Activity recognition in smart homes based on electrical devices identification

Activity recognition constitutes the key challenge in the development of smart home assistive systems. In this paper, we propose a new algorithmic method for activity recognition in a smart home, based on load signatures of appliances. Most recognition approaches rely on distributed and heterogeneous sensors (ex. RFID), which are intrusive require complex installation, deployment and maintenance. On the other hand, most applications of appliance load monitoring (signal analysis) refer to the energy saving and the costs reducing of energy consumption. Consequently, our proposal constitutes an original application and new algorithmic method based on steady-state operations and signatures. The extraction process of load signatures of appliances is carried out in a three-dimensional space through a single power analyzer, which is non-intrusive (NIALM). We have rigorously tested this new approach by conducting an experiment in our smart home prototype by simulating daily scenarios taken from clinical trials previously done with Alzheimer patients. The promising results we obtained are presented and compared to other approaches, showing that, with an exceptionally minimal investment and the exploitation of relatively limited data, our method can efficiently recognize activities of daily living for providing assistive services.

[1]  S. Drenker,et al.  Nonintrusive monitoring of electric loads , 1999 .

[2]  Steven B. Leeb,et al.  Power signature analysis , 2003 .

[3]  Abdenour Bouzouane,et al.  Smart homes for people with Alzheimer's disease: adapting prompting strategies to the patient's cognitive profile , 2012, PETRA '12.

[4]  Xiaohua Xia,et al.  Active power residential non-intrusive appliance load monitoring system , 2009, AFRICON 2009.

[5]  G. W. Hart,et al.  Nonintrusive appliance load monitoring , 1992, Proc. IEEE.

[6]  J.W.M. Cheng,et al.  Electric-Load Intelligence (E-LI): Concept and Applications , 2006, TENCON 2006 - 2006 IEEE Region 10 Conference.

[7]  Adrian D. C. Chan,et al.  Usage monitoring of electrical devices in a smart home , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[8]  Yu-Hsiu Lin,et al.  A novel feature extraction method for the development of nonintrusive load monitoring system based on BP-ANN , 2010, 2010 International Symposium on Computer, Communication, Control and Automation (3CA).

[9]  Michael Baranski,et al.  Detecting patterns of appliances from total load data using a dynamic programming approach , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[10]  Abdenour Bouzouane,et al.  A NEW PLATFORM TO EASILY EXPERIMENT ACTIVITY RECOGNITION SYSTEMS BASED ON PASSIVE RFID TAGS: EXPERIMENTATION WITH DATA MINING ALGORITHMS , 2010 .

[11]  A.C. Liew,et al.  Neural-network-based signature recognition for harmonic source identification , 2006, IEEE Transactions on Power Delivery.