基於表面肌電信號的人機互動系統關鍵技術綜述

Q. Wu, X. Chen, L. Ding, C.F. Wei, H. Ren, R. Law, H.H. Dong, X.L. Li, Classification of EMG signals by BFA-Optimized GSVCM for diagnosis of fatigue status, IEEE Trans. Autom. Sci. Eng. 14 (2) (2017) 915–930Elbow joint static and motion states（肘關節靜態和運動狀態）該模型的應用可以進一步提高基於表面肌電信號的肌肉疲勞分類的準確性。Q.C. Ding, X.G. Zhao, Z.Y. Li, J.D. Han, An EMG-motion recognition method with self-update hybrid classification model, Acta Autom. Sin. 45 (8) (2018) 1464–1474.sEMG instability, Outlier motions（表面肌電信號不穩定，異常運動）該方法可以有效地降低表面肌電信號失穩和異常運動的幹擾，提高識別的魯棒性。Q.C. Ding, X.G. Zhao, J.D. Han, C.G. Bu, C.D. Wu, Adaptive hybrid classifier for myoelectric pattern recognition against the interferences of outlier motion, muscle fatigue, and electrode doffing, IEEE Trans. Neural Syst. Rehabil. Eng. 27 (5) (2019) 1071–1080.Outlier motions, Muscle fatigue, Electrode doffing（異常運動，肌肉疲勞，電極脫落）與傳統的非自適應分類器相比，該方法具有明顯的優勢，能有效地消除異常運動、肌肉疲勞和電極落紗幹擾。F. Duan, L.L. Dai, Recognizing the gradual changes in sEMG characteristics based on incremental learning of wavelet neural network ensemble, IEEE Trans. Ind. Electron. 64 (5) (2017) 4276–4286.Muscle fatigue caused by prolonged motion（長時間運動引起的肌肉疲勞）該方法能有效補償肌肉疲勞，顯著提高運動分類的準確性和識別的穩定性。G. Biagetti, P. Crippa, A. Curzi, S. Orcioni, C. Turchetti, Analysis of the EMG signal during cyclic movements using multicomponent AM-FM decomposition, IEEE J. Biomed. Health Inform. 19 (5) (2015) 1672–1681.Q.C. Ding, J.D. Han, X.G. Zhao, Y. Chen, Missing-data classification with the extended full-dimensional Gaussian mixture model: applications to EMG-Based motion recognition, IEEE Trans. Ind. Electron. 62 (8) (2015) 4994–5005.J.X. Qi, G.Z. Jiang, G.F. Li, Y. Sun, B. Tao, Intelligent human-computer interaction based on surface EMG gesture recognition, IEEE Access 7 (2019) 61378–61387.該方法可以提高表面肌電信號在人機互動中的泛化能力，減少冗餘信號的幹擾。H.J. Hwang, W.H. Chung, J.H. Song, J.K. Lim, H.S. Kim, Prediction of biceps muscle fatigue and force using electromyography signal analysis for repeated isokinetic dumbbell curl exercise, J. Mech. Sci. Technol. 30 (11) (2016) 5329–5336./-/C.Y. Jung, J.S. Park, Y. Lim, Y.B. Kim, K.K. Park, J.H. Moon, J.H. Song, S.H. Lee, Estimating fatigue level of femoral and gastrocemius muscles based on surface electromyography in time and frequency domain, J. Mech. Med. Biol. 18 (05) (2018) 1–15.該方法可用於基於實時表面肌電信號的股骨和腓腸肌疲勞和肌力估計。T.D. Lalitharatne, K. Teramoto, Y. Hayashi, T. Nanayakkara, K. Kiguchi, Evaluation of fuzzy-neuro modifiers for compensation of the effects of muscle fatigue on EMG-based control to be used in upper-limb power-assist exoskeletons, J. Adv. Mech. Des. Syst. Manuf. 7 (4) (2013) 736–751.該方法對慢動作下的肌肉疲勞有較高的補償效果，可以提高外骨骼的控制精度。Y. Na, J. Kim, Dynamic elbow flexion force estimation through a muscle twitch model and sEMG in a fatigue condition, IEEE Trans. Neural Syst. Rehabil. Eng. 25 (9) (2017) 1431–1439.該方法在疲勞狀態下的計算結果與傳統回歸方法一致，且性能優於人工神經網絡。T. Triwiyanto, W. Oyas, H.A. Nugroho, H. Herianto, Muscle fatigue compensation of the electromyography signal for elbow joint angle estimation using adaptive feature, Comput. Electr. Eng. 71 (2018) 284–293.該方法可以補償肌肉疲勞對肘關節角度預測精度的影響。通道數(NCs)；細菌覓食優化算法(BFA)；高斯支持向量分類機(GSVCM)；均方根(RMS)；中值頻率(MF)；綜合肌電圖(IEMG)；平均功率頻率(MPF)；平均瞬時頻率(MIF)；平均絕對值(MAV)；倒譜係數(Ceps)；過零(ZC)；小波神經網絡(WNN)；負相關學習(NCL)；幅度譜平均頻率(MFA)；高斯混合模型(GMM)；線性判別分析(LDA)；極端學習機(ELM)；波形長度(WL)；中值振幅譜(MAS)；人工神經網絡(ANN)；威爾遜振幅(WAMP)。