A Lightweight CNN Approach for Hand Gesture Recognition via GAF Encoding of A-Mode Ultrasound Signals

IF 5.2 2区 医学 Q2 ENGINEERING, BIOMEDICAL
Qican Shangguan;Yue Lian;Zhiwei Liao;Jinshui Chen;Yiru Song;Ligang Yao;Cai Jiang;Zongxing Lu;Zhonghua Lin
{"title":"A Lightweight CNN Approach for Hand Gesture Recognition via GAF Encoding of A-Mode Ultrasound Signals","authors":"Qican Shangguan;Yue Lian;Zhiwei Liao;Jinshui Chen;Yiru Song;Ligang Yao;Cai Jiang;Zongxing Lu;Zhonghua Lin","doi":"10.1109/TNSRE.2025.3608180","DOIUrl":null,"url":null,"abstract":"Hand gesture recognition(HGR) is a key technology in human-computer interaction and human communication. This paper presents a lightweight, parameter-free attention convolutional neural network (LPA-CNN) approach leveraging Gramian Angular Field(GAF)transformation of A-mode ultrasound signals for HGR. First, this paper maps 1-dimensional (1D) A-mode ultrasound signals, collected from the forearm muscles of 10 healthy participants, into 2-dimensional (2D) images. Second, GAF is selected owing to its higher sensitivity against Markov Transition Field (MTF) and Recurrence Plot (RP) in HGR. Third, a novel LPA-CNN consisting of four components, i.e., a convolution-pooling block, an attention mechanism, an inverted residual block, and a classification block, is proposed. Among them, the convolution-pooling block consists of convolutional and pooling layers, the attention mechanism is applied to generate 3-D weights, the inverted residual block consists of multiple channel shuffling units, and the classification block is performed through fully connected layers. Fourth, comparative experiments were conducted on GoogLeNet, MobileNet, and LPA-CNN to validate the effectiveness of the proposed method. Experimental results show that compared to GoogLeNet and MobileNet, LPA-CNN has a smaller model size and better recognition performance, achieving a classification accuracy of 0.98 ± 0.02. This paper achieves efficient and high-accuracy HGR by encoding A-mode ultrasound signals into 2D images and integrating the LPA-CNN model, providing a new technological approach for HGR based on ultrasonic signals.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"3734-3743"},"PeriodicalIF":5.2000,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11156155","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/11156155/","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Hand gesture recognition(HGR) is a key technology in human-computer interaction and human communication. This paper presents a lightweight, parameter-free attention convolutional neural network (LPA-CNN) approach leveraging Gramian Angular Field(GAF)transformation of A-mode ultrasound signals for HGR. First, this paper maps 1-dimensional (1D) A-mode ultrasound signals, collected from the forearm muscles of 10 healthy participants, into 2-dimensional (2D) images. Second, GAF is selected owing to its higher sensitivity against Markov Transition Field (MTF) and Recurrence Plot (RP) in HGR. Third, a novel LPA-CNN consisting of four components, i.e., a convolution-pooling block, an attention mechanism, an inverted residual block, and a classification block, is proposed. Among them, the convolution-pooling block consists of convolutional and pooling layers, the attention mechanism is applied to generate 3-D weights, the inverted residual block consists of multiple channel shuffling units, and the classification block is performed through fully connected layers. Fourth, comparative experiments were conducted on GoogLeNet, MobileNet, and LPA-CNN to validate the effectiveness of the proposed method. Experimental results show that compared to GoogLeNet and MobileNet, LPA-CNN has a smaller model size and better recognition performance, achieving a classification accuracy of 0.98 ± 0.02. This paper achieves efficient and high-accuracy HGR by encoding A-mode ultrasound signals into 2D images and integrating the LPA-CNN model, providing a new technological approach for HGR based on ultrasonic signals.
基于GAF编码的A模超声信号手势识别的轻量级CNN方法。
手势识别(Hand gesture recognition, HGR)是人机交互和人类交流的关键技术。本文提出了一种轻量级、无参数注意卷积神经网络(LPA-CNN)方法,利用a型超声信号的格拉曼角场(GAF)变换进行HGR。首先,本文将从10名健康参与者的前臂肌肉收集的一维(1D) a型超声信号映射为二维(2D)图像。其次,由于GAF对HGR中的马尔可夫跃迁场(MTF)和递归图(RP)具有较高的敏感性,因此选择GAF。第三,提出了一种由卷积池块、注意机制、倒残差块和分类块四部分组成的新型LPA-CNN。其中,卷积池化块由卷积层和池化层组成,注意机制用于生成三维权值,倒立残差块由多通道洗牌单元组成,分类块通过全连通层进行。第四,在GoogLeNet、MobileNet和LPA-CNN上进行对比实验,验证所提方法的有效性。实验结果表明,与GoogLeNet和MobileNet相比,LPA-CNN具有更小的模型尺寸和更好的识别性能,分类准确率为0.98±0.02。本文通过将a型超声信号编码到二维图像中,结合LPA-CNN模型实现了高效、高精度的HGR,为基于超声信号的HGR提供了一种新的技术途径。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
8.60
自引率
8.20%
发文量
479
审稿时长
6-12 weeks
期刊介绍: Rehabilitative and neural aspects of biomedical engineering, including functional electrical stimulation, acoustic dynamics, human performance measurement and analysis, nerve stimulation, electromyography, motor control and stimulation; and hardware and software applications for rehabilitation engineering and assistive devices.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信