摘要：This study presents the implementation of a convolutional neural network focused on the recognitionof hand gestures for this case 3 specific types of gestures using the EMG signals as input which were acquiredthrough the Myo armband device and processed by means of a characteristic map extraction technique whichis the power spectral density. The development of this work is divided into 2 phases where the first consistsof the acquisition and processing of the electromyographic signals of different users with different armthickness from which 2 databases were built and the second phase describes the architecture of theconvolutional neural network to be used and the training that was performed with each database independently,obtaining two trained networks. Finally, two types of tests are performed, a validation test in which theaccuracy of the two trained networks is verified where a accuracy rate of 91.7 and 92.5% was achieved and areal-time behavioral test where the two networks responded adequately, meaning that the use of convolutionalneural networks for the recognition of hand gestures by means of electromyographic signals can reach highranges of accuracy, even greater than 90%.
