Exploiting Passive RFID Technology for Activity Recognition in Smart Homes

The number of seniors and other people needing daily assistance continues to increase, but the current human resources available to achieve this in the coming years will certainly be insufficient. To remedy this situation, smart habitats have emerged as an innovative avenue for supporting needs of daily assistance. Smart homes aim to provide cognitive assistance in decision making by giving hints, suggestions, and reminders, with different kinds of effectors, to residents. To implement such technology, the first challenge to overcome is the recognition of ongoing activity. Some researchers have proposed solutions based on binary sensors or cameras, but these types of approaches infringed on residents' privacy. A new affordable activity-recognition system based on passive RFID technology can detect errors related to cognitive impairment. The entire system relies on an innovative model of elliptical trilateration with several filters, as well as on an ingenious representation of activities with spatial zones. The authors have deployed the system in a real smart-home prototype; this article renders the results of a complete set of experiments conducted on this new activity-recognition system with real scenarios.

[1]  T. Bayes.  An essay towards solving a problem in the doctrine of chances , 2003 .

[2]  M. Egenhofer,et al.  Point-Set Topological Spatial Relations , 2001 .

[3]  Kevin Bouchard,et al.  Accurate passive RFID localization system for smart homes , 2012, 2012 IEEE 3rd International Conference on Networked Embedded Systems for Every Application (NESEA).

[4]  James Brusey,et al.  Reasoning about uncertainty in location identification with auto-ID , 2003 .

[5]  Andreas Zell,et al.  Self-Localization with RFID snapshots in densely tagged environments , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Xiuwen Liu,et al.  Accurate localization of RFID tags using phase difference , 2010, 2010 IEEE International Conference on RFID (IEEE RFID 2010).

[7]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[8]  Weiping Zhu,et al.  A hybrid method for achieving high accuracy and efficiency in object tracking using passive RFID , 2012, 2012 IEEE International Conference on Pervasive Computing and Communications.

[9]  Myrna F. Schwartz,et al.  The Naturalistic Action Test: A standardised assessment for everyday action impairment , 2002 .

[10]  Gabriel Robins,et al.  An RFID-based object localisation framework , 2011, Int. J. Radio Freq. Identif. Technol. Appl..

[11]  M. Harrison,et al.  Reasoning about Uncertainty in Location Identification with RFID , 2003 .

[12]  Hans W. Guesgen,et al.  Spatiotemporal Reasoning for Smart Homes , 2006, Designing Smart Homes.

[13]  Diane J. Cook,et al.  Enhancing Smart Home Algorithms Using Temporal Relations , 2007 .

[14]  Kevin Bouchard,et al.  Discovery of topological relations for spatial Activity Recognition , 2013, 2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).