Skip to main content
SpringerLink
Log in

An Information Retrieval-Based Approach to Activity Recognition in Smart Homes

  • Conference paper
  • First Online:
Service-Oriented Computing – ICSOC 2020 Workshops (ICSOC 2020)

Part of the book series: Lecture Notes in Computer Science ((LNPSE,volume 12632))

Included in the following conference series:

Abstract

One of the principal challenges in developing robust Machine Learning (ML) classification algorithms for Human Activity Recognition (HAR) from real-time smart home sensor data is how to account for variations in 1) the activity sequence length, 2) the contribution each sensor has to an activity, and 3) the amount of activity class imbalance. Such changes generate observations that do not conform to expected patterns potentially reducing the efficacy of classification models. Moreover the architecture of prior solutions have been quite complex which have resulted in large training times for these approaches to achieve acceptable classification accuracy. In this paper we address these three issues by 1) proposing a data structure representing the duration and frequency information of each sensor for an activity, 2) transforming this data structure into an Information Retrieval (IR)-based representation, and finally 3) compare and contrast the utility of this IR-based representation using four different supervised classifiers. Our proposed framework in combination with a state-of-the-art ensemble learner results in more accurate and scalable ML classification models that are better suited toward off-line HAR in a smart home setting.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    http://hyperopt.github.io/hyperopt/. Last accessed 30th September, 2020.

References

  1. Abidine, M.B., Fergani, L., Fergani, B., Fleury, A.: Improving human activity recognition in smart homes. Int. J. E-Health Med. Commun. 6(3), 19–37 (2015). https://doi.org/10.4018/IJEHMC.2015070102

    Article  Google Scholar 

  2. Amiribesheli, M., Benmansour, A., Bouchachia, A.: A review of smart homes in healthcare. J. Amb. Intell. Hum. Comput. 6(4), 495–517 (2015). https://doi.org/10.1007/s12652-015-0270-2

    Article  Google Scholar 

  3. Bouchachia, A., Vanret, C.: GT2FC: an online growing interval type-2 self-learning fuzzy classifier. IEEE Trans. Fuzzy Syst. 22(4), 999–1018 (2014)

    Article  Google Scholar 

  4. Chen, L., Nugent, C.D., Wang, H.: A knowledge-driven approach to activity recognition in smart homes. IEEE Trans. Knowl. Data Eng. 24(6), 961–974 (2012)

    Article  Google Scholar 

  5. Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2016, pp. 785–794. ACM, New York (2016)

    Google Scholar 

  6. Cook, D.J.: Learning setting-generalized activity models for smart spaces. IEEE Intel. Syst. 27(1), 32–38 (2012)

    Article  Google Scholar 

  7. Cook, D.J., Schmitter-Edgecombe, M.: Assessing the quality of activities in a smart environment. Method Inf. Med. 48(5), 480–485 (2009)

    Article  Google Scholar 

  8. Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)

    MATH  Google Scholar 

  9. Dietterich, T.G.: An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach. Learn. 40(2), 139–157 (2000)

    Article  Google Scholar 

  10. Duarte, J., Gama, J., Bifet, A.: Adaptive model rules from high-speed data streams. ACM Trans. Knowl. Discov. Data 10(3), 30:1–30:22 (2016)

    Google Scholar 

  11. Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM Comput. Surv. 46(4), 44:1–44:37 (2014)

    Google Scholar 

  12. Gu, T., Wu, Z., Tao, X., Pung, H.K., Lu, J.: epSICAR: an emerging patterns based approach to sequential, interleaved and concurrent activity recognition. In: Proceedings of 7th IEEE International Conference on Pervasive Computing and Communications, pp. 1–9. IEEE (2009)

    Google Scholar 

  13. Guo, J., Mu, Y., Xiong, M., Liu, Y., Gu, J.: Activity feature solving based on TF-IDF for activity recognition in smart homes. Complexity 37, 1–10 (2019)

    Google Scholar 

  14. Hoque, E., Dickerson, R.F., Preum, S.M., Hanson, M., Barth, A., Stankovic, J.A.: Holmes: a comprehensive anomaly detection system for daily in-home activities. In: 2015 International Conference on Distributed Computing in Sensor Systems, pp. 40–51. IEEE Press, June 2015

    Google Scholar 

  15. Jurek, A., Nugent, C., Bi, Y., Wu, S.: Clustering-Based Ensemble Learning for Activity Recognition in Smart Homes. Sensors 14, 12285–12304 (2014)

    Article  Google Scholar 

  16. Kim, E., Helal, S., Cook, D.: Human activity recognition and pattern discovery. IEEE Perv. Comput. 9(1), 48–53 (2010)

    Article  Google Scholar 

  17. Kim, E., Helal, S., Nugent, C., Beattie, M.: Analyzing activity recognition uncertainties in smart home environments. ACM Trans. Intell. Syst. Technol. 6(4), 52:1–52:28 (2015). https://doi.org/10.1145/2651445

  18. Kondylidis, N., Tzelepi, M., Tefas, A.: Exploiting TF-IDF in deep convolutional neural networks for content based image retrieval. Multimed. Tools Appl. 77(23), 30729–30748 (2018)

    Article  Google Scholar 

  19. Krishnan, N.C., Cook, D.J.: Activity recognition on streaming sensor data. Perv. Mob. Comput. 10(Part B), 138–154 (2014)

    Google Scholar 

  20. Lühr, S., Lazarescu, M.: Incremental clustering of dynamic data streams using connectivity-based representative points. IEEE Trans. Knowl. Data Eng. 68, 1–27 (2009)

    Article  Google Scholar 

  21. Okeyo, G., Chen, L., Wang, H., Sterritt, R.: Dynamic sensor data segmentation for real-time knowledge-driven activity recognition. Perv. Mob. Comput. 10(Part B), 155–172 (2014)

    Google Scholar 

  22. Sagha, H., Bayati, H., Millán, J.D.R., Chavarriaga, R.: On-line anomaly detection and resilience in classifier ensembles. Patt. Recogn. Lett. 34(15), 1916–1927 (2013)

    Article  Google Scholar 

  23. Silva, J.A., Faria, E.R., Barros, R.C., Hruschka, E.R., Carvalho, A.C.D., Gama, J.: Data stream clustering: a survey. ACM Comput. Surv. 46(1), 13:1–13:31 (2013)

    Google Scholar 

  24. Van Kasteren, T., Noulas, A., Englebienne, G., Kröse, B.: Accurate activity recognition in a home setting. In: Proceedings of 10th International Conference on Ubiquitous Computing, pp. 1–9. ACM (2008)

    Google Scholar 

  25. Wen, J., Zhong, M.: Activity discovering and modelling with labelled and unlabelled data in smart environments. Expert Syst. Appl. 42(14), 5800–5810 (2015)

    Article  Google Scholar 

  26. Wu, X., et al.: Top 10 algorithms in data mining. Knowl. Inf. Syst. 14(1), 1–37 (2007)

    Article  Google Scholar 

  27. Zhu, C., Sheng, W., Liu, M.: Wearable sensor-based behavioral anomaly detection in smart assisted living systems. IEEE Trans. Autom. Sci. Eng. 12(4), 1225–1234 (2015)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Science, University of Otago, Dunedin, New Zealand

    Brendon J. Woodford

  2. College of Business, Al Ain University, Abu Dhabi, United Arab Emirates

    Ahmad Ghandour

Authors
  1. Brendon J. Woodford
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ahmad Ghandour
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Brendon J. Woodford .

Editor information

Editors and Affiliations

  1. Zayed University, Dubai, United Arab Emirates

    Hakim Hacid

  2. Zayed University, Dubai, United Arab Emirates

    Fatma Outay

  3. University of New South Wales, Sydney, NSW, Australia

    Hye-young Paik

  4. Huawei Paris Research Center, Paris, France

    Amira Alloum

  5. National Research Council C.N.R., Pisa, Italy

    Marinella Petrocchi

  6. Deakin University, Waurn Ponds, VIC, Australia

    Mohamed Reda Bouadjenek

  7. Macquarie University, Sydney, NSW, Australia

    Amin Beheshti

  8. Rochester Institute of Technology, Rochester, NY, USA

    Xumin Liu

  9. Université de Paris, Paris, France

    Abderrahmane Maaradji

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Woodford, B.J., Ghandour, A. (2021). An Information Retrieval-Based Approach to Activity Recognition in Smart Homes. In: Hacid, H., et al. Service-Oriented Computing – ICSOC 2020 Workshops. ICSOC 2020. Lecture Notes in Computer Science(), vol 12632. Springer, Cham. https://doi.org/10.1007/978-3-030-76352-7_51

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-76352-7_51

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-76351-0

  • Online ISBN: 978-3-030-76352-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation