Skip to main content
Article
Classification of movement data concerning user's activity recognition via mobile phones
Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics (2014)
  • Spiridoula Tragopoulou
  • Iraklis Varlamis
  • Magdalini Eirinaki, San Jose State University
Abstract
Smartphones are becoming a powerful platform for event recognition due to the number of sensors they are equipped with. This provides an opportunity to apply data mining techniques on movement data in order to recognize people's daily activities without changing their routine. In this paper, we present a methodology for collecting and analysing user activity information with a smartphone application. This information can be further exploited in various applications ranging from m-health (e.g. fitness application) and transportation (e.g. user driving habits detection) to m-commerce (e.g. shopping recommendations). In order to demonstrate this methodology, we have developed GPSTracker a prototype application for Android phones, which collects position, speed, altitude and time information and performs real-time classification of user's movement. The processed information is collected in a private user folder, on a cloud storage service, and can be further processed in order to extract aggregate user habits, or in order to detect user activity over time and provide recommendations. We also provide a visualisation of user trajectories, as recorded and classified by GPSTracker application. We exploited all the possible sensors of the smartphone and employed additional geo-location data from public transportation services. Finally, we tested several movement classification algorithms and trajectory pattern analysis techniques in order to improve the performance of our activity recognition process.
Keywords
  • movement data,
  • mobile phones
Publication Date
June, 2014
Citation Information
Spiridoula Tragopoulou, Iraklis Varlamis and Magdalini Eirinaki. "Classification of movement data concerning user's activity recognition via mobile phones" Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics Vol. 42 (2014)
Available at: http://works.bepress.com/magdalini_eirinaki/32/