Surface Electromyography Gesture Recognition Based on Personalized Feature Analysis
LIU Dongbo1,LIU Yun1,FANG Yu1,YI Minsheng2,WANG Weibo1
1. School of Electrical and Electronic Information, Xihua University, Chengdu,Sichuan 610039, China
2. Shaoyang Polytechnic, Shaoyang, Hunan 422004,China
Abstract：To realize artificial limb control, it is an important method to use surface electromyography (sEMG) signal to recognize gestures. sEMG signals are electromyographic signals collected from the surface layer of the skin, which can reflect the neuromuscular activities to a certain extent. Due to its random and non-smooth characteristics, the use of sEMG signals to control artificial intelligent prosthetic limbs has never been able to achieve the desired results, especially reflected in the influence of individual differences such as gender. A gesture recognition method based on surface EMG signals is proposed for seven types of gesture movements through differentiated gender characterization. Experimental results show that the recognition accuracy of the method is significantly improved in all five classifiers. Among them, linear discriminant analysis has the most significant improvement, reaching 15.84%; support vector machine and extreme gradient boosting are the most effective in gesture recognition, with an accuracy of 98.41%.
ARTEAGA M V, CASTIBLANCO J C, MONDRAGON I F, et al. EMG-driven hand model based on the classification of individual finger movements [J]. Biomedical Signal Processing and Control, 2020, 58: 101834.
[5]
FOUGNER A, STAVDAHL Φ, KYBERD P J, et al. Control of Upper Limb Prostheses: Terminology and Proportional Myoelectric Control—A Review [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2012, 20(5), 663-677.
JIE Y G, WANG Q. A review of visual based dynamic gesture recognition research [J]. Computer Engineering and Applications, 2021, 57(22): 68-77.
[9]
OSKOEO M A, HU H. Support Vector Machine-Based Classification Scheme for Myoelectric Control Applied to Upper Limb [J]. IEEE Transactions on Biomedical Engineering, 2008, 55(8), 1956-1965.
[12]
NISHIKASA Y, WATANABE K, TAKAHASHI T, et al. Sex differences in variances of multi-channel surface electromyography distribution of the vastus lateralis muscle during isometric knee extension in young adults [J]. Eur J Appl Physiol, 2017, 117(3): 583-589.
GU Q, GU Q, JIN D Y, et al. Effect of push-ups on the surface myoelectric signals of the shoulder perimuscular group in patients with wing-shaped shoulders [J]. Chinese Journal of Physical Medicine and Rehabilitation, 2018, 40(7): 532-535.
[16]
KAMBAYASHI I, ISHIMURA N, KOBAYASHI K, et al. Differences in Muscle Oxygenation Level According to Gender during Isometric Hand-grip Exercises [J]. Journal of Hokkaido University of Education. Natural Sciences, 2003, 54, 89-96.
[18]
WANG M, WANG X, PENG C, et al. Research on EMG segmentation algorithm and walking analysis based on signal envelope and integral electrical signal [J]. Photonic Network Communications, 2019, 37(2): 195-203.
[20]
王朋. 基于MYO臂环的假肢手控制技术研究[D]. 上海: 上海师范大学, 2017.
[1]
WORLD HEALTH ORGANIZATION. Global Report on Health Equality for Persons with Disabilities [R/OL]. (2022-12-02). https: //www. who. int/ publications/i/item/ 9789240063600.
DU M Y, BAO G J, YANG Q H, et al. Novel method in pattern recognition of hand actions based on improved support vector machine [J]. Journal of Zhejiang University (Engineering Edition), 2018, 52(7): 1239-1246.
[10]
KARNAM N K, TURLAPATY A C, DUBEY S R, et al. Classification of sEMG signals of hand gestures based on energy features [J]. Biomedical Signal Processing and Control, 2021, 70:102948.
[17]
MATEO J, SáNCHEZ-MORLA E M, SANTOS J L. A new method for removal of powerline interference in ECG and EEG recordings [J]. Computers & Electrical Engineering, 2015, 45: 235-248.
WANG H Y, LI J H, YANG F L. Review of Support Vector Machine Theory and Algorithm Research [J]. Computer Application Research, 2014, 31 (5): 1281-1286.
[23]
SHASTRY K A, SANJAY H A, DEEXITH G. Quadratic-radial-basis function-kernel for classifying multi-class agricultural datasets with continuous attributes [J]. Appl Soft Comput, 2017, 58: 65-74.
WANG J W, CAO L, KAN X, et al. LDA-BPNN dual arm gesture recognition algorithm based on surface electromyography signals [J]. Sensors and microsystems, 2023, 42(6): 158-160.
LIANG X, WANG W Q, HOU Z G, et al. Human machine interaction control method for rehabilitation robots [J]. Chinese Science: Information Science, 2018, 48(1): 24-46.
[14]
JOCHUMSEN M, WARIS A, KAMAVUAKO E N. The effect of arm positionon classification of handgestures with intramuscular EMG [J]. Biomedical Signal Processing and Control, 2018, 43: 1-8.
[15]
MANJUANTH H, VENKATESH D, RAJKUMAR S, et al. Gender difference in hand grip strength and electromyogram (EMG) changes in upper limb [J]. Research Journal of Pharmaceutical Biological and Chemical Sciences, 2015, 6(4): 1889-1893.
CAO A, ZHANG K J, LIU R, et al. Muscle fatigue state classification system based on surface electromyography signal [J]. Journal of Computer Applications, 2018, 38(6): 1801-1808.
LEI J C, LIU D B, FANG Y, et al. Gender based gesture recognition based on surface electromyography signals [J]. Chinese Journal of Medical Physics, 2020, 37(3): 337-341.
JIANG Q, LI Y H, ZOU K, et al. Multi channel correlation feature gesture recognition method for electromyographic signals [J]. Computer Engineering and Applications, 2023, 59 (7): 102-109.
2024, Vol. 45 
