Single channel EMG-based continuous terrain identification with simple classifier for lower limb prosthesis

• Autorzy: Gupta Rohit , Agarwal Ravinder

Identyfikatory

DOI

10.1016/j.bbe.2019.07.002

• Języki publikacji: EN

Abstrakty

EN

The focus of the present research endeavour is to propose a single channel Electromyogram (EMG) signal driven continuous terrain identification method utilizing a simple classifier. An iterative feature selection algorithm has also been proposed to provide effective information to the classifiers. The proposed method has been validated on EMG signal of fifteen subjects and ten subjects for three and five daily life terrains respectively. Feature selection algorithm has significantly improved the identification accuracy (ANOVA, p-value < 0.05) as compared to principal component analysis (PCA) technique. The average identification accuracies obtained by Support Vector Machine (SVM), Linear Discriminant Analysis (LDA) and Neural Network (NN) classifiers are 96.83 ± 0.28%, 97.45 ± 0.32% and 97.61 ± 0.22% respectively. Subject wise performance (five subjects) of individually trained classifiers shows no significant degradation and difference in performance among the subjects even for the untrained data (ANOVA, p-value > 0.05). The study has been extended to dual muscle approach for terrain identification. However, the proposed algorithm has shown similar performance even with the single muscle approach (ANOVA, p-value > 0.05). The outcome of the proposed continuous terrain identifi-cation method shows a pronounced potential in efficient lower limb prosthesis control.

Słowa kluczowe

EN

pattern recognition; terrain identification; electromyography; lower limb prosthesis

PL

rozpoznawanie wzorca; elektromiografia; proteza kończyny dolnej

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 3
• Strony: 775--788
• Opis fizyczny: Bibliogr. 50 poz., rys., tab., wykr.

Twórcy

autor

Gupta Rohit

• EIED, Thapar University, Patiala, Punjab 147001, India

autor

Agarwal Ravinder

• EIED, Thapar University, Patiala, Punjab 147001, India

Bibliografia

• [1] Ziegler-Graham K, MacKenzie EJ, Ephraim PL, Travison TG, Brookmeyer R. Estimating the prevalence of limb loss in the United States: 2005 to 2050. Arch Phys Med Rehabil 2008;89:422–9. http://dx.doi.org/10.1016/j.apmr.2007.11.005.
• [2] Waters RL, Mulroy S. The energy expenditure of normal and pathologic gait. Gait Posture 1999;9:207–31. http://dx.doi.org/10.1016/S0966-6362(99)00009-0.
• [3] Windrich M, Grimmer M, Christ O, Rinderknecht S, Beckerle P. Active lower limb prosthetics: a systematic review of design issues and solutions. Biomed Eng Online 2016;15:5– 19. http://dx.doi.org/10.1186/s12938-016-0284-9.
• [4] Au S, Berniker M, Herr H. Powered ankle-foot prosthesis to assist level-ground and stair-descent gaits. Neural Netw 2008;21:654–66. http://dx.doi.org/10.1016/j.neunet.2008.03.006.
• [5] Cherelle P, Grosu V, Matthys A, Vanderborght B, Lefeber D. Design and validation of the ankle mimicking. IEEE Trans NEURAL Syst Rehabil Eng 2014;22:138–48.
• [6] Joshi D, Hahn ME, Joshi D, Hahn ME, Joshi D, Hahn ME. Terrain and direction classification of locomotion transitions using neuromuscular and mechanical input. Ann Biomed Eng 2016;44:1275–84. http://dx.doi.org/10.1007/s10439-015-1407-3.
• [7] Liu M, Wang D, Huang HH. Development of an environment-aware locomotion mode recognition system for powered lower limb prostheses. IEEE Trans Neural Syst Rehabil Eng 2016;24:434–43. http://dx.doi.org/10.1109/TNSRE.2015.2420539.
• [8] Chen B, Zheng E, Wang Q. A locomotion intent prediction system based on multi-sensor fusion. Sensors 2014;14:12349–6. http://dx.doi.org/10.3390/s140712349.
• [9] Chen B, Wang X, Huang Y, Wei K, Wang Q, Wang X, et al. A foot-wearable interface for locomotion mode recognition based on discrete contact force distribution. Mechatronics 2015;32:12–21. http://dx.doi.org/10.1016/j.mechatronics.2015.09.002.
• [10] Yuan K, Wang Q, Wang L. Fuzzy-logic-based terrain identification with multisensor fusion for transtibial amputees. IEEE Trans Mechatron 2015;20:618–30.
• [11] Young AJ, Hargrove LJ. A classification method for user-independent intent recognition for transfemoral amputees using powered lower limb prostheses. IEEE Trans Neural Syst Rehabil Eng 2016;24:217–25. http://dx.doi.org/10.1109/TNSRE.2015.2412461.
• [12] Varol HA, Sup F, Goldfarb M. Multiclass real-time intent recognition of a powered lower limb prosthesis. IEEE Trans Biomed Eng 2010;57:542–51. http://dx.doi.org/10.1109/TBME.2009.2034734.
• [13] Sup F, Varol HA, Goldfarb M. Upslope walking with a powered knee and ankle prosthesis: initial results with an amputee subject. IEEE Trans Neural Syst Rehabil Eng 2011;19:71–8. http://dx.doi.org/10.1109/TNSRE.2010.2087360.
• [14] Young AJ, Simon AM, Eey NP, Hargrove LJ. Intent recognition in a powered lower limb prosthesis using time history information. Ann Biomed Eng 2014;42:631–41. http://dx.doi.org/10.1007/s10439-013-0909-0.
• [15] Young AJ, Simon AM, Hargrove LJ. A training method for locomotion mode prediction using powered lower limb prostheses. IEEE Trans Neural Syst Rehabil Eng 2014;22:671–7.
• [16] Farrell MT, Herr H. A method to determine the optimal features for control of a powered lower-limb prostheses. 33rd Annu Int Conf IEEE EMBS; 2011. pp. 6041–6.
• [17] Zhang X, Wang D, Yang Q, Huang H. An automatic and user-driven training method for locomotion mode recognition for artificial leg control. 34th Annu Int Conf IEEE EMBS; 2012. pp. 6116–9.
• [18] Du L, Zhang F, Liu M, Huang H. Toward design of an environment-aware adaptive locomotion-mode- recognition system. IEEE Trans Biomed Eng 2012;59:2716–25.
• [19] Miller JD, Beazer MS, Hahn ME. Myoelectric walking mode classification for transtibial amputees. IEEE Trans Biomed Eng 2013;60:2745–50. http://dx.doi.org/10.1109/TBME.2013.2264466.
• [20] Zhang F, Huang H. Source selection for real-time user intent recognition toward volitional control of artificial legs. IEEE J Biomed Heal Inform 2013;17:907–14.
• [21] Young AJ, Kuiken TA, Hargrove LJ. Analysis of using EMG and mechanical sensors to enhance intent recognition in powered lower limb prostheses. J Neural Eng 2014;11:1–12. http://dx.doi.org/10.1088/1741-2560/11/5/056021.
• [22] Spanias JA, Simon AM, Ingraham KA, Hargrove LJ. Effect of additional mechanical sensor data on an EMG-based pattern recognition system for a powered leg prosthesis. IEEE EMBS Conf Neural Eng; 2015. pp. 22–4. http://dx.doi.org/10.1109/NER.2015.7146704.
• [23] Huang H, Zhang F, Hargrove LJ, Dou Z, Rogers DR, Englehart KB. Continuous locomotion-mode identification for prosthetic legs based on neuromuscular–mechanical fusion. IEEE Trans Biomed Eng 2011;58:2867–75.
• [24] Young A, Simon A, Hargrove L. An intent recognition strategy for transfemoral amputee ambulation across different locomotion modes. Annu Int Conf IEEE EMBS; 2013. pp. 1587–90.
• [25] Pati S, Joshi D, Mishra A. Locomotion classification using EMG signal – a comparative study. Int Conf Inf Emerg Technol; 2010. pp. 1–6. http://dx.doi.org/10.1109/ICIET.2010.5625677.
• [26] Huang H, Zhang F, Sun YL, He H. Design of a robust EMG sensing interface for pattern classification. J Neural Eng 2010;7:056005. http://dx.doi.org/10.1088/1741-2560/7/5/056005.
• [27] Afzal T, KI, GW, AB. W.. A method for locomotion mode identification using muscle synergies. IEEE Trans Neural Syst Rehabil Eng 2017;25:608–17. http://dx.doi.org/10.1109/TNSRE.2016.2585962.
• [28] Chandrashekar G, Sahin F. A survey on feature selection methods. Comput Electr Eng 2014;40:16–28. http://dx.doi.org/10.1016/j.compeleceng.2013.11.024.
• [29] Urbanowicz RJ, Meeker M, La Cava W, Olson RS, Moore JH. Relief-based feature selection: introduction and review. J Biomed Inform 2018;85:189–203. http://dx.doi.org/10.1016/j.jbi.2018.07.014.
• [30] Pudil P, Novovicova J. Novel methods for subset selection with respect to problem knowledge. IEEE Intell Syst Their Appl 1998;13:66–74. http://dx.doi.org/10.1109/5254.671094.
• [31] Senliot B, Gulgezen G, Yu L, Cataltepe Z. Fast correlation based filter (FCBF) with a different search strategy. 23rd Int Symp Comput Inf Sci; 2008. pp. 1–4. http://dx.doi.org/10.1109/ISCIS.2008.4717949.
• [32] Reduction D. Correlation-based feature selection for discrete and numeric class machine learning. 17th Int Conf Mach Learn. 2000. pp. 359–66.
• [33] Pudil P, Novovicová J, Kittler J. Floating search methods in feature selection. Pattern Recognit Lett 1994;15:1119–25. http://dx.doi.org/10.1016/0167-8655(94)90127-9.
• [34] Reunanen J. Overfitting in making comparisons between variable selection methods. J Mach Learn Res 2003;3:1371– 82. http://dx.doi.org/10.1162/153244303322753715.
• [35] Somol P, Pudil P, Novovicova J, Paclik P. Adaptive floating search methods in feature selection. Pattern Recognit Lett 1999;14:88–100. http://dx.doi.org/10.1016/S0167-8655(99)00083-5.
• [36] Xue B, Zhang M, Member S, Browne WN, Member S, Browne WN. Particle swarm optimization for feature selection in classification: a multi-objective approach. IEEE Trans Cybern 2013;43:1656–71. http://dx.doi.org/10.1109/TSMCB.2012.2227469.
• [37] Winter DA. The biomechanics and motor control of human gait. 2nd ed. Ontario, Canada: University of Waterloo Press; 1987. http://dx.doi.org/10.1016/0021-9290(92)90236-T.
• [38] SENIAM. Sensors location: recommendations for sensor locations on individual muscles; 2016, http://seniam.org/sensor_location.htm.
• [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] Gupta R, Agarwal R. Electromyographic signal-driven continuous locomotion mode identification module design for lower limb prosthesis control. Arab J Sci Eng 2018;43:7817–35. http://dx.doi.org/10.1007/s13369-018-3193-3.
• [41] Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Inf Process Manag 2009;45:427–37. http://dx.doi.org/10.1016/j.ipm.2009.03.002.
• [42] Ma J, Thakor NV, Matsuno F. Hand and wrist movement control of myoelectric prosthesis based on synergy. 74 IEEE Trans Human–Machine Syst 2015;45:74–83. http://dx.doi.org/10.1109/THMS.2014.2358634.
• [43] Pati S, Joshi D, Mishra A. Locomotion classification using EMG signal. 2010 Int Conf Inf Emerg Technol; 2010. pp. 1–6. http://dx.doi.org/10.1109/ICIET.2010.5625677.
• [44] Winter DA. Biomechanical motor patterns in normal walking. J Mot Behav 1983;15:302–30. http://dx.doi.org/10.1080/00222895.1983.10735302.
• [45] Winter DA. Kinematic and kinetic patterns in human gait: variability and compensating effects. Hum Mov Sci 1984;3:51–76.
• [46] Winter DA, Yack HJ. EMG profiles during normal human walking: stride-to-stride and inter-subject variability. Electroencephalogr Clin Neurophysiol 1987;67:402–11.
• [47] Winter DA. Human balance and posture standing and walking control during; 1995.
• [48] Crommert HWAA, Van De, Mulder T, Duysens J. Neural control of locomotion: sensory control of the central pattern generator and its relation to treadmill training. Gait Posture 1998;7:251–63.
• [49] Dimitrijevic MR, Persy I, Forstner C, Kern H, Dimitrijevic MM. Motor control in the human spinal cord. Artif Organs 2005;29:216–9.
• [50] Jimenez-Fabian R, Verlinden O. Review of control algorithms for robotic ankle systems in lower-limb orthoses, prostheses, and exoskeletons. Med Eng Phys 2012;34:397–408. http://dx.doi.org/10.1016/j.medengphy.2011.11.018.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).