Daily Activity Recognition based on Meta-classification of Low-level Audio Events

Theodoros Giannakopoulos, Stasinos Konstantopoulos

2017

Abstract

This paper presents a method for recognizing activities taking place in a home environment. Audio is recorded and analysed realtime, with all computation taking place on a low-cost Raspberry PI. In this way, data acquisition, low-level signal feature calculation, and low-level event extraction is performed without transferring any raw data out of the device. This first-level analysis produces a time-series of low-level audio events and their characteristics: the event type (e.g., ‘music’) and acoustic features that are relevant to further processing, such as energy that is indicative of how loud the event was. This output is used by a meta-classifier that extracts long-term features from multiple events and recognizes higher-level activities. The paper also presents experimental results on recognizing kitchen and living-room activities of daily living that are relevant to assistive living and remote health monitoring for the elderly. Evaluation on this dataset has shown that our approach discriminates between six activities with an accuracy of more than 90%, that our two-level classification approach outperforms one-level classification, and that including low-level acoustic features (such as energy) in the input of the meta-classifier significantly boosts performance.

References

  1. Artikis, A., Gal, A., Kalogeraki, V., and Weidlich, M. (2014). Event recognition challenges and techniques. ACM Transactions on Internet Technology, 14(1).
  2. Barger, T. S., Brown, D. E., and Alwan, M. (2005). Healthstatus monitoring through analysis of behavioral patterns. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 35(1):22-27.
  3. Botia, J. A., Villa, A., and Palma, J. (2012). Ambient assisted living system for in-home monitoring of healthy independent elders. Expert Systems with Applications, 39(9):8136-8148.
  4. Breiman, L. (1997). Arcing the edge. Technical report, Technical Report 486, Statistics Department, University of California at Berkeley.
  5. Chernbumroong, S., Cang, S., Atkins, A., and Yu, H. (2013). Elderly activities recognition and classification for applications in assisted living. Expert Systems with Applications, 40(5):1662-1674.
  6. Costa, R., Carneiro, D., Novais, P., Lima, L., Machado, J., Marques, A., and Neves, J. (2009). Ambient assisted living. In 3rd Symposium of Ubiquitous Computing and Ambient Intelligence 2008, pages 86-94. Springer.
  7. de la Concepción, M. Í. Í., Morillo, L. M. S., García, J. A. Í., and González-Abril, L. (2017). Mobile activity recognition and fall detection system for elderly people using ameva algorithm. Pervasive and Mobile Computing, 34:3-13.
  8. El-Bendary, N., Tan, Q., Pivot, F. C., and Lam, A. (2013). Fall detection and prevention for the elderly: A review of trends and challenges. Int. J. Smart Sens. Intell. Syst, 6(3):1230-1266.
  9. Friedman, J. H. (2002). Stochastic gradient boosting. Computational Statistics & Data Analysis, 38(4):367-378.
  10. Geurts, P., Ernst, D., and Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1):3-42.
  11. Giannakopoulos, T. (2015). pyaudioanalysis: An opensource python library for audio signal analysis. PloS one, 10(12):e0144610.
  12. Giannakopoulos, T., Konstantopoulos, S., Siantikos, G., and Karkaletsis, V. (2017). Design for a system of multimodal interconnected adl recognition services. In Components and Services for IoT Platforms, pages 323-333. Springer.
  13. Hagler, S., Austin, D., Hayes, T. L., Kaye, J., and Pavel, M. (2010). Unobtrusive and ubiquitous in-home monitoring: a methodology for continuous assessment of gait velocity in elders. Biomedical Engineering, IEEE Transactions on, 57(4):813-820.
  14. Ho, T. K. (1995). Random decision forests. In Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on, volume 1, pages 278-282. IEEE.
  15. Khan, A. M., Lee, Y.-K., Lee, S. Y., and Kim, T.- S. (2010). A triaxial accelerometer-based physicalactivity recognition via augmented-signal features and a hierarchical recognizer. IEEE transactions on information technology in biomedicine, 14(5):1166-1172.
  16. Li, X., Chen, J., Zhao, G., and Pietikainen, M. (2014). Remote heart rate measurement from face videos under realistic situations. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4264-4271.
  17. Mann, W. C., Marchant, T., Tomita, M., Fraas, L., and Kathleen, S. (2002). Elder acceptance of health monitoring devices in the home. Care Management Journals, 3(2):91-98.
  18. Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1):217-222.
  19. Petridis, S., Giannakopoulos, T., and Perantonis, S. (2015a). Unobtrusive low-cost physiological monitoring using visual information. In Handbook of Research on Innovations in the Diagnosis and Treatment of Dementia, pages 306-316. IGI Global.
  20. Petridis, S., Giannakopoulos, T., and Spyropoulos, C. D. (2015b). A low cost pupillometry approach. International Journal of E-Health and Medical Communications, 6(4):49-61.
  21. Platt, J. C. (1999). Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In Advances in large margin classifiers . Citeseer.
  22. Siantikos, G., Giannakopoulos, T., and Konstantopoulos, S. (2016). A low-cost approach for detecting activities of daily living using audio information: A use case on bathroom activity monitoring. In Proceedings of the 2nd International Conference on Information and Communication Technologies for Ageing Well and eHealth (ICT4AWE 2016).
  23. Stikic, M., Huynh, T., Van Laerhoven, K., and Schiele, B. (2008). Adl recognition based on the combination of rfid and accelerometer sensing. In Pervasive Computing Technologies for Healthcare, 2008. PervasiveHealth 2008. Second International Conference on, pages 258-263. IEEE.
  24. Vacher, M., Portet, F., Fleury, A., and Noury, N. (2010). Challenges in the processing of audio channels for ambient assisted living. In e-Health Networking Applications and Services (Healthcom), 2010 12th IEEE International Conference on, pages 330-337. IEEE.
  25. Vacher, M., Portet, F., Fleury, A., and Noury, N. (2013). Development of audio sensing technology for ambient assisted living: Applications and challenges. Digital Advances in Medicine, E-Health, and Communication Technologies, page 148.
Download


Paper Citation


in Harvard Style

Giannakopoulos T. and Konstantopoulos S. (2017). Daily Activity Recognition based on Meta-classification of Low-level Audio Events . In Proceedings of the 3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE, ISBN 978-989-758-251-6, pages 220-227. DOI: 10.5220/0006372502200227


in Bibtex Style

@conference{ict4awe17,
author={Theodoros Giannakopoulos and Stasinos Konstantopoulos},
title={Daily Activity Recognition based on Meta-classification of Low-level Audio Events},
booktitle={Proceedings of the 3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE,},
year={2017},
pages={220-227},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006372502200227},
isbn={978-989-758-251-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE,
TI - Daily Activity Recognition based on Meta-classification of Low-level Audio Events
SN - 978-989-758-251-6
AU - Giannakopoulos T.
AU - Konstantopoulos S.
PY - 2017
SP - 220
EP - 227
DO - 10.5220/0006372502200227