Hand Movement Pattern Recognition Based on Convolutional Neural Network And AlexNet Architecture
fatemeh heidari, Seyed Amirhossein Mousavi, Mitra Etemadi · 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · 2020
This paper presents a method for classifying hand movements for use in wheelchairs, robots, and artificial hand prostheses. Deep learning neural networks are a new method that has been welcomed by researchers in the last decade and has been used more in image and speech processing. In this study, using hand convolution neural network, 6 images of hand movements were taken from 93 healthy individuals and examined. The results show that the proposed method has been able to accurately detect hand movement with 97.36% accuracy.