Physiotherapy-based human activity recognition using deep learning | Neural Computing and Applications Skip to main content
Springer Nature Link
Log in

Physiotherapy-based human activity recognition using deep learning

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

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Nowadays, continuous human activity recognition is being studied broadly by investigators for diverse applications. However, the studies based on physiotherapy action tracking from the physiotherapy video dataset are limited. Hence, the physiotherapy dataset has been considered in this present study. Moreover, deep learning-based (DL) neural networks have promoted the enhancement of activity detection study to become an essential technique. DL-based neural networks, such as long short-term memory, can automatically acquire the significant features from the physiotherapy video of sub-activity and main activity. Nevertheless, some physiotherapy videos are inappropriate and correspond to insignificant actions. Consequently, these insignificant actions can cause the recognition of continuous movements. Therefore, a novel strawberry-based recurrent neural framework is proposed to address this issue. Here, a physiotherapy video is taken as the input, and this dataset consists of several actions. Consequently, all the steps are done by one single person. So, the proposed design initially identifies all sub-activities based on that sub-activities, and the main physiotherapy actions were classified. After that, repeated action counts and their starting and ending times are evaluated. Finally, the present study's design is considered in terms of performance metrics. Three things are mentioned in this article. First the class determines whether the human body is static, dynamic, or transitional, which class indicates the position of action. To recognize the main activity, it is important to first identify all sub-activities in the physiotherapy video. Then, you should count the number of times each sub-activity was performed and how long it took overall. The proposed model was implemented using the Python platform, and the results were compared with the existing models. The proposed model shows higher recognition accuracy in comparison.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

References

  1. Lim JS et al (2020) The role of wishful identification, emotional engagement, and parasocial relationships in repeated viewing of live-streaming games: a social cognitive theory perspective. Comput Hum Behav 108:106327

    Article  Google Scholar 

  2. Liu J et al (2019) Wireless sensing for human activity: a survey. IEEE Commun Surv Tutor 22(3):1629–1645

    Article  Google Scholar 

  3. Goldberg P et al (2021) Attentive or not? Toward a machine learning approach to assessing students’ visible engagement in classroom instruction. Educ Psychol Rev 33(1):27–49

    Article  MathSciNet  Google Scholar 

  4. Ahad MAR, Antar AD, Ahmed M (2020) IoT sensor-based activity recognition. Springer

    Google Scholar 

  5. Oksuz K et al (2021) Imbalance problems in object detection: a review. IEEE Trans Pattern Anal Mach Intell 43(10):3388–3415

    Article  Google Scholar 

  6. Beddiar DR et al (2020) Vision-based human activity recognition: a survey. Multimed Tools Appl 79(41):30509–30555

    Article  Google Scholar 

  7. Subasi A et al (2020) Human activity recognition using machine learning methods in a smart healthcare environment. In: Innovation in health informatics. Academic press, pp 123–144

  8. Prasanth SM et al (2021) Application of biomass derived products in Mid-Size automotive industries: a review. Chemosphere 280:130723

    Article  Google Scholar 

  9. Chen Y, Shen C (2017) Performance analysis of smartphone-sensor behavior for human activity recognition. IEEE Access 5:3095–3110

    Article  Google Scholar 

  10. Ramanujam E, Perumal T, Padmavathi S (2021) Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review. IEEE Sens J 21:13029–13040

    Article  Google Scholar 

  11. Chen K et al (2021) Deep learning for sensor-based human activity recognition: overview, challenges, and opportunities. ACM Comput Surv 54(4):1–40

    Google Scholar 

  12. Biagetti G et al (2018) Human activity monitoring system based on wearable sEMG and accelerometer wireless sensor nodes. Biomed Eng Online 17(1):1–18

    Google Scholar 

  13. Yeung S (2018) Visual understanding of human activity: towards ambient intelligence in AI-assisted hospitals. Stanford University

    Google Scholar 

  14. Reynolds CR, Altmann RA, Allen DN (2021) The problem of bias in psychological assessment. In: Mastering modern psychological testing. Springer, Cham, pp 573–613

  15. Ronald M et al (2021) iSPLInception: an inception-ResNet deep learning architecture for human activity recognition. IEEE Access 9:68985–69001

    Article  Google Scholar 

  16. Hassan MM et al (2018) A robust human activity recognition system using smartphone sensors and deep learning. Futur Gener Comput Syst 81:307–313

    Article  Google Scholar 

  17. Zhou X et al (2020) Deep-learning-enhanced human activity recognition for internet of healthcare things. IEEE Internet Things J 7(7):6429–6438

    Article  MathSciNet  Google Scholar 

  18. Nweke HF et al (2018) Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: state of the art and research challenges. Expert Syst Appl 105:233–261

    Article  Google Scholar 

  19. Hu JF et al (2018) Early action prediction by soft regression. IEEE Trans Pattern Anal Mach Intell 41(11):2568–2583

    Article  Google Scholar 

  20. Yıldırım Ö, Baloglu UB, Acharya UR (2020) A deep convolutional neural network model for automated identification of abnormal EEG signals. Neural Comput Appl 32(20):15857–15868

    Article  Google Scholar 

  21. Shrestha A et al (2020) Continuous human activity classification from FMCW radar with Bi-LSTM networks. IEEE Sens J 20(22):13607–13619

    Article  Google Scholar 

  22. Gorji A et al (2021) On the generalization and reliability of single radar-based human activity recognition. IEEE Access 2021:85334–85349

    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

    Article  Google Scholar 

  24. Li H et al (2019) Bi-LSTM network for multimodal continuous human activity recognition and fall detection. IEEE Sens J 20(3):1191–1201

    Article  Google Scholar 

  25. Altuve M, PLizarazo P, Villamizar J (2020) Human activity recognition using improved complete ensemble EMD with adaptive noise and long short-term memory neural networks. Biocybern Biomed Eng 40(3):901–909

    Article  Google Scholar 

  26. Sreejith S, Nehemiah HK, Kannan A (2020) A classification framework using a diverse intensified strawberry optimized neural network (DISON) for clinical decision-making. Cogn Syst Res 64:98–116

    Article  Google Scholar 

  27. Chianese A et al (2013) A novel challenge into multimedia cultural heritage: an integrated approach to support cultural information enrichment. In: International conference on signal-image technology and internet-based systems, pp 217–224

  28. Palma G et al (2013) 3D Non-Local Means denoising via multi-GPU. In: Federated conference on computer science and information systems, pp 495–498

  29. Piccialli F, Cuomo S, De Michele P (2013) A regularized MRI image reconstruction based on hessian penalty term on CPU/GPU systems. Procedia Comput Sci 18:2643–2646

    Article  Google Scholar 

  30. Kashif NQ, Ahmad A, Piccialli F et al (2021) Nature-inspired algorithm-based secure data dissemination framework for smart city networks. Neural Comput Appl 33:10637–10656

    Article  Google Scholar 

  31. Verma P, Sah A, Srivastava R (2020) Deep learning-based multi-modal approach using RGB and skeleton sequences for human activity recognition. Multimed Syst 26(6):671–685

    Article  Google Scholar 

  32. Mahmud T et al (2020) A novel multi-stage training approach for human activity recognition from multimodal wearable sensor data using deep neural network. IEEE Sens J 21(2):1715–1726

    Article  Google Scholar 

  33. Chung S et al (2019) Sensor data acquisition and multimodal sensor fusion for human activity recognition using deep learning. Sensors 19(7):1716

    Article  Google Scholar 

  34. Kerdjidj O et al (2020) Fall detection and human activity classification using wearable sensors and compressed sensing. J Ambient Intell Humaniz Comput 11(1):349–361

    Article  Google Scholar 

  35. Huang Po-Sen, et al (2014) Kernel methods match deep neural networks on timit. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 205–209

  36. Lima WS, Bragança HLS, Souto EJP (2021) NOHAR-NOvelty discrete data stream for Human Activity Recognition based on smartphones with inertial sensors. Expert Syst Appl 166:114093

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Artificial Intelligence, G H Raisoni College of Engineering and Management, Pune, India

    Disha Deotale

  2. School of Computer Science Engineering and Technology, Bennett University, Greater Noida, India

    Madhushi Verma

  3. CIDRIE, Muthoot Institute of Technology and Science, Ernakulam, Kochi, India

    P. Suresh

  4. Department of Computer Science and Engineering, Thapar University Patiala Punjab and School of Computer Science, University of Petroleum and Energy Studies, Dehradun, Uttarakhand, India

    Neeraj Kumar

  5. Department of Electrical and Computer Engineering, Lebanese American University, Beirut, Lebanon

    Neeraj Kumar

  6. Chandigarh University, Gharuan, Mohali and Faculty of Computing and IT, King Abdulaziz University, Jeddah, Saudi Arabia

    Neeraj Kumar

Authors
  1. Disha Deotale
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Madhushi Verma
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. P. Suresh
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Neeraj Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Disha Deotale.

Ethics declarations

Conflict of interest

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

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Deotale, D., Verma, M., Suresh, P. et al. Physiotherapy-based human activity recognition using deep learning. Neural Comput & Applic 35, 11431–11444 (2023). https://doi.org/10.1007/s00521-023-08307-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-08307-4

Keywords

Search

Navigation