An Activity Recognition Model for Alzheimer's Patients: Extension of the COACH Task Guidance System

  • Authors:
  • B. Bouchard;P. Roy;A. Bouzouane;S. Giroux;A. Mihailidis

  • Affiliations:
  • Université du Québec à Chicoutimi, (QC) Canada, email: Bruno.Bouchard@uqac.ca;Université de Sherbrooke, (QC) Canada, email: Patrice.C.Roy@usherbrooke.ca;Université du Québec à Chicoutimi, (QC) Canada, email: Abdenour.Bouzouane@uqac.ca;Université de Sherbrooke, (QC) Canada, email: Sylvain.Giroux@usherbrooke.ca;University of Toronto, (ON) Canada, email: Alex.Mihailidis@utoronto.ca

  • Venue:
  • Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a hybrid plan recognition model, based on probabilistic description logic, which addresses the issue of recognizing the activities and the errors of Alzheimer's patients at an early stage of the disease. This model has been implemented to be a new extension of the COACH system, an emerging prototype of cognitive device for persons with Alzheimer's disease that offers assistance in task completion. We present an initial experimentation done on this new recognition module for COACH, which is based on the results of two sets of clinical trials.