HONG KONG BAPTIST UNIVERSITY
FACULTY OF SCIENCE
Department of Computer Science Seminar
2010 Series
Learning Situation Models in Smart Spaces
Dr. Oliver Brdiczka
Palo Alto Research Center
USA
Date: February 12, 2010 (Friday)
Time: 10:30 - 11:30 am
Venue: SCT909,
Cha Chi Ming Science Tower, Ho Sin Hang Campus
AbstractSmart Spaces enhance user capabilities and comfort
by providing new services and automated service execution based on sensed user activity. Though, when becoming
really "smart", such spaces should not only provide some service automation, but further learn and adapt their
behavior during use. This article motivates and investigates learning of situation models in a smart space,
covering knowledge acquisition from observation as well as evolving situation models during use. An integral
framework for acquiring and evolving different layers of a situation model is detailed. Different learning
methods are presented as part of this framework: role detection per entity, unsupervised extraction of situations
from multimodal data, supervised learning of situation representations, and the evolution of a predefined
situation model with feedback. The situation model serves as frame and support for the different methods,
permitting to stay in an intuitive declarative framework. An implementation of the whole framework for a smart
home environment is described, and the results of several evaluations are depicted.
BiographyOliver Brdiczka is a Scientific Researcher at PARC’s current Ubiquitous Computing
research area. His research focus has been on building models of human behavior for providing novel assistive
technology. His extensive experience in machine learning and statistical modeling has served in a number of
research and commercial projects, including several European projects (IST CAVIAR, IST CHIL) and national French
research projects (ANR CASPER). He has built a number of systems and prototypes in the past: situation and social
activity detection system for France Telecom Research, a collaborative note taking and sharing system at TU
Darmstadt, Germany, and activity logging and mining applications at PARC. He has chaired the 2nd and 3rd
Workshops on Multimedia Technologies for E-Learning (MTEL), and has served as program committee member of the
Workshop of Context Modeling and Reasoning (CoMoRea), and the Workshop on Social Computing with Mobile Phones &
Sensors: Modeling, Sensing and Sharing.
********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)
http://www.comp.hkbu.edu.hk/v1/?page=seminars&id=120&lang=tc