Skip to main content
SpringerLink
Log in

Deep ensemble learning approach for lower limb movement recognition from multichannel sEMG signals

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

Abstract

Walking is a complex task that requires consistent practice to master, and it involves the synchronisation between the lower limbs and the brain, making it challenging. While bipedal robots have been developed to mimic human walking, they must achieve an efficient gait due to structural differences and walking challenges. This study aims to produce a more human-like walk by analysing human lower extremity activities. To capture the bipedal robot locomotion learning process, an ensemble classifier based on deep learning is introduced to recognise human lower activities. A publicly available UC Irvine Machine Learning Repository (UCI) dataset on surface electromyography (sEMG) signal for the lower extremity of 11 fit participants and 11 participants with knee disorders for sitting while performing knee extension, walking, and standing while performing knee flexion is used. A hybrid ensemble of deep learning models comprising long short-term memory and convolution neural network is employed to classify activities, with reported average accuracies of 98.8%, 98.3%, and 99.3% for healthy subjects for sitting, standing and walking, respectively. Moreover, the ensemble model reported average accuracies of 98.2%, 98.1%, and 99.0% for individuals with knee pathology. Notably, this study holds promising significance, as it has yielded a considerable enhancement in performance as opposed to state-of-the-art work. The applications of this work are diverse and include improving postural stability in elderly subjects, aiding in the rehabilitation of patients recovering from stroke and trauma, generating walking trajectories for robots in complex environments, and reconstructing walking patterns in individuals with impairments.

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
Algorithm 1
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

The dataset analysed during the current study are available in the UCI Machine Learning repository, http://archive.ics.uci.edu/ml/datasets/emg+dataset+in+lower+limb.

References

  1. Kujala UM, Orava S, Parkkari J, Kaprio J, Sarna S (2003) Sports career-related musculoskeletal injuries: long-term health effects on former athletes. Sports Med 33:869–75

    Article  PubMed  Google Scholar 

  2. Kianifar R, Lee A, Raina S, Kulic D (2017) Automated assessment of dynamic knee valgus and risk of knee injury during the single leg squat. IEEE J Trans Eng Health Med 30(5):1–3

    Article  Google Scholar 

  3. Dua Nidhi, Singh Shiva, Semwal Vijay, Challa Sravan (2022) Inception inspired CNN-GRU hybrid network for human activity recognition. Multimed Tools Appl 82:03

    Google Scholar 

  4. Anjali Gupta and Vijay Bhaskar Semwal (2022) Occluded gait reconstruction in multi person gait environment using different numerical methods. Multimed Tools Appl 81(16):23421–23448

    Article  Google Scholar 

  5. Baker R (2006) Gait analysis methods in rehabilitation. J Neuroeng Rehabil 3(1):4

    Article  PubMed  PubMed Central  Google Scholar 

  6. Muro-De-La-Herran A, Garcia-Zapirain B, Mendez-Zorrilla A (2014) Gait analysis methods: an overview of wearable and non-wearable systems, highlighting clinical applications. Sensors Basel Switz 14:3362–94

    Article  ADS  Google Scholar 

  7. Semwal VB, Gaud N, Nandi GC. (2019) Human gait state prediction using cellular automata and classification using elm. In M. Tanveer and Ram Bilas Pachori, editors, Machine intelligence and signal analysis, pp 135–145, Singapore, Springer Singapore

  8. Semwal VB, Gupta A, Lalwani P (2021) An optimized hybrid deep learning model using ensemble learning approach for human walking activities recognition. J Supercomput 77(11):12256–12279

    Article  Google Scholar 

  9. Challa SK, Kumar A, Semwal VB (2021) A multibranch CNN-BILSTM model for human activity recognition using wearable sensor data. Vis Comput 38(12):4095–4109

    Article  Google Scholar 

  10. Qiu Sen, Fan Tianqi, Jiang Junhan, Wang Zhelong, Wang Yongzhen, Junnan Xu, Sun Tao, Jiang Nan (2023) A novel two-level interactive action recognition model based on inertial data fusion. Inform Sci 633:264–279

    Article  Google Scholar 

  11. Del Din S, Godfrey A, Mazza C, Lord S, Rochester L. (2016) Free-living monitoring of parkinson’s disease: lessons from the field. Movement Disorders, 31, 06

  12. Gautam Arvind, Panwar Madhuri, Biswas Dwaipayan, Acharyya Amit (2020) Myonet: a transfer-learning-based LRCN for lower limb movement recognition and knee joint angle prediction for remote monitoring of rehabilitation progress from semg. IEEE J Trans Eng Health Med 8:1–10

    Article  Google Scholar 

  13. Khan IU, Afzal S, Lee JW (2022) Human activity recognition via hybrid deep learning based model. Sensors 22(1):323

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  14. Krawczyk Bartosz (2016) Learning from imbalanced data: open challenges and future directions. Prog Artif Intell 5:04

    Article  Google Scholar 

  15. Rajesh KN, Dhuli R (2018) Classification of imbalanced ECG beats using re-sampling techniques and AdaBoost ensemble classifier. Biomed Signal Process Control 41:242–54

    Article  Google Scholar 

  16. Nahar J, Imam T, Tickle KS, Ali AS, Chen YP (2012) Computational intelligence for microarray data and biomedical image analysis for the early diagnosis of breast cancer. Expert Syst Appl 39(16):12371–7

    Article  Google Scholar 

  17. Taft LM, Evans RS, Shyu CR, Egger MJ, Chawla N, Mitchell JA, Thornton SN, Bray B, Varner M (2009) Countering imbalanced datasets to improve adverse drug event predictive models in labor and delivery. J Biomed Inform 42(2):356–364

    Article  CAS  PubMed  Google Scholar 

  18. He H, Bai Y, Garcia E, Li SA (2008) Adasyn: Adaptive synthetic sampling approach for imbalanced learning. pp 1322 – 1328, 07

  19. Nur Ghaniaviyanto Ramadhan (2021) Comparative analysis of Adasyn-Svm and smote-Svm methods on the detection of type 2 diabetes mellitus. Sci J Inform 8(2):276–282

    Google Scholar 

  20. Jia Hairui, Chen Shuwei (2020) Integrated data and knowledge driven methodology for human activity recognition. Inform Sci 536:409–430

    Article  Google Scholar 

  21. Sekaran SR, Han PY, Yin OS (2023) Smartphone-based human activity recognition using lightweight multiheaded temporal convolutional network. Expert Syst Appl 227:120132

    Article  Google Scholar 

  22. Han Chaolei, Zhang Lei, Tang Yin, Huang Wenbo, Min Fuhong, He Jun (2022) Human activity recognition using wearable sensors by heterogeneous convolutional neural networks. Expert Syst Appl 198:116764

    Article  Google Scholar 

  23. Roetenberg Daniel, Luinge Henk, Slycke Per (2009) Xsens mvn: full 6dof human motion tracking using miniature inertial sensors. Xsens Motion Technol BV Tech Rep 3:01

    Google Scholar 

  24. Naik GR, Selvan SE, Arjunan SP, Acharyya A, Kumar DK, Ramanujam A, Nguyen HT (2018) An ICA-EBM-based sEMG classifier for recognizing lower limb movements in individuals with and without knee pathology. IEEE Trans Neural Syst Rehabil Eng 26(3):675–86

    Article  PubMed  Google Scholar 

  25. Zhang Y, Xu P, Li P, Duan K, Wen Y, Yang Q, Zhang T, Yao D (2017) Noise-assisted multivariate empirical mode decomposition for multichannel emg signals. Biomed Eng Online 16(1):107

    Article  PubMed  PubMed Central  Google Scholar 

  26. Wang Xingjian, Dong Dengpeng, Chi Xiaokai, Wang Shaoping, Miao Yinan, An Mailing, Gavrilov Alexander I (2021) SEMG-based consecutive estimation of human lower limb movement by using multi-branch neural network. Biomed Signal Process Control 68:102781

    Article  Google Scholar 

  27. Bansal H, Chinagundi B, Rana PS, Kumar N (2022) An ensemble machine learning technique for detection of abnormalities in knee movement sustainability. Sustainability 14(20):13464

    Article  Google Scholar 

  28. Cai Shibo, Chen Dipei, Fan Bingfei, Mingyu Du, Bao Guanjun, Li Gang (2023) Gait phases recognition based on lower limb SEMG signals using lda-Pso-lstm algorithm. Biomed Signal Process Control 80:104272

    Article  Google Scholar 

  29. Juan Tu, Dai ZunXiang, Zhao Xiang, Huang Zijuan (2023) Lower limb motion recognition based on surface electromyography. Biomed Signal Process Control 81:104443

    Article  Google Scholar 

  30. Venkatachalam K, Yang Z, Trojovsky P, Bacanin N, Deveci M, Ding W (2023) Bimodal HAR-An efficient approach to human activity analysis and recognition using bimodal hybrid classifiers. Inform Sci 628:542–57

    Article  Google Scholar 

  31. Sola J, Sevilla J (1997) Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans Nucl Sci 44(3):1464–8

    Article  ADS  Google Scholar 

  32. Demšar Janez (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(1):1–30

    MathSciNet  Google Scholar 

  33. Olive Jean Dunn (1961) Multiple comparisons among means. J Am Stat Assoc 56:52–64

    Article  MathSciNet  Google Scholar 

  34. Wilcoxon F (1945) Individual comparisons by ranking methods. Biometrics 1:196–202

    MathSciNet  Google Scholar 

  35. Hayashi M, Koga S, Kitagawa T (2023) Effectiveness of rehabilitation for knee osteoarthritis associated with isolated meniscus injury—a scoping review. Cureus 14(e34544):02

    Google Scholar 

  36. Wren TA, Do KP, Rethlefsen SA, Healy B (2006) Cross-correlation as a method for comparing dynamic electromyography signals during gait. J Biomech 39(14):2714–8

    Article  PubMed  Google Scholar 

  37. Al-Ayyad M, Owida HA, De Fazio R, Al-Naami B, Visconti P (2023) Electromyography monitoring systems in rehabilitation: a review of clinical applications, wearable devices and signal acquisition methodologies. Electronics 12(7):1520

    Article  Google Scholar 

  38. Herrera-Gonzalez M, Martinez-Hernandez GA, Rodriguez-Sotelo JL, Aviles-Sanchez OF (2015) Knee functional state classification using surface electromyographic and goniometric signals by means of artificial neural networks. Ing Univ 1:51–66

    Google Scholar 

  39. Ertugrul OF, Kaya Y, Tekin R (2016) A novel approach for SEMG signal classification with adaptive local binary patterns. Med Biol Eng Comput 54:1137–46

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This work was supported by the Ministry of Education, Government of India, through the project HEFA CSR under Grant SAN/CSR/08/2021-22. The authors would like to thank the volunteers who have participated and contributed in preparation of the dataset and also the creator of the dataset.

Funding

The work is funded by Ministry of Education, Govt. of India to Dr. Vijay Bhaskar Semwal under Higher Education Financing Agency (HEFA) under CSR Grant with Sanctioned order no- SAN/CSR/08/2021-22.

Author information

Authors and Affiliations

  1. Maulana Azad National Institute of Technology, Bhopal, M.P., India

    Pratibha Tokas, Vijay Bhaskar Semwal & Sweta Jain

Authors
  1. Pratibha Tokas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vijay Bhaskar Semwal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sweta Jain
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

P.T and V.B contributed to conceptualisation and methodology; P.T contributed to software; P.T, V.B and S.J contributed to validation and writing–original draft preparation and review and editing; V.B and S.J supervised the study. All authors have read and approved the final manuscript.

Corresponding author

Correspondence to Pratibha Tokas.

Ethics declarations

Conflict of interest

The authors state that they do not have any conflicts of interest.

Compliance with Ethical Standards

All the ethical issues have been taken care of while writing the manuscript, and we have complied with all the standards to the best of our knowledge.

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

Tokas, P., Semwal, V.B. & Jain, S. Deep ensemble learning approach for lower limb movement recognition from multichannel sEMG signals. Neural Comput & Applic 36, 7373–7388 (2024). https://doi.org/10.1007/s00521-024-09465-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-024-09465-9

Keywords

Search

Navigation