Finger Motion Estimation Based on Sparse Multi-Channel Surface Electromyography Signals Using Convolutional Neural Network

This paper presents a finger motion estimation based on sparse multi-channel surface electromyography (sEMG) signals using a convolutional neural network (CNN). Although classification with CNNs has achieved high accuracy in gesture recognition, the most cases use a high-density sEMG as the signal acquisition method, which is problematic because this requires many sensors for measuring sEMG signals, resulting in high costs. We therefore propose estimating the finger motion with a sparse multi-channel sEMG method using ring-shaped sensors. The finger motion estimation is performed by classifying images generated from the amplitude variations of sEMG signals, and the image classification is achieved with a simple CNN model featuring two pairs of convolutional and pooling layers and two fully connected layers. Experimental results showed that the test accuracy reached 90% in classifying sEMG signals into four types: thumb opened, thumb closed, fingers (excluding thumb) opened, and fingers (excluding thumb) closed.

[1]  Luca Benini,et al.  An EMG Gesture Recognition System with Flexible High-Density Sensors and Brain-Inspired High-Dimensional Classifier , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[2]  P. Dario,et al.  Control of multifunctional prosthetic hands by processing the electromyographic signal. , 2002, Critical reviews in biomedical engineering.

[3]  Antonio Frisoli,et al.  An EMG-Controlled Robotic Hand Exoskeleton for Bilateral Rehabilitation , 2015, IEEE Transactions on Haptics.

[4]  K. Englehart,et al.  Electromyogram Whitening for Improved Classification Accuracy in Upper Limb Prosthesis Control , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

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

[6]  Ping Zhou,et al.  High-Density Myoelectric Pattern Recognition Toward Improved Stroke Rehabilitation , 2012, IEEE Transactions on Biomedical Engineering.

[7]  Vasiliki Kosmidou,et al.  Sign Language Recognition Using Intrinsic-Mode Sample Entropy on sEMG and Accelerometer Data , 2009, IEEE Transactions on Biomedical Engineering.

[8]  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..

[9]  Luca Benini,et al.  Towards EMG control interface for smart garments , 2014, ISWC '14 Adjunct.

[10]  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.

[11]  Neena Aloysius,et al.  A review on deep convolutional neural networks , 2017, 2017 International Conference on Communication and Signal Processing (ICCSP).

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

[13]  Clément Gosselin,et al.  A convolutional neural network for robotic arm guidance using sEMG based frequency-features , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[14]  D. Farina,et al.  Spatial Correlation of High Density EMG Signals Provides Features Robust to Electrode Number and Shift in Pattern Recognition for Myocontrol , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  Monica Rojas-Martínez,et al.  High-density surface EMG maps from upper-arm and forearm muscles , 2012, Journal of NeuroEngineering and Rehabilitation.

[16]  Ankit Chaudhary.  Robust Hand Gesture Recognition for Robotic Hand Control , 2017 .

[17]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[18]  Sean R. Anderson,et al.  Compact Deep Neural Networks for Computationally Efficient Gesture Classification From Electromyography Signals , 2018, 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob).

[19]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[20]  Norio Takase,et al.  Finger motion estimation based on frequency conversion of EMG signals and image recognition using convolutional neural network , 2017, 2017 17th International Conference on Control, Automation and Systems (ICCAS).

[21]  Chin-Hui Lee,et al.  Sign Transition Modeling and a Scalable Solution to Continuous Sign Language Recognition for Real-World Applications , 2016, ACM Trans. Access. Comput..

[22]  K. Englehart,et al.  Classification of the myoelectric signal using time-frequency based representations. , 1999, Medical engineering & physics.

[23]  Tanja Schultz,et al.  Advancing Muscle-Computer Interfaces with High-Density Electromyography , 2015, CHI.

[24]  Pentti Kanerva,et al.  Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors , 2009, Cognitive Computation.

[25]  Vincent Becker,et al.  Touchsense: classifying finger touches and measuring their force with an electromyography armband , 2018, UbiComp.