Skip to main content
SpringerLink
Log in

Feature learning using convolutional denoising autoencoder for activity recognition

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Wearable technology offers a prospective solution to the increasing demand for activity monitoring in pervasive healthcare. Feature extraction and selection are crucial steps in activity recognition since it determines the accuracy of activity classification. However, existing feature extraction and selection methods involve manual feature engineering, which is time-consuming, laborious and prone to error. Therefore, this paper proposes an unsupervised feature learning method that automatically extracts and selects the features without human intervention. Specifically, the proposed method jointly trains a convolutional denoising autoencoder with a convolutional neural network to learn the underlying features and produces a compact feature representation of the data. This allows not only more accurate and discriminative features to be extracted but also reduces the computational cost and improves generalization of the classification models. The proposed method was evaluated and compared with deep learning convolutional neural networks on a public dataset. Results have shown that the proposed method can learn a salient feature representation and subsequently recognize the activities with an accuracy of 0.934 and perform comparably well to the convolutional neural networks.

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

Similar content being viewed by others

References

  1. Landi F, Onder G, Carpenter I et al (2007) Physical activity prevented functional decline among frail community-living elderly subjects in an international observational study. J Clin Epidemiol 60:518–524. https://doi.org/10.1016/j.jclinepi.2006.09.010

    Article  Google Scholar 

  2. Jansen FM, Prins RG, Etman A et al (2015) Physical activity in non-frail and frail older adults. PLoS ONE 10:e0123168. https://doi.org/10.1371/journal.pone.0123168

    Article  Google Scholar 

  3. Durstine JL, Gordon B, Wang Z, Luo X (2013) Chronic disease and the link to physical activity. J Sport Health Sci 2:3–11. https://doi.org/10.1016/j.jshs.2012.07.009

    Article  Google Scholar 

  4. Naci H, Ioannidis JPA (2013) Comparative effectiveness of exercise and drug interventions on mortality outcomes: metaepidemiological study. BMJ 347:f5577. https://doi.org/10.1136/bmj.f5577

    Article  Google Scholar 

  5. Lara OD, Labrador MA (2013) A survey on human activity recognition using wearable sensors. IEEE Commun Surv Tutor 15:1192–1209. https://doi.org/10.1109/SURV.2012.110112.00192

    Article  Google Scholar 

  6. Suto J, Oniga S, Lung C, Orha I (2018) Comparison of offline and real-time human activity recognition results using machine learning techniques. Neural Comput Appl. https://doi.org/10.1007/s00521-018-3437-x

    Article  Google Scholar 

  7. Rosati S, Balestra G, Knaflitz M (2018) Comparison of different sets of features for human activity recognition by wearable sensors. Sensors 18:4189. https://doi.org/10.3390/s18124189

    Article  Google Scholar 

  8. Parkka J, Ermes M, Korpipaa P et al (2006) Activity classification using realistic data from wearable sensors. IEEE Trans Inf Technol Biomed 10:119–128. https://doi.org/10.1109/TITB.2005.856863

    Article  Google Scholar 

  9. Kwon M-C, Choi S (2018) Recognition of daily human activity using an artificial neural network and smartwatch. Wirel Commun Mob Comput 2018:2618045. https://doi.org/10.1155/2018/2618045

    Article  Google Scholar 

  10. Fuentes D, Gonzalez-Abril L, Angulo C, Ortega JA (2012) Online motion recognition using an accelerometer in a mobile device. Expert Syst Appl 39:2461–2465. https://doi.org/10.1016/j.eswa.2011.08.098

    Article  Google Scholar 

  11. Catal C, Tufekci S, Pirmit E, Kocabag G (2015) On the use of ensemble of classifiers for accelerometer-based activity recognition. Appl Soft Comput 37:1018–1022. https://doi.org/10.1016/j.asoc.2015.01.025

    Article  Google Scholar 

  12. Xu S, Tang Q, Jin L, Pan Z (2019) A cascade ensemble learning model for human activity recognition with smartphones. Sensors. https://doi.org/10.3390/s19102307

    Article  Google Scholar 

  13. Ronao CA, Cho S-B (2017) Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models. Int J Distrib Sens Netw 13:1550147716683687. https://doi.org/10.1177/1550147716683687

    Article  Google Scholar 

  14. Preece SJ, Goulermas JY, Kenney LPJ, Howard D (2009) A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Trans Biomed Eng 56:871–879. https://doi.org/10.1109/TBME.2008.2006190

    Article  Google Scholar 

  15. Balli S, Sağbaş EA, Peker M (2018) Human activity recognition from smart watch sensor data using a hybrid of principal component analysis and random forest algorithm. Meas Control. https://doi.org/10.1177/0020294018813692

    Article  Google Scholar 

  16. Vanrell SR, Milone DH, Rufiner HL (2018) Assessment of homomorphic analysis for human activity recognition from acceleration signals. IEEE J Biomed Health Inform 22:1001–1010. https://doi.org/10.1109/JBHI.2017.2722870

    Article  Google Scholar 

  17. Wang Z, Wu D, Chen J et al (2016) A triaxial accelerometer-based human activity recognition via EEMD-based features and game-theory-based feature selection. IEEE Sens J 16:3198–3207. https://doi.org/10.1109/JSEN.2016.2519679

    Article  Google Scholar 

  18. Ker J, Wang L, Rao J, Lim T (2018) Deep learning applications in medical image analysis. IEEE Access 6:9375–9389. https://doi.org/10.1109/ACCESS.2017.2788044

    Article  Google Scholar 

  19. Justesen N, Bontrager P, Togelius J, Risi S (2019) Deep learning for video game playing. IEEE Trans Games. https://doi.org/10.1109/TG.2019.2896986

    Article  Google Scholar 

  20. Xin Y, Kong L, Liu Z et al (2018) Machine learning and deep learning methods for cybersecurity. IEEE Access 6:35365–35381. https://doi.org/10.1109/ACCESS.2018.2836950

    Article  Google Scholar 

  21. Ronao CA, Cho S-B (2016) Human activity recognition with smartphone sensors using deep learning neural networks. Expert Syst Appl 59:235–244. https://doi.org/10.1016/j.eswa.2016.04.032

    Article  Google Scholar 

  22. Almaslukh B, Al Muhtadi J, Artoli AM (2018) A robust convolutional neural network for online smartphone-based human activity recognition. J Intell Fuzzy Syst 35:1609–1620. https://doi.org/10.3233/JIFS-169699

    Article  Google Scholar 

  23. Ignatov A (2018) Real-time human activity recognition from accelerometer data using convolutional neural networks. Appl Soft Comput 62:915–922. https://doi.org/10.1016/j.asoc.2017.09.027

    Article  Google Scholar 

  24. Huang J, Lin S, Wang N et al (2019) TSE-CNN: a two-stage end-to-end CNN for human activity recognition. IEEE J Biomed Health Inform. https://doi.org/10.1109/JBHI.2019.2909688

    Article  Google Scholar 

  25. Ordóñez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16:115. https://doi.org/10.3390/s16010115

    Article  Google Scholar 

  26. Wang L (2016) Recognition of human activities using continuous autoencoders with wearable sensors. Sensors 16:189. https://doi.org/10.3390/s16020189

    Article  Google Scholar 

  27. Gao X, Luo H, Wang Q et al (2019) A human activity recognition algorithm based on stacking denoising autoencoder and lightGBM. Sensors 19:947. https://doi.org/10.3390/s19040947

    Article  Google Scholar 

  28. Gu F, Khoshelham K, Valaee S et al (2018) Locomotion activity recognition using stacked denoising autoencoders. IEEE Internet Things J 5:2085–2093. https://doi.org/10.1109/JIOT.2018.2823084

    Article  Google Scholar 

  29. Mohd Noor MH, Ahmadon MA, Osman MK (2019) Activity Recognition using Deep Denoising Autoencoder. In: 2019 9th IEEE international conference on control system, computing and engineering (ICCSCE), pp 188–192

  30. Gao L, Bourke AK, Nelson J (2014) Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems. Med Eng Phys 36:779–785. https://doi.org/10.1016/j.medengphy.2014.02.012

    Article  Google Scholar 

  31. Banos O, Galvez J-M, Damas M et al (2014) Window size impact in human activity recognition. Sensors 14:6474–6499. https://doi.org/10.3390/s140406474

    Article  Google Scholar 

  32. Fida B, Bernabucci I, Bibbo D et al (2015) Varying behavior of different window sizes on the classification of static and dynamic physical activities from a single accelerometer. Med Eng Phys 37:705–711. https://doi.org/10.1016/j.medengphy.2015.04.005

    Article  Google Scholar 

  33. Noor MHM, Salcic Z, Wang KI-K (2017) Adaptive sliding window segmentation for physical activity recognition using a single tri-axial accelerometer. Pervasive Mob Comput 38:41–59. https://doi.org/10.1016/j.pmcj.2016.09.009

    Article  Google Scholar 

  34. Vincent P, Larochelle H, Bengio Y, Manzagol P-A (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning. ACM, New York, NY, USA, pp 1096–1103

  35. Ismail Fawaz H, Forestier G, Weber J et al (2019) Deep learning for time series classification: a review. Data Min Knowl Discov 33:917–963. https://doi.org/10.1007/s10618-019-00619-1

    Article  MathSciNet  MATH  Google Scholar 

  36. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539

    Article  Google Scholar 

  37. Goodfellow I, Pouget-Abadie J, Mirza M et al (2014) Generative Adversarial Nets. In: Ghahramani Z, Welling M, Cortes C et al (eds) Advances in neural information processing systems 27. Curran Associates, Inc., Red Hook, pp 2672–2680

    Google Scholar 

  38. Reyes-Ortiz J-L, Oneto L, Samà A et al (2016) Transition-aware human activity recognition using smartphones. Neurocomputing 171:754–767. https://doi.org/10.1016/j.neucom.2015.07.085

    Article  Google Scholar 

Download references

Acknowledgements

This work has been supported in part by the Universiti Sains Malaysia under Short-Term Grant 304/PKOMP/6315206.

Author information

Authors and Affiliations

  1. School of Computer Sciences, Universiti Sains Malaysia, 11800, USM, Pulau Pinang, Malaysia

    Mohd Halim Mohd Noor

Authors
  1. Mohd Halim Mohd Noor
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohd Halim Mohd Noor.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mohd Noor, M.H. Feature learning using convolutional denoising autoencoder for activity recognition. Neural Comput & Applic 33, 10909–10922 (2021). https://doi.org/10.1007/s00521-020-05638-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-05638-4

Keywords

Search

Navigation