Abstract

Smart Homes are smart spaces that contain devices are connected with each other to get information about user’s activities; these devices can be controlled through one central point. Like door locks, thermostats, televisions, home monitor and lights. Behavior recognition in dynamic environments is one of the most challenging issues in this research area, each behavior has a specific number of activities to be performed. In this paper, a new approach to recognize the human behaviors based on finding the minimum number of activities to perform the behavior by determining the membership degree of each activity for each behavior. The proposed approach learns the performed behaviors and uses that knowledge to recognize the behavior through applying a threshold and Alpha cut concept on the membership degree of each activity. In addition, it can adapt to environment modifications, variations in human habits. The conducted simulation results show that the proposed approach achieves better performance than existing approaches in terms of accuracy, recall, and f-measure metrics.

References

• M. Skubic and M. Rantz. 2011. Active Elders: Center for Eldercare and Rehabilitation Technology, http://eldertech.missouri.edu/.
• M. Rantz, M. Aud, G. Alexander,D. Oliver, D. Minner, M. Skubic, J. Keller, Z. He, M. Popescu, G. Demiris, S.Miller,2008. “Tiger place: An innovative educational and research environment,” in AAAI in Eldercare: New Solutions to Old Problems.
• S.W. Lee, Y.S. Kim, K.H. Park, Z. Bien,2010Iterative bayesian fuzzy clustering toward flexible icon-based assistive software for the disabled, Inform. Sci.
• J. Boger, J. Hoey, P. Poupart, C. Boutilier, G. Fernie, A. Mihailidis,2006 A planning system based on markov decision processes to guide people with dementia through activities of daily living, IEEE Trans. Inform. Technol. Biomed. 323–333.
• M. Ros *, M.P. Cuéllar, M. Delgado, A. Vila, 2013 Online recognition of human activities and adaptation to habit changes by means of learning automata and fuzzy temporal windows.
• X. Meng, K.K. Lee, Y. Xu, 2006Human driving behavior recognition based on hidden markov models, in: IEEE International Conference on Robotics and Biomimetics, vol. 0, pp. 274–279.
• U. Naeem, J. Bigham, 2007A comparison of two hidden markov approaches to task identification in the home environment, in: 2nd International Conference on Pervasive Computing and Applications, IEEE, pp. 383–388.
• D.J. Cook, M. Youngblood, E.O. Heierman III, K. Gopalratnam, S. Rao, A. Litvin, F. Khawaja, 2003Mavhome: an agent-based smart home, in: PERCOM’03: Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, IEEE Computer Society, Washington, DC, USA, p. 521.
• F. Doctor, H. Hagras, V. Callaghan, 2005A fuzzy embedded agent-based approach for realizing ambient intelligence in intelligent inhabited environments, IEEE Trans. Syst. Man Cybernet., Part A 35 (2005) 55–65.
• P. Rashidi, D. Cook,2009 Keeping the resident in the loop: Adapting the smart home to the user, IEEE Trans. Syst. Man Cybernet., Part A: Syst. Humans 39 (2009) 949–959.
• J.A. Kientz, S.N. Patel, B. Jones, E. Price, E.D. Mynatt, G.D. Abowd, 2008The georgia tech aware home, in: CHI’08: CHI’08 Extended Abstracts on Human Factors in Computing Systems, ACM, New York, NY, USA, pp. 3675–3680.
• R.M. Droes, M. Mulvenna, C. Nugent, D. Finlay, M. Donnelly, M. Mikalsen, S. Walderhaug, T.v.Kasteren, B. Krose, S. Puglia, F. Scanu, M.O. Migliori, E. Ucar, C. Atlig, Y. Kilicaslan, O. Ucar, J. Hou, 2007Healthcare systems and other applications, IEEE Perv. Comput. 6 (2007) 59–63.
• B. Krose, van T. Kasteren, C. Gibson, van den T. Dool, Care: context awareness in residences for elderly, in: Proceedings of ISG’08: The 6th International Conference of the International Society for Gerontechnology, pp. 101–105.
• E. Kim, S. Helal, D. Cook,2010 Human activity recognition and pattern discovery, IEEE Perv. Comput. 9 (2010) 48–53.
• P. Rashidi, D.J. Cook, L.B. Holder, M. Schmitter-Edgecombe, 2010Discovering activities to recognize and track in a smart environment, IEEE Trans. Knowl. Data Eng. 99 (2010).
• V. Jakkula, D.J. Cook, 2008Anomaly detection using temporal data mining in a smart home environment, Methods Inform. Med.
• D.J.C. VikramadityaJakkula, A. Crandall,2008 Enhancing Anomaly Detection using Temporal Pattern Discovery, Advanced Intelligent Systems, Springer. pp. 175–194.
• S. Luhr, G. West, S. Venkatesh, 2007Recognition of emergent human behaviour in a smart home: a data mining approach, Perv. Mobile Comput. 3 (2007) 95–116. Design and Use of Smart Environments.
• T. Gu, Z. Wu, X. Tao, H.K. Pung, J. Lu, 2009Epsicar: an emerging patterns based approach to sequential, interleaved and concurrent activity recognition, in: IEEE International Conference on Pervasive Computing and Communications, vol. 0, 2009, pp. 1–9.
• D. Zhang, D. Gatica-Perez, S. Bengio, 2004I. McCowan, G. Lathoud, Modeling individual and group actions in meetings with layered hmms, IEEE Trans. Multimedia 8 (2004) 509–520.
• G. Acampora, V. Loia, 2005Fuzzy control interoperability and scalability for adaptive domotic framework, IEEE Trans. Indus. Inform. 1 (2005) 97–111.