Evaluation of Feature Extraction and Classification for Lower Limb Motion Based on sEMG Signal

The real-time and accuracy of motion classification plays an essential role for the elderly or frail people in daily activities. This study aims to determine the optimal feature extraction and classification method for the activities of daily living (ADL). In the experiment, we collected surface electromyography (sEMG) signals from thigh semitendinosus, lateral thigh muscle, and calf gastrocnemius of the lower limbs to classify horizontal walking, crossing obstacles, standing up, going down the stairs, and going up the stairs. Firstly, we analyzed 11 feature extraction methods, including time domain, frequency domain, time-frequency domain, and entropy. Additionally, a feature evaluation method was proposed, and the separability of 11 feature extraction algorithms was calculated. Then, combined with 11 feature algorithms, the classification accuracy and time of 55 classification methods were calculated. The results showed that the Gaussian Kernel Linear Discriminant Analysis (GK-LDA) with WAMP had the highest classification accuracy rate (96%), and the calculation time was below 80 ms. In this paper, the quantitative comparative analysis of feature extraction and classification methods was a benefit to the application for the wearable sEMG sensor system in ADL.

[1]  Jinwu Qian,et al.  Real-Time Surface EMG Pattern Recognition for Hand Gestures Based on an Artificial Neural Network , 2019, Sensors.

[2]  Abdulhamit Subasi,et al.  Surface EMG signal classification using ternary pattern and discrete wavelet transform based feature extraction for hand movement recognition , 2020, Biomed. Signal Process. Control..

[3]  Yue Zhang,et al.  Research on GA-SVM Based Head-Motion Classification via Mechanomyography Feature Analysis , 2019, Sensors.

[4]  Wei Dong,et al.  An epidermal sEMG tattoo-like patch as a new human–machine interface for patients with loss of voice , 2020, Microsystems & nanoengineering.

[5]  Suman Samui,et al.  An experimental study on upper limb position invariant EMG signal classification based on deep neural network , 2020, Biomed. Signal Process. Control..

[6]  Qiang Huang,et al.  SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy , 2019, Sensors.

[7]  Abdulkadir Sengur,et al.  Flexible Analytic Wavelet Transform Based Features for Physical Action Identification Using sEMG Signals , 2020 .

[8]  Zeng-Guang Hou,et al.  Bp-AR-Based Human Joint angle estimation using Multi-Channel sEMG , 2015, Int. J. Robotics Autom..

[9]  Mahmoud Tavakoli,et al.  Foot Gesture Recognition Through Dual Channel Wearable EMG System , 2019, IEEE Sensors Journal.

[10]  Li-Juan Ge,et al.  Feature Extraction and Classification of Hand Movements Surface Electromyogram Signals Based on Multi-method Integration , 2018, Neural Processing Letters.

[11]  Jiahao Shi,et al.  Surface Electromyography-Based Daily Activity Recognition Using Wavelet Coherence Coefficient and Support Vector Machine , 2019, Neural Processing Letters.

[12]  Oleksiy B. Pogrebnyak,et al.  Hand Movement Classification Using Burg Reflection Coefficients , 2018, Sensors.

[13]  Xinjun Sheng,et al.  Spatial Information Enhances Myoelectric Control Performance With Only Two Channels , 2019, IEEE Transactions on Industrial Informatics.

[14]  Boreom Lee,et al.  Myoelectric Signal Classification of Targeted Muscles Using Dictionary Learning , 2019, Sensors.

[15]  Ke Zhang,et al.  Surface electromyography–based hand movement recognition using the Gaussian mixture model, multilayer perceptron, and AdaBoost method , 2019, Int. J. Distributed Sens. Networks.

[16]  Kaur Amanpreet,et al.  Machine learning-based novel approach to classify the shoulder motion of upper limb amputees , 2019, Biocybernetics and Biomedical Engineering.

[17]  Bai Chen,et al.  Neural-network-enhanced torque estimation control of a soft wearable exoskeleton for elbow assistance , 2019, Mechatronics.

[18]  Xiang Xie,et al.  Design of a Flexible Wearable Smart sEMG Recorder Integrated Gradient Boosting Decision Tree Based Hand Gesture Recognition , 2019, IEEE Transactions on Biomedical Circuits and Systems.

[19]  Qinghua Gao,et al.  A novel, co-located EMG-FMG-sensing wearable armband for hand gesture recognition , 2020 .

[20]  Yinfeng Fang,et al.  Surface electromyography feature extraction via convolutional neural network , 2020, Int. J. Mach. Learn. Cybern..

[21]  Adrian Kotelba,et al.  Aligning human psychomotor characteristics with robots, exoskeletons and augmented reality , 2020, Robotics Comput. Integr. Manuf..

[22]  Zhijun Li,et al.  Human-Cooperative Control of a Wearable Walking Exoskeleton for Enhancing Climbing Stair Activities , 2020, IEEE Transactions on Industrial Electronics.

[23]  Ying Feng,et al.  Human-Cooperative Control Design of a Walking Exoskeleton for Body Weight Support , 2020, IEEE Transactions on Industrial Informatics.

[24]  Can Eyupoglu,et al.  A cepstrum analysis-based classification method for hand movement surface EMG signals , 2019, Medical & Biological Engineering & Computing.

[25]  Sachin Taran,et al.  An efficient approach for physical actions classification using surface EMG signals , 2020, Health Inf. Sci. Syst..

[26]  Qingsong Ai,et al.  Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals , 2017, Symmetry.

[27]  Kazuo Kiguchi,et al.  Real-time detection of the interaction between an upper-limb power-assist robot user and another person for perception-assist , 2020, Cognitive Systems Research.

[28]  Stephen D. Laycock,et al.  Smart System for Prediction of Accurate Surface Electromyography Signals Using an Artificial Neural Network , 2019, Future Internet.

[29]  Xun Chen,et al.  Feasibility Study of Advanced Neural Networks Applied to sEMG-Based Force Estimation , 2018, Sensors.

[30]  Taha Khan,et al.  A Novel Method for Classification of Running Fatigue Using Change-Point Segmentation , 2019, Sensors.

[31]  Shouqian Sun,et al.  A Low-Cost End-to-End sEMG-Based Gait Sub-Phase Recognition System , 2020, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[32]  Yutong Wu,et al.  Exploration of Feature Extraction Methods and Dimension for sEMG Signal Classification , 2019 .

[33]  Marco Gazzoni,et al.  A Modular, Smart, and Wearable System for High Density sEMG Detection , 2019, IEEE Transactions on Biomedical Engineering.

[34]  Rohit Gupta,et al.  Electromyographic Signal-Driven Continuous Locomotion Mode Identification Module Design for Lower Limb Prosthesis Control , 2018 .

[35]  Yurong Li,et al.  Entropy-Based Surface Electromyogram Feature Extraction for Knee Osteoarthritis Classification , 2019, IEEE Access.

[36]  Sheng Quan Xie,et al.  A review of gait disorders in the elderly and neurological patients for robot-assisted training , 2020, Disability and rehabilitation. Assistive technology.

[37]  Jun Tao,et al.  Human-robot cooperative control based on sEMG for the upper limb exoskeleton robot , 2020, Robotics Auton. Syst..

[38]  Alexandre Balbinot,et al.  Enhancing the classification of hand movements through sEMG signal and non-iterative methods , 2019, Health and Technology.

[39]  Zhizeng Luo,et al.  SEMG-based multifeatures and predictive model for knee-joint-angle estimation , 2019 .

[40]  Ying Sun,et al.  Multi-object intergroup gesture recognition combined with fusion feature and KNN algorithm , 2020, J. Intell. Fuzzy Syst..

[41]  Hu Wang,et al.  Motion Estimation From Surface Electromyogram Using Adaboost Regression and Average Feature Values , 2019, IEEE Access.