Improving Activity Recognition in Smart Environments with Ontological Modeling
The problem of activity recognition in smart environments has produced multiple divergent paths of research in an attempt to improve the usability and usefulness of smart environments. In this paper we merge these research paths by defining a method for mapping smart environment sensor activities into an ontologically defined semantic feature space. We show that by using this approach we are able to improve activity recognition by between 5–20 %.
KeywordsActivity recognition Ontological modeling Ontologies Semantic Web
Thanks to the CASAS project at Washington State University for making the data used in this study available. This work is supported in part by National Science Foundation grant DGE-0900781.
- 7.Dernbach, S., Das, B., Krishnan, N.C., Thomas, B.L., Cook, D.J.: Simple and complex activity recognition through smart phones. In: 2012 8th International Conference on Intelligent Environments (IE), pp. 214–221. IEEE (2012)Google Scholar
- 10.Matuszek, C., Cabral, J., Witbrock, M.J., DeOliveira, J.: An introduction to the syntax and content of Cyc. In: AAAI Spring Symposium: Formalizing and Compiling Background Knowledge and Its Applications to Knowledge Representation and Question Answering, pp. 44–49. Citeseer (2006)Google Scholar
- 12.Sahaf, Y.: Comparing Sensor Modalities for Activity Recognition. Master’s thesis, Washington State University (2011)Google Scholar
- 13.Sculley, D.: Large scale learning to rank. In: NIPS 2009 Workshop on Advances in Ranking, pp. 1–6 (2009)Google Scholar
- 14.Szewcyzk, S., Minor, B., Swedlove, B., Cook, D.: Annotating smart environment sensor data for activity learning. Technol. Health Care 17(3), 161–169 (2009)Google Scholar
- 15.Wang, X.H., Gu, T., Zhang, D.Q., Pung, H.K.: An ontology-based context model in intelligent environments. In: Proceedings of Communication Networks and Distributed Systems Modeling and Simulation Conference, vol. 2004, pp. 270–275 (2004)Google Scholar