sEMG-Based Gesture Recognition with Convolution Neural Networks

The traditional classification methods for limb motion recognition based on sEMG have been deeply researched and shown promising results. However, information loss during feature extraction reduces the recognition accuracy. To obtain higher accuracy, the deep learning method was introduced. In this paper, we propose a parallel multiple-scale convolution architecture. Compared with the state-of-art methods, the proposed architecture fully considers the characteristics of the sEMG signal. Larger sizes of kernel filter than commonly used in other CNN-based hand recognition methods are adopted. Meanwhile, the characteristics of the sEMG signal, that is, muscle independence, is considered when designing the architecture. All the classification methods were evaluated on the NinaPro database. The results show that the proposed architecture has the highest recognition accuracy. Furthermore, the results indicate that parallel multiple-scale convolution architecture with larger size of kernel filter and considering muscle independence can significantly increase the classification accuracy.

[1]  Jianguang Niu,et al.  The Influencing Factors, Regional Difference and Temporal Variation of Industrial Technology Innovation: Evidence with the FOA-GRNN Model , 2018 .

[2]  Manfredo Atzori,et al.  Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands , 2016, Front. Neurorobot..

[3]  Ganesh R. Naik,et al.  A dynamic channel selection algorithm for the classification of EEG and EMG data , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[4]  Yu Hu,et al.  Surface EMG-Based Inter-Session Gesture Recognition Enhanced by Deep Domain Adaptation , 2017, Sensors.

[5]  Hong Liu,et al.  Robust EMG pattern recognition in the presence of confounding factors: features, classifiers and adaptive learning , 2018, Expert Syst. Appl..

[6]  Seungmin Rho,et al.  Bridging the semantic gap in multimedia emotion/mood recognition for ubiquitous computing environment , 2010, The Journal of Supercomputing.

[7]  Barbara Caputo,et al.  Exploiting accelerometers to improve movement classification for prosthetics , 2013, 2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR).

[8]  Athanasios V. Vasilakos,et al.  Cyber physical systems technologies and applications , 2016, Future Gener. Comput. Syst..

[9]  Jhing-Fa Wang,et al.  Smart Homecare Surveillance System: Behavior Identification Based on State-Transition Support Vector Machines and Sound Directivity Pattern Analysis , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[10]  Seungmin Rho,et al.  Social Internet of Things: Applications, architectures and protocols , 2019, Future Gener. Comput. Syst..

[11]  John J. Soraghan,et al.  Study on Interaction Between Temporal and Spatial Information in Classification of EMG Signals for Myoelectric Prostheses , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[12]  Øyvind Stavdahl,et al.  A multi-modal approach for hand motion classification using surface EMG and accelerometers , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Bo-Wei Chen,et al.  Efficient multiple incremental computation for Kernel Ridge Regression with Bayesian uncertainty modeling , 2017, Future Gener. Comput. Syst..

[14]  Ganesh R. Naik,et al.  Classification of finger extension and flexion of EMG and Cyberglove data with modified ICA weight matrix , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  Harksoo Kim,et al.  Low-Cost Implementation of a Named Entity Recognition System for Voice-Activated Human-Appliance Interfaces in a Smart Home , 2018, Sustainability.

[16]  Bruce C. Wheeler,et al.  EMG feature evaluation for movement control of upper extremity prostheses , 1995 .

[17]  Erik Scheme,et al.  Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use. , 2011, Journal of rehabilitation research and development.

[18]  Blair A. Lock,et al.  Determining the Optimal Window Length for Pattern Recognition-Based Myoelectric Control: Balancing the Competing Effects of Classification Error and Controller Delay , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[19]  Reza Langari,et al.  A performance comparison of hand motion EMG classification , 2014, 2nd Middle East Conference on Biomedical Engineering.

[20]  Shyamanta M. Hazarika,et al.  EMG Feature Set Selection Through Linear Relationship for Grasp Recognition , 2016 .

[21]  Jing Yang,et al.  A Novel Method for Disease Prediction: Hybrid of Random Forest and Multivariate Adaptive Regression Splines , 2013, J. Comput..

[22]  Ilja Kuzborskij,et al.  On the challenge of classifying 52 hand movements from surface electromyography , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[23]  Kevin B. Englehart,et al.  A wavelet-based continuous classification scheme for multifunction myoelectric control , 2001, IEEE Transactions on Biomedical Engineering.

[24]  Mamun Bin Ibne Reaz,et al.  Surface Electromyography Signal Processing and Classification Techniques , 2013, Sensors.

[25]  Manfredo Atzori,et al.  Electromyography data for non-invasive naturally-controlled robotic hand prostheses , 2014, Scientific Data.

[26]  Yinghong Peng,et al.  EMG‐Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks , 2018, Artificial organs.

[27]  Abdulhamit Subasi,et al.  Comparison of decision tree algorithms for EMG signal classification using DWT , 2015, Biomed. Signal Process. Control..

[28]  Marimuthu Palaniswami,et al.  Subtle Hand Gesture Identification for HCI Using Temporal Decorrelation Source Separation BSS of Surface EMG , 2007, 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007).

[29]  Weidong Geng,et al.  Gesture recognition by instantaneous surface EMG images , 2016, Scientific Reports.

[30]  Jhing-Fa Wang,et al.  A Novel Video Summarization Based on Mining the Story-Structure and Semantic Relations Among Concept Entities , 2009, IEEE Transactions on Multimedia.

[31]  Wen Ji,et al.  Intelligent Marketing in Smart Cities: Crowdsourced Data for Geo-Conquesting , 2016, IT Professional.

[32]  Panagiotis K. Artemiadis,et al.  Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems , 2012, 2012 IEEE International Conference on Robotics and Automation.

[33]  Manfredo Atzori,et al.  Movement Error Rate for Evaluation of Machine Learning Methods for sEMG-Based Hand Movement Classification , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[34]  R.N. Scott,et al.  A new strategy for multifunction myoelectric control , 1993, IEEE Transactions on Biomedical Engineering.

[35]  Ganesh R. Naik,et al.  Nonlinear multiscale Maximal Lyapunov Exponent for accurate myoelectric signal classification , 2015, Appl. Soft Comput..

[36]  Seungmin Rho,et al.  Clustering algorithm for internet of vehicles (IoV) based on dragonfly optimizer (CAVDO) , 2018, The Journal of Supercomputing.

[37]  Han-Pang Huang,et al.  Recognition of Electromyographic Signals Using Cascaded Kernel Learning Machine , 2007, IEEE/ASME Transactions on Mechatronics.

[38]  G. Naik,et al.  Transradial Amputee Gesture Classification Using an Optimal Number of sEMG Sensors: An Approach Using ICA Clustering , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[39]  Kevin B. Englehart,et al.  A robust, real-time control scheme for multifunction myoelectric control , 2003, IEEE Transactions on Biomedical Engineering.

[40]  Beth Jelfs,et al.  Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network , 2017, Front. Neurosci..

[41]  Marie-Françoise Lucas,et al.  Multi-channel surface EMG classification using support vector machines and signal-based wavelet optimization , 2008, Biomed. Signal Process. Control..

[42]  D Graupe,et al.  Multifunctional prosthesis and orthosis control via microcomputer identification of temporal pattern differences in single-site myoelectric signals. , 1982, Journal of biomedical engineering.

[43]  Ganesh R. Naik,et al.  Nonnegative Matrix Factorization for the Identification of EMG Finger Movements: Evaluation Using Matrix Analysis , 2015, IEEE Journal of Biomedical and Health Informatics.

[44]  Marimuthu Palaniswami,et al.  Signal processing evaluation of myoelectric sensor placement in low‐level gestures: sensitivity analysis using independent component analysis , 2014, Expert Syst. J. Knowl. Eng..

[45]  Baihua Li,et al.  Pattern Classification of Hand Movements using Time Domain Features of Electromyography , 2017, MOCO.

[46]  P. Geethanjali,et al.  Actuation of prosthetic drive using EMG signal , 2009, TENCON 2009 - 2009 IEEE Region 10 Conference.

[47]  Clément Gosselin,et al.  Transfer learning for sEMG hand gestures recognition using convolutional neural networks , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).