The utilization of surface EMG and intramuscular EMG signals has been observed to create significant improvement in pattern recognition approaches and myoelectric control. However, there is less data of different arm positions and hand postures available. Hand postures and arm positions tend to affect the combination of surface and intramuscular EMG signal acquisition in terms of classifier accuracy. Hence, this study aimed to find a robust classifier for two scenarios: (1) at fixed arm position (FAP) where classifiers classify different hand postures and (2) at fixed hand posture (FHP) where classifiers classify different arm positions. A total of 20 healthy male participants (30.62 ± 3.87 years old) were recruited for this study. They were asked to perform five motion classes including hand grasp, hand open, rest, hand extension, and hand flexion at four different arm positions at 0°, 45°, 90°, and 135°. SVM, KNN, and LDA classifier were deployed. Statistical analysis in the form of pairwise comparisons was carried out using SPSS. It is concluded that there is no significant difference among the three classifiers. SVM gave highest accuracy of 75.35% and 58.32% at FAP and FHP respectively for each motion classification. KNN yielded the highest accuracies of 69.11% and 79.04% when data was pooled and was classified at different arm positions and at different hand postures respectively. The results exhibited that there is no significant effect of changing arm position and hand posture on the classifier accuracy.
JochumsenMWarisAKamavuakoEN.The effect of arm position on classification of hand gestures with intramuscular EMG. Biomed Signal Process Control2018; 43: 1–8.
2.
SimaoMMendesNGibaruO, et al. A review on electromyography decoding and pattern recognition for human-machine interaction. IEEE Access2019; 7: 39564–39582.
3.
Jaramillo-YánezABenalcázarMEMena-MaldonadoE.Real-time hand gesture recognition using surface electromyography and machine learning: a systematic literature review. Sensors2020; 20(9): 2467.
4.
ReazMBIHussainMSMohd-YasinF.Techniques of EMG signal analysis: detection, processing, classification and applications. Biol Proced Online2006; 8(1): 11–35.
5.
HahneJMMarkovicMFarinaD.User adaptation in myoelectric man-machine interfaces. Sci Rep2017; 7(1): 1–10.
NielsenJLHolmgaardSJiangN, et al. Simultaneous and proportional force estimation for multifunction myoelectric prostheses using mirrored bilateral training. IEEE Trans Biomed Eng2010; 58(3): 681–688.
8.
HudginsBParkerPScottRN.A new strategy for multifunction myoelectric control. IEEE Trans Biomed Eng1993; 40(1): 82–94.
9.
ParkerPEnglehartKHudginsB.Myoelectric signal processing for control of powered limb prostheses. J Electromyogr Kinesiol2006; 16(6): 541–548.
10.
SchemeEEnglehartK.Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use. J Rehabil Res Dev2011; 48(6): 643.
11.
GengYZhouPLiG.Toward attenuating the impact of arm positions on electromyography pattern-recognition based motion classification in transradial amputees. J Neuroeng Rehabil2012; 9(1): 1–11.
12.
SimonAMHargroveLJLockBA, et al. A decision-based velocity ramp for minimizing the effect of misclassifications during real-time pattern recognition control. IEEE Trans Biomed Eng2011; 58(8): 2360–2368.
13.
YangDGuYJiangL, et al. Dynamic training protocol improves the robustness of PR-based myoelectric control. Biomed Signal Process Control2017; 31: 249–256.
14.
TkachDHuangHKuikenTA.Study of stability of time-domain features for electromyographic pattern recognition. J Neuroeng Rehabil2010; 7(1): 1–13.
15.
KhushabaRNShiLKodagodaS. Time-dependent spectral features for limb position invariant myoelectric pattern recognition. In: 2012 International symposium on communications and information technologies (ISCIT), Gold Coast, QLD, Australia, 2–5 October 2012, pp.1015-1020. New York, NY: IEEE.
16.
KhushabaRNTakruriMMiroJV, et al. Towards limb position invariant myoelectric pattern recognition using time-dependent spectral features. Neural Netw2014; 55: 42–58.
17.
KamavuakoENFarinaDYoshidaK, et al. Relationship between grasping force and features of single-channel intramuscular EMG signals. J Neurosci Methods2009; 185(1): 143–150.
18.
FarrellTRWeirRF.A comparison of the effects of electrode implantation and targeting on pattern classification accuracy for prosthesis control. IEEE Trans Biomed Eng2008; 55(9): 2198–2211.
19.
WarisAKamavuakoEN.Effect of threshold values on the combination of EMG time domain features: surface versus intramuscular EMG. Biomed Signal Process Control2018; 45: 267–273.
20.
FougnerASchemeEChanAD, et al. Resolving the limb position effect in myoelectric pattern recognition. IEEE Trans Neural Syst Rehabil Eng2011; 19(6): 644–651.
21.
ZhangLLiuGHanB, et al. sEMG based human motion intention recognition. J Robot2019; 2019: 1–12.
22.
SunLAnHMaH, et al. Real-time human intention recognition of multi-joints based on MYO. IEEE Access2020; 8: 4235–4243.
23.
JiangYChenCZhangX, et al. Shoulder muscle activation pattern recognition based on sEMG and machine learning algorithms. Comput Methods Programs Biomed2020; 197: 105721.
24.
DuanFDaiLChangW, et al. sEMG-based identification of hand motion commands using wavelet neural network combined with discrete wavelet transform. IEEE Trans Ind Electron2016; 63(3): 1923–1934.
25.
KopkeJVEllisMDHargroveLJ.Determining user intent of partly dynamic shoulder tasks in individuals with chronic stroke using pattern recognition. IEEE Trans Neural Syst Rehabil Eng2020; 28(1): 350–358.
26.
KopkeJVHargroveLJEllisMD.Applying LDA-based pattern recognition to predict isometric shoulder and elbow torque generation in individuals with chronic stroke with moderate to severe motor impairment. J Neuroeng Rehabil2019; 16(1): 35–11.
27.
CaiSChenYHuangS, et al. SVM-based classification of sEMG signals for upper-limb self-rehabilitation training. Front Neurorobot2019; 13: 31.
28.
ChayaNABhavanaBRAnoognaSB, et al. Real-time replication of arm movements using surface EMG signals. Procedia Comput Sci2019; 154: 186–193.
29.
SuthaharanS. Support vector machine. In: Machine learning models and algorithms for big data classification. Boston, MA: Springer, 2016, pp.207–235.
LubisARLubisMKhowarizmiA.Optimization of distance formula in K-Nearest Neighbor method. Bull Electr Eng Inform2020; 9(1): 326–338.
32.
XanthopoulosPPardalosPMTrafalisTB. Linear discriminant analysis. In: Robust data mining. New York, NY: Springer, 2013, pp.27–33.
33.
TharwatAGaberTIbrahimA, et al. Linear discriminant analysis: a detailed tutorial. AI Commun2017; 30(2): 169–190.
34.
HeydariSSMountrakisG.Effect of classifier selection, reference sample size, reference class distribution and scene heterogeneity in per-pixel classification accuracy using 26 Landsat sites. Remote Sens Environ2018; 204: 648–658.
35.
ShiW-TLyuZ-JTangS-T, et al. A bionic hand controlled by hand gesture recognition based on surface EMG signals: a preliminary study. Biocybern Biomed Eng2018; 38(1): 126–135.
36.
TavakoliMBenussiCAlhais LopesP, et al. Robust hand gesture recognition with a double channel surface EMG wearable armband and SVM classifier. Biomed Signal Process Control2018; 46: 121–130.
37.
AmanpreetK.Machine learning-based novel approach to classify the shoulder motion of upper limb amputees. Biocybern Biomed Eng2019; 39(3): 857–867.
38.
FajardoJMGomezOPrietoF.EMG hand gesture classification using handcrafted and deep features. Biomed Signal Process Control2021; 63: 65: 102210.
39.
RauraleSAMcAllisterJdel RinconJM.Real-time embedded EMG signal analysis for wrist-hand pose identification. IEEE Trans Signal Process2020; 68: 2713–2723.
40.
MukhopadhyayAKSamuiS.An experimental study on upper limb position invariant EMG signal classification based on deep neural network. Biomed Signal Process Control2020; 55: 101669.
41.
SaikiaAMazumdarSSahaiN, et al. Performance analysis of artificial neural network for hand movement detection from EMG signals. IETE J Res2019; 65: 1–10.
42.
CeneVTosinMMachadoJ, et al. Open database for accurate upper-limb intent detection using electromyography and reliable extreme learning machines. Sensors2019; 19(8): 1864.
43.
YuMLiGJiangD, et al. Hand medical monitoring system based on machine learning and optimal EMG feature set. Pers Ubiquitous Comput. Epub ahead of print 2 August 2019. DOI: 10.1007/s00779-019-01285-2.
44.
Al OmariFHuiJMeiC, et al. Pattern recognition of eight hand motions using feature extraction of forearm EMG signal. Proc Natl Acad Sci India Sect A Phys Sci2014; 84(3): 473–480.
45.
AlkanAGünayM.Identification of EMG signals using discriminant analysis and SVM classifier. Expert Syst Appl2012; 39(1): 44–47.
