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

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