1. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; 2. Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China; 3. University of Chinese Academy of Sciences, Beijing 100049, China; 4. Rehabilitation Center, Shengjing Hospital of China Medical University, Shenyang 110134, China
Abstract:A hand motion intention recognition method with a high recognition rate and suitable for patients of different rehabilitation levels is proposed to solve the problem of low recognition rate of motion intention of stroke patients based on surface electromyography (sEMG) signal. Firstly, the sEMG data from 30 patients of different rehabilitation levels are used to carry out feature extraction based on tsfresh library and feature selection based on Feature-Selector library, and the most suitable sliding window parameters and the features suitable for the patient motion recognition task are determined. Then, some action recognition experiments are conducted with the proposed method, which is compared with other methods, including random forest, convolutional neural network, etc. The experimental results show that the average recognition accuracy of the proposed method for 9 commonly used hand rehabilitation actions is 97.94%. Finally, a hand rehabilitation system is developed based on the proposed method, its real-time performance is analyzed based on online recognition experiments, and a patient tracking experiment is designed to verify the effectiveness of the system for patient hand rehabilitation.
[1] Mozaffarian D, Benjamin E J, Go A S, et al. Heart disease and stroke statistics-2016 update:A report from the American Heart Association[J]. Circulation, 2016, 133(4):e38-e360. [2] Yap H K, Ang B W K, Lim J H, et al. A fabric-regulated soft robotic glove with user intent detection using EMG and RFID for hand assistive application[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2016:3537-3542. [3] Metzger J C, Lambercy O, Califfi A, et al. Neurocognitive robot-assisted therapy of hand function[J]. IEEE Transactions on Haptics, 2014, 7(2):140-149. [4] Geoff B, Sandy B, Louise G, et al. Clinical guidelines for stroke management 2010[R]. Melbourne, Australia:National Stroke Foundation, 2010. [5] Johansson B B. Current trends in stroke rehabilitation. A review with focus on brain plasticity[J]. Acta Neurologica Scandinavica, 2011, 123(3):147-159. [6] Epstein D, Mason A, Manca A. The hospital costs of care for stroke in nine European countries[J]. Health Economics, 2008, 17(S1):S21-S31. [7] Zhang F, Hou Z G, Cheng L, et al. iLeg-A lower limb rehabilitation robot:A proof of concept[J]. IEEE Transactions on Human-Machine Systems, 2016, 46(5):761-768. [8] Li H C, Cheng L. Preliminary study on the design and control of a pneumatically-actuated hand rehabilitation device[C]//32nd Youth Academic Annual Conference of Chinese Association of Automation. Piscataway, USA:IEEE, 2017:860-865. [9] 李敏,徐光华,谢俊,等.脑卒中意念控制的主被动运动康复技术[J].机器人, 2017, 39(5):759-768. Li M, Xu G H, Xie J, et al. Motor rehabilitation with control based on human intent for stroke survivors[J]. Robot, 2017, 39(5):759-768. [10] Lynch D, Ferraro M, Krol J, et al. Continuous passive motion improves shoulder joint integrity following stroke[J]. Clinical Rehabilitation, 2005, 19(6):594-599. [11] Miao Q, Zhang M M, Cao J H, et al. Reviewing high-level control techniques on robot-assisted upper-limb rehabilitation[J]. Advanced Robotics, 2018, 32(24):1253-1268. [12] 丁其川,熊安斌,赵新刚,等.基于表面肌电的运动意图识别方法研究及应用综述[J].自动化学报, 2016, 42(1):13-25. Ding Q C, Xiong A B, Zhao X G, et al. A review on researches and applications of sEMG-based motion intent recognition methods[J]. Acta Automatica Sinica, 2016, 42(1):13-25. [13] Wei W T, Wong Y K, Du Y, et al. A multi-stream convolutional neural network for sEMG-based gesture recognition in musclecomputer interface[J]. Pattern Recognition Letters, 2019, 119:131-138. [14] Tsinganos P, Cornelis B, Cornelis J, et al. Improved gesture recognition based on sEMG signals and TCN[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, USA:IEEE, 2019:1169-1173. [15] 丁其川,赵新刚,李自由,等.基于自更新混合分类模型的肌电运动识别方法[J].自动化学报, 2019, 45(8):1464-1474. Ding Q C, Zhao X G, Li Z Y, et al. An EMG-motion recognition method with self-update hybrid classification model[J]. Acta Automatica Sinica, 2019, 45(8):1464-1474. [16] Lee S W, Wilson K M, Lock B A, et al. Subject-specific myoelectric pattern classification of functional hand movements for stroke survivors[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2011, 19(5):558-566. [17] Zhang X, Zhou P. High-density myoelectric pattern recognition toward improved stroke rehabilitation[J]. IEEE Transactions on Biomedical Engineering, 2012, 59(6):1649-1657. [18] 王丰焱,张道辉,李自由,等.适用不同Brunnstrom等级患者基于表面肌电信号的动作识别方法[J].机器人, 2020, 42(6):661-671,685. Wang F Y, Zhang D H, Li Z Y, et al. Method for sEMGbased motion recognition for patients at different Brunnstrom stages[J]. Robot, 2020, 42(6):661-671,685. [19] Chen M, Cheng L, Huang F B, et al. Towards robot-assisted post-stroke hand rehabilitation:Fugl-Meyer gesture recognition using sEMG[C]//IEEE 7th Annual International Conference on Cyber Technology in Automation, Control, and Intelligent Systems. Piscataway, USA:IEEE, 2017:1472-1477. [20] Liu Y, Cheng L. Spiking-neural-network based Fugl-Meyer hand gesture recognition for wearable hand rehabilitation robot[C]//International Joint Conference on Neural Networks. Piscataway, USA:IEEE, 2018. DOI:10.1109/IJCNN.2018.8489141. [21] Christ M, Braun N, Neuffer J, et al. Time series FeatuRe extraction on basis of scalable hypothesis tests (tsfresh-A Python package)[J]. Neurocomputing, 2018, 307:72-77. [22] Fındık M, Yılmaz Ş, Koseoglu M. Random forest classification of finger movements using electromyogram (EMG) signals[C]//IEEE SENSORS. Piscataway, USA:IEEE, 2020. DOI:10. 1109/SENSORS47125.2020.9278619. [23] Koehrsen W. Feature selector:Simple feature selection in Python[EB/OL].[2020-12-30]. https://github.com/WillKoehrsen/feature-selector. [24] Brunnstrom S. Motor testing procedures in hemiplegia:Based on sequential recovery stages[J]. Physical Therapy, 1966, 46(4):357-375. [25] Tengku Zawawi T N S, Abdullah A R, Jopri M H, et al. A review of electromyography signal analysis techniques for musculoskeletal disorders[J]. Indonesian Journal of Electrical Engineering and Computer Science, 2018, 11(3):1136-1146. [26] Venkatesh B, Anuradha J. A review of feature selection and its methods[J]. Cybernetics and Information Technologies, 2019, 19(1):3-26. [27] Saeys Y, Abeel T, van de Peer Y. Robust feature selection using ensemble feature selection techniques[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany:Springer, 2008:313-325. [28] Zhou Z H, Feng J. Deep forest:Towards an alternative to deep neural networks[C]//26th International Joint Conference on Artificial Intelligence. 2017. DOI:10.24963/ijcai.2017/497.