Comparison of machine learning methods in sEMG signal processing for shoulder motion recognition

Abstract Machine learning (ML) methods have been previously applied and compared in pattern recognition of hand and elbow motions based on surface electromyographic (sEMG) signals. However, there are only a few studies that have investigated the ML methods for shoulder motion pattern recognition. This study compared the efficiency of ML algorithms, including support vector machine (SVM), logistic regression (LR), and artificial neural network (ANN) in processing sEMG signals for shoulder motion pattern recognition. This study also investigated the the effects of sliding time window epoch on the recognition accuracy. Eighteen healthy subjects were recruited for this study, their EMG signals were collected from twelve muscles during performing activities of daily living (ADL) motions including drinking, pushing forward/pulling backward, and abduction/adduction. The 80 % of recoded sEMG datasets were used for model training to build the ML models and 20 % were used for model validation and determination of the accuracy of ML algorithms in motion pattern recognition. The influence of sliding time window sizes was studied for algorithm optimization. Statistical analysis was performed to determine the difference in the accuracy of ML methods. Results showed that there was a significant difference among the three machine learning methods and different sliding time window sizes. There was not a significant difference in overlapping time. The highest accuracy was 97.41 ± 1.8 % using the SVM method with a sliding time window of 270 ms. Machine learning techniques provided a quick approach for shoulder motion pattern recognition. The better classifier for pattern recognition of shoulder motion was SVM.

[1]  Cassie Meeker,et al.  EMG pattern classification to control a hand orthosis for functional grasp assistance after stroke , 2017, 2017 International Conference on Rehabilitation Robotics (ICORR).

[2]  Nurhazimah Nazmi,et al.  A Review of Classification Techniques of EMG Signals during Isotonic and Isometric Contractions , 2016, Sensors.

[3]  Aggelos K. Katsaggelos,et al.  Neural Networks for Modeling Neural Spiking in S1 Cortex , 2019, Front. Syst. Neurosci..

[4]  K. Sunnerhagen,et al.  Movement Kinematics During a Drinking Task Are Associated With the Activity Capacity Level After Stroke , 2012, Neurorehabilitation and neural repair.

[5]  Oluwarotimi Williams Samuel,et al.  Identification of Upper-Limb Movements Based on Muscle Shape Change Signals for Human-Robot Interaction , 2020, Comput. Math. Methods Medicine.

[6]  Huosheng Hu,et al.  Myoelectric control systems - A survey , 2007, Biomed. Signal Process. Control..

[7]  I. Cathers,et al.  The role of shoulder muscles is task specific. , 2010, Journal of science and medicine in sport.

[8]  Yongping Zheng,et al.  The Effects of Upper-Limb Training Assisted with an Electromyography-Driven Neuromuscular Electrical Stimulation Robotic Hand on Chronic Stroke , 2017, Front. Neurol..

[9]  Bongsu Kim,et al.  An upper-body rehabilitation exoskeleton Harmony with an anatomical shoulder mechanism: Design, modeling, control, and performance evaluation , 2017, Int. J. Robotics Res..

[10]  Barbara Cagnie,et al.  The influence of induced shoulder muscle pain on rotator cuff and scapulothoracic muscle activity during elevation of the arm. , 2017, Journal of shoulder and elbow surgery.

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

[12]  Chi-Woong Mun,et al.  Comparison of k-nearest neighbor, quadratic discriminant and linear discriminant analysis in classification of electromyogram signals based on the wrist-motion directions , 2011 .

[13]  Esteban Pavan,et al.  Processing of surface EMG through pattern recognition techniques aimed at classifying shoulder joint movements , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[14]  Mohammad Hassan Moradi,et al.  Evaluation of the forearm EMG signal features for the control of a prosthetic hand. , 2003, Physiological measurement.

[15]  Mark Halaki,et al.  Shoulder muscle activation patterns and levels differ between open and closed-chain abduction. , 2017, Journal of science and medicine in sport.

[16]  Angkoon Phinyomark,et al.  EMG feature evaluation for improving myoelectric pattern recognition robustness , 2013, Expert Syst. Appl..

[17]  Chaoyang Chen,et al.  Shoulder muscle activation pattern recognition based on sEMG and machine learning algorithms , 2020, Comput. Methods Programs Biomed..

[18]  Erik J. Scheme,et al.  EMG Pattern Recognition for Persons with Cervical Spinal Cord Injury , 2019, 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR).

[19]  M. Halaki,et al.  The rotator cuff muscles are activated at low levels during shoulder adduction: an experimental study. , 2010, Journal of physiotherapy.

[20]  Huosheng Hu,et al.  Support Vector Machine-Based Classification Scheme for Myoelectric Control Applied to Upper Limb , 2008, IEEE Transactions on Biomedical Engineering.

[21]  Junyou Yang,et al.  Upper Arm Motion High-Density sEMG Recognition Optimization Based on Spatial and Time-Frequency Domain Features , 2019, Journal of healthcare engineering.

[22]  Xiaodong Zhang,et al.  Processing Surface EMG Signals for Exoskeleton Motion Control , 2020, Frontiers in Neurorobotics.

[23]  Yoshiaki Hayashi,et al.  An EMG-Based Control for an Upper-Limb Power-Assist Exoskeleton Robot , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[24]  Ta-Te Lin,et al.  A comparison of upper-limb motion pattern recognition using EMG signals during dynamic and isometric muscle contractions , 2014, Biomed. Signal Process. Control..

[25]  Richard Hansen,et al.  National Instruments LabVIEW: A Programming Environment for Laboratory Automation and Measurement , 2007 .

[26]  Panagiotis Kosmas,et al.  An Embedded, 8-Channel, Noise Canceling, Wireless, Wearable sEMG Data Acquisition System with Adaptive Muscle Contraction Detection , 2017 .

[27]  Wenwei Yu,et al.  Classification of Upper Limb Motions from Around-Shoulder Muscle Activities: Hand Biofeedback , 2010, The open medical informatics journal.

[28]  Hyung-Soon Park,et al.  Developing a Multi-Joint Upper Limb Exoskeleton Robot for Diagnosis, Therapy, and Outcome Evaluation in Neurorehabilitation , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[29]  Sunil Kumar Agrawal,et al.  Design of a Cable-Driven Arm Exoskeleton (CAREX) for Neural Rehabilitation , 2012, IEEE Transactions on Robotics.

[30]  Daniel P. Ferris,et al.  Robotic lower limb exoskeletons using proportional myoelectric control , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[31]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[32]  Claudio Turchetti,et al.  A Comparative Study of Computational Methods for Compressed Sensing Reconstruction of EMG Signal , 2019, Sensors.

[33]  A. Cools,et al.  Rehabilitation of scapular dyskinesis: from the office worker to the elite overhead athlete , 2013, British Journal of Sports Medicine.

[34]  Xinjun Sheng,et al.  Quantification and solutions of arm movements effect on sEMG pattern recognition , 2014, Biomed. Signal Process. Control..

[35]  Yongping Zheng,et al.  Early Stroke Rehabilitation of the Upper Limb Assisted with an Electromyography-Driven Neuromuscular Electrical Stimulation-Robotic Arm , 2017, Front. Neurol..

[36]  Haiqing Zheng,et al.  SVM-Based Classification of sEMG Signals for Upper-Limb Self-Rehabilitation Training , 2019, Front. Neurorobot..

[37]  J.C. Perry,et al.  Upper-Limb Powered Exoskeleton Design , 2007, IEEE/ASME Transactions on Mechatronics.

[38]  Pornchai Phukpattaranont,et al.  Feature reduction and selection for EMG signal classification , 2012, Expert Syst. Appl..

[39]  Chusak Limsakul,et al.  Feature Extraction and Reduction of Wavelet Transform Coefficients for EMG Pattern Classification , 2012 .

[40]  S. Micera,et al.  EMG-based pattern recognition approach in post stroke robot-aided rehabilitation: a feasibility study , 2013, Journal of NeuroEngineering and Rehabilitation.

[41]  Stephan Trenn,et al.  Multilayer Perceptrons: Approximation Order and Necessary Number of Hidden Units , 2008, IEEE Transactions on Neural Networks.

[42]  Giuseppina Gini,et al.  Analysis and Comparison of Features and Algorithms to Classify Shoulder Movements From sEMG Signals , 2018, IEEE Sensors Journal.

[43]  Jun-hee Kim,et al.  Effects of horizontal shoulder abduction and adduction on the activity and strength of the scapular protractors. , 2017, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[44]  Maury A. Nussbaum,et al.  Assessing the influence of a passive, upper extremity exoskeletal vest for tasks requiring arm elevation: Part I - "Expected" effects on discomfort, shoulder muscle activity, and work task performance. , 2018, Applied ergonomics.