PAKDD 2009

Pacific-Asia Conference on Knowledge Discovery and Data Mining

27 - 30 April Bangkok, Thailand



Search

Organized by

Sirindhorn International Institute of Technology (SIIT)
Thammasat University
Chulalongkorn University
Asian Institute of Technology (AIT)

Sponsored by

National Electronics and Computer Technology Center (NECTEC), Thailand
ECTI, Thailand
Thailand Convention and Exhibition Bureau (TCEB)
The Air Force Office of Scientific Research, Asian Office of Aerospace Research and Development (AFOSR/AOARD)
Print

Keynote and Invited Speakers

Andrew Tomkins, PhD

Yahoo! Research

http://www.tomkinshome.com/andrew/

Homepage

http://research.yahoo.com/bouncer_user/11

Yahoo! Research

The future of search: an online content perspective


Andrew Tomkins is Chief Scientist of Search at Yahoo!, where his research interests include web search, web analysis, and online communities. Prior to joining Yahoo!, Andrew spent 8 years at IBM's Almaden Research Center, where he managed the information management principles group and served as Chief Scientist of the WebFountain project. He has published over eighty technical papers, and serves on the editorial boards of IEEE Internet Computing and ACM Transactions on the Web. Andrew received his PhD in Computer Science from Carnegie Mellon University in 1997.

Abstract


Nonprofessional creation of public online content has outstripped professional content creation of all forms, both online and offline. And two orders of magnitude more content is created daily to flow through social networks, with as much as two more orders of magnitude still to come as user engagement increases. Content is diversifying in creation, consumption, and nature. Web search engines provide rapid targeted access to this page content, and increasingly to other information such as news articles, weather, movie showtimes, and product and restaurant listings. In this talk, I'll discuss these trends from the standpoint of the search engine, I'll cover some research results in this area, and I'll close with some challenges for the future.

Guang-Zhong Yang, PhD

Imperial College London

http://www.doc.ic.ac.uk/~gzy/

Homepage

KDD for BSN – towards the future of pervasive sensing


Professor Guang-Zhong Yang received Ph.D. in Computer Science from Imperial College London and is Director and Founder of the Royal Society/Wolfson MIC Laboratory at Imperial College. His main research interest is in biomedical imaging, sensing and robotics. He has published over 250 original research articles including over 150 peer reviewed academic journal papers on these topics. He is widely regarded as a pioneer of Body Sensor Networks (BSN), which is attracting increasingly significant international focus. Professor Yang currently heads the Centre for Pervasive Sensing at Imperial College and has led some of the major developments internationally in BSN. He has developed a range of wireless, pervasive sensing platforms including the miniaturised e-AR sensor featured at the 2007 Royal Society Summer Science Exhibition and the BA Festival of Science, and received a Medical Futures Translational Research Innovation Award. He is Fellow of the IET and a recipient of the Royal Society Research Merit Award and the ISMRM I.I Rabi Award.

Abstract


With increasing sophistication and miniaturisation of wireless sensor technologies, integrated microsensors no more than a few millimetres in size combined with onboard processing and wireless data transfer has become a reality. The provision of “ubiquitous” and “pervasive” monitoring of physical, physiological, and biochemical parameters in any environment and without activity restriction and behaviour modification is the primary motivation of Body Sensor Network (BSN) research. The general scope of BSN is broad, ranging from monitoring of patients with chronic disease and care for the elderly, to general well-being monitoring and performance evaluation in sports. It also has important applications in gaming and human-computer-interaction. One of the significant challenges of BSN is the provision of context aware sensing with effective multi-sensor fusion, data inferencing, mining, and trend analysis. Other research issues currently being addressed include novel miniaturised bioelectrical, biochemical, biophysical, and mechanical sensors; low power RF transceiver, energy scavenging, and battery technologies; biocompatibility, materials, system integration and miniaturisation; autonomic sensor networks and light-weight communication protocols and standards. This talk will address some of the key research topics and current advances in BSN, particularly those related to the KDD community. It will also cover the use of bio-inspired design for providing distributed inferencing and ultra-low power on-node processing, demonstrating how this alternate paradigm based on the strategies used by biological systems can be used to deal with the challenges of scale, complexity, heterogeneity, and uncertainty involved in pervasive sensing.

Yu Xu, Jeffrey, BE, ME, PhD

The Chinese University of Hong Kong

http://www.se.cuhk.edu.hk/people/yu.html

Homepage

Finding Hidden Structures in Relational Databases


Dr Jeffrey Xu Yu is a Professor in the Department of Systems Engineering and Engineering Management, the Chinese University of Hong Kong. His current main research interests include keywords search in relational databases, graph mining, graph query processing, and graph pattern matching. Dr. Yu served/serves in over 150 organization committees and program committees in international conferences/workshops. Dr. Yu also served as an associate editor of IEEE Transactions on Knowledge and Data Engineering (2004-2008), and servers in VLDB Journal editorial board and ACM SIGMOD executive committee. He has published over 190 papers including papers published in reputed journals and major international conferences.

Abstract


Relational database management systems have been widely used over decades. An important research issue is to find hidden structural information in large relational databases. By hidden structural information we mean the information that cannot be easily found using a traditional query language SQL. In this talk, we discuss how to find hidden structural information in a relational database by viewing a relational database as a large directed graph where nodes represent tuples and edges represent foreign key references between tuples in the database. We discuss how to find trees and communities in such a large graph for user-given keywords. We also discuss how to find frequent and additional keywords associated with the structures identified in a relational database using SQL.