"One Size Does Not Fit All: Customized Mobile Computing for Improved System Performance"
by Iqbal MOHOMED

Abstract

Mobile devices are increasingly being used to access Web content but lack the resources for proper presentation to the user. To address this problem, content is typically customized to be more suitable for a mobile environment. Automatic customization of web content is a challenging problem because optimal adaptation often depends on both the relevance of individual objects on a web page, as well as the context of access (e.g. screen size of device being used, network connectivity, location, etc.). I will present Usage-aware Interactive Content Adaptation, an adaptation technique that allows a user who is unsatisfied with the system's current adaptation prediction to take control of the adaptation process and make changes until the content is suitably adapted for her purposes. The adaptation system learns from the user's modifications and adjusts its prediction for future accesses by other users. With this approach, users are empowered to correct bad adaptation decisions made by the system without being overly burdened. I applied the technique in two domains: adapting the quality of images to save bandwidth and customizing the layout of images to improve the utilization of screen real-estate. The work was evaluated through a series of user studies, and the results show that user feedback can be effectively used to provide appropriate customizations (i) for objects with varying relevance, (ii) when context affects the user's adaptation requirements, and (iii) when the same content can be used for multiple purposes by different users. In addition to my work on content adaptation, I will describe my ongoing research in addressing the systems challenges in remote health monitoring, wherein on-body sensors relay data to backend servers on the Internet via a mobile device.

About the speaker

Iqbal MOHOMED is a Ph.D. candidate in the Computer Science Department at the University of Toronto with an interest in systems, mobile computing and the application of pervasive computing technology to problems in healthcare. Mr. Mohomed has lectured several courses at the University of Toronto including Information Systems Analysis and Design, Software Tools and Systems Programming, and Discrete-Event Simulation and Modeling. In 2000, Mr. Mohomed received a B.Sc. Hons. from the University of Toronto with a specialist in Software Engineering, major in Economics and a minor in Mathematics. In 2001, Mr. Mohomed received a Graduate Certificate in Intelligent Information Systems from the Illinois Institute of Technology. That year, he was also a visiting student studying Game Theory at Northwestern University. In 2004, he completed an M.Sc. in Computer Science from the University of Toronto. Mr. Mohomed has designed and developed large software systems at telecommunications companies such as Nortel Networks and Motorola. He has also been involved developing application software for CaseWare International and Pervasive Software.