedure of modulating the influence of unlabeled data in model parameter estimation in order to adequately balance predictive values between both types of data and to improve classification performance. Experimental results with several textual data corpora show that the proper integration of unlabeled data in learning developed for the framework can reduce classification errors.