基于柔性可拉伸材料电极的肌电信号获取与手势识别

表面肌电信号是能够表征各项人体健康指数的一项关键的生理数据，现有研究中针对表面肌电信号的模式识别已有了长足的发展，但是如何将其更好的应用于实际生活仍是一个值得探索的问题。当今时代，人们对于卒中、偏瘫等患者的康复治疗愈发看重，且传统康复训练中或多或少存在一定的缺陷，本课题的目的在于将基于表面肌电信号的手部动作识别与虚拟现实结合，实现具备生理反馈的一种针对性的康复训练方案。以往的研究中，表面肌电信号的采集中采集电极多使用传统刚性电极或者质地坚硬的阵列电极，采集时易与皮肤产生相对位移，影响表面肌电信号质量。

本课题主要使用一种柔性可拉伸材料电极粘贴在受试者前臂肌肉附近，采集了8位受试者在进行32种精细手部动作时的表面肌电信号，采集过程中使用了新型的自研神经肌肉电生理采集系统，能够采集到信噪比更高、特征更明显的表面肌电信号。通过对采集到的表面肌电数据进行分析判别，对32种手部动作的平均识别率达到了92.06%。基于对8位受试者的表面肌电信号分析结果，本课题结合Unity设计了一款虚拟手部动作识别软件，能够实时处理采集到的表面肌电信号，分析判别出对应手部动作并生成指令控制虚拟手部骨骼模型，使得虚拟手部骨骼模型能够实时跟随人体手部动作。

针对患者五指肌肉的康复训练，课题中开发了一款消除方块的康复训练小游戏，小游戏中通过五路通道信号监测五根手指动作，能够更有针对性的对患者的五指进行康复训练，不仅充满了趣味性，更能记录每一次的康复训练数据，不断的给予训练反馈，对于未来的虚拟康复领域提供了一种可参考性的思路。课题中将手部动作识别应用于对智能小车的控制，通过将控制指令与手部动作匹配，根据不同动作时的表面肌电信号实时判别出控制指令并传输给智能小车，使得智能小车能够根据动作的不同实现前进、后退、加速等操作。

[1] 王亚楠, 吴思缈, 刘鸣. 中国脑卒中15年变化趋势和特点 [J]. 华西医学, 2021, 36(06): 803-807.
[2] Nam Y, Koo B, Cichocki A, et al. GOM-Face: GKP, EOG, and EMG-based multimodal interface with application to humanoid robot control [J]. IEEE Transactions on Biomedical Engineering, 2013, 61(2): 453-462.
[3] Farina D, Merletti R, Enoka R M. The extraction of neural strategies from the surface EMG [J]. Journal of applied physiology, 2004, 96(4): 1486-1495.
[4] 吴宸宇. 柔性电极的发展与应用前景 [J]. 中国高新科技, 2019(09): 105-107.
[5] Chan A D C, Englehart K B. Continuous myoelectric control for powered prostheses using hidden Markov models [J]. IEEE Transactions on biomedical engineering, 2004, 52(1): 121-124.
[6] Hu X, Wang Z, Ren X. Classification of surface EMG signal using relative wavelet packet energy [J]. Computer methods and programs in biomedicine, 2005, 79(3): 189-195.
[7] Englehart K, Hudgins B, Parker P A, et al. Classification of the myoelectric signal using time-frequency based representations [J]. Medical engineering & physics, 1999, 21(6-7): 431-438.
[8] 徐瑞, 李志才, 王雯婕, 王紫尧, 明东. 基于肌电的人机交互控制策略及其应用与挑战 [J]. 电子测量与仪器学报, 2020, 34(02): 1-11.
[9] 石月. 柔性电极制备及导电聚合物修饰研究 [D]. 北京印刷学院, 2021.
[10] Xie K, Zhang S, Dong S, et al. Portable wireless electrocorticography system with a flexible microelectrodes array for epilepsy treatment [J]. Scientific reports, 2017, 7(1): 1-8.
[11] Tang L J, Wang M H, Tian H C, et al. Progress in research of flexible MEMS microelectrodes for neural interface [J]. Micromachines, 2017, 8(9): 281.
[12] 吴军. 聚酰亚胺表面高功率脉冲磁控溅射技术制备Cu膜工艺研究 [D]. 哈尔滨工业大学, 2020.
[13] Lapatki B G, Van Dijk J P, Jonas I E, et al. A thin, flexible multielectrode grid for high-density surface EMG [J]. Journal of Applied Physiology, 2004, 96(1): 327-336.
[14] 董中飞, 陈香, 邓浩, 张永强. 柔性同心圆差分阵列表面肌电电极研制 [J]. 电子测量与仪器学报, 2012, 26(04): 359-366.
[15] Corporation H P. Applied computational intelligence and soft computing [J]. Hindawi Limited, 2008, 2010(10):752-63.
[16] 曹玉珍, 陈成, 胡勇, 刘洪涛. 基于独立成份分析的肌电信号消噪方法研究 [J]. 信号处理, 2003(04): 369-372.
[17] Graupe D, Cline W K. Functional separation of EMG signals via ARMA identification methods for prosthesis control purposes [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1975 (2): 252-259.
[18] Saridis G N, Gootee T P. EMG pattern analysis and classification for a prosthetic arm [J]. IEEE Transactions on Biomedical Engineering, 1982 (6): 403-412.
[19] Zardoshti-Kermani M, Wheeler B C, Badie K, et al. EMG feature evaluation for movement control of upper extremity prostheses [J]. IEEE Transactions on Rehabilitation Engineering, 1995, 3(4): 324-333.
[20] 韩晓新, 邢绍邦, 刘海燕, 朱品伟, 胡春华, 沃松林. 基于EMG频域特征的假肢机电信号识别研究 [J]. 测试技术学报, 2011, 25(04): 346-350.
[21] Gant L, Fethke N, Gerr F. Spectral analysis of root-mean-square processed surface electromyography data as a measure of repetitive muscular exertion [C]. Proceedings of the Human Factors and Ergonomics Society Annual Meeting. Sage CA: Los Angeles, CA: SAGE Publications, 2012, 56(1): 1140-1144.
[22] 蔡立羽, 王志中, 张海虹. 基于短时傅里叶变换的肌电信号识别方法 [J]. 中国医疗器械杂志, 2000(03): 133-136.
[23] Englehart K, Hudgins B. A robust, real-time control scheme for multifunction myoelectric control [J]. IEEE transactions on biomedical engineering, 2003, 50(7): 848-854.
[24] Almström C, Herberts P, Körner L. Experience with Swedish multifunctional prosthetic hands controlled by pattern recognition of multiple myoelectric signals [J]. International orthopaedics, 1981, 5(1): 15-21.
[25] 王人成, 黄昌华, 李波, 金德闻, 张济川. 基于BP神经网络的表面肌电信号模式分类的研究 [J]. 中国医疗器械杂志, 1998(02): 63-66.
[26] Saponas T S, Tan D S, Morris D, et al. Demonstrating the feasibility of using forearm electromyography for muscle-computer interfaces [C]. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2008: 515-524.
[27] Villarejo J J, Frizera A, Bastos T F, et al. Pattern recognition of hand movements with low density sEMG for prosthesis control purposes [C]. 2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR). IEEE, 2013: 1-6.
[28] Veer K, Sharma T. A novel feature extraction for robust EMG pattern recognition [J]. Journal of medical engineering & technology, 2016, 40(4): 149-154.
[29] Yi Z, Lingling D, Yuan L, et al. Design of a surface EMG based human-machine interface for an intelligent wheelchair [C]. IEEE 2011 10th International Conference on Electronic Measurement & Instruments. IEEE, 2011, 3: 132-136.
[30] 刘建伟. 肌电控制接口的自适应方法研究 [D]. 上海交通大学, 2016.
[31] He J, Sheng X, Zhu X, et al. Electrode density affects the robustness of myoelectric pattern recognition system with and without electrode shift [J]. IEEE journal of biomedical and health informatics, 2018, 23(1): 156-163.
[32] 邱青菊. 表面肌电信号的特征提取与模式分类研究 [D]. 上海交通大学, 2009.
[33] Li G, Schultz A E, Kuiken T A. Quantifying pattern recognition—Based myoelectric control of multifunctional transradial prostheses [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2010, 18(2): 185-192.
[34] 王涛. 基于表面肌电信号的多自由度假肢控制算法及系统研究 [D]. 重庆大学, 2016.
[35] 马丽. 基于表面肌电信号的手指活动模式检测 [D]. 重庆大学, 2008.
[36] 李醒飞, 朱嘉, 杨晶晶, 张国雄, 卢志扬. 基于肌电信号的人手运动状态的辨识 [J]. 中国生物医学工程学报, 2007(02): 166-169.
[37] 李会军, 宋爱国. 上肢康复训练机器人的研究进展及前景 [J]. 机器人技术与应用, 2006(04): 32-36.
[38] Huang H, Ingalls T, Olson L, et al. Interactive multimodal biofeedback for task-oriented neural rehabilitation [C]. 2005 IEEE engineering in medicine and biology 27th annual conference. IEEE, 2006: 2547-2550.
[39] 徐宝国, 彭思, 宋爱国. 基于运动想象脑电的上肢康复机器人 [J]. 机器人, 2011, 33(03): 307-313.
[40] 张冬蕊, 耿艳娟, 徐礼胜, 张秀峰, 李光林. 虚拟现实手部康复训练系统的设计与实现 [J]. 集成技术, 2013, 2(04): 32-38.
[41] OREHAB-ARM智能康复训练[EB/OL].http://www.oymotion.com/product44/103
[2021-11-18]
[42] Xiang Z, Yen S C, Sheshadri S, et al. Progress of Flexible Electronics in Neural Interfacing–A Self‐Adaptive Non‐Invasive Neural Ribbon Electrode for Small Nerves Recording [J]. Advanced Materials, 2016, 28(22): 4472-4479.
[43] Tang L J, Wang M H, Tian H C, et al. Progress in research of flexible MEMS microelectrodes for neural interface [J]. Micromachines, 2017, 8(9): 281.
[44] Ferro M D, Melosh N A. Electronic and ionic materials for neurointerfaces [J]. Advanced Functional Materials, 2018, 28(12): 1704335.
[45] 路敦强, 王为, 陈永鹏. 基于ADS1298的表面肌电采集系统设计 [J]. 天津师范大学学报(自然科学版), 2015, 35(01): 34-37.
[46] 薛金伟. 面向前臂截肢患者的虚拟现实康复方法研究 [D]. 中国科学院大学(中国科学院深圳先进技术研究院), 2020.
[47] 班帅. 人体上肢表面肌电信号采集与处理的研究 [D]. 东北大学, 2012.
[48] Boschmann A, Platzner M. Reducing classification accuracy degradation of pattern recognition based myoelectric control caused by electrode shift using a high density electrode array [C]. 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2012: 4324-4327.
[49] Zhou P, Lowery M M, Englehart K B, et al. Decoding a new neural–machine interface for control of artificial limbs [J]. Journal of neurophysiology, 2007, 98(5): 2974-2982.
[50] Hargrove L, Englehart K, Hudgins B. The effect of electrode displacements on pattern recognition based myoelectric control [C]. 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2006: 2203-2206.
[51] 李强. 表面肌电信号的运动单位动作电位检测 [D]. 中国科学技术大学, 2008.
[52] Inbar G F, Paiss O, Allin J, et al. Monitoring surface EMG spectral changes by the zero crossing rate [J]. Medical and Biological Engineering and Computing, 1986, 24(1): 10-18.
[53] Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification [J]. Expert systems with applications, 2012, 39(8): 7420-7431.
[54] Adewuyi A A, Hargrove L J, Kuiken T A. Evaluating EMG feature and classifier selection for application to partial-hand prosthesis control [J]. Frontiers in neurorobotics, 2016, 10: 15.
[55] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016: 60-121.
[56] Kumar S, Kumar D K, Alemu M, et al. EMG based voice recognition [C]. Proceedings of the 2004 Intelligent Sensors, Sensor Networks and Information Processing Conference, 2004. IEEE, 2004: 593-597.