Skip to main content
SpringerLink
Log in

Decoding movement intent patterns based on spatiotemporal and adaptive filtering method towards active motor training in stroke rehabilitation systems

  • S.I. : Higher Level Artificial Neural Network Based Intelligent Systems
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Upper extremity (UE) neuromuscular dysfunction critically affects post-stroke patients from performing activities of daily life. In this regard, various rehabilitation robotics have been developed for providing assistive and/or resistive forces that allow stroke survivors to train their arms towards regaining the lost arm function. However, most of the rehabilitation systems function in a passively such that they only allow patients navigate already-defined trajectories that often does not align with their UE movement intention, thus hindering adequate motor function recovery. One possible way to address this problem is to use a decoded UE motion intent to trigger active and intuitive motor training for the patients, which would help restore their UE arm functions. In this study, a new approach based on spatiotemporal neuromuscular descriptor and adaptive filtering technique (STD-AFT) is proposed to optimally characterize multiple patterns of UE movements in post-stroke patients towards providing inputs for intelligently driven motor training in the rehabilitation robotic systems. The proposed STD-AFT performance was systematically investigated and assessed in comparison with commonly adopted methods via high-density surface electromyogram recordings obtained from post-stroke survivors who performed 21 distinct classes of pre-defined limb movements. Furthermore, the movement intent decoding was done using four different classification algorithms. The experimental results showed that the proposed STD-AFT achieved significant improvement of up to 13.36% (p < 0.05) in characterizing the multiple patterns of movement intents with relatively lower standard-error value even in the presence of the external interference in form of noise compared to the existing benchmark methods. Also, the STD-AFT showed obvious pattern seperability for individual movement class in a two-dimensional space. The outcomes of this study suggest that the proposed STD-AFT could provide potential inputs for active and intuitive motor training in robotic systems targeted towards stroke-rehabilitation.

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Feigin VL et al (2016) Global burden of stroke and risk factors in 188 countries, during 1990–2013: a systematic analysis for the global burden of disease study 2013. Lancet Neurol 15(9):913–924

    Article  Google Scholar 

  2. Béjot Y, Bailly H, Durier J, Giroud M (2016) Epidemiology of stroke in Europe and trends for the 21st century. La Presse Médicale 45(12):e391–e398

    Article  Google Scholar 

  3. Trujillo P, Alfonso M, Alessandro S et al (2017) Quantitative EEG for predicting upper limb motor recovery in chronic stroke robot-assisted rehabilitation. IEEE Trans Neural Syst Rehabil Eng 25(7):1058–1067

    Article  Google Scholar 

  4. Li X et al (2017) A motion-classification strategy based on sEMG-EEG signal combination for upper-limb amputees. J NeuroEng Rehabil 14(1):1–13

    Article  Google Scholar 

  5. Blank AA, French JA, Pehlivan AU, O’Malley MK (2014) Current trends in robot-assisted upper-limb stroke rehabilitation: promoting patient engagement in therapy. Curr Phys Med Rehabil Rep 2(3):184–195

    Article  Google Scholar 

  6. Krebs HI, Volpe BT, Williams D et al (2007) Robot-aided neurorehabilitation: a robot for wrist rehabilitation. IEEE Trans Neural Syst Rehabil Eng 15(3):327–335

    Article  Google Scholar 

  7. Lu Z, Tong KY, Zhang X, Li S, Zhou P (2018) Myoelectric pattern recognition for controlling a robotic hand: a feasibility study in stroke. IEEE Trans Biomed Eng 66(2):365–372

    Article  Google Scholar 

  8. Atashzar SF, Shahbazi M, Tavakoli M, Patel RV (2018) A computational model based study of supervised haptics-enabled therapist-in-the-loop training for upper-limb post-stroke robotic rehabilitation. IEEE/ASME Trans Mechatron 23:563–574

    Article  Google Scholar 

  9. Nikmaram N, Scholz DS, Großbach M, Schmidt SB, Spogis J et al (2019) Musical sonification of arm movements in stroke rehabilitation yields limited benefits. Front Neurosci. https://doi.org/10.3389/fnins.2019.01378

    Article  Google Scholar 

  10. Hu XL, Tong KY, Wei XJ et al (2013) The effects of post-stroke upper-limb training with an electromyography (EMG)-driven hand robot. J Electromyogr Kinesiol 23(5):1065–1074

    Article  Google Scholar 

  11. Song R, Tong KY, Hu X, Zhou W (2013) Myoelectrically controlled wrist robot for stroke rehabilitation. J Neuroeng Rehabil 10(1):52

    Article  Google Scholar 

  12. Samuel OW et al. (2016) Examining the effect of subjects' mobility on upper-limb motion identification based on EMG-pattern recognition. In: IEEE intelligent robot systems (ACIRS), Asia-Pacific conference, 137–14

  13. Cesqui B, Tropea P, Micera S, Krebs HI (2013) EMG-based pattern recognition approach in post stroke robot-aided rehabilitation: a feasibility study. J NeuroEng Rehabil 10(1):75

    Article  Google Scholar 

  14. Samuel OW et al (2017) Resolving the adverse impact of mobility on myoelectric pattern recognition in upper-limb multifunctional prostheses. Comput Biol Med 90:76–87

    Article  Google Scholar 

  15. Geng Y et al (2019) A robust sparse representation based pattern recognition approach for myoelectric control. IEEE Access 6:38326–38335

    Article  Google Scholar 

  16. Samuel OW et al (2018) Pattern recognition of electromyography signals based on novel time domain features for amputees’ limb motion classification. Comput Electr Eng 67:646–655

    Article  Google Scholar 

  17. Tkach D, Huang H, Kuiken TA (2010a) Study of stability of time-domain features for electromyographic pattern recognition. J NeuroEng Rehabil 7(1):21

    Article  Google Scholar 

  18. Al-Timemy AH, Khushaba RN et al (2016) Improving the performance against force variation of EMG controlled multifunctional upper-limb prostheses for transradial amputees. IEEE Trans Neural Syst Rehabil Eng 24(6):650–661

    Article  Google Scholar 

  19. Phinyomark A et al (2017) Navigating features: a topologically informed chart of electromyographic features space. J R Soc Interface 14(137):20170734

    Article  Google Scholar 

  20. Samuel OW et al (2019) Intelligent EMG pattern recognition control method for upper-limb multifunctional prostheses: advances, current challenges, and future prospects. IEEE Access 7:10150–10165

    Article  Google Scholar 

  21. Asogbon MG et al (2020) Towards resolving the co-existing impacts of multiple dynamic factors on the performance of EMG-pattern recognition based prostheses. Comput Methods Progr Biomed 184:105278

    Article  Google Scholar 

  22. Hudgins B, Parker P, Scott RN (1993) A new strategy for multifunction myoelectric control. IEEE Trans Biomed Eng 40(1):82–94

    Article  Google Scholar 

  23. Khushaba RN et al (2014) Towards limb position invariant myoelectric pattern recognition using time-dependent spectral features. Neural Netw 55:42–58

    Article  Google Scholar 

  24. Fong S, Song W, Cho K, Wong R, Wong KKL (2017) Training classifiers with shadow features for sensor-based human activity recognition. Sensors 17(3):476

    Article  Google Scholar 

  25. Tkach D, Huang H, Kuiken TA (2010b) Study of stability of time-domain features for electromyographic pattern recognition. J NeuroEng Rehabil 7(21):21

    Article  Google Scholar 

  26. Geng Y, Samuel OW, Wei Y, Li G (2017) Improving the robustness of real-time myoelectric pattern recognition against arm position changes in transradial amputees. BioMed Res Int 2017:1–10

    Google Scholar 

  27. He J, Zhang D, Sheng X, Li S, Zhu X (2015) Invariant surface EMG feature against varying contraction level for myoelectric control based on muscle coordination. IEEE J Biomed Health Inf 19(3):874–882

    Google Scholar 

  28. Samuel OW, Asogbon MG, Geng Y, Chen S, Feng P, Chuang L and Li G (2018) A novel time-domain descriptor for improved prediction of upper limb movement intent in EMG-PR system. In: 2018 40th Annual international conference of the IEEE engineering in medicine and biology society (EMBC) pp 3513–3516, IEEE

  29. Asogbon MG, Samuel OW, Geng Y, Chen S, Mzurikwao D, Fang P and Li G (2018) Effect of window conditioning parameters on the classification performance and stability of EMG-based feature extraction methods. In: 2018 IEEE international conference on cyborg and bionic systems (CBS) pp 576–580, IEEE

  30. Lu Y, Zhang X, Chen FF, and Wong KK (2019) Ensemble machine learning for estimating fetal weight at varying gestational age. In: Proceedings of the AAAI conference on artificial intelligence 33: 9522–9527

  31. Al-Timemy AH, Khushaba RN, Bugmann G, Escudero J (2016) Improving the performance against force variation of EMG controlled multifunctional upper-limb prostheses for transradial amputees. IEEE Trans Neural Syst Rehabilit Eng 24(6):650–661

    Article  Google Scholar 

  32. Wei L, Wan S, Guo J, Wong KK (2017) A novel hierarchical selective ensemble classifier with bioinformatics application. Artif Intell Med 83:82–90

    Article  Google Scholar 

  33. Khushaba RN, Takruri M, Miro JV, Kodagoda S (2014) Towards limb position invariant myoelectric pattern recognition using time-dependent spectral features. Neural Netw 55:42–58

    Article  Google Scholar 

  34. Scheme E, Englehart K (2013) Training strategies for mitigating the effect of proportional control on classification in pattern recognition-based myoelectric control. JPO J Prosthet Orthot 25(2):76–83

    Article  Google Scholar 

Download references

Acknowledgements

The Research work was supported in part by the National Natural Science Foundation of China under Grants (#U1613222, #81850410557, #U1613228, #81771927), the Shenzhen Science and Technology Program (#SGLH20180625142402055), and CAS President’s International Fellowship Initiative Grant (#2019PB0036). Mojisola G. Asogbon Samuel sincerely appreciate the support of Chinese Government Scholarship in the pursuit of a PhD degree at the University of Chinese Academy of Sciences, Beijing, China.

Author information

Author notes

  1. Oluwarotimi Williams Samuel, Mojisola Grace Asogbon have contributed equally to this work.

Authors and Affiliations

  1. CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (CAS), Shenzhen, 518055, China

    Oluwarotimi Williams Samuel, Mojisola Grace Asogbon, Yanjuan Geng, Naifu Jiang, Yue Zheng, Kelvin K. L. Wong & Guanglin Li

  2. Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, 518055, China

    Guanglin Li

  3. The SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, 518055, China

    Oluwarotimi Williams Samuel, Mojisola Grace Asogbon, Yanjuan Geng, Naifu Jiang, Yue Zheng & Guanglin Li

  4. Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, 518055, China

    Oluwarotimi Williams Samuel, Mojisola Grace Asogbon, Yue Zheng & Guanglin Li

  5. Department of Engineering and Digital Arts, University of Kent, Canterbury, UK

    Deogratias Mzurikwao

  6. Centre for Biomedical Engineering, School of Electrical and Electronic Engineering, The University of Adelaide, Adelaide, SA5005, Australia

    Kelvin K. L. Wong

  7. Università Campus Bio-Medico di Roma, Via Alvaro del Portillo 21, Roma, Italy

    Luca Vollero

Authors
  1. Oluwarotimi Williams Samuel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mojisola Grace Asogbon
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yanjuan Geng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Naifu Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Deogratias Mzurikwao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yue Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Kelvin K. L. Wong
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Luca Vollero
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Guanglin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Kelvin K. L. Wong or Guanglin Li.

Ethics declarations

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential 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

Samuel, O.W., Asogbon, M.G., Geng, Y. et al. Decoding movement intent patterns based on spatiotemporal and adaptive filtering method towards active motor training in stroke rehabilitation systems. Neural Comput & Applic 33, 4793–4806 (2021). https://doi.org/10.1007/s00521-020-05536-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-05536-9

Keywords

Search

Navigation