Elderly activities recognition and classification for applications in assisted living

  • Authors:

  • Saisakul Chernbumroong;Shuang Cang;Anthony Atkins;Hongnian Yu

  • Affiliations:

  • Faculty of Computing, Engineering and Technology, Staffordshire University, Stafford ST18 0AD, UK and Department of Software Engineering, College of Arts, Media and Technology, Chiang Mai Universi ...;School of Tourism, Bournemouth University, Poole, Dorset BH12 5BB, UK;Faculty of Computing, Engineering and Technology, Staffordshire University, Stafford ST18 0AD, UK;School of Design, Engineering & Computing, Bournemouth University, Poole, Dorset BH12 5BB, UK

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2013

Quantified Score

Hi-index 12.05

Visualization

Abstract

Assisted living systems can help support elderly persons with their daily activities in order to help them maintain healthy and safety while living independently. However, most current systems are ineffective in actual situation, difficult to use and have a low acceptance rate. There is a need for an assisted living solution to become intelligent and also practical issues such as user acceptance and usability need to be resolved in order to truly assist elderly people. Small, inexpensive and low-powered consumption sensors are now available which can be used in assisted living applications to provide sensitive and responsive services based on users current environments and situations. This paper aims to address the issue of how to develop an activity recognition method for a practical assisted living system in term of user acceptance, privacy (non-visual) and cost. The paper proposes an activity recognition and classification method for detection of Activities of Daily Livings (ADLs) of an elderly person using small, low-cost, non-intrusive non-stigmatize wrist worn sensors. Experimental results demonstrate that the proposed method can achieve a high classification rate (90%). Statistical tests are employed to support this high classification rate of the proposed method. Also, we prove that by combining data from temperature sensor and/or altimeter with accelerometer, classification accuracy can be improved.