Speaker : Prof. Byeong Ho Kang
Date & Time : 16:00 p.m.~, October 29. 2015(Thur
Place : E2-1, #1222 Seminar Room
Title : Web Information Monitoring System: Possibilities and Limitations
Abstract : The major problem of Web technology is that people have to visit Web pages, where the information waits for visitors. A more preferred way of information sharing is the‘push’ style (Franklin and Zdonik 1998), where new information is delivered to the users when it becomes available. Recently, there have been several attempts focusing on the development of ‘push’ based information delivery. However, these were not successful because they could not overcome two major problems.
The first problem is the method of knowing when new information is made available. Without knowing the update times, large amount of resources such as network bandwidth and computing time is required, because the system is required to constantly monitor the target pages. The other issue is how to integrate the information classification system. Without the information classification system, people find that the delivered information is often irrelevant or redundant and they will be overwhelmed by garbage information. Therefore, an automated classification system, which selects relevant information for each user, is crucial for the success of Web information monitoring system. In UTAS, we have worked on this information project for several years and we have managed a few significant breakthroughs on these dilemmas. The system is equipped with a smart scheduler to adjust the revisit schedule dynamically and smart classification system using an AI based knowledge acquisition system.
Early versions of the UTAS development have been used to maintain a section of state government Web site. The State government has maintained the updated information about the state related issues from various Australian government Web sites. The UTAS has worked on this project with the US Air Force research team since 2006. Also, a few companies in Korea have developed the system using the proposed method by a UTAS research group.
Bio : Dr. Byeong Ho Kang, computer scientist, is the Associate Professor of Computing and Information Systems, University of Tasmania, Australia. Over his 25-year professional career, he received his Ph.D from the University of New South Wales, Sydney, in 1996, and has worked as a visiting researcher in the Advanced Research Lab HITACHI situated in Japan. He has also taken part in major research and development projects with industries and research organizations including the Smart Internet Collaborative Research Centre, the US Air Force, Hyundai Steel and many others.
His research interests include basic knowledge acquisition methods and applied researches in internet systems as well as medical expert systems. He has been involved in the development of several commercial and internet based applications including AI products, expert system development tools, intelligent help desk systems, Web based information monitoring and classification systems and many more. In addition, he has played a role in the foundation of several spinning companies.
Dr Kang has published more than 150 papers in journals and international conferences, and was an editor for several books of proceedings and has been a guest editor for special issues in journals. He has served as a chair and steering committee member of many international organizations and conferences. His skills are clearly illustrated in the various leadership roles he takes. He was the chair of Australian Artificial Intelligent Conference in 2006 and has been frequently elected as the chair of Knowledge Management and Acquisition for Intelligent Systems Workshop, 2006-2014. Furthermore, he is a steering committee member of Pacific Rim International Conference on AI and Australian AI conference and also currently serving as Vice President of Korean Academy of Scientists and Engineers in Australia.