Personal and Ubiquitous Computing

, Volume 15, Issue 3, pp 271–289 | Cite as

COSAR: hybrid reasoning for context-aware activity recognition

Original Article

Abstract

Human activity recognition is a challenging problem for context-aware systems and applications. Research in this field has mainly adopted techniques based on supervised learning algorithms, but these systems suffer from scalability issues with respect to the number of considered activities and contextual data. In this paper, we propose a solution based on the use of ontologies and ontological reasoning combined with statistical inferencing. Structured symbolic knowledge about the environment surrounding the user allows the recognition system to infer which activities among the candidates identified by statistical methods are more likely to be the actual activity that the user is performing. Ontological reasoning is also integrated with statistical methods to recognize complex activities that cannot be derived by statistical methods alone. The effectiveness of the proposed technique is supported by experiments with a complete implementation of the system using commercially available sensors and an Android-based handheld device as the host for the main activity recognition module.

Keywords

Activity recognition Context awareness Ontological reasoning 

Notes

Acknowledgments

This work has been partially supported by a grant from \(\hbox{Sun}^{\circledR}\) Microsystems. The authors would like to thank the volunteers that collaborated to the collection of data used in our experiments.

References

  1. 1.
    Agostini A, Bettini C, Riboni D (2009) Hybrid reasoning in the CARE middleware for context awareness. Int J Web Eng Technol 5(1):3–23CrossRefGoogle Scholar
  2. 2.
    Amft O, Tröster G (2008) Recognition of dietary activity events using on-body sensors. Artif Intell Med 42(2):121–136CrossRefGoogle Scholar
  3. 3.
    Baader F, Calvanese D, McGuinness DL, Nardi D, Patel-Schneider PF (eds) (2003) The description logic handbook: theory, implementation, and applications. Cambridge University Press, CambridgeMATHGoogle Scholar
  4. 4.
    Bishop CM (2008) Pattern recognition and machine learning. Springer, ISBN 0387310738Google Scholar
  5. 5.
    Brdiczka O, Crowley JL, Reignier P (2007) Learning situation models for providing context-aware services. In: Proceedings of HCI 2007, volume 4555 of lecture notes in computer science. Springer, pp 23–32Google Scholar
  6. 6.
    Chang K-H, Liu S-Y, Chu H-H, Yung-Jen Hsu J, Chen C, Lin T-Y, Chen C-Y, Huang P (2006) The diet-aware dining table: observing dietary behaviors over a tabletop surface. In: Proceedings of pervasive 2006, volume 3968 of lecture notes in computer science. Springer, pp 366–382Google Scholar
  7. 7.
    Chen H, Finin T, Joshi A (2004) Semantic web in the context broker architecture. In: Proceedings of the second IEEE international conference on pervasive computing and communications (PerCom 2004). IEEE Computer Society, pp 277–286Google Scholar
  8. 8.
    Golding AR, Lesh N (1999) Indoor navigation using a diverse set of cheap, wearable sensors. In: Proceedings of the third international symposium on wearable computers (ISWC’99). IEEE Computer Society, pp 29–36Google Scholar
  9. 9.
    Gu T, Wang XH, Pung HK, Zhang DQ (2004) An ontology-based context model in intelligent environments. In: Proceedings of communication networks and distributed systems modeling and simulation conference, San DiegoGoogle Scholar
  10. 10.
    Gu T, Wu Z, Tao X, Pung HK, Lu J (2009) epSICAR: an emerging patterns based approach to sequential, interleaved and concurrent activity recognition. In: Proceedings of the seventh annual IEEE international conference on pervasive computing and communications (PerCom). IEEE Computer Society, pp 1–9Google Scholar
  11. 11.
    Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182MATHCrossRefGoogle Scholar
  12. 12.
    Hong X, Nugent CD, Mulvenna MD, McClean SI, Scotney BW, Devlin S (2009) Evidential fusion of sensor data for activity recognition in smart homes. Pervasive and Mob Comput 5(3):236–252CrossRefGoogle Scholar
  13. 13.
    Horrocks I, Patel-Schneider PF, van Harmelen F (2003) From SHIQ and RDF to OWL: the making of a web ontology language. J Web Semantics 1(1):7–26, ISSN 1570-8268Google Scholar
  14. 14.
    Huynh T, Schiele B (2006) Towards less supervision in activity recognition from wearable sensors. In: Proceedings of the tenth IEEE international symposium on wearable computers (ISWC 2006), pp 3–10. IEEEGoogle Scholar
  15. 15.
    Kern N, Schiele B, Schmidt A (2003) Multi-sensor activity context detection for wearable computing. In: Proceedings of the first European symposium on ambient intelligence (EUSAI 2003), volume 2875 of lecture notes in computer science. Springer, pp 220–232Google Scholar
  16. 16.
    le Cessie S, van Houwelingen JC (1992) Ridge estimators in logistic regression. Appl Stat 41(1):191–201MATHCrossRefGoogle Scholar
  17. 17.
    Lester J, Choudhury T, Kern N, Borriello G, Hannaford B (2005) A hybrid discriminative/generative approach for modeling human activities. In: Kaelbling LP, Saffiotti A (eds) In: IJCAI-05, Proceedings of the nineteenth international joint conference on artificial intelligence. Professional Book Center, pp 766–772Google Scholar
  18. 18.
    Liao L, Fox D, Kautz HA (2005) Location-based activity recognition using relational markov networks. In: Proceedings of the nineteenth international joint conference on artificial intelligence (IJCAI-05). Professional Book Center, pp 773–778Google Scholar
  19. 19.
    Liu H, Setiono R (1995) Chi2: feature selection and discretization of numeric attributes. In: Proceedings of the IEEE international conference on tools with artificial intelligence. IEEE Computer Society, pp 388–391Google Scholar
  20. 20.
    Malandrino D, Mazzoni F, Riboni D, Bettini C, Colajanni M, Scarano V (2010) MIMOSA: context-aware adaptation for ubiquitous web access. Pers Ubiquit Comput 14(4):301–320Google Scholar
  21. 21.
    Oliver N, Horvitz E, Garg A (2002) Layered representations for human activity recognition. In: Proceedings of the 4th IEEE international conference on multimodal interfaces (ICMI 2002). IEEE Computer Society, pp 3–8Google Scholar
  22. 22.
    Pareschi L, Riboni D, Agostini A, Bettini C (2008) Composition and generalization of context data for privacy preservation. In: Sixth annual IEEE international conference on pervasive computing and communications (PerCom 2008), Proceedings of the workshops. IEEE Computer Society, pp 429–433Google Scholar
  23. 23.
    Riboni D, Bettini C (2009) Context-aware activity recognition through a combination of ontological and statistical reasoning. In: Proceedings of the 6th international conference on ubiquitous intelligence and computing (UIC), volume 5585 of lecture notes in computer science. Springer, pp 39–53Google Scholar
  24. 24.
    Riboni D, Pareschi L, Bettini C (2008) Shadow attacks on users’ anonymity in pervasive computing environments. Pervasive Mob Comput 4(6):819–835CrossRefGoogle Scholar
  25. 25.
    Stikic M, Huynh T, Van Laerhoven K, Schiele B (2008) ADL Recognition based on the combination of RFID and accelerometer sensing. In: Proceedings of pervasive health 2008. IEEE Computer Society, pp 2237–2242Google Scholar
  26. 26.
    Tentori M, Favela J (2008) Activity-aware computing for healthcare. IEEE Pervasive Comput 7(2):51–57CrossRefGoogle Scholar
  27. 27.
    Wang S, Pentney W, Popescu A-M, Choudhury T, Philipose M (2007) Common sense based joint training of human activity recognizers. In: Proceedings of IJCAI 2007, pp 2237–2242Google Scholar
  28. 28.
    Yu Z, Yu Z, Aoyama H, Ozeki M, Nakamura Y (2010) Capture, recognition, and visualization of human semantic interactions in meetings. In: Proceedings of the 8th IEEE international conference on pervasive computing and communications (PerCom). IEEE Computer Society, pp 107–115Google Scholar

Copyright information

© Springer-Verlag London Limited 2010

Authors and Affiliations

  1. 1.Università degli Studi di Milano, D.I.Co.MilanItaly

Personalised recommendations