Article(id=1208051029912953519, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1208051024368083510, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405964, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1723046400000, receivedDateStr=2024-08-08, revisedDate=1743436800000, revisedDateStr=2025-04-01, acceptedDate=null, acceptedDateStr=null, onlineDate=1765951410034, onlineDateStr=2025-12-17, pubDate=1751040000000, pubDateStr=2025-06-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765951410034, onlineIssueDateStr=2025-12-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765951410034, creator=13701087609, updateTime=1765951410034, updator=13701087609, issue=Issue{id=1208051024368083510, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='18', pageStart='7455', pageEnd='7883', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765951408712, creator=13701087609, updateTime=1765951896766, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1208053071507198943, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1208051024368083510, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1208053071507198944, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1208051024368083510, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=7686, endPage=7692, ext={EN=ArticleExt(id=1208051030495961832, articleId=1208051029912953519, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Upper Limb sEMG Classification Based on BPSO-PSO-LSSVM Algorithm, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

sEMG (surface electromyography) signals are physiological signal closely related to human movement, and the analysis of sEMG signals play an important role in the field of human-machine interaction. Aiming at the difficulty of both efficiency and accuracy of electromyographic signal classification, an upper limb sEMG classification method was innovatively proposed, which combined feature screening with classifier hyperparameter optimization. BPSO (binary particle swarm optimization) algorithm was adopted to screen the features. PSO (particle swarm optimization) algorithm was further utilized to adjust the hyperparameters of the LSSVM (least-squares support vector machine). By collecting sEMG signals from four parts of the human upper body and extracting 48-dimensional features from them, classification experiments were conducted on four common movements of upper limb. The results show that the BPSO-PSO-LSSVM algorithm retains only the 21-dimensional features of the EMG data, and the average classification accuracy obtained reaches 97.54%. It is proved that this method can effectively screen out the optimal combination of features for upper limb motion classification and improve the accuracy of movement classification.

, correspAuthors=Guan MIAO, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jin-tian YUN, Guan MIAO, Shuai LI, Zi-jing GENG), CN=ArticleExt(id=1208051035780784261, articleId=1208051029912953519, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于BPSO-PSO-LSSVM算法的上肢sEMG分类, columnId=1156262729783567290, journalTitle=科学技术与工程, columnName=论文·自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

作为与人体运动密切相关的生理信号,表面肌电(surface electromyography, sEMG)信号的解析在人机交互领域具有重要的作用。针对肌电信号分类效率和精度难以兼顾的问题,提出了一种特征筛选与分类器超参数优化相结合的上肢sEMG分类方法,该方法采用二进制粒子群优化(binary particle swarm optimization, BPSO)算法对特征进行筛选后,进一步采用粒子群优化(particle swarm optimization, PSO)算法调整最小二乘支持向量机(least squares support vector machine, LSSVM)的超参数。通过采集人上体4个部位的表面肌电信号并提取其中48维特征,对上肢常见的4种动作进行分类实验,结果表明,BPSO-PSO-LSSVM算法仅保留肌电数据的21维特征,得到的平均分类准确率达到97.54%,证明该方法可以有效筛选出用于上肢动作分类的最佳特征组合,并且提高运动分类的准确率。

, correspAuthors=苗冠, authorNote=null, correspAuthorsNote=
* 苗冠(1997—),男,汉族,河南南阳人,硕士研究生。研究方向:肌电控制、上肢外骨骼机器人。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Np2QIjRiGpBASrxHgeLPHw==, magXml=VIqNjpwrjDeFgQm2vAfAcA==, pdfUrl=null, pdf=Bo1nMnkS9LXuKaAUUCzLxQ==, pdfFileSize=5456877, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=8XDOedSCS0ey7qfUu4vk4Q==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=lnfWz1mvnXKw7eh5eqEeug==, mapNumber=null, authorCompany=null, fund=null, authors=

贠今天(1970—),男,汉族,河北唐山人,博士,教授。研究方向:机器人动力学、外骨骼机器人。E-mail:

, authorsList=贠今天, 苗冠, 李帅, 耿梓敬)}, authors=[Author(id=1208085583889539119, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yunjintian@tiangong.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1208085584006979640, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085583889539119, language=EN, stringName=Jin-tian YUN, firstName=Jin-tian, middleName=null, lastName=YUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085584095060035, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085583889539119, language=CN, stringName=贠今天, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=天津工业大学机械工程学院, 天津 300387, bio={"content":"

贠今天(1970—),男,汉族,河北唐山人,博士,教授。研究方向:机器人动力学、外骨骼机器人。E-mail:

"}, bioImg=null, bioContent=

贠今天(1970—),男,汉族,河北唐山人,博士,教授。研究方向:机器人动力学、外骨骼机器人。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085583751127073, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, xref=null, ext=[AuthorCompanyExt(id=1208085583763709986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China), AuthorCompanyExt(id=1208085583776292899, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津工业大学机械工程学院, 天津 300387)])]), Author(id=1208085584174751821, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2231050715@tiangong.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1208085584300580956, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085584174751821, language=EN, stringName=Guan MIAO, firstName=Guan, middleName=null, lastName=MIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085584447381611, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085584174751821, language=CN, stringName=苗冠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=天津工业大学机械工程学院, 天津 300387, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085583751127073, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, xref=null, ext=[AuthorCompanyExt(id=1208085583763709986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China), AuthorCompanyExt(id=1208085583776292899, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津工业大学机械工程学院, 天津 300387)])]), Author(id=1208085584678068354, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1208085584829063310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085584678068354, language=EN, stringName=Shuai LI, firstName=Shuai, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085586053800100, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085584678068354, language=CN, stringName=李帅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=天津工业大学机械工程学院, 天津 300387, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085583751127073, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, xref=null, ext=[AuthorCompanyExt(id=1208085583763709986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China), AuthorCompanyExt(id=1208085583776292899, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津工业大学机械工程学院, 天津 300387)])]), Author(id=1208085586217377977, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1208085586313846980, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085586217377977, language=EN, stringName=Zi-jing GENG, firstName=Zi-jing, middleName=null, lastName=GENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085586452259028, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, authorId=1208085586217377977, language=CN, stringName=耿梓敬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=天津工业大学机械工程学院, 天津 300387, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085583751127073, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, xref=null, ext=[AuthorCompanyExt(id=1208085583763709986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China), AuthorCompanyExt(id=1208085583776292899, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津工业大学机械工程学院, 天津 300387)])])], keywords=[Keyword(id=1208085586666168558, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, orderNo=1, keyword=sEMG (surface electromyography) signal), Keyword(id=1208085586779414777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, orderNo=2, keyword=feature selection), Keyword(id=1208085586905243909, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, orderNo=3, keyword=BPSO (binary particle swarm optimization)), Keyword(id=1208085587047850257, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, orderNo=4, keyword=PSO (particle swarm optimization)), Keyword(id=1208085587156902175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, orderNo=5, keyword=motion classification), Keyword(id=1208085587282731310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, orderNo=6, keyword=LSSVM (least squares support vector machine)), Keyword(id=1208085587454697796, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, orderNo=1, keyword=表面肌电信号), Keyword(id=1208085587572138326, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, orderNo=2, keyword=特征选择), Keyword(id=1208085587693773155, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, orderNo=3, keyword=二进制粒子群优化), Keyword(id=1208085587878322551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, orderNo=4, keyword=粒子群优化), Keyword(id=1208085588004151688, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, orderNo=5, keyword=动作分类), Keyword(id=1208085588188701074, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, orderNo=6, keyword=最小二乘支持向量机)], refs=[Reference(id=1208085592303313588, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2013, volume=13, issue=9, pageStart=12431, pageEnd=12466, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Chowdhury R, Reaz M, Ali M, journalName=Sensors, refType=null, unstructuredReference=Chowdhury R, Reaz M, Ali M, et al. Surface electromyography signal processing and classification techniques[J]. Sensors, 2013, 13(9): 12431-12466., articleTitle=Surface electromyography signal processing and classification techniques, refAbstract=null), Reference(id=1208085592395588287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=4, pageStart=4543, pageEnd=4581, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Dhal P, Azad C, journalName=Applied Intelligence, refType=null, unstructuredReference=Dhal P, Azad C. A comprehensive survey on feature selection in the various fields of machine learning[J]. Applied Intelligence, 2022, 52(4): 4543-4581., articleTitle=A comprehensive survey on feature selection in the various fields of machine learning, refAbstract=null), Reference(id=1208085592529806028, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=5, pageStart=526, pageEnd=538, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=胡少康, 张道辉, 赵新刚, journalName=机器人, refType=null, unstructuredReference=胡少康, 张道辉, 赵新刚, 等. 基于特征工程与级联森林的中风患者手部运动肌电识别方法[J]. 机器人, 2021, 43(5) : 526-538., articleTitle=基于特征工程与级联森林的中风患者手部运动肌电识别方法, refAbstract=null), Reference(id=1208085592672412383, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=5, pageStart=526, pageEnd=538, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Hu Shaokang, Zhang Daohui, Zhao Xingang, journalName=Robot, refType=null, unstructuredReference=Hu Shaokang, Zhang Daohui, Zhao Xingang, et al. An sEMG-based hand motion recognition method for stroke patients with feature engineering and cascade forest[J]. Robot, 2021, 43(5): 526-538., articleTitle=An sEMG-based hand motion recognition method for stroke patients with feature engineering and cascade forest, refAbstract=null), Reference(id=1208085592798241513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2023, volume=39, issue=4, pageStart=513, pageEnd=520, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=刘永, 宁蕊, 李言, journalName=西安理工大学学报, refType=null, unstructuredReference=刘永, 宁蕊, 李言, 等. 用于装配动作识别的肌电信号特征优化选择方法[J]. 西安理工大学学报, 2023, 39(4): 513-520., articleTitle=用于装配动作识别的肌电信号特征优化选择方法, refAbstract=null), Reference(id=1208085592919876338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2023, volume=39, issue=4, pageStart=513, pageEnd=520, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Liu Yong, Ning Rui, Li Yan, journalName=Journal of Xi’an University of Technology, refType=null, unstructuredReference=Liu Yong, Ning Rui, Li Yan, et al. Optimal selection method of electromyographic signal features for assembly gesture recognition[J]. Journal of Xi’an University of Technology, 2023, 39(4): 513-520., articleTitle=Optimal selection method of electromyographic signal features for assembly gesture recognition, refAbstract=null), Reference(id=1208085592991179515, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2012, volume=42, issue=1, pageStart=30, pageEnd=38, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Huang H, Xie H B, Guo J Y, journalName=Computers in Biology and Medicine, refType=null, unstructuredReference=Huang H, Xie H B, Guo J Y, et al. Ant colony optimization-based feature selection method for surface electromyography signals classification[J]. Computers in Biology and Medicine, 2012, 42(1): 30-38., articleTitle=Ant colony optimization-based feature selection method for surface electromyography signals classification, refAbstract=null), Reference(id=1208085593108620036, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=35, pageStart=15133, pageEnd=15141, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=崔冰艳, 邓嘉, 张祥, journalName=科学技术与工程, refType=null, unstructuredReference=崔冰艳, 邓嘉, 张祥. 基于表面肌电信号的手势识别方法[J]. 科学技术与工程, 2023, 23(35): 15133-15141., articleTitle=基于表面肌电信号的手势识别方法, refAbstract=null), Reference(id=1208085593247032085, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=35, pageStart=15133, pageEnd=15141, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Cui Bingyan, Deng Jia, Zhang Xiang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Cui Bingyan, Deng Jia, Zhang Xiang. Gesture recognition based on surface EMG signals[J]. Science Technology and Engineering, 2023, 23(35): 15133-15141., articleTitle=Gesture recognition based on surface EMG signals, refAbstract=null), Reference(id=1208085593402221341, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=5044, pageEnd=5050, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=胡学政, 陶庆, 赵暮超, journalName=科学技术与工程, refType=null, unstructuredReference=胡学政, 陶庆, 赵暮超, 等. 采用迁移学习的表面肌电信号手势识别方法[J]. 科学技术与工程, 2024, 24(12): 5044-5050., articleTitle=采用迁移学习的表面肌电信号手势识别方法, refAbstract=null), Reference(id=1208085593490301738, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=5044, pageEnd=5050, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=Hu Xuezheng, Tao Qing, Zhao Muchao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Hu Xuezheng, Tao Qing, Zhao Muchao, et al. sEMG gesture recognition method using transfer learning[J]. Science Technology and Engineering, 2024, 24(12): 5044-5050., articleTitle=sEMG gesture recognition method using transfer learning, refAbstract=null), Reference(id=1208085593616130871, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=18, pageStart=4004, pageEnd=4025, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=Alotaibi N D, Jahanshahi H, Yao Q J, journalName=Mathematics, refType=null, unstructuredReference=Alotaibi N D, Jahanshahi H, Yao Q J, et al. An ensemble of long short-term memory networks with an attention mechanism for upper limb electromyography signal classification[J]. Mathematics, 2023, 11(18): 4004-4025., articleTitle=An ensemble of long short-term memory networks with an attention mechanism for upper limb electromyography signal classification, refAbstract=null), Reference(id=1208085593779708738, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=6, pageStart=158, pageEnd=160, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=王金玮, 曹乐, 阚秀, journalName=传感器与微系统, refType=null, unstructuredReference=王金玮, 曹乐, 阚秀, 等. 基于表面肌电信号的LDA-BPNN双臂手势识别算法[J]. 传感器与微系统, 2023, 42(6): 158-160, 168., articleTitle=基于表面肌电信号的LDA-BPNN双臂手势识别算法, refAbstract=null), Reference(id=1208085595037999953, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=6, pageStart=158, pageEnd=160, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Wang Jinwei, Cao Le, Kan Xiu, journalName=Transducer and Microsystem Technologies, refType=null, unstructuredReference=Wang Jinwei, Cao Le, Kan Xiu, et al. LDA-BPNN algorithm for double-arm gestures recognition based on sEMG signal[J]. Transducer and Microsystem Technologies, 2023, 42(6): 158-160, 168., articleTitle=LDA-BPNN algorithm for double-arm gestures recognition based on sEMG signal, refAbstract=null), Reference(id=1208085595168023390, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=17, pageStart=161, pageEnd=166, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=隋修武, 牛佳宝, 李昊天, journalName=计算机工程与应用, refType=null, unstructuredReference=隋修武, 牛佳宝, 李昊天, 等. 基于NMF-SVM模型的上肢sEMG手势识别方法[J]. 计算机工程与应用, 2020, 56(17): 161-166., articleTitle=基于NMF-SVM模型的上肢sEMG手势识别方法, refAbstract=null), Reference(id=1208085595365155690, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=17, pageStart=161, pageEnd=166, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=Sui Xiuwu, Niu Jiabao, Li Haotian, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Sui Xiuwu, Niu Jiabao, Li Haotian, et al. Upper limb sEMG gesture recognition method based on NMF-SVM model[J]. Computer Engineering and Applications, 2020, 56(17): 161-166., articleTitle=Upper limb sEMG gesture recognition method based on NMF-SVM model, refAbstract=null), Reference(id=1208085595495179128, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=null, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Feng Y F, Yu L, Dong F Y, journalName=Frontiers in Bioengineering and Biotechnology, refType=null, unstructuredReference=Feng Y F, Yu L, Dong F Y, et al. Research on the method of identifying upper and lower limb coordinated movement intentions based on surface EMG signals[J]. Frontiers in Bioengineering and Biotechnology, 2024, 11: 1-11., articleTitle=Research on the method of identifying upper and lower limb coordinated movement intentions based on surface EMG signals, refAbstract=null), Reference(id=1208085595591648130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2012, volume=39, issue=8, pageStart=7420, pageEnd=7431, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Phinyomark A, Phukpattaranont P, Limsakul C, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification[J]. Expert Systems with Applications, 2012, 39(8): 7420-7431., articleTitle=Feature reduction and selection for EMG signal classification, refAbstract=null), Reference(id=1208085595734254475, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2020, volume=22, issue=3, pageStart=362, pageEnd=397, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Freitas D, Lopes L G, Morgado-Dias F, journalName=Entropy, refType=null, unstructuredReference=Freitas D, Lopes L G, Morgado-Dias F. Particle swarm optimisation: a historical review up to the current developments[J]. Entropy, 2020, 22(3): 362-397., articleTitle=Particle swarm optimisation: a historical review up to the current developments, refAbstract=null), Reference(id=1208085595931386777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2013, volume=9, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=Mirjalili S, Lewis A, journalName=Swarm and Evolutionary Computation, refType=null, unstructuredReference=Mirjalili S, Lewis A. S-shaped versus V-shaped transfer functions for binary Particle Swarm Optimization[J]. Swarm and Evolutionary Computation, 2013, 9: 1-14., articleTitle=S-shaped versus V-shaped transfer functions for binary Particle Swarm Optimization, refAbstract=null), Reference(id=1208085596082381730, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=7, pageStart=2687, pageEnd=2692, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=石瑞敏, 刘岩松, 马旭, journalName=科学技术与工程, refType=null, unstructuredReference=石瑞敏, 刘岩松, 马旭, 等. 基于CQGA-LSSVM的桥式起重机主梁损伤识别[J]. 科学技术与工程, 2021, 21(7): 2687-2692., articleTitle=基于CQGA-LSSVM的桥式起重机主梁损伤识别, refAbstract=null), Reference(id=1208085596195627945, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=7, pageStart=2687, pageEnd=2692, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=Shi Ruimin, Liu Yansong, Ma Xu, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Shi Ruimin, Liu Yansong, Ma Xu, et al. Damage identification of main girder of bridge crane based on CQGA-LSSVM[J]. Science Technology and Engineering, 2021, 21(7): 2687-2692., articleTitle=Damage identification of main girder of bridge crane based on CQGA-LSSVM, refAbstract=null)], funds=[Fund(id=1208085592051655320, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, awardId=51975409, language=CN, fundingSource=国家自然科学基金(51975409), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1208085583751127073, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, xref=null, ext=[AuthorCompanyExt(id=1208085583763709986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical Engineering, Tiangong University, Tianjin 300387, China), AuthorCompanyExt(id=1208085583776292899, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, companyId=1208085583751127073, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津工业大学机械工程学院, 天津 300387)])], figs=[ArticleFig(id=1208085588436165044, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Fig.1, caption=Examples of four upper body movements, figureFileSmall=DDOJgTCLSuAQICwSCYfU0Q==, figureFileBig=bwzbIR3LmogTVnvgyBNyqg==, tableContent=null), ArticleFig(id=1208085588536828350, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=图1, caption=4种上肢动作示例, figureFileSmall=DDOJgTCLSuAQICwSCYfU0Q==, figureFileBig=bwzbIR3LmogTVnvgyBNyqg==, tableContent=null), ArticleFig(id=1208085588662657484, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Fig.2, caption=Myoelectric acquisition experiment, figureFileSmall=VmGeIVIWoF7ejhkEM6A2Mw==, figureFileBig=Twrpe50dlCw2lQ89NrpupQ==, tableContent=null), ArticleFig(id=1208085588880761315, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=图2, caption=肌电采集实验, figureFileSmall=VmGeIVIWoF7ejhkEM6A2Mw==, figureFileBig=Twrpe50dlCw2lQ89NrpupQ==, tableContent=null), ArticleFig(id=1208085589203722738, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Fig.3, caption=Filtered EMG signal, figureFileSmall=3KpfKb3mRWRO2D3ogVcqrw==, figureFileBig=jsJ1ibmWPZ9Xrn1Z1w9Twg==, tableContent=null), ArticleFig(id=1208085589321163262, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=图3, caption=滤波后肌电信号, figureFileSmall=3KpfKb3mRWRO2D3ogVcqrw==, figureFileBig=jsJ1ibmWPZ9Xrn1Z1w9Twg==, tableContent=null), ArticleFig(id=1208085590583648778, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Fig.4, caption=Block diagram of algorithm optimization, figureFileSmall=iMLhUblQlYbONdXe1ZM12w==, figureFileBig=3E9qJkKd/4oR+igQCvjoeA==, tableContent=null), ArticleFig(id=1208085590743032340, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=图4, caption=算法优化框图, figureFileSmall=iMLhUblQlYbONdXe1ZM12w==, figureFileBig=3E9qJkKd/4oR+igQCvjoeA==, tableContent=null), ArticleFig(id=1208085590889832991, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Fig.5, caption=Particle fitness curve, figureFileSmall=4BhT4c0MLY1p8/g47+v/5w==, figureFileBig=RS7WCn7D/5T9PEHGK5pY3w==, tableContent=null), ArticleFig(id=1208085590998884904, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=图5, caption=粒子适应度曲线, figureFileSmall=4BhT4c0MLY1p8/g47+v/5w==, figureFileBig=RS7WCn7D/5T9PEHGK5pY3w==, tableContent=null), ArticleFig(id=1208085591095353901, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Fig.6, caption=Classification confusion matrix and individual action classification scenarios, figureFileSmall=zgi7BxqFg3S0lB5dcl4zgw==, figureFileBig=LPa3fI/FAZNSNzTU9pBTQA==, tableContent=null), ArticleFig(id=1208085591196017208, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=图6, caption=分类混淆矩阵及单个动作分类情况, figureFileSmall=zgi7BxqFg3S0lB5dcl4zgw==, figureFileBig=LPa3fI/FAZNSNzTU9pBTQA==, tableContent=null), ArticleFig(id=1208085591359595079, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Fig.7, caption=Comparison of classification accuracy, figureFileSmall=VkZkLc2kip4j93vSmhdUFg==, figureFileBig=kFQGFJxNfKPUDGQDsVabjA==, tableContent=null), ArticleFig(id=1208085591518978652, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=图7, caption=分类准确率对比, figureFileSmall=VkZkLc2kip4j93vSmhdUFg==, figureFileBig=kFQGFJxNfKPUDGQDsVabjA==, tableContent=null), ArticleFig(id=1208085591640613482, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=EN, label=Table 1, caption=

Optimizing parameter values

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 BPSO算法 PSO算法
粒子数量N 50 50
粒子维数D 48 2
迭代次数T 50 50
k[max,min] [0.4,0.8] [0.4,0.8]
c1 1.7 1.7
c2 1.5 1.5
优化参数范围 {0,1} gam=[0.1,200],
sig2=[0.1,20]
初始值参数 [0,1,0,…,1]48 gam=10,sig2=1
), ArticleFig(id=1208085591774831223, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051029912953519, language=CN, label=表1, caption=

优化参数取值

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 BPSO算法 PSO算法
粒子数量N 50 50
粒子维数D 48 2
迭代次数T 50 50
k[max,min] [0.4,0.8] [0.4,0.8]
c1 1.7 1.7
c2 1.5 1.5
优化参数范围 {0,1} gam=[0.1,200],
sig2=[0.1,20]
初始值参数 [0,1,0,…,1]48 gam=10,sig2=1
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405964, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405964, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405964, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405964, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于BPSO-PSO-LSSVM算法的上肢sEMG分类
收藏切换
PDF下载
贠今天 , 苗冠 * , 李帅 , 耿梓敬
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(18): 7686-7692
收起
收藏切换
科学技术与工程 | 论文·自动化技术、计算机技术 2025, 25(18): 7686-7692
基于BPSO-PSO-LSSVM算法的上肢sEMG分类
全屏
贠今天 , 苗冠* , 李帅, 耿梓敬
作者信息
  • 天津工业大学机械工程学院, 天津 300387
  • 贠今天(1970—),男,汉族,河北唐山人,博士,教授。研究方向:机器人动力学、外骨骼机器人。E-mail:

通讯作者:

* 苗冠(1997—),男,汉族,河南南阳人,硕士研究生。研究方向:肌电控制、上肢外骨骼机器人。E-mail:
Upper Limb sEMG Classification Based on BPSO-PSO-LSSVM Algorithm
Jin-tian YUN , Guan MIAO* , Shuai LI, Zi-jing GENG
Affiliations
  • School of Mechanical Engineering, Tiangong University, Tianjin 300387, China
出版时间: 2025-06-28 doi: 10.12404/j.issn.1671-1815.2405964
文章导航
收藏切换

作为与人体运动密切相关的生理信号,表面肌电(surface electromyography, sEMG)信号的解析在人机交互领域具有重要的作用。针对肌电信号分类效率和精度难以兼顾的问题,提出了一种特征筛选与分类器超参数优化相结合的上肢sEMG分类方法,该方法采用二进制粒子群优化(binary particle swarm optimization, BPSO)算法对特征进行筛选后,进一步采用粒子群优化(particle swarm optimization, PSO)算法调整最小二乘支持向量机(least squares support vector machine, LSSVM)的超参数。通过采集人上体4个部位的表面肌电信号并提取其中48维特征,对上肢常见的4种动作进行分类实验,结果表明,BPSO-PSO-LSSVM算法仅保留肌电数据的21维特征,得到的平均分类准确率达到97.54%,证明该方法可以有效筛选出用于上肢动作分类的最佳特征组合,并且提高运动分类的准确率。

表面肌电信号  /  特征选择  /  二进制粒子群优化  /  粒子群优化  /  动作分类  /  最小二乘支持向量机

sEMG (surface electromyography) signals are physiological signal closely related to human movement, and the analysis of sEMG signals play an important role in the field of human-machine interaction. Aiming at the difficulty of both efficiency and accuracy of electromyographic signal classification, an upper limb sEMG classification method was innovatively proposed, which combined feature screening with classifier hyperparameter optimization. BPSO (binary particle swarm optimization) algorithm was adopted to screen the features. PSO (particle swarm optimization) algorithm was further utilized to adjust the hyperparameters of the LSSVM (least-squares support vector machine). By collecting sEMG signals from four parts of the human upper body and extracting 48-dimensional features from them, classification experiments were conducted on four common movements of upper limb. The results show that the BPSO-PSO-LSSVM algorithm retains only the 21-dimensional features of the EMG data, and the average classification accuracy obtained reaches 97.54%. It is proved that this method can effectively screen out the optimal combination of features for upper limb motion classification and improve the accuracy of movement classification.

sEMG (surface electromyography) signal  /  feature selection  /  BPSO (binary particle swarm optimization)  /  PSO (particle swarm optimization)  /  motion classification  /  LSSVM (least squares support vector machine)
贠今天, 苗冠, 李帅, 耿梓敬. 基于BPSO-PSO-LSSVM算法的上肢sEMG分类. 科学技术与工程, 2025 , 25 (18) : 7686 -7692 . DOI: 10.12404/j.issn.1671-1815.2405964
Jin-tian YUN, Guan MIAO, Shuai LI, Zi-jing GENG. Upper Limb sEMG Classification Based on BPSO-PSO-LSSVM Algorithm[J]. Science Technology and Engineering, 2025 , 25 (18) : 7686 -7692 . DOI: 10.12404/j.issn.1671-1815.2405964
表面肌电信号(surface electromyography, sEMG)是肌肉在收缩过程中产生的生理电信号,可以通过粘贴在皮肤表面的电极捕获到。近年来,随着人工智能和机器人技术的飞速发展,肌电信号的应用在人机交互领域取得了广泛成效,在假体控制、康复医疗、运动分析和生物识别技术方面已经存在很多应用先例[1]
肌电信号中隐含人体运动的大量信息,获取这些信息需要对肌电信号进行特征提取,然而,从肌电信号中提取的特征数量庞杂,其中不乏冗余信息,这不仅增加了数据处理的复杂性,还可能降低分类器的性能,因此对特征进行筛选十分必要[2]。胡少康等[3]基于tsfresh库对肌电信号进行特征提取,并通过Feature-Selector库筛选对肌电信号分类贡献度大的特征,结合在线实验检验了所采用方法的实时性;刘永等[4]采用极限梯度提升和单变量特征选择算法实现了对手部动作94.7%的分类准确率。一些学者提出了基于智能群体优化算法的特征筛选,Huang等[5]采用蚁群优化算法筛选特征并对手部动作进行分类,达到96.08%的准确率。尽管特征筛选是提升动作辨识精度的重要手段,但是仅通过特征筛选对提升动作辨识精度是有限的。
肌电信号的分类方法吸引众多学者深入探索,当前,这一领域广泛采用的方法主要包括机器学习、深度学习[6]和迁移学习[7]等。Alotaibi等[8]集成了长短期记忆神经网络(long short-term memory, LSTM)和注意力机制,对上肢肌电信号分类的平均准确率达到91.5%;王金玮等[9]采用线性判别分析(linear discriminant analysis, LDA)对肌电信号特征进行降维,利用反向传播神经网络(back propagation neural network, BPNN)实现了对双臂4种动作92.7%的分类准确率;隋修武等[10]采用非负矩阵分解对肌电信号进行特征降维并通过支持向量机(support vector machine, SVM)进行分类,平均识别率达到91.7%以上;Feng等[11]采用改进的LSSVM分类器,对下肢离散运动的识别准确率达到92.87%。通过对比以上研究发现,LSSVM具有较好的分类性能,满足肌电信号的实际分类任务需求。
肌电信号作为动作分类器的输入,其特征筛选和分类器参数的选择存在显著的随机性。在此背景下,特征筛选无疑决定了分类器性能的上限,而分类器的超参数调整通常依赖于经验假设,这一过程不仅耗时耗力,还极大限制了分类器精度的进一步提升。针对上述问题,将肌电信号的特征筛选与分类器超参数优化策略有效结合显得尤为重要。因此,现提出一种基于BPSO-PSO-LSSVM算法的肌电信号分类方法,具体而言,该方法首先利用二进制粒子群优化(binary particle swarm optimization, BPSO)算法筛选出对上肢动作分类最为关键的特征组合,随后,引入粒子群优化(particle swarm optimization, PSO)算法对最小二乘支持向量机(least squares support vector machine, LSSVM)的超参数进行优化。为验证所提出动作分类算法的性能,通过实验采集人体上肢表面的肌电信号,将该算法的动作分类结果与其他算法进行对比,证明所提出分类方法的优越性。
人体上肢的运动主要发生在矢状面上,其中肩关节和肘关节的前屈后伸构成上肢的主要运动,因此本实验采集4种运动信息构建数据集,包括肘关节前屈、肘关节后伸、肩关节前屈和肩关节后伸。上述4种动作如图1所示。
实验准备与环境如图2所示,选取上肢运动的关键肌肉位置作为采样点,包括:大臂处的肱二头肌、肱三头肌、背部的大圆肌以及肩部的喙肱肌。肌电传感器的每个通道配备2个检测电极和1个参考电极,电极片采用贴片式氯化银。检测电极粘贴在肌肉活跃的区域,而参考电极粘贴在没有肌肉的骨骼处。实验开始前,为减小皮肤表面角质层对肌电信号采集的干扰,对受试者的采样部位使用酒精清洁处理;为保证后续肌电数据的可区分性,提前用相机录制标准的运动示例并制作采集动画。
实验选用了无锡思知瑞科技的无线肌电传感器,传感器的采样频率可以在100~1 000 Hz调整。遵循奈奎斯特采样定理,采样频率至少应为待测信号最高频率的两倍,以确保信号完整无失真。由于肌肉动作信号的频率普遍处于20~500 Hz,因此肌电传感器的采样频率设定为1 000 Hz。
本次数据采集实验选取6名健康受试者,包含4名男性和2名女性,年龄跨度在22~27周岁,体重范围在45~74 kg。信号采集前,明确告知受试者需要注意的基本事项,每个动作的持续时间为3 s,动作到达预定位置之后停顿3 s,每种动作重复五次,在两种动作采集之间,为每名受试者提供10 min的休息时间。信号采集时,要求受试者注意力集中并紧盯面前的屏幕,保持与动画当中的手臂动作一致。
实验采集到的肌电信号数据均以CSV格式保留,每个受试者的肌电数据经过整理以后得到4组数据,6个受试者一共得到24组数据,每组数据包含58 000个样本。本次实验所使用的电脑CPU配置为i7-8750H,所有数据处理及分析使用MATLAB 2022b。
原始肌电信号中不可避免地会混入大量噪声干扰,对后续的运动分类精度构成重大挑战。为提升信号质量,在信号采集过程中通过屏蔽肌电传感器,有效削弱了工频干扰。鉴于肩部采集的肌电信号距心脏较近,心电噪声的频率主要集中在0~30 Hz,因此本次实验采用30 Hz的高通滤波器以最大程度减少心电噪声的干扰。同时,为了消除潜在的高频噪声,进一步引入300 Hz的低通滤波器对肌电信号进行滤波处理,滤波后肌电信号的时域图和功率谱图如图3所示。
考虑到受试者的动作可能存在标签偏离的情况,需要根据采集信号的时间轴和信号幅值对4种不同的动作进行标签重划分,以确定运动信息的起点和终点。肌电信号通常在动作起点前150 ms左右发生变化,为确保肌电信号在控制决策中的实时响应性以及考虑不同窗长对分类精度的潜在影响,提取肌电信号的滑动窗长设定为315 ms,窗口重叠设定为210 ms,窗口的增量设定为105 ms。针对同一个窗口出现的标签冲突问题,采用众数表决作为决策依据。
由于肌电信号固有的非平稳特性,短期内的肌电信号不具备代表性,通过对窗口数据进行特征提取可以假定肌电信号的变化为平稳信号。在基于肌电信号的动作分类领域,时域和频域特征受到广泛青睐,Phinyomark等[12]将这些特征逐个分析对比,指出一些在肌电信号分类领域中应用较好的特征组合。本文研究结合肌电信号中的时域和频域特征对肌电信号进行分类,提取的时域特征包括:均方根值、平均绝对值、积分肌电值、零点交叉次数、波形长度、四阶AR系数和威尔逊振幅,提取的频域特征包括中值频率和功率谱平均功率。
最终,从单个肌电通道中提取出12维特征,其中包括4维四阶AR系数以及另外8个各占1维的特征,4个肌电通道提取共计48维特征,构成一个特征矩阵。为统一特征量纲,通过归一化公式(1),将所有特征映射至[0,1]区间内。
$x^{*}=\frac{x-x_{\min }}{x_{\max }-x_{\min }}$
式(1)中:x*为归一化后的肌电信号幅值;x为原始肌电信号的幅值。
BPSO算法可以筛选肌电信号的特征组合,PSO算法可以优化LSSVM的超参数,结合BPSO和PSO算法可以实现LSSVM的最佳分类性能。
PSO算法凭借其快速收敛性能受到了众多学者的关注[13],在迭代之初,所有粒子具有局部最优位置(pb)和全局最优位置(gb),最终收敛于全局最优位置,PSO算法在优化过程中,原理如下。
$\left\{\begin{aligned} V_{i}(j+1)= & k V_{i}(j)+c_{1} r_{1}\left[p_{\mathrm{b}}-X_{i}(j)\right]+ \\ & c_{2} r_{2}\left[g_{\mathrm{b}}-X_{i}(j)\right] \\ X_{i}(j+1)= & X_{i}(j)+V_{i}(j+1) \end{aligned}\right.$
式(2)中:Vi为粒子的速度大小;j为粒子迭代的次数;k为学习上一代粒子速度的权重;c1c2为粒子的局部和全局学习率;r1r2为随机数;Xi为粒子更新的位置。
PSO算法容易陷入局部最优位置,通过线性调整粒子群迭代的学习率和速度学习权重,可以帮助PSO算法跳出局部最优位置,调整方式为
$\left\{\begin{array}{l} c_{1}^{j+1}=c_{1}^{j}\left(1-\frac{t}{T}\right) \\ c_{2}^{j+1}=c_{2}^{j} \frac{t}{T} \\ k_{j+1}=k_{j}\left(1-\frac{t}{T}\right) \end{array}\right.$
式(3)中:c 1 jc 2 j为粒子迭代过程中的局部和全局学习率;kj为粒子迭代过程中的速度学习权重;t为当前迭代的次数;T为迭代的总次数。
BPSO算法是在PSO算法基础上提出来的一种离散二进制优化方法,BPSO算法中粒子采用二进制0和1的形式编码,将粒子连续的速度映射在[0,1]区间上,并转化为概率形式来决定粒子的位置更新。粒子最初的位置更新依赖于Sigmoid函数进行,Mirjalili等[14]通过对比S型和V型位置更新函数,发现V型函数在特征筛选方面展现出更为优越的性能,V型函数为
$S(v)=\left|\tanh \left[V_{i}(j+1)\right]\right|$
BPSO算法的速度更新方式与PSO算法保持一致,BPSO算法的位置更新公式为
$X_{i}(j+1)=\left\{\begin{array}{ll} \sim X_{i}(j), & S\left[V_{i}(j+1)\right] \geqslant t r \\ X_{i}(j), & S\left[V_{i}(j+1)\right]<t r \end{array}\right.$
式(5)中:t为粒子编码的阈值;r为[0,1]间的随机数;~为取非运算符。
LSSVM作为SVM的一种重要改进,巧妙融合了最小二乘线性理论,通过引入等式约束替代传统的非等式约束,将复杂的二次规划问题变为线性规划问题。这一革新提升了学习速度并保留了SVM的泛化能力,特别是在处理小样本数据和非线性复杂模式识别任务时[15],LSSVM的原理为
$\left\{\begin{array}{l} \min Q(\boldsymbol{\omega}, \boldsymbol{\xi})=\frac{1}{2}| | \boldsymbol{\omega}| |^{2}+\frac{\gamma}{2} \sum_{i=1}^{n} \xi_{i}^{2} \\ \text { s. t. } y_{i}=\boldsymbol{\omega}^{\mathrm{T}} \boldsymbol{\varphi}\left(x_{i}\right)+b+\xi_{i} \end{array}\right.$
式(6)中:Q为目标函数;ω为高维特征空间的权向量;ε为松弛变量的向量;n为样本的数量;ξi为松弛变量;γ为正则化参数;yi为第i个样本的实际值;φ(xi)为输入空间转化为高维空间的非线性映射函数;b为相应的偏置项。
在等式中引入拉格朗日函数,构造求解方程,得到的求解模型为
$f(x)=\sum_{i=1}^{n} \alpha_{i} K\left(x_{i}, x_{j}\right)+b$
式(7)中:αi为拉格朗日函数。
其中采用RBF核函数,K(xi,xj)可以表示为
$K\left(x_{i}, x_{j}\right)=\exp \left(\frac{-\left\|x_{i}-x_{j}\right\|^{2}}{2 \sigma^{2}}\right)$
式(8)中:σ为RBF核函数的参数。
LSSVM的正则化参数γ和核函数参数σ会影响分类器的精度,通过有效的优化算法寻求最佳参数显得尤为重要。
在对肌电信号分类前,首先进行特征筛选以精简特征集,随后采用优化后的分类器超参数以实现最佳分类准确率,算法优化流程如图4所示。
具体步骤如下。
(1)通过Rand函数对粒子群的各维度进行0和1随机二进制编码,0代表未选中特征,1代表选中特征。随后,所有选中特征被送入分类器进行评估,优化目标设定为同时实现最佳分类准确率和最小特征数量,BPSO算法的适应度函数为
$S_{1}=\frac{p C}{L}+(1-p) \frac{d}{D}$
式(9)中:S1为BPSO算法的适应度值;p为权重因子,代表准确率所占的比重,这里设定p=0.8;C为正确分类的样本数;L为样本标签的总数;d为优化后选中的特征维数;D为肌电信号原始特征空间的总维数。
(2)定义gam为正则化参数γ,sig2为核函数参数σ2,随机赋予gam和sig2以初始值。PSO算法在每一次迭代中根据当前分类情况更新局部最优值和全局最优值,粒子通过比较其当前适应度与全局最优适应度,来指导粒子速度和位置的更新。PSO算法的适应度函数为
$S_{2}=1-\frac{C}{L}$
式(10)中:S2为PSO算法的适应度值。
在优化过程中,算法的具体参数设置如表1所示。
为全面验证本文所提出的特征选择与超参数优化相结合方法的创新性与有效性,分别采用准确率、精确率、召回率和F1-score 4个关键指标来量化算法的分类性能。进一步地,为凸显该方法在处理上肢动作分类任务中的独特优势,将所提出的方法与传统的LSSVM算法、PSO-LSSVM算法和BPSO-LSSVM算法进行对比。
从原始肌电信号中共提取出48维特征,BPSO算法筛选的特征数量与适应度值关系如图5(a)所示。迭代初始时保留25维特征,迭代过程中特征数量呈现出先增加后减少的趋势,最终选定21维特征,相较于原特征数量减少了27维,显著降低了数据维度。图5(b)描述了PSO算法在优化分类器参数过程中的适应度变化曲线。所有粒子在迭代50次后均收敛,体现了该方法的高效性和稳定性。
为验证所提出的BPSO-PSO-LSSVM分类方法在动作分类任务中的细致区分能力,引入混淆矩阵对分类结果进行分析,其可视化结果如图6(a)所示;进一步地,为了直观展示该方法对特定动作的识别能力,单个动作的分类情况如图6(b)所示。
最终分类性能的综合评估涵盖准确率、精确率、召回率和F1-score 4个指标,其计算公式为
A = T P + T N T P + T N + F P + F N × 100 % P = T P T P + F P × 100 % R = T P T P + F N × 100 % F = 2 P R P + R × 100 %
式(11)中:A为分类准确率;P为分类精确率;R为分类召回率;FF1-score;TP为真阳性的个数;TN为真阴性的个数;FP为假阳性的个数;FN为假阴性的个数。
结合最终分类结果看,动作分类准确率达到97.54%,精确率达到97.58%,召回率达到97.55%,F1-score达到97.56%,这一系列指标充分证明了所提出方法对动作辨识的有效性。
在分类对比实验中,LSSVM算法和PSO-LSSVM算法均直接以原始数据特征作为输入,而BPSO-LSSVM算法采用筛选出来的最佳特征组合作为输入,BPSO-PSO-LSSVM算法不仅采用筛选出来的最佳特征组合作为输入,还融入了优化后的分类器超参数值,图7所示为以上算法对单个动作和整体动作的分类情况。
通过对分类对比实验的分析,LSSVM在动作分类任务中的准确率相较其他优化算法表现欠佳;BPSO-LSSVM优化算法尽管分类精度一般,但其显著优势在于减少了所需的特征数量;PSO-LSSVM算法专注于优化分类器超参数,虽然分类准确率有所提升,但是特征维数仍相对较高;而本文提出的BPSO-PSO-LSSVM分类算法则脱颖而出,不仅在所有优化算法中取得了最高分类准确率,而且实现了特征数量最少化。此外,BPSO-PSO-LSSVM算法相较于其他分类算法,单个动作的分类准确率呈线性增长趋势,表明筛选后的特征数目和分类器性能的优化并没有倾向于某一分类动作,而是提升了单个动作及整体动作分类的准确率。
针对肌电信号应用于动作分类领域精度和效率难以同时保证的问题,提出了一种特征筛选与分类器超参数优化相结合的方法对动作进行辨识。
(1)通过BPSO算法对肌电信号中所提取的特征进行筛选,创新性地结合PSO算法对分类器的超参数进行优化,最后通过LSSVM算法对动作进行分类。通过肌电信号采集实验,获取了6名受试者上体4个关键位置的肌电信号,对上肢常见的4种动作进行分类。所采集的肌电信号经过预处理和特征提取,进一步采用所提出的方法进行特征筛选和分类器参数优化。
(2)分类实验结果表明,该方法提升整体动作识别率至97.54%,仅保留肌电数据的21维特征,不仅有效缩减了样本特征维数,还大幅提高了动作分类的准确率;同时与LSSVM算法、BPSO-LSSVM算法和PSO-LSSVM算法相比,该方法分别实现了4.39%、2.28%和0.88%的准确率提升。这一方法为上肢动作分类领域的研究提供了一种更加有效的解决方案。
  • 国家自然科学基金(51975409)
参考文献 引证文献
排序方式:
[1]
Chowdhury R, Reaz M, Ali M, et al. Surface electromyography signal processing and classification techniques[J]. Sensors, 2013, 13(9): 12431-12466.
[2]
Dhal P, Azad C. A comprehensive survey on feature selection in the various fields of machine learning[J]. Applied Intelligence, 2022, 52(4): 4543-4581.
[3]
胡少康, 张道辉, 赵新刚, 等. 基于特征工程与级联森林的中风患者手部运动肌电识别方法[J]. 机器人, 2021, 43(5) : 526-538.
Hu Shaokang, Zhang Daohui, Zhao Xingang, et al. An sEMG-based hand motion recognition method for stroke patients with feature engineering and cascade forest[J]. Robot, 2021, 43(5): 526-538.
[4]
刘永, 宁蕊, 李言, 等. 用于装配动作识别的肌电信号特征优化选择方法[J]. 西安理工大学学报, 2023, 39(4): 513-520.
Liu Yong, Ning Rui, Li Yan, et al. Optimal selection method of electromyographic signal features for assembly gesture recognition[J]. Journal of Xi’an University of Technology, 2023, 39(4): 513-520.
[5]
Huang H, Xie H B, Guo J Y, et al. Ant colony optimization-based feature selection method for surface electromyography signals classification[J]. Computers in Biology and Medicine, 2012, 42(1): 30-38.
[6]
崔冰艳, 邓嘉, 张祥. 基于表面肌电信号的手势识别方法[J]. 科学技术与工程, 2023, 23(35): 15133-15141.
Cui Bingyan, Deng Jia, Zhang Xiang. Gesture recognition based on surface EMG signals[J]. Science Technology and Engineering, 2023, 23(35): 15133-15141.
[7]
胡学政, 陶庆, 赵暮超, 等. 采用迁移学习的表面肌电信号手势识别方法[J]. 科学技术与工程, 2024, 24(12): 5044-5050.
Hu Xuezheng, Tao Qing, Zhao Muchao, et al. sEMG gesture recognition method using transfer learning[J]. Science Technology and Engineering, 2024, 24(12): 5044-5050.
[8]
Alotaibi N D, Jahanshahi H, Yao Q J, et al. An ensemble of long short-term memory networks with an attention mechanism for upper limb electromyography signal classification[J]. Mathematics, 2023, 11(18): 4004-4025.
[9]
王金玮, 曹乐, 阚秀, 等. 基于表面肌电信号的LDA-BPNN双臂手势识别算法[J]. 传感器与微系统, 2023, 42(6): 158-160, 168.
Wang Jinwei, Cao Le, Kan Xiu, et al. LDA-BPNN algorithm for double-arm gestures recognition based on sEMG signal[J]. Transducer and Microsystem Technologies, 2023, 42(6): 158-160, 168.
[10]
隋修武, 牛佳宝, 李昊天, 等. 基于NMF-SVM模型的上肢sEMG手势识别方法[J]. 计算机工程与应用, 2020, 56(17): 161-166.
Sui Xiuwu, Niu Jiabao, Li Haotian, et al. Upper limb sEMG gesture recognition method based on NMF-SVM model[J]. Computer Engineering and Applications, 2020, 56(17): 161-166.
[11]
Feng Y F, Yu L, Dong F Y, et al. Research on the method of identifying upper and lower limb coordinated movement intentions based on surface EMG signals[J]. Frontiers in Bioengineering and Biotechnology, 2024, 11: 1-11.
[12]
Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification[J]. Expert Systems with Applications, 2012, 39(8): 7420-7431.
[13]
Freitas D, Lopes L G, Morgado-Dias F. Particle swarm optimisation: a historical review up to the current developments[J]. Entropy, 2020, 22(3): 362-397.
[14]
Mirjalili S, Lewis A. S-shaped versus V-shaped transfer functions for binary Particle Swarm Optimization[J]. Swarm and Evolutionary Computation, 2013, 9: 1-14.
[15]
石瑞敏, 刘岩松, 马旭, 等. 基于CQGA-LSSVM的桥式起重机主梁损伤识别[J]. 科学技术与工程, 2021, 21(7): 2687-2692.
Shi Ruimin, Liu Yansong, Ma Xu, et al. Damage identification of main girder of bridge crane based on CQGA-LSSVM[J]. Science Technology and Engineering, 2021, 21(7): 2687-2692.
2025年第25卷第18期
PDF下载
160
72
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405964
  • 接收时间:2024-08-08
  • 首发时间:2025-12-17
  • 出版时间:2025-06-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-08-08
  • 修回日期:2025-04-01
基金
国家自然科学基金(51975409)
作者信息
    天津工业大学机械工程学院, 天津 300387

通讯作者:

* 苗冠(1997—),男,汉族,河南南阳人,硕士研究生。研究方向:肌电控制、上肢外骨骼机器人。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405964
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏