Home
  • English
  • ÄŒeÅ¡tina
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • LatvieÅ¡u
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Log In
    New user? Click here to register. Have you forgotten your password?
Home
  • Browse Our Collections
  • Publications
  • Researchers
  • Research Data
  • Institutions
  • Statistics
    • English
    • ÄŒeÅ¡tina
    • Deutsch
    • Español
    • Français
    • Gàidhlig
    • LatvieÅ¡u
    • Magyar
    • Nederlands
    • Português
    • Português do Brasil
    • Suomi
    • Log In
      New user? Click here to register. Have you forgotten your password?
  1. Home
 
Options

Abnormality detection approach using deep learning models in smart home environments

Journal
ACM International Conference Proceeding Series
Date Issued
2019-04-12
Author(s)
Sukor A.S.A.
Zakaria A.
Rahim N.A.
Kamarudin L.M.
Nishizaki H.
DOI
10.1145/3330180.3330185
Abstract
The rising number of elderly populations has become a common concern in many countries. As one of the solutions, smart homes have been developed to help them live independently in their own homes. However, the accurate interpretation in monitoring human situations is still limited. This paper presents an abnormality detection approach that can monitor smart home residents' behavior and identify any abnormalities regarding their daily routines. In particular, this study investigates the use of two deep learning models that are commonly used in the pattern recognition communities, which are known as Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). The learned models are used to classify between normal and abnormal situations and their performance are then compared using a publicly available smart home dataset. Experimental results show that MLP has significant performance and outperforms RNN in terms of accuracy.
Subjects
  • Abnormality detection...

  • About Us
  • Contact Us
  • Policies

We collect and process your personal information for the following purposes: Authentication, Preferences, Acknowledgement and Statistics.
To learn more, please read our
privacy policy.

Customize