Cargando…

sEMG-Based Hand Gesture Recognition Using Binarized Neural Network

Recently, human–machine interfaces (HMI) that make life convenient have been studied in many fields. In particular, a hand gesture recognition (HGR) system, which can be implemented as a wearable system, has the advantage that users can easily and intuitively control the device. Among the various se...

Descripción completa

Detalles Bibliográficos
Autores principales: Kang, Soongyu, Kim, Haechan, Park, Chaewoon, Sim, Yunseong, Lee, Seongjoo, Jung, Yunho
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9920778/
https://www.ncbi.nlm.nih.gov/pubmed/36772476
http://dx.doi.org/10.3390/s23031436
_version_ 1784887153225891840
author Kang, Soongyu
Kim, Haechan
Park, Chaewoon
Sim, Yunseong
Lee, Seongjoo
Jung, Yunho
author_facet Kang, Soongyu
Kim, Haechan
Park, Chaewoon
Sim, Yunseong
Lee, Seongjoo
Jung, Yunho
author_sort Kang, Soongyu
collection PubMed
description Recently, human–machine interfaces (HMI) that make life convenient have been studied in many fields. In particular, a hand gesture recognition (HGR) system, which can be implemented as a wearable system, has the advantage that users can easily and intuitively control the device. Among the various sensors used in the HGR system, the surface electromyography (sEMG) sensor is independent of the acquisition environment, easy to wear, and requires a small amount of data. Focusing on these advantages, previous sEMG-based HGR systems used several sensors or complex deep-learning algorithms to achieve high classification accuracy. However, systems that use multiple sensors are bulky, and embedded platforms with complex deep-learning algorithms are difficult to implement. To overcome these limitations, we propose an HGR system using a binarized neural network (BNN), a lightweight convolutional neural network (CNN), with one dry-type sEMG sensor, which is implemented on a field-programmable gate array (FPGA). The proposed HGR system classifies nine dynamic gestures that can be useful in real life rather than static gestures that can be classified relatively easily. Raw sEMG data collected from a dynamic gesture are converted into a spectrogram with information in the time-frequency domain and transferred to the classifier. As a result, the proposed HGR system achieved 95.4% classification accuracy, with a computation time of 14.1 ms and a power consumption of 91.81 mW.
format Online
Article
Text
id pubmed-9920778
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99207782023-02-12 sEMG-Based Hand Gesture Recognition Using Binarized Neural Network Kang, Soongyu Kim, Haechan Park, Chaewoon Sim, Yunseong Lee, Seongjoo Jung, Yunho Sensors (Basel) Article Recently, human–machine interfaces (HMI) that make life convenient have been studied in many fields. In particular, a hand gesture recognition (HGR) system, which can be implemented as a wearable system, has the advantage that users can easily and intuitively control the device. Among the various sensors used in the HGR system, the surface electromyography (sEMG) sensor is independent of the acquisition environment, easy to wear, and requires a small amount of data. Focusing on these advantages, previous sEMG-based HGR systems used several sensors or complex deep-learning algorithms to achieve high classification accuracy. However, systems that use multiple sensors are bulky, and embedded platforms with complex deep-learning algorithms are difficult to implement. To overcome these limitations, we propose an HGR system using a binarized neural network (BNN), a lightweight convolutional neural network (CNN), with one dry-type sEMG sensor, which is implemented on a field-programmable gate array (FPGA). The proposed HGR system classifies nine dynamic gestures that can be useful in real life rather than static gestures that can be classified relatively easily. Raw sEMG data collected from a dynamic gesture are converted into a spectrogram with information in the time-frequency domain and transferred to the classifier. As a result, the proposed HGR system achieved 95.4% classification accuracy, with a computation time of 14.1 ms and a power consumption of 91.81 mW. MDPI 2023-01-28 /pmc/articles/PMC9920778/ /pubmed/36772476 http://dx.doi.org/10.3390/s23031436 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kang, Soongyu
Kim, Haechan
Park, Chaewoon
Sim, Yunseong
Lee, Seongjoo
Jung, Yunho
sEMG-Based Hand Gesture Recognition Using Binarized Neural Network
title sEMG-Based Hand Gesture Recognition Using Binarized Neural Network
title_full sEMG-Based Hand Gesture Recognition Using Binarized Neural Network
title_fullStr sEMG-Based Hand Gesture Recognition Using Binarized Neural Network
title_full_unstemmed sEMG-Based Hand Gesture Recognition Using Binarized Neural Network
title_short sEMG-Based Hand Gesture Recognition Using Binarized Neural Network
title_sort semg-based hand gesture recognition using binarized neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9920778/
https://www.ncbi.nlm.nih.gov/pubmed/36772476
http://dx.doi.org/10.3390/s23031436
work_keys_str_mv AT kangsoongyu semgbasedhandgesturerecognitionusingbinarizedneuralnetwork
AT kimhaechan semgbasedhandgesturerecognitionusingbinarizedneuralnetwork
AT parkchaewoon semgbasedhandgesturerecognitionusingbinarizedneuralnetwork
AT simyunseong semgbasedhandgesturerecognitionusingbinarizedneuralnetwork
AT leeseongjoo semgbasedhandgesturerecognitionusingbinarizedneuralnetwork
AT jungyunho semgbasedhandgesturerecognitionusingbinarizedneuralnetwork