Semantic Knowledge Base in Support of Activity Recognition in Smart Home Environments

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Activity recognition plays a major role in smart home technologies in providing services to users. One of the approaches to identify activity is through the use of knowledge-driven reasoning. This paper presents a framework of semantic activity recognition, which is used to support smart home systems to identify users’ activities based on the existing context. The framework consists of two main components: a semantic knowledge base and an activity recognition module. The knowledge base is represented using ontology and it is used to provide a semantic understanding of the environment in order to classify users’ patterns of activities. Experimental results show that the proposed approach can support the classification process and accurately infer users’ activities with the accuracy of 90.9%.



  • Keywords

    Smart homes; Semantic knowledge base; Activity recognition; Knowledge representation; Ontology

  • References

      [1] United Nations (2000), “Magnitude and Speed of Population Ageing,” World Population Ageing 1950-2050, pp. 11–13.

      [2] P. Rashidi and A. Mihailidis (2013), “A Survey on Ambient-assisted Living Tools for Older Adults,” IEEE Journal of Biomedic Health Informatics, vol. 17, no. 3, pp. 579–590.

      [3] Q. Ni, A. García Hernando, and I. de la Cruz (2015), “The Elderly’s Independent Living in Smart Homes: A Characterization of Activities and Sensing Infrastructure Survey to Facilitate Services Development,” Journal of Smart Home Sensors, vol. 15, no. 5, pp. 11312–11362.

      [4] M. E. Morris et al. (2013), “Smart-home Technologies to Assist Older People to Live Well at Home,” Journal of Aging Science., vol. 1, no. 1, pp. 1–9.

      [5] J. Synnott, C. Nugent, and P. Jeffers (2015), “Simulation of Smart Home Activity Datasets,” Journal of Sensors, vol. 15, no. 6, pp. 14162–14179.

      [6] A. S. M. Salih and A. Abraham (2013), “A Review of Ambient Intelligence Assisted Healthcare Monitoring,” Mirlabs.Org, vol. 5, pp. 741–750.

      [7] S. Chatterjee, K. Dutta, H. Q. Xie, J. Byun, A. Pottathil, and M. Moore (2013), “Persuasive and Pervasive Sensing: A New Frontier to Monitor, Track and Assist Older Adults Suffering from Type-2 Diabetes,” International Conference of System Science, pp. 2636–2645.

      [8] L. Chen, C. D. Nugent, and H. Wang (2012), “A Knowledge-driven Approach to Activity Recognition in Smart Homes,” IEEE Transaction Knowledge Data Engineering, vol. 24, no. 6, pp. 961–974.

      [9] L. Chen, C. Nugent, and G. Okeyo (2014), “An Ontology-based Hybrid approach to Activity Modeling for Smart Homes,” IEEE Transaction Human-Machine System, vol. 44, no. 1, pp. 92–105.

      [10] J. Wang, Z. Cheng, M. Zhang, Y. Zhou, and L. Jing (2015), “A Situation-Aware Abnormality Detection System for Elderly Care Using SVDD,” International Journal of Innovative Computing, vol. 11, no. 2.

      [11] Q. Ni, A. B. García Hernando, and I. P. De La Cruz (2016), “A Context-Aware System Infrastructure for Monitoring Activities of Daily Living in Smart Home,” Journal Sensors, vol. 2016, pp. 1–9, 2016.

      [12] K. Wongpatikaseree, M. Ikeda, M. Buranarach, T. Supnithi, A. O. Lim, and Y. Tan (2012), “Activity Recognition using Context-aware Infrastructure Ontology in Smart Home Domain,” International Conference of Knowledge Informatic Creation Support System KICSS 2012, pp. 50–57.

      [13] J. yi Hong, E. Ho Suh, and S. J. Kim (2009), “Context-aware Systems: A Literature Review and Classification,” Expert System Application, vol. 36, no. 4, pp. 8509–8522.

      [14] L. Chen and C. D. Nugent (2009), “Ontology-based Activity Recognition in Intelligent Pervasive Environments,” International Journal Web Informatic System, vol. 5, no. 4, pp. 410–430.

      [15] A. S. Crandall and D. J. Cook (2010), “Using a Hidden Markov Model for Resident Identification,” Intelligent Environment (IE), 2010 Sixth International Conference, pp. 74–79.

      [16] E. Nazerfard and D. Cook (2013), “Using Bayesian Networks for Daily Activity Prediction,” Assoc. Advanced Artificial Intelligence, pp. 32–38.

      [17] J. Hoey, T. Pltz, D. Jackson, A. Monk, C. Pham, and P. Olivier (2011), “Rapid specification and automated generation of prompting systems to assist people with dementia,” Pervasive Computing., vol. 7, no. 3, pp. 299–318.

      [18] J. Ye, S. Dobson, and S. McKeever (2012), “Situation Identification Techniques in Pervasive Computing: A Review,” Pervasive Mobile Computing, vol. 8, no. 1, pp. 36–66.

      [19] I. K. Ihianle (2018), “A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment,” Journal of Informatics, vol. 5, pp. 1–25.

      [20] G. Azkune, A. Almeida, and L. Diego (2014), “Extending Knowledge-Driven Activity Models through Data-Driven Learning Techniques,” Expert System. Application.

      [21] D. Riboni and C. Bettini (2011), “COSAR: Hybrid Reasoning for Context-aware Activity Recognition,” Pervasive. Ubiquitous Computing., vol. 15, no. 3, pp. 271–289.

      [22] I. H. Bae (2014), “An Ontology-based Approach to ADL Recognition in Smart Homes,” Future Generation Computing System., vol. 33, pp. 32–41.

      [23] M. A. Mohammad, I. Kaloskampis, Y. Hicks, and R. Setchi (2015), “Ontology-based Framework for Risk Assessment in Road Scenes using Videos,” Procedia Computing Science., vol. 60, no. 1, pp. 1532–1541.

      [24] H. Lee and J. Kwon (2013), “Ontology Model-based Situation and Socially-aware Health Care Service in a Smart Home Environment,” International Journal of Smart Home, vol. 7, no. 5, pp. 239–250.

      [25] F. Latfi, B. Lefebvre, and C. Descheneaux (2007), “Ontology-based Management of the Telehealth Smart Home Dedicated to Elderly in Loss of Cognitive Autonomy,” CEUR Workshop Proceding., vol. 258.

      [26] B. Y. E. Davis, G. Marcus, and W. Taller (2015), “Commonsense Reasoning and Commonsense Knowledge in Artificial Intelligence,” vol. 58

      [27] E. Cambria and N. Howard (2014), “Common and Common-Sense Knowledge Integration for Concept-Level Sentiment Analysis,” pp. 170–173.

      [28] T. Van Kasteren and A. Noulas (2008), “Accurate Activity Recognition in a Home Setting,” in Tenth International Conference on Ubiquitous Computing (Ubicomp’08), pp. 1–9.

      [29] T. L. M. van Kasteren, G. Englebienne, and Ben Krose (2011), “Effective Performance Metrics for Evaluating Activity Recognition Methods,” Activity Recognition in Pervasive Intelligent Environments, Atlantic Press, pp. 1–34.




Article ID: 22482
DOI: 10.14419/ijet.v7i4.27.22482

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.