Skip to main content
SpringerLink
Log in

Reusing training data with generative/discriminative hybrid model for practical acceleration-based activity recognition

  • Published:
Computing Aims and scope Submit manuscript

Abstract

This paper proposes a new daily activity recognition method that can learn an activity classification model with small quantities of training data by sharing training data among different activity classes. Many existing activity recognition studies employ a supervised machine learning approach and thus require an end user’s labeled training data, this approach places a large burden on the user. In this study, we assume that a user wears sensors (accelerometers) on several parts of the body such as the hands, waist, and thigh, and we attempt to share sensor data obtained from only selected accelerometers (e.g., only waist and thigh sensors) among two different activity classes based on a sensor data similarity measure. This approach permits us to correctly learn parameters of an activity classification model by using sufficient quantities of shared sensor data without adding new training data. We confirmed the effectiveness of our method by using 48 h of sensor data obtained from 20 participants, and achieved a good recognition accuracy.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

References

  1. Bao L, Intille S (2004) Activity recognition from user-annotated acceleration data. In: Ferscha A, Mattern F (eds) Pervasive 2004. LNCS, vol 3001, pp 1–17

  2. Bouchard B, Giroux S, Bouzouane A (2007) A keyhole plan recognition model for Alzheimer’s patients: first results. Appl Artif Intell 21(7):623–658

    Article  Google Scholar 

  3. Casio Inc. Casio products. http://www.casio.com/products/Timepiece/Sports/

  4. Dempster A, Laird N, Rubin D et al (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc Ser B (Methodological) 39(1):1–38

    MATH  MathSciNet  Google Scholar 

  5. Forster K, Biasiucci A, Chavarriaga R, del R Millan, J, Roggen D, Tröster G (2010) On the use of brain decoded signals for online user adaptive gesture recognition systems. In: Proceedings of 8th international conference on pervasive computing, pp 427–444

  6. Huynh T, Schiele B (2006) Towards less supervision in activity recognition from wearable sensors. In: Proceedings of international symposium on wearable computers, pp 3–10

  7. Jenssen R, Erdogmus D, Hild K, Principe J, Eltoft T (2005) Optimizing the Cauchy-Schwarz PDF distance for information theoretic, non-parametric clustering. In: Energy minimization methods in computer vision and pattern recognition, pp 34–45

  8. Kampa K, Hasanbelliu E, Principe J (2011) Closed-form Cauchy-Schwarz PDF divergence for mixture of Gaussians. In: Proceedings of international joint conference on neural networks, pp 2578–2585

  9. Krassnig G, Tantinger D, Hofmann C, Wittenberg T, Struck M (2010) User-friendly system for recognition of activities with an accelerometer. In: Proceedings of 4th international conference on-no permissions, pp 1–8

  10. Lane N, Xu Y, Lu H, Hu S, Choudhury T, Campbell A, Zhao F (2011) Enabling large-scale human activity inference on smartphones using community similarity networks (CSN). In: Proceedings of UbiComp, 17–21 Sept 2011, Beijing, China, pp 355–364

  11. Lester J, Choudhury T, Borriello G (2006) A practical approach to recognizing physical activities. In: Pervasive, LNCS 3968, pp 1–16

  12. Lukowicz P, Junker H, Stager M, Buren TV, Tröster G (2002) Wearnet: A distributed multi-sensor system for context aware wearables. In: Proceedings of Ubicomp 2002, pp 361–370

  13. Maekawa T, Watanabe S (2011) Unsupervised activity recognition with user’s physical characteristics data. In: Proceedings of international symposium on wearable computers, pp 89–96

  14. Maekawa T, Yanagisawa Y, Kishino Y, Ishiguro K, Kamei K, Sakurai Y, Okadome T (2010) Object-based activity recognition with heterogeneous sensors on wrist. In: Pervasive 2010, pp 246–264

  15. NIKE Inc. Nike+. http://nikeplus.nike.com/plus/

  16. Ohmura R, Hashida N, Imai M (2009) Preliminary evaluation of personal adaptation techniques in accelerometer-based activity recognition. In: Proceedings of 13th international symposium on late breaking results, wearable computers, Linz, Austria, Sept 2009

  17. Pollack M, Brown L, Colbry D, McCarthy C, Orosz C, Peintner B, Ramakrishnan S, Tsamardinos I (2003) Autominder: an intelligent cognitive orthotic system for people with memory impairment. Robot Auton Syst 44(3):273–282

    Article  Google Scholar 

  18. Ravi N, Dandekar N, Mysore P, Littman M (2005) Activity recognition from accelerometer data. In: IAAI 2005, vol. 20, pp 1541–1546

  19. Stikic M, Van Laerhoven K, Schiele B (2008) Exploring semi-supervised and active learning for activity recognition. In: Proceedings of international symposium on wearable computers, pp 81–88

  20. Welk G, Differding J (2000) The utility of the digi-walker step counter to assess daily physical activity patterns. Med Sci Sports Exerc 32(9):S481–S488

    Article  Google Scholar 

  21. Witten I, Frank E (2004) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, Burlington

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Grad. Sch. of Information Science and Technology, Osaka University, Suita, Japan

    Quan Kong & Takuya Maekawa

Authors
  1. Quan Kong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Takuya Maekawa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Takuya Maekawa.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kong, Q., Maekawa, T. Reusing training data with generative/discriminative hybrid model for practical acceleration-based activity recognition. Computing 96, 875–895 (2014). https://doi.org/10.1007/s00607-013-0326-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00607-013-0326-0

Keywords

Mathematics Subject Classification

Search

Navigation