Location tracking systems are becoming more popular as mobile computing and wireless communication gain more grounds everyday. While location tracking applications vary widely in terms of the subjects being tracked (oil spills, endangered species of animals, fleets of trucks and taxis, and individuals in shopping areas, to name a few), they all share the challenge of being able to locate the moving object at all times. The problem is that whatever mechanism is used to report the location of the object, it can't do so continuously. Trying to estimate the location of the object between location reports opens the door for uncertainty and estimation error. In this talk we'll focus on human moving objects (we call them Roving Users or RUs) and how we can capitalize on the fact that humans are creatures of habit. We'll show how using user modeling has the potential of capturing these habits and turning this knowledge into a "crystal ball" the system can then use to estimate the user's location more accurately. We'll discuss the other approaches to user location estimation and show why the use of user modeling for this purpose is an innovative and important contribution in this area of research. Because nothing comes for free, we'll discuss the different challenges that face user modelers for this type of applications and our approach to solving them. We'll compare some popular user modeling techniques and discuss the pros and cons of using each of them for our purposes. Some implementation issues will also be discussed. Finally we'll give a brief introduction to the other related research projects currently underway in the Intelligent Pervasive Computing research group at the computer science department at WLU under supervision of Dr. Maher Ahmed and Dr. Siu-Cheung Chau.

Yasser Ebrahim is a lecturer of computer science at Wilfrid Laurier University, Waterloo, ON. He received his Master's degree in Computer Science and Information Systems in 1995 from DePaul university, Chicago, IL. He also has other graduate degrees in Computer Science and Business Administration. His research interests include pervasive computing, artificial intelligence and pattern recognition. He has publications in the areas of HCI, image processing, and pervasive computing. He is one of the founders of the Intelligent Pervasive Computing Lab at WLU. Besides his work in academia, he worked in the industry for many years as a Systems Analyst and Project Manager in organizations such as Bank of Nova Scotia and Inco.