Abstract
A transfemoral prosthesis is required to assist amputees to perform the activity of daily living (ADL). The passive prosthesis has some drawbacks such as utilization of high metabolic energy. In contrast, the active prosthesis consumes less metabolic energy and offers better performance. However, the recent active prosthesis uses surface electromyography as its sensory system which has weak signals with microvolt-level intensity and requires a lot of computation to extract features. This paper focuses on recognizing different phases of sitting and standing of a transfemoral amputee using in-socket piezoelectric-based sensors. 15 piezoelectric film sensors were embedded in the inner socket wall adjacent to the most active regions of the agonist and antagonist knee extensor and flexor muscles, i. e. region with the highest level of muscle contractions of the quadriceps and hamstring. A male transfemoral amputee wore the instrumented socket and was instructed to perform several sitting and standing phases using an armless chair. Data was collected from the 15 embedded sensors and went through signal conditioning circuits. The overlapping analysis window technique was used to segment the data using different window lengths. Fifteen time-domain and frequency-domain features were extracted and new feature sets were obtained based on the feature performance. Eight of the common pattern recognition multiclass classifiers were evaluated and compared. Regression analysis was used to investigate the impact of the number of features and the window lengths on the classifiers’ accuracies, and Analysis of Variance (ANOVA) was used to test significant differences in the classifiers’ performances. The classification accuracy was calculated using k-fold cross-validation method, and 20% of the data set was held out for testing the optimal classifier. The results showed that the feature set (FS-5) consisting of the root mean square (RMS) and the number of peaks (NP) achieved the highest classification accuracy in five classifiers. Support vector machine (SVM) with cubic kernel proved to be the optimal classifier, and it achieved a classification accuracy of 98.33 % using the test data set. Obtaining high classification accuracy using only two time-domain features would significantly reduce the processing time of controlling a prosthesis and eliminate substantial delay. The proposed in-socket sensors used to detect sit-to-stand and stand-to-sit movements could be further integrated with an active knee joint actuation system to produce powered assistance during energy-demanding activities such as sit-to-stand and stair climbing. In future, the system could also be used to accurately predict the intended movement based on their residual limb’s muscle and mechanical behaviour as detected by the in-socket sensory system.
Acknowledgments
The authors would like to thank Nur Hidayah Mohd Yusof for fabricating the socket.
-
Research funding: Authors state no funding involved.
-
Conflict of interest: Authors state no conflict of interest.
References
1. Zijlstra A, Mancini M, Lindemann U, Chiari L, Zijlstra W. Sit-stand and stand-sit transitions in older adults and patients with Parkinson’s disease: event detection based on motion sensors versus force plates. J Neuroeng Rehabili 2012;9:10. https://doi.org/10.1186/1743-0003-9-75.Search in Google Scholar
2. Kralj A, Jaeger RJ, Munih M. Analysis of standing up and sitting down in humans - definitions and normative data presentation. J Biomec 1990;23:1123–38. https://doi.org/10.1016/0021-9290(90)90005-n.10.1016/0021-9290(90)90005-NSearch in Google Scholar
3. Wang J, Kannape OA, Herr HM. Proportional emg control of ankle plantar flexion in a powered transtibial prosthesis, IEEE 13th Inter Conf Rehab Robo 2013. https://doi.org/10.1109/icorr.2013.6650391.Search in Google Scholar
4. Jasni F, Hamzaid NA, Abd Muthalif AG, Zakaria Z, Shasmin HN, Ng SC. In-socket sensory system for transfemoral amputees using piezoelectric sensors: an efficacy study. IEEE-Asme Trans Mechatr 2016;21:2466–76. https://doi.org/10.1109/tmech.2016.2578679.Search in Google Scholar
5. Lara-Barrios CM, Blanco-Ortega A, Guzman-Valdivia CH, Valles KDB. Literature review and current trends on transfemoral powered prosthetics. Adv Robo 2018;32:51–62. https://doi.org/10.1080/01691864.2017.1402704.Search in Google Scholar
6. Grimmer M, Seyfarth A. Mimicking human-like leg function in prosthetic limbs. In: Artemiadis P, editor. Neuro-Robotics: From Brain Machine Interfaces to Rehabilitation Robotics, 2, 2014, 105–55.10.1007/978-94-017-8932-5_5Search in Google Scholar
7. Popovic D, Tomovic R, Tepavac D, Schwirtlich L. Control aspects of active above-knee prosthesis. Inter J Man-Machine Stud 1991;35:751–67. https://doi.org/10.1016/s0020-7373(05)80159-2.Search in Google Scholar
8. Chen BJ, Zheng EH, Fan XD, Liang T, Wang QN, Wei KL, et al. Locomotion mode classification using a wearable capacitive sensing system. IEEE Trans Neural Sys Rehabili Eng 2013;21:744–55. https://doi.org/10.1109/tnsre.2013.2262952.Search in Google Scholar
9. Kapti AO, Yucenur MS. Design and control of an active artificial knee joint. Mechan Mach Theo 2006;41:1477–85. https://doi.org/10.1016/j.mechmachtheory.2006.01.017.Search in Google Scholar
10. 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. https://doi.org/10.1109/tbme.2011.2161671.Search in Google Scholar
11. El-Sayed, Hamzaid, Tan, Abu Osman. Detection of prosthetic knee movement phases via in-socket Sensors: a feasibility study. Sci World J 2015:13. https://doi.org/10.1155/2015/923286.Search in Google Scholar
12. Mueller JKP, Evans BM, Ericson MN, Farquhar E, Lind R, Kelley K, et al. A mobile motion analysis system using inertial sensors for analysis of lower limb prosthetics. 2011.10.1109/FIIW.2011.6476802Search in Google Scholar
13. Huang, Englehart, Hudgins, Chan. A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses. IEEE Trans Biomed Eng 2005;52:1801–11. https://doi.org/10.1109/tbme.2005.856295.Search in Google Scholar
14. Li N, Yang DP, Jiang L, Liu H, Cai HG. Combined use of fsr sensor array and svm classifier for finger motion recognition based on pressure distribution map. J Bionic Eng 2012;9:39–47. https://doi.org/10.1016/s1672-6529(11)60095-4.Search in Google Scholar
15. El-Sayed, Hamzaid, Abu Osman. Piezoelectric Bimorphs’ Characteristics as in-socket sensors for transfemoral amputees. Sensors 2014;14:23724–41. https://doi.org/10.3390/s141223724.Search in Google Scholar PubMed PubMed Central
16. Wheeler JW, Dabling JG, Chinn D, Turner T, Filatov A, Anderson L, et al. MEMS-based bubble pressure sensor for prosthetic socket interface pressure measurement, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Conference Proceedings; 2011, 2925–8.10.1109/IEMBS.2011.6090805Search in Google Scholar PubMed
17. Maurizio R, Matteo N, Leandro L, Davide B. Dual mode pressure sensing for lower-limb prosthetic interface 2017.Search in Google Scholar
18. Lorenzelli L, Sordo G, Bagolini A, Resta G. Socketmaster: Integrated sensors system for the optimised design of prosthetic socket for above knee amputees. 2017.10.1109/NGCAS.2017.70Search in Google Scholar
19. Hamzaid N, Hidayah N, Jasni F. Sensory systems in micro-processor controlled prosthetic leg: a review. IEEE Sen J 2019;PP:1–1. https://doi.org/10.1109/jsen.2019.2944653.Search in Google Scholar
20. Hefferman GM, Zhang F, Nunnery MJ, Huang H. Integration of surface electromyographic sensors with the transfemoral amputee socket: a comparison of four differing configurations. Prosth Ortho Inter 2015;39:166–73. https://doi.org/10.1177/0309364613516484.Search in Google Scholar PubMed
21. Jasni F, Hamzaid NA, Al-Nusairi TY, Yusof NHM, Shasmin HN, Ng S-C. Feasibility of a gait phase identification tool for transfemoral amputees using piezoelectric-based in-socket sensory system. IEEE Sen J 2019;19:6437–44. https://doi.org/10.1109/jsen.2019.2910161.Search in Google Scholar
22. Prendergast, Helm, Duda. Analysis of muscle and joint loads. Basic Orthopaedic Biomechanics and Mechano-Biology 3rd edtion, by C Mow and Rik Huiskes. 3rd editio. Philadelphia: C. Mow, R. Huiskes; 2005.Search in Google Scholar
23. Wentink EC, Beijen SI, Hermens HJ, Rietman JS, Veltink PH. Intention detection of gait initiation using EMG and kinematic data. Gait & Posture 2013;37:223–8. https://doi.org/10.1016/j.gaitpost.2012.07.013.Search in Google Scholar PubMed
24. Hong JH, Mun MS. Relationship between socket pressure and EMG of two muscles in trans-femoral stumps during gait. Prosth Orthotics Inter 2005;29:59–72. https://doi.org/10.1080/03093640500116764.Search in Google Scholar PubMed
25. Demura S, Yamada T. Height of chair seat and movement characteristics in sit-to-stand by young and elderly adults. Perceptual and Motor Skills 2007;104:21–31. https://doi.org/10.2466/pms.104.1.21-31.Search in Google Scholar PubMed
26. Millington PJ, Myklebust BM, Shambes GM. Biomechanical analysis of the sit-to-stand motion in elderly persons. Arch Phy Med Rehab 1992;73:609–17. https://doi.org/10.5505/saufbe.2012.85570.Search in Google Scholar
27. Riillo F, Quitadamo LR, Cavrini F, Gruppioni E, Pinto CA, Pasto NC, et al. Optimization of EMG-based hand gesture recognition: Supervised vs. unsupervised data preprocessing on healthy subjects and transradial amputees. Biomed Signal Process Cont 2014;14:117–25. https://doi.org/10.1016/j.bspc.2014.07.007.Search in Google Scholar
28. Smith LH, Hargrove LJ, Lock BA, Kuiken TA. Determining the optimal window length for pattern recognition-based myoelectric control: balancing the competing effects of classification error and controller delay. IEEE Trans Neural Sys Rehab Eng 2011;19:186–92. https://doi.org/10.1109/tnsre.2010.2100828.Search in Google Scholar
29. Oskoei MA, Hu HS. Support vector machine-based classification scheme for myoelectric control applied to upper limb. IEEE Trans Biomed Eng 2008;55:1956–65. https://doi.org/10.1109/tbme.2008.919734.Search in Google Scholar
30. Angkoon P, Chusak L, Pornchai P. A Novel feature extraction for robust emg pattern recognition. J Med Eng Tech 2009;40 4:149–54. https://doi.org/10.3109/03091902.2016.1153739.Search in Google Scholar PubMed
31. Geethanjali P, Ray KK. EMG based man-machine interaction-A pattern recognition research platform. Rob Auto Sys 2014;62:864–70. https://doi.org/10.1016/j.robot.2014.01.008.Search in Google Scholar
32. Chen, Wang. Pattern recognition of number gestures based on a wireless surface EMG system. Biomed Sign Process Cont 2013;8:184–92. https://doi.org/10.1016/j.bspc.2012.08.005.Search in Google Scholar
33. Polat K, Gunes S. Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. App Math Comp 2007;187:1017–26. https://doi.org/10.1016/j.amc.2006.09.022.Search in Google Scholar
34. Wu, Lin, Weng. Probability estimates for multi-class classification by pairwise coupling. J Mach Learn Res 2004;5:975–1005.Search in Google Scholar
35. Xi XG, Tang MY, Miran SM, Luo ZZ. Evaluation of feature extraction and recognition for activity monitoring and fall detection based on wearable sEMG sensors. Sensors 2017;17. https://doi.org/10.3390/s17061229.Search in Google Scholar PubMed PubMed Central
36. Hargrove LJ, Simon AM, Young AJ, Lipschutz RD, Finucane SB, Smith DG, et al. Robotic leg control with emg decoding in an amputee with nerve transfers. New England J Med 2013;369:1237–42. https://doi.org/10.1056/nejmoa1300126.Search in Google Scholar
37. Yusof NHM, Hamzaid NA, Jasni F, Lai KW. In-socket sensory system with an adaptive neuro-based fuzzy inference system for active transfemoral prosthetic legs. J Elect Imag 2019;28. https://doi.org/10.1117/1.jei.28.2.021002.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
