A real-world deployment of the COACH prompting system

  • Authors:
  • Stephen Czarnuch;Sharon Cohen;Varakini Parameswaran;Alex Mihailidis

  • Affiliations:
  • Institute of Biomaterials and Biomedical Engineering, University of Toronto, Toronto, Canada and Toronto Rehabilitation Institute-UHN, Toronto, Canada;Toronto Memory Program, Toronto, Canada;Toronto Memory Program, Toronto, Canada;Institute of Biomaterials and Biomedical Engineering, University of Toronto, Toronto, Canada and Toronto Rehabilitation Institute-UHN, Toronto, Canada and Dept. of Occupational Science and Occupat ...

  • Venue:
  • Journal of Ambient Intelligence and Smart Environments - Design and Deployment of Intelligent Environments
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The loss of cognition associated with dementia affects an individual's ability to participate in even the most fundamental activities of daily living ADL. Assistive technology for cognition ATC has shown potential to support ADL completion, but few devices have undergone real-world deployments. The COACH is an existing ATC that has been shown in supervised trials to support older adults with dementia through the ADL of hand washing. This paper presents the results of a study of the COACH in a long-term, real-world, community-based deployment.The COACH was installed in a washroom at the Toronto Memory Program. The COACH was configured to run in an unsupervised state, interacting with users when they were not progressing through the task. Video was collected from an overhead camera, and was manually annotated to determine the system's capabilities. The trials were conducted from February to May, 2012.Twenty participants contributed forty-one hand washing trials. Results suggest that the COACH was able to identify completed task steps with 46.6% accuracy and the participants' true performance with 54.9% accuracy. This study clarifies the need for more robust, accurate and generalized user tracking, including the use of three-dimensional tracking, gesture, grip and rotation detection.