2020
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
Hilbert sEMG data scanning for hand gesture recognition based on deep learning Journal Article
In: Neural Computing and Applications, 2020, ISBN: 1433-3058.
Abstract | Links | BibTeX | Tags: classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, Multi-scale, semg
@article{Tsinganos2020,
title = {Hilbert sEMG data scanning for hand gesture recognition based on deep learning},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
url = {https://github.com/DSIP-UPatras/sEMG-hilbert-curve},
doi = {10.1007/s00521-020-05128-7},
isbn = {1433-3058},
year = {2020},
date = {2020-07-07},
journal = {Neural Computing and Applications},
abstract = {Deep learning has transformed the field of data analysis by dramatically improving the state of the art in various classification and prediction tasks, especially in the area of computer vision. In biomedical engineering, a lot of new work is directed toward surface electromyography (sEMG)-based gesture recognition, often addressed as an image classification problem using convolutional neural networks (CNNs). In this paper, we utilize the Hilbert space-filling curve for the generation of image representations of sEMG signals, which allows the application of typical image processing pipelines such as CNNs on sequence data. The proposed method is evaluated on different state-of-the-art network architectures and yields a significant classification improvement over the approach without the Hilbert curve. Additionally, we develop a new network architecture (MSHilbNet) that takes advantage of multiple scales of an initial Hilbert curve representation and achieves equal performance with fewer convolutional layers.},
keywords = {classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, Multi-scale, semg},
pubstate = {published},
tppubtype = {article}
}
Deep learning has transformed the field of data analysis by dramatically improving the state of the art in various classification and prediction tasks, especially in the area of computer vision. In biomedical engineering, a lot of new work is directed toward surface electromyography (sEMG)-based gesture recognition, often addressed as an image classification problem using convolutional neural networks (CNNs). In this paper, we utilize the Hilbert space-filling curve for the generation of image representations of sEMG signals, which allows the application of typical image processing pipelines such as CNNs on sequence data. The proposed method is evaluated on different state-of-the-art network architectures and yields a significant classification improvement over the approach without the Hilbert curve. Additionally, we develop a new network architecture (MSHilbNet) that takes advantage of multiple scales of an initial Hilbert curve representation and achieves equal performance with fewer convolutional layers.