Version 1
: Received: 31 December 2022 / Approved: 4 January 2023 / Online: 4 January 2023 (09:21:39 CET)
How to cite:
Sehat, K.; Shokouhyan, S.M.; Abdallah, N.K.; Khalaf, K. Deep Network Optimization Using a Genetic Algorithm for Recognizing Hand Gestures via EMG Signals. Preprints2023, 2023010075. https://doi.org/10.20944/preprints202301.0075.v1
Sehat, K.; Shokouhyan, S.M.; Abdallah, N.K.; Khalaf, K. Deep Network Optimization Using a Genetic Algorithm for Recognizing Hand Gestures via EMG Signals. Preprints 2023, 2023010075. https://doi.org/10.20944/preprints202301.0075.v1
Sehat, K.; Shokouhyan, S.M.; Abdallah, N.K.; Khalaf, K. Deep Network Optimization Using a Genetic Algorithm for Recognizing Hand Gestures via EMG Signals. Preprints2023, 2023010075. https://doi.org/10.20944/preprints202301.0075.v1
APA Style
Sehat, K., Shokouhyan, S.M., Abdallah, N.K., & Khalaf, K. (2023). Deep Network Optimization Using a Genetic Algorithm for Recognizing Hand Gestures via EMG Signals. Preprints. https://doi.org/10.20944/preprints202301.0075.v1
Chicago/Turabian Style
Sehat, K., Nada K. Abdallah and Kinda Khalaf. 2023 "Deep Network Optimization Using a Genetic Algorithm for Recognizing Hand Gestures via EMG Signals" Preprints. https://doi.org/10.20944/preprints202301.0075.v1
Abstract
Hand gesture recognition has many valuable applications in engineering and health care. This study proposes a novel model which can accurately distinguish hand gestures using forearm muscles' surface electromyogram (sEMG) signals. A deep learning algorithmwith hyper parameters impacting the final model’s accuracyand a convolutional neural network (CNN) were employed in the recognition stage. The number of convolutional layers, kernels per layer, and neurons in the dense layerwere selected for optimization, while the remaining parameters, such as the learning rate, batch size, and number of epochs, were chosen based on trial and error and prior knowledge. The optimal values for the selected hyperparameters were obtained using a genetic algorithm to achieve maximum recognition accuracy. The UC2018 Dual-Myo database was used for training and testing the model based on EMG signals characterizing the activity of eight different hand gestures. The final structure of the model consisted of two convolutional layers with 131 and 28 kernels, a dense layer with 111 neurons, and a softmax layer with eight neurons. Upon optimizing the hyperparameters using the genetic algorithm, the accuracy of the proposed model increased from 91.86% to 96.4% at best and 95.3% on average in real-time applicationsand 99.6% in an offline mode. Future work is warranted towards improving the architecture and the computational cost.
Keywords
EMG; optimization; genetic algorithm; deep learning
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
