Skip to main content
SpringerLink
Log in

A Deep Learning and Probabilistic Approach to Recognising Activities of Daily Living with Privacy Preserving Thermal Sensors

  • Conference paper
  • First Online:
Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023) (UCAmI 2023)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 842))

  • 132 Accesses

Abstract

A privacy preserving approach for recognising Activities of Daily Living (ADLs) is proposed within this work. Low-resolution thermal sensors and Convolutional Neural Network (CNN) models were utilised for detecting positions within a smart environment and classifying human poses. A Hidden Markov Model (HMM) was implemented for which the position and pose data acted as the model’s observable information. An average F-score of 0.8171 was achieved for the poses on a test dataset. From a separate test dataset, the times in which each ADL began and ended were estimated with a maximum of 30 s between estimations and ground truth. Each ADL was correctly classified from the test dataset. Further discussion on the results are presented in this article.

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 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
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

References

  1. Köping, L., Shirahama, K., Grzegorzek, M.: A general framework for sensor-based human activity recognition. Comput. Biol. Med. 95, 248–260 (2018)

    Article  Google Scholar 

  2. Nguyen, H., Lebel, K., Bogard, S., Goubault, E., Boissy, P., Duval, C.: Using inertial sensors to automatically detect and segment activities of daily living in people with Parkinson’s disease. IEEE Trans. Neural Syst. Rehabil. Eng. 26, 197–204 (2018)

    Article  Google Scholar 

  3. Alam, M.A.U., Roy, N.: GeSmart: a gestural activity recognition model for predicting behavioral health. In: 2014 International Conference on Smart Computing, Hong Kong, China, pp. 193–200. IEEE (2014)

    Google Scholar 

  4. Galasko, D., et al.: An inventory to assess activities of daily living for clinical trials in Alzheimerʼs disease. Alzheimer Dis. Assoc. Disord. 11, 33–39 (1997)

    Article  Google Scholar 

  5. Bucks, R.S., Ashworth, D.L., Wilcock, G.K., Siegfried, K.: Assessment of activities of daily living in dementia: development of the Bristol activities of daily living scale. Age Ageing 25, 113–120 (1996)

    Article  Google Scholar 

  6. Debes, C., Merentitis, A., Sukhanov, S., Niessen, M., Frangiadakis, N., Bauer, A.: Monitoring activities of daily living in smart homes: understanding human behavior. IEEE Signal Process. Mag. 33, 81–94 (2016)

    Article  Google Scholar 

  7. Rantz, M.J., et al.: Sensor technology to support aging in place. J. Am. Med. Dir. Assoc. 14, 386–391 (2013)

    Article  Google Scholar 

  8. Ding, D., Cooper, R.A., Pasquina, P.F., Fici-Pasquina, L.: Sensor technology for smart homes. Maturitas 69, 131–136 (2011)

    Article  Google Scholar 

  9. Pontes, B., Cunha, M., Pinho, R., Fuks, H.: Human-sensing: low resolution thermal array sensor data classification of location-based postures. In: Streitz, N., Markopoulos, P. (eds.) DAPI 2017. LNCS, vol. 10291, pp. 444–457. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58697-7_33

  10. Mo, L., Li, F., Zhu, Y., Huang, A.: Human physical activity recognition based on computer vision with deep learning model. In: 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings, Taipei, Taiwan. IEEE (2016)

    Google Scholar 

  11. Cook, D.J.: How smart is your home? Science 335, 1579–1581 (2012)

    Article  Google Scholar 

  12. Caine, K.E., Rogers, W.A., Fisk, A.D.: Privacy perceptions of an aware home with visual sensing devices. Proc. Hum. Factors Ergon. Soc. Annu. Meet. 49, 1856–1858 (2005)

    Article  Google Scholar 

  13. Pittaluga, F., Zivkovic, A., Koppal, S.J.: Sensor-level privacy for thermal cameras. In: 2016 IEEE International Conference on Computational Photography (ICCP), Evanston, IL, USA, pp. 1–12. IEEE (2016)

    Google Scholar 

  14. Griffiths, E., Assana, S., Whitehouse, K.: Privacy-preserving image processing with binocular thermal cameras. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 1, 1–25 (2018)

    Article  Google Scholar 

  15. Guettari, T., et al.: Thermal signal analysis in smart home environment for detecting a human presence. In: 2014 1st International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), Sousse, Tunisia, pp. 334–339. IEEE (2014)

    Google Scholar 

  16. Hevesi, P., Wille, S., Pirkl, G., Wehn, N., Lukowicz, P.: Monitoring household activities and user location with a cheap, unobtrusive thermal sensor array. In: Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 141–145. ACM, New York (2014)

    Google Scholar 

  17. Burns, M., Morrow, P., Nugent, C., McClean, S.: Gesture recognition with thermopile sensors. In: Irish Machine Vision and Image Processing Conference Proceedings, pp. 89–96. Irish Pattern Recognition and Classification Society, Belfast, Northern Ireland (2018)

    Google Scholar 

  18. Burns, M., Morrow, P., Nugent, C., McClean, S.: Fusing thermopile infrared sensor data for single component activity recognition within a smart environment. J. Sens. Actuator Netw. 8, 1–16 (2019)

    Article  Google Scholar 

  19. Burns, M., Cruciani, F., Morrow, P., Nugent, C., McClean, S.: Using convolutional neural networks with multiple thermal sensors for unobtrusive pose recognition. Sensors 20, 1–26 (2020)

    Article  Google Scholar 

  20. Quero, J., Burns, M., Razzaq, M., Nugent, C., Espinilla, M.: Detection of falls from non-invasive thermal vision sensors using convolutional neural networks. Proc. West Mark. Ed. Assoc. Conf. 2, 1–10 (2018)

    Google Scholar 

  21. Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proc. IEEE 77, 257–286 (1989)

    Article  Google Scholar 

  22. Liciotti, D., Frontoni, E., Zingaretti, P., Bellotto, N., Duckett, T.: HMM-based activity recognition with a ceiling RGB-D camera. In: Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods, vol. 1, pp. 567–574. Science and Technology Publications, Porto, Portugal (2017)

    Google Scholar 

  23. Chen, B., Fan, Z., Cao, F.: Activity recognition based on streaming sensor data for assisted living in smart homes. In: 2015 International Conference on Intelligent Environments, Prague, Czech Republic, pp. 124–127. IEEE (2015)

    Google Scholar 

  24. H. Medjahed, D. Istrate, J. Boudy, and B. Dorizzi, “Human Activities of Daily Living Recognition Using Fuzzy Logic For Elderly Home Monitoring,” in 2009 IEEE International Conference on Fuzzy Systems, IEEE, Jeju Island, South Korea (2009)

    Google Scholar 

  25. Cheng, B.-C., Tsai, Y.-A., Liao, G.-T., Byeon, E.-S.: HMM machine learning and inference for activities of daily living recognition. J. Supercomput. 54, 29–42 (2010)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computing, Ulster University, Belfast, Co. Antrim, Northern Ireland

    Matthew Burns, Chris Nugent & Sally McClean

  2. Department of Computer Engineering, Automation and Robotics Higher Technical School of Computer Engineering and Telecommunications, University of Granada, Granada, Spain

    Javier Medina Quero

  3. Department of Computer Science, University of Jaén, Campus Las Lagunillas, 23071, Jaén, Spain

    Aurora Polo-Rodríguez

Authors
  1. Matthew Burns
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chris Nugent
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sally McClean
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Javier Medina Quero
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Aurora Polo-Rodríguez
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Matthew Burns .

Editor information

Editors and Affiliations

  1. Ciudad Real, Spain

    José Bravo

  2. Mérida, Yucatán, Mexico

    Gabriel Urzáiz

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Burns, M., Nugent, C., McClean, S., Quero, J.M., Polo-Rodríguez, A. (2023). A Deep Learning and Probabilistic Approach to Recognising Activities of Daily Living with Privacy Preserving Thermal Sensors. In: Bravo, J., Urzáiz, G. (eds) Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023). UCAmI 2023. Lecture Notes in Networks and Systems, vol 842. Springer, Cham. https://doi.org/10.1007/978-3-031-48642-5_15

Download citation

Publish with us

Policies and ethics

Search

Navigation