基于GA-BLS方法的手势识别研究

doi:10.3969/j.issn.1000-1158.2024.01.17

摘要
图/表
参考文献(17)
相关文章 (15)

全文: PDF (731 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为进一步提升人机交互领域中手势识别的精度和速度,探究肌肉疲劳对手势识别的影响规律,提出了改进的GA-BLS方法,利用遗传算法(genetic algorithms, GA)优化宽度学习(broad learning system, BLS)模型参数,并使用弹性网络回归改进传统的BLS模型。利用所提模型对8种手势下的A型超声信号和肌电信号进行手势识别分析,并与SVM、KNN、RF、LDA等方法进行对比,以验证所研究方法的有效性;将长时间段下的A型超声信号和肌电信号切分成4个数据段,发现随着肌肉疲劳程度的增加,手势识别的准确率均呈现出明显下降的趋势,而且A型超声信号相较于肌电信号具有更好的抗疲劳特性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杜义浩
	曹添福
	范强
	王孝冉

关键词 ：手势识别;生理信号, 遗传算法;宽度学习;肌肉疲劳, 弹性网络回归

Abstract：To further improve the accuracy and speed of gesture recognition in the field of human-computer interaction, and explore the influence of muscle fatigue on gesture recognition, an improved GA-BLS method was proposed, genetic algorithms (GA) were used to optimize the parameters of the broad learning system (BLS) model, and elastic network regression was used to improve the traditional BLS model. The proposed model was used to analyze the A-mode ultrasound signal and EMG signal under eight kinds of gestures for gesture recognition, and compared with SVM, KNN, RF, LDA and other methods to verify the effectiveness of the research methods. Furthermore, the A-mode ultrasound and EMG in a long period of time were divided into four data segments. It was found that with the increase of muscle fatigue, the accuracy of gesture recognition showed a significant downward trend, and A-mode ultrasound signal had better fatigue resistance than EMG signal.

Key words： gesture recognition physiological signals genetic algorithms broad learning system muscle fatigue elastic network regression

收稿日期: 2023-04-28 发布日期: 2024-01-22

PACS:	TB99
	TB973

基金资助:河北省自然科学基金(C2020203012);河北省创新能力提升计划项目(22567619H)

作者简介: 杜义浩( 1983- ),河北沧州人,燕山大学副教授,主要从事康复机器人生物反馈控制等方面的研究。Email:duyihao@126.com

引用本文:

杜义浩,曹添福,范强,王孝冉. 基于GA-BLS方法的手势识别研究[J]. 计量学报, 2024, 45(1): 121-127.
DU Yihao,CAO Tianfu,FAN Qiang,WANG Xiaoran. Research on Gesture Recognition Based on GA-BLS. Acta Metrologica Sinica, 2024, 45(1): 121-127.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2024.01.17 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2024/V45/I1/121

［2］	LI F, FEI J. Gesture recognition algorithm based on image information fusion in virtual reality［J］. Personal and Ubiquitous Computing, 2019, 23(3-4): 487-497.
［4］	HE J, ZHANG C, HE X, et al. Visual recognition of traffic police gestures with convolutional pose machine and handcrafted features［J］. Neurocomputing, 2020, 390: 248-259.
［5］	程淑红,杨镇豪,王唱. 多通道融合下的手势识别算法研究及船舶虚拟交互平台设计［J］. 计量学报,2022,43(7):856-862.
［6］	MENDES N. Surface Electromyography Signal Recognition Based on Deep Learning for Human-Robot Interaction and Collaboration［J］. Journal of Intelligent & Robotic Systems, 2022, 105(2): 42.
［11］	YANG X, YAN J, CHEN Z, et al. A proportional pattern recognition control scheme for wearable a-mode ultrasound sensing［J］. IEEE Transactions on Industrial Electronics, 2019, 67(1): 800-808.
［13］	ZENG J, ZHOU Y, YANG Y, et al. Fatigue-sensitivity comparison of semg and a-mode ultrasound based hand gesture recognition［J］. IEEE Journal of Biomedical and Health Informatics, 2021, 26(4): 1718-1725.
［14］	GUO L, LU Z, YAO L, et al. A gesture recognition strategy based on A-mode ultrasound for identifying known and unknown gestures［J］. IEEE Sensors Journal, 2022, 22(11): 10730-10739.
［16］	DUAN F, REN X, YANG Y. A gesture recognition system based on time domain features and linear discriminant analysis［J］. IEEE Transactions on Cognitive and Developmental Systems, 2018, 13(1): 200-208.
［3］	CHEN J, ZHAO S, MENG H, et al. An interactive game for rehabilitation based on real-time hand gesture recognition［J］. Frontiers in Physiology, 2022, 13: 2250.
［12］	YIN Z, CHEN H, YANG X, et al. A wearable ultrasound interface for prosthetic hand control［J］. IEEE Journal of Biomedical and Health Informatics, 2022, 26(11): 5384-5393.
［8］	HE J, LUO H, JIA J, et al. Wrist and finger gesture recognition with single-element ultrasound signals: A comparison with single-channel surface electromyogram［J］. IEEE Transactions on Biomedical Engineering, 2018, 66(5): 1277-1284.
［1］	MISHRA A, KIM J, CHA J, et al. Authorized traffic controller hand gesture recognition for situation-aware autonomous driving［J］. Sensors, 2021, 21(23): 7914.
［7］	WANG H, ZHANG Y, LIU C, et al. sEMG based hand gesture recognition with deformable convolutional network［J］. International Journal of Machine Learning and Cybernetics, 2022, 13(6): 1729-1738.
［10］	YANG X, SUN X, ZHOU D, et al. Towards wearable A-mode ultrasound sensing for real-time finger motion recognition［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26(6): 1199-1208.
［17］	PHILIP CHEN C L, LIU Z. Broad learning system: An effective and efficient incremental learning system without the need for deep architecture［J］. IEEE transactions on neural networks and learning systems, 2017, 29(1): 10-24.
	CHENG S H, YANG Z H, WANG C. Research on Gesture Recognition Algorithm under Multi-channel Fusion and Design of Ship Virtual Interaction Platform［J］. Acta Metrologica Sinica, 2022,43(7):856-862.
［15］	ZENG Y Q, LU Z, ZHOU J L, et al. A Simultaneous Gesture Classification and Force Estimation Strategy Based on Wearable A-Mode Ultrasound and Cascade Model［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 2301-2311.
［9］	AKHLAGHI N, BAKER C A, LAHLOU M, et al. Real-time classification of hand motions using ultrasound imaging of forearm muscles［J］. IEEE Transactions on Biomedical Engineering, 2015, 63(8): 1687-1698.