Extracting spatiotemporal human activity patterns in assisted living using a home sensor network

  • Authors:
  • Dimitrios Lymberopoulos;Athanasios Bamis;Andreas Savvides

  • Affiliations:
  • Embedded Networks and Applications Lab, ENALAB, New Haven, CT;Embedded Networks and Applications Lab, ENALAB, New Haven, CT;Embedded Networks and Applications Lab, ENALAB, New Haven, CT

  • Venue:
  • Proceedings of the 1st international conference on PErvasive Technologies Related to Assistive Environments
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an automated methodology for extracting the spatiotemporal activity model of a person using a wireless sensor network deployed inside a home. The sensor network is modeled as a source of spatiotemporal symbols whose output is triggered by the monitored person's motion over space and time. Using this stream of symbols, we formulate the problem of human activity modeling as a spatiotemporal pattern-matching problem on top of the sequence of symbolic information the sensor network produces and solve it using an exhaustive search algorithm. The effectiveness of the proposed methodology is demonstrated on a real 30-day dataset extracted from an ongoing deployment of a sensor network inside a home monitoring an elder. Our algorithm examines the person's data over these 30 days and automatically extracts the person's daily pattern.