Using Wavelet Analysis and Deep Learning for EMG-Based Hand Movement Signal Classification

Authors : Harun GÜNEŞ, Abdullah Erhan AKKAYA

Pages : 214-225

Doi:10.16984/saufenbilder.1176459

View : 20 | Download : 11

Publication Date : 2023-02-28

Article Type : Research Paper

Abstract :In this study; time series electromyography insert ignore into journalissuearticles values(EMG); data have been classified according to hand movements using wavelet analysis and deep learning. A pre-trained deep CNN insert ignore into journalissuearticles values(Convolitonal Neural Network-GoogLeNet); has been used in the classification process performed with signal processing, by this way the results can be obtained by continuous wavelet transform and classification methods. The dataset used has been taken from the Machine Learning Repository at the University of California. In the data set; EMG data of 5 healthy individuals, 2 males and 3 females, of the same age insert ignore into journalissuearticles values(~20-22 years); are available. Data; It consists of grasping spherical objects insert ignore into journalissuearticles values(Spher);, grasping small objects with fingertips insert ignore into journalissuearticles values(Tip);, grasping objects with palms insert ignore into journalissuearticles values(Palm);, grasping thin/flat objects insert ignore into journalissuearticles values(Lat);, grasping cylindrical objects insert ignore into journalissuearticles values(Cyl); and holding heavy objects insert ignore into journalissuearticles values(Hook);. It is desired to perform 6 hand movements at the same time. While these movements are necessary, speed and power depend on one\`s will. People perform each movement for 6 seconds and repeat each movement insert ignore into journalissuearticles values(action); 30 times. The CWT insert ignore into journalissuearticles values(Continuous Wavelet Transform); method was used to transform the signal into an image. The scalogram image of the signal was created using the CWT method and the generated images were collected in a data set folder. The collected scalogram images have been classified using GoogLeNet, a deep learning network model. With GoogLeNet, results with 97.22% and 88.89% accuracy rates were obtained by classifying the scalogram images of the signals received separately from channel 1 and channel 2 in the data set. The applied model can be used to classify EMG signals in EMG data with high success rate. In this study, 80% of data was used for educational purposes and 20% for validation purposes. In the study, the results of the classification processes have been evaluated separately for first and second channel data.
Keywords : Deep learning, continuous wavelet transform CWT, skalogram, electromyography EMG, GoogLeNet