Intent based recognition of walking and ramp activities for amputee using sEMG based lower limb prostheses

• Autorzy: Hussain Tahir , Iqbal Nadeem , Maqbool Hafiz Farhan , Khan Mukhtaj , Awad Mohammed Ibrahim , Dehghani-Sanij Abbas A.

Identyfikatory

DOI

10.1016/j.bbe.2020.05.010

• Języki publikacji: EN

Abstrakty

EN

The use of surface electromyogram (sEMG) has grown in the field of gait analysis, prostheses and exoskeleton. Surface electromyogram can directly reflect the human intention for locomotion modes and can be used as a source of control for lower limb prosthesis. The variations factors such as non-Gaussian nature of sEMG signal and mobility of amputees have been observed to degrade the activity recognition performance. This study investigates the properties of the sEMG signal with the purpose of determining the discriminant features to classify the feature space into various activities especially in the context of amputees. To address the variations in activity recognition performance, this study proposed the magnitude of bispectrum as a novel feature extraction method that is invariant to the variations factors and an unsupervised feature reduction method was used to extract the discriminant features. Furthermore, sEMG signals from eleven wearable sensors located on the lower limb muscles were recorded from six subjects including four able-bodies, one unilateral transti-bial, and one unilateral transfemoral amputee during walking and ramp activities. Distinct muscles were selected using the L1-norm method. Effective classifier namely support vector machine and linear discriminant analysis were used to classify the multi-class sEMG signal patterns. The experimental results consistently showed an average accuracy of 99.7%. Further evaluation on three different types of prostheses revealed that the proposed method is more robust compared to the existing methods. The promising results of this study can be applied potentially in the control of lower limb wearable devices such as prostheses/ exoskeletons.

Słowa kluczowe

EN

surface electromyography; principal component analysis; bispectrum; limb prosthesis; non-Gaussian EMG

PL

elektromiografia powierzchniowa; analiza składowych głównych; bispektrum; proteza kończyny dolnej

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 3
• Strony: 1110--1123
• Opis fizyczny: Bibliogr. 72 poz., rys., tab., wykr.

Twórcy

autor

Hussain Tahir

• Department of Computer Science, Abdul Wali Khan University Mardan, KP, Pakistan

autor

Iqbal Nadeem

• Department of Computer Science, Abdul Wali Khan University Mardan, KP, Pakistan

autor

Maqbool Hafiz Farhan

• Department of Mechatronics & Control Engineering, University of Engineering & Technology Lahore Faisalabad Campus, Pakistan; Human-Centered Robotics Lab, Lahore of National Centre of Robotics and Automation, Rawalpindi, Pakistan

autor

Khan Mukhtaj

• Department of Computer Science, Abdul Wali Khan University Mardan, KP, Pakistan

autor

Awad Mohammed Ibrahim

• Department of Mechatronics Engineering, Ain Shams University, Cairo, Egypt

autor

Dehghani-Sanij Abbas A.

• School of Mechanical Engineering, University of Leeds, Leeds, UK

Bibliografia

• [1] McEwan JK, Tribe HC, Jacobs N, Hancock N, Qureshi AA, Dunlop DG. Regenerative medicine in lower limb reconstruction. Regen Med 2018;13:477–90. http://dx.doi.org/10.2217/rme-2018-0011.
• [2] Maqbool HF, Husman MAB, Awad MI, Abouhossein A, Iqbal N, Dehghani-Sanij AA. A real-time gait event detection for lower limb prosthesis control and evaluation. IEEE Trans Neural Syst Rehabil Eng 2017;25:1500–9. http://dx.doi.org/10.1109/TNSRE. 2016.2636367.
• [3] Zhang K, de Silva CW, Fu C. Sensor fusion for predictive control of human-prosthesis-environment dynamics in assistive walking: a survey; 2019, ArXiv Prepr ArXiv1903076741-8.
• [4] Gautam D, Malhotra R. Megaprosthesis versus allograft prosthesis composite for massive skeletal defects. J Clin Orthop Trauma 2018;9:63–80. http://dx.doi.org/10.1016/j.jcot.2017.09.010.
• [5] Liptak MG, Theodoulou A, Kaambwa B, Saunders S, Hinrichs SW, Woodman RJ, et al. The safety, efficacy and cost-effectiveness of the Maxm Skate, a lower limb rehabilitation device for use following total knee arthroplasty: study protocol for a randomised controlled trial. Trials 2019;20. http://dx.doi.org/10.1186/s13063-018-3102-9.
• [6] Yatsun A, Jatsun S. Modeling quasi-static gait of a person wearing lower limb exoskeleton. Lect Notes Mech Eng 2019;565–75. http://dx.doi.org/10.1007/978-3-319-95630-5_59.
• [7] Li M, Deng J, Zha F, Qiu S, Wang X, Chen F. Towards online estimation of human joint muscular torque with a lower limb exoskeleton robot. Appl Sci 2018;8:1–17. http://dx.doi.org/10.3390/app8091610.
• [8] Yang Y, Huang D, Dong X. Enhanced neural network control of lower limb rehabilitation exoskeleton by add-on repetitive learning. Neurocomputing 2019;323:256–64. http://dx.doi.org/10.1016/j.neucom.2018.09.085.
• [9] Ringhof S, Patzer I, Beil J, Asfour T, Stein T. Does a passive unilateral lower limb exoskeleton affect human static and dynamic balance control? Front Sport Act Living 2019;1:1–10. http://dx.doi.org/10.3389/fspor.2019.00022.
• [10] Pardoel S, Doumit M. Development and testing of a passive ankle exoskeleton. Biocybern Biomed Eng 2019;39:902–13. http://dx.doi.org/10.1016/j.bbe.2019.08.007.
• [11] Lovrenovic Z, Doumit M. Development and testing of a passive walking assist exoskeleton. Biocybern Biomed Eng 2019;39:992–1004. http://dx.doi.org/10.1016/j.bbe.2019.01.002.
• [12] Yamamoto M, Shimatani K, Hasegawa M, Murata T, Kurita Y. Estimation of knee joint reaction force based on the plantar flexion resistance of an ankle-foot orthosis during gait. J Phys Ther Sci 2018;30:966–70. http://dx.doi.org/10.1589/jpts.30.966.
• [13] Diffo Kaze A, Maas S, Arnoux PJ, Wolf C, Pape D. A finite element model of the lower limb during stance phase of gait cycle including the muscle forces. Biomed Eng Online 2017;16:138. http://dx.doi.org/10.1186/s12938-017-0428-6.
• [14] Ren B, Luo X, Chen J. Single leg gait tracking of lower limb exoskeleton based on adaptive iterative learning control. Appl Sci 2019;9:1–10. http://dx.doi.org/10.3390/app9112251.
• [15] Accogli A, Grazi L, Crea S, Panarese A, Carpaneto J, Vitiello N, et al. EMG-based detection of user's intentions for human-machine shared control of an assistive upper-limb exoskeleton. Biosyst Biorobotics 2017. http://dx.doi.org/10.1007/978-3-319-46532-6_30.
• [16] Thomas TM, Candrea DN, Fifer MS, McMullen DP. Decoding native cortical representations for flexion and extension at upper limb joints using electrocorticography. IEEE Trans Neural Syst Rehabil Eng 2019;27:1–11. http://dx.doi.org/10.1109/TNSRE.2019.2891362.
• [17] Toda M, Chin T, Shibata Y, Mizobe F. Use of powered prosthesis for children with upper limb deficiency at Hyogo Rehabilitation Center. PLoS One 2015. http://dx.doi.org/10.1371/journal.pone.0131746.
• [18] Zhang F, Liu M, Huang H. Investigation of timing to switch control mode in powered knee prostheses during task transitions. PLoS One 2015. http://dx.doi.org/10.1371/journal.pone.0133965.
• [19] Abdolzadegan D, Moattar MH, Ghoshuni M. A robust method for early diagnosis of autism spectrum disorder from EEG signals based on feature selection and DBSCAN method. Biocybern Biomed Eng 2020;40:482–93. http://dx.doi.org/10.1016/j.bbe.2020.01.008.
• [20] Mokhlesabadifarahani B, Gunjan VK. EMG signals characterization in three states of contraction by fuzzy network and feature extraction. SpringerBriefs Appl Sci Technol 2015;11–21. http://dx.doi.org/10.1007/978-981-287-320-0.
• [21] Gregory U, Ren L. Intent prediction of multi-axial ankle motion using limited EMG signals. Front Bioeng Biotechnol 2019;7. http://dx.doi.org/10.3389/fbioe.2019.00335.
• [22] Yuen CHN, Lam CPY, Tong KCT, Yeung JCY, Yip CHY, So BCL. Investigation the EMG activities of lower limb muscles when doing squatting exercise in water and on land. Int J Environ Res Public Health 2019;16. http://dx.doi.org/10.3390/ijerph16224562.
• [23] COAPT Engineering. Available from: http://www.coaptengineering.com/ [accessed 03.01.20].
• [24] Open Bionics. Available from: https://openbionics.com/ [accessed 03.01.20].
• [25] Ottobock. Available from: https://www.ottobock.com/ [accessed 30.12.19].
• [26] Delafontaine A, Fourcade P, Honeine JL, Ditcharles S, Yiou E. Postural adaptations to unilateral knee joint hypomobility induced by orthosis wear during gait initiation. Sci Rep 2018;8. http://dx.doi.org/10.1038/s41598-018-19151-1.
• [27] Crowe CS, Impastato KA, Donaghy AC, Earl C, Friedly JL, Keys KA. Prosthetic and orthotic options for lower extremity amputation and reconstruction. Plast Aesthetic Res 2019. http://dx.doi.org/10.20517/2347-9264.2018.70.
• [28] Xi X, Tang M, Miran SM, Luo Z. Evaluation of feature extraction and recognition for activity monitoring and fall detection based on wearable sEMG sensors. Sensors (Switzerland) 2017;17. http://dx.doi.org/10.3390/s17061229.
• [29] Raju AR, Suresh P, Rao RR. Bayesian HCS-based multi- SVNN: a classification approach for brain tumor segmentation and classification using Bayesian fuzzy clustering. Biocybern Biomed Eng 2018;38:646–60. http://dx.doi.org/10.1016/j.bbe.2018.05.001.
• [30] Morbidoni C, Cucchiarelli A, Fioretti S, Di Nardo F. A deep learning approach to EMG-based classification of gait phases during level ground walking. Electron 2019;8. http://dx.doi.org/10.3390/electronics8080894.
• [31] Sánchez-Velasco LE, Arias-Montiel M, Guzmán-Ramírez E, Lugo-González E. A low-cost EMG-controlled anthropomorphic robotic hand for power and precision grasp. Biocybern Biomed Eng 2020;40:221–37. http://dx.doi.org/10.1016/j.bbe.2019.10.002.
• [32] Biagetti G, Crippa P, Curzi A, Orcioni S, Turchetti C. Analysis of the EMG signal during cyclic movements using multicomponent AM–FM decomposition. IEEE J Biomed Heal Informatics 2015;19:1672–81. http://dx.doi.org/10.1109/JBHI.2014.2356340.
• [33] Mengying X, Xiaoli Y, Chenli X, Bin Y. EMG signal processing and application based on empirical mode decomposition. Math Comput Sci 2019;4:99–103. http://dx.doi.org/10.11648/j.mcs.20190406.11.
• [34] Zhang Y, Xu P, Li P, Duan K, Wen Y, Yang Q, et al. Noise-assisted multivariate empirical mode decomposition for multichannel EMG signals. Biomed Eng Online 2017;16:1–17. http://dx.doi.org/10.1186/s12938-017-0397-9.
• [35] Spanias JA, Simon AM, Finucane SB, Perreault EJ, Hargrove LJ. Online adaptive neural control of a robotic lower limb prosthesis. J Neural Eng 2018;15. http://dx.doi.org/10.1088/1741-2552/aa92a8.
• [36] Ai Q, Zhang Y, Qi W, Liu Q, Chen K. Research on lower limb motion recognition based on fusion of sEMG and accelerometer signals. Symmetry (Basel) 2017;9. http://dx.doi.org/10.3390/sym9080147.
• [37] Too J, Abdullah AR, Saad NM, Tee W. EMG feature selection and classification using a Pbest-guide binary particle swarm optimization. Computation 2019;7. http://dx.doi.org/10.3390/computation7010012.
• [38] Sunny Sonia Mary George JT, Joseph S, Kizhakkethottam JJ. Applications and challenges of human activity recognition using sensors in a smart environment. Int J Innov Res Sci Technol 2015;2:50–7.
• [39] Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Syst Appl 2012;39:7420–31. http://dx.doi.org/10.1016/j.eswa.2012.01.102.
• [40] Davila J, Cretu A-M, Zaremba M. Wearable sensor data classification for human activity recognition based on an iterative learning framework. Sensors 2017;17:1287. http://dx.doi.org/10.3390/s17061287.
• [41] Chowdhury R, Reaz M, Ali M, Bakar A, Chellappan K, Chang T. Surface electromyography signal processing and classification techniques. Sensors 2013;13:12431–66. http://dx.doi.org/10.3390/s130912431.
• [42] Zhang J, Liu CW, Bi FR, Bi XB, Yang X. Fault feature extraction of diesel engine based on bispectrum image fractal dimension. Chin J Mech Eng Engl Ed 2018;31. http://dx.doi.org/10.1186/s10033-018-0230-9.
• [43] Chen X, Zhu X, Zhang D. A discriminant bispectrum feature for surface electromyogram signal classification. Med Eng Phys 2010;32:126–35. http://dx.doi.org/10.1016/j.medengphy.2009.10.016.
• [44] Orosco EC, Lopez NM, Di Sciascio F. Bispectrum-based features classification for myoelectric control. Biomed Signal Process Control 2013;8:153–68. http://dx.doi.org/10.1016/j.bspc.2012.08.008.
• [45] Bu D, Guo S, Ma1 H, Hao X. Pattern recognition of continuous elbow joint movements using bispectrum-based sEMG; 2018;551–6.
• [46] Chereshnev R, Kertész-Farkas A. GaIn: human gait inference for lower limbic prostheses for patients suffering from double trans-femoral amputation. Sensors (Switzerland) 2018;18. http://dx.doi.org/10.3390/s18124146.
• [47] Phinyomark A, Limsakul C, Phukpattaranont P. Application of wavelet analysis in EMG feature extraction for pattern classification. Meas Sci Rev 2011;11:45–52. http://dx.doi.org/10.2478/v10048-011-0009-y.
• [48] Stegeman DF, Blok JH, Hermens HJ, Roeleveld K. Surface EMG models: properties and applications. J Electromyogr Kinesiol 2000;10:313–26. http://dx.doi.org/10.1016/S1050-6411(00)00023-7.
• [49] Walton E, Casey C, Mitsch J, Vázquez-Diosdado JA, Yan J, Dottorini T, et al. Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour. R Soc Open Sci 2018;5. http://dx.doi.org/10.1098/rsos.171442.
• [50] Hong YNG, Lee J, Pankwon K, Choongsoo SS. Gender diferences in the activation and co-activation of lower extremity muscles during the stair-to-ground descent transition. Int J Precis Eng Manuf 2020. http://dx.doi.org/10.1007/s12541-020-00348-2.
• [51] Im YG, Han SH, Park J, Lim HS, Kim BG, Kim JH. Repeatability of measurements of surface electromyographic variables during maximum voluntary contraction of temporalis and masseter muscles in normal adults. J Oral Sci 2017. http://dx.doi.org/10.2334/josnusd.16-0434.
• [52] Taborri J, Palermo E, Prete ZD, Rossi S. On the reliability and repeatability of surface electromyography factorization by muscle synergies in daily life activities. Appl Bionics Biomech 2018. http://dx.doi.org/10.1155/2018/5852307.
• [53] Yang Z, Wen Y, Chen Y. Semg-based drawing trace reconstruction: a novel hybrid algorithm fusing gene expression programming into Kalman filter. Sensors (Switzerland) 2018;18. http://dx.doi.org/10.3390/s18103296.
• [54] Xu L, Chen X, Cao S, Zhang X, Chen X. Feasibility study of advanced neural networks applied to sEMG-based force estimation. Sensors (Switzerland) 2018;18. http://dx.doi.org/10.3390/s18103226.
• [55] Chen TLW, Wong DWC, Xu Z, Tan Q, Wang Y, Luximon A, et al. Lower limb muscle co-contraction and joint loading of flip-flops walking in male wearers. PLoS One 2018;13. http://dx.doi.org/10.1371/journal.pone.0193653.
• [56] Hussain T, Maqbool HF, Iqbal N, Khan M, Salman, Dehghani-Sanij AA. Computational model for the recognition of lower limb movement using wearable gyroscope sensor. Int J Sens Networks 2019;30:35–45. http://dx.doi.org/10.1504/IJSNET.2019.099230.
• [57] Naik GR, Nguyen HT. Nonnegative matrix factorization for the identification of EMG finger movements: evaluation using matrix analysis. IEEE J Biomed Heal Informatics 2015;19:478–85. http://dx.doi.org/10.1109/JBHI.2014.2326660.
• [58] Tresch MC. Matrix factorization algorithms for the identification of muscle synergies: evaluation on simulated and experimental data sets. J Neurophysiol 2005;95:2199– 212. http://dx.doi.org/10.1152/jn.00222.2005.
• [59] Gupta R, Agarwal R. Single channel EMG-based continuous terrain identification with simple classifier for lower limb prosthesis. Biocybern Biomed Eng 2019;39:775–88. http://dx.doi.org/10.1016/j.bbe.2019.07.002.
• [60] Setiawan FB, Siswanto. Multi channel electromyography (EMG) signal acqiusition using microcontroller with rectifier. Proc – 2016 3rd Int Conf Inf Technol Comput Electr Eng ICITACEE, 2016. 2017. pp. 21–4. http://dx.doi.org/10.1109/ICITACEE.2016.7892403.
• [61] Phinyomark A, Nuidod A, Phukpattaranont P, Limsakul C. Feature extraction and reduction of wavelet transform coefficients for EMG pattern classification. Elektron Ir Elektrotechnika 2012;122:27–32. http://dx.doi.org/10.5755/j01.eee.122.6.1816.
• [62] Duan F, Dai L, Chang W, Chen Z, Zhu C, Li W. SEMG-based identification of hand motion commands using wavelet neural network combined with discrete wavelet transform. IEEE Trans Ind Electron 2016;63:1923–34. http://dx.doi.org/10.1109/TIE.2015.2497212.
• [63] González S, Sedano J, Villar JR, Corchado E, Herrero Á, Baruque B. Features and models for human activity recognition. Neurocomputing 2015;167:52–60. http://dx.doi.org/10.1016/j.neucom.2015.01.082.
• [64] Angelova S, Ribagin S, Raikova R, Veneva I. Power frequency spectrum analysis of surface EMG signals of upper limb muscles during elbow flexion – a comparison between healthy subjects and stroke survivors. J Electromyogr Kinesiol 2018;38:7–16. http://dx.doi.org/10.1016/j.jelekin.2017.10.013.
• [65] Karamizadeh S, Abdullah SM, Manaf AA, Zamani M, Hooman A. An overview of principal component analysis. J Signal Inf Process 2013;04:173–5. http://dx.doi.org/10.4236/jsip.2013.43B031.
• [66] Peng Z, Cao C, Liu Q, Pan W. Human walking pattern recognition based on KPCA and SVM with ground reflex pressure signal. Math Probl Eng 2013. http://dx.doi.org/10.1155/2013/2013/143435.
• [67] Zhang H, Zhao Y, Yao F, Xu L, Shang P, Li G. An adaptation strategy of using LDA classifier for EMG pattern recognition. Proc Annu Int Conf IEEE Eng Med Biol Soc EMBS. 2013. pp. 4267–70. http://dx.doi.org/10.1109/EMBC.2013.6610488.
• [68] Ma J, Thakor NV, Matsuno F. Hand and wrist movement control of myoelectric prosthesis based on synergy. IEEE Trans Hum Mach Syst 2015;45:74–83. http://dx.doi.org/10.1109/THMS.2014.2358634.
• [69] Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2011;2. http://dx.doi.org/10.1145/1961189.1961199.
• [70] Huang H, Kuiken TA, Lipschutz RD. A strategy for identifying locomotion modes using surface electromyography. IEEE Trans Biomed Eng 2009. http://dx.doi.org/10.1109/TBME.2008.2003293.
• [71] Attal F, Amirat Y, Chibani A, Mohammed S. Automatic recognition of gait phases using a multiple-regression hidden Markov model. IEEE/ASME Trans Mechatronics 2018;23:1597–607. http://dx.doi.org/10.1109/TMECH.2018.2836934.
• [72] Fida B, Bernabucci I, Bibbo D, Conforto S, Schmid M. Varying behavior of different window sizes on the classification of static and dynamic physical activities from a single accelerometer. Med Eng Phys 2015;37:705–11. http://dx.doi.org/10.1016/j.medengphy.2015.04.005.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).