Article(id=1156983789705584877, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2400599, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1705680000000, receivedDateStr=2024-01-20, revisedDate=1731427200000, revisedDateStr=2024-11-13, acceptedDate=null, acceptedDateStr=null, onlineDate=1753776031185, onlineDateStr=2025-07-29, pubDate=1739808000000, pubDateStr=2025-02-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753776031185, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753776031185, creator=13701087609, updateTime=1753776031185, updator=13701087609, issue=Issue{id=1156983783787421903, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='5', pageStart='1753', pageEnd='2192', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753776029774, creator=13701087609, updateTime=1769691857141, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1223739602251436918, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1223739602251436919, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1988, endPage=1995, ext={EN=ArticleExt(id=1156983791332974838, articleId=1156983789705584877, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Multi-view Convolutional Network with Fused Attention for Intelligent-assisted Epilepsy Detection and Recognition, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

In response to the problem of low accuracy in epilepsy detection and recognition using single-view networks, a multi-view convolutional network model with fused attention mechanism (FAM-MCNN) was proposed. Multiple view features were extracted from time domain, frequency domain, time-frequency domain and nonlinear domain to characterize electroencephalogram(EEG) signals comprehensively. Multi-scale convolution was used to capture different levels of detail information. In order to improve the ability to distinguish different types of EEG signals in epileptic patients, the attention mechanism was introduced to combine the features from view dimension and single feature vector dimension respectively. The results of the comparison experiments performed on the CHB-MIT epilepsy dataset show that the average accuracy, sensitivity, and specificity of the FAM-MCNN model are improved by 14.29%, 16.13%, and 12.54%, respectively, when compared to a single-view network. In addition, experiments under a small number of training samples (25%) show that its detection performance reaches the level of the comparison model with a large number of training samples (80%~90%).

, correspAuthors=null, 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=Qi LI, Xu-rong YAN, Yan WU, Di ZHAO, Li-na CHANG, Han-lin SUN), CN=ArticleExt(id=1156983901345375000, articleId=1156983789705584877, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=融合注意力机制的多视图卷积网络癫痫智能辅助检测, 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=

针对单一视图网络癫痫检测识别精度低的问题,提出一种融合注意力机制的多视图卷积网络癫痫智能辅助检测模型(multi-view convolutional network with fused attention mechanism,FAM-MCNN)。该模型从时域、频域、时频域和非线性域提取多视图特征来全面表征脑电信号;采用多尺度卷积捕捉不同层次的细节信息;引入注意力机制分别从视图维度和单个特征向量维度对特征进行加权融合,从而提高对癫痫患者不同类别脑电信号的区分能力。在CHB-MIT癫痫数据集上进行的对比实验结果显示,与单一视图网络相比,FAM-MCNN模型的平均准确率、灵敏度、特异度分别提高了14.29%、16.13%、12.54%。此外,对该模型采用少量训练样本(25%)进行实验,结果显示其检测性能达到了拥有大量训练样本(80%~90%)的对比模型水平。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=89cVN3ANPpJuqnQIyvQtmA==, magXml=CRsSqim/bsHLpK9dPOv29g==, pdfUrl=null, pdf=NDsrqzqRdjLZLTNSR7guWw==, pdfFileSize=6264190, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=vD8HhjfxQjErvFh1n6CWMw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=D8/LgyVnc2U+Gu6Uy6FDFg==, mapNumber=null, authorCompany=null, fund=null, authors=

李奇(1977—),男,汉族,辽宁葫芦岛人,博士,教授。研究方向:脑机接口技术、神经康复工程、类脑计算、智能感知。E-mail:

, authorsList=李奇, 闫旭荣, 武岩, 赵迪, 常立娜, 孙瀚琳)}, authors=[Author(id=1225467166439424333, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liqi@cust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467166611390819, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467166439424333, language=EN, stringName=Qi LI, firstName=Qi, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China
2 Zhongshan Institute, Changchun University of Science and Technology, Zhongshan 528400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467166737219951, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467166439424333, language=CN, stringName=李奇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 长春理工大学计算机科学技术学院, 长春 130022
2 长春理工大学中山研究院, 中山 528400, bio={"content":"

李奇(1977—),男,汉族,辽宁葫芦岛人,博士,教授。研究方向:脑机接口技术、神经康复工程、类脑计算、智能感知。E-mail:

"}, bioImg=null, bioContent=

李奇(1977—),男,汉族,辽宁葫芦岛人,博士,教授。研究方向:脑机接口技术、神经康复工程、类脑计算、智能感知。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467166116462898, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=1, ext=[AuthorCompanyExt(id=1225467166133240117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China), AuthorCompanyExt(id=1225467166145823032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长春理工大学计算机科学技术学院, 长春 130022)]), AuthorCompany(id=1225467166292623678, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=2, ext=[AuthorCompanyExt(id=1225467166321983809, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166292623678, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Zhongshan Institute, Changchun University of Science and Technology, Zhongshan 528400, China), AuthorCompanyExt(id=1225467166326178114, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166292623678, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 长春理工大学中山研究院, 中山 528400)])]), Author(id=1225467166871437696, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, orderNo=1, 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=1225467167181816212, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467166871437696, language=EN, stringName=Xu-rong YAN, firstName=Xu-rong, middleName=null, lastName=YAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467167714492840, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467166871437696, language=CN, stringName=闫旭荣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长春理工大学计算机科学技术学院, 长春 130022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467166116462898, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=1, ext=[AuthorCompanyExt(id=1225467166133240117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China), AuthorCompanyExt(id=1225467166145823032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长春理工大学计算机科学技术学院, 长春 130022)])]), Author(id=1225467168964395448, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, 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=1225467169723564500, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467168964395448, language=EN, stringName=Yan WU, firstName=Yan, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China
2 Zhongshan Institute, Changchun University of Science and Technology, Zhongshan 528400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467169903919573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467168964395448, language=CN, stringName=武岩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 长春理工大学计算机科学技术学院, 长春 130022
2 长春理工大学中山研究院, 中山 528400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467166116462898, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=1, ext=[AuthorCompanyExt(id=1225467166133240117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China), AuthorCompanyExt(id=1225467166145823032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长春理工大学计算机科学技术学院, 长春 130022)]), AuthorCompany(id=1225467166292623678, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=2, ext=[AuthorCompanyExt(id=1225467166321983809, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166292623678, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Zhongshan Institute, Changchun University of Science and Technology, Zhongshan 528400, China), AuthorCompanyExt(id=1225467166326178114, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166292623678, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 长春理工大学中山研究院, 中山 528400)])]), Author(id=1225467170025554396, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, 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=1225467170331738609, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467170025554396, language=EN, stringName=Di ZHAO, firstName=Di, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467170667282953, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467170025554396, language=CN, stringName=赵迪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长春理工大学计算机科学技术学院, 长春 130022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467166116462898, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=1, ext=[AuthorCompanyExt(id=1225467166133240117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China), AuthorCompanyExt(id=1225467166145823032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长春理工大学计算机科学技术学院, 长春 130022)])]), Author(id=1225467172357587518, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, orderNo=4, 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=1225467173565547076, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467172357587518, language=EN, stringName=Li-na CHANG, firstName=Li-na, middleName=null, lastName=CHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467173871731281, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467172357587518, language=CN, stringName=常立娜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长春理工大学计算机科学技术学院, 长春 130022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467166116462898, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=1, ext=[AuthorCompanyExt(id=1225467166133240117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China), AuthorCompanyExt(id=1225467166145823032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长春理工大学计算机科学技术学院, 长春 130022)])]), Author(id=1225467174064669277, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, orderNo=5, 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=1225467174358270578, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467174064669277, language=EN, stringName=Han-lin SUN, firstName=Han-lin, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467174563791489, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, authorId=1225467174064669277, language=CN, stringName=孙瀚琳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长春理工大学计算机科学技术学院, 长春 130022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467166116462898, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=1, ext=[AuthorCompanyExt(id=1225467166133240117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China), AuthorCompanyExt(id=1225467166145823032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长春理工大学计算机科学技术学院, 长春 130022)])])], keywords=[Keyword(id=1225467175046136483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, orderNo=1, keyword=electroencephalogram signal), Keyword(id=1225467175213908660, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, orderNo=2, keyword=multi-view convolution), Keyword(id=1225467175402652359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, orderNo=3, keyword=attention mechanisms), Keyword(id=1225467175562035925, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, orderNo=4, keyword=intelligent auxiliary detection of epilepsy), Keyword(id=1225467175784334053, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, orderNo=1, keyword=脑电信号), Keyword(id=1225467176178598654, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, orderNo=2, keyword=多视图卷积), Keyword(id=1225467176400896779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, orderNo=3, keyword=注意力机制), Keyword(id=1225467176585446168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, orderNo=4, keyword=癫痫智能辅助检测)], refs=[Reference(id=1225467185221517636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=2, pageStart=335, pageEnd=350, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=彭睿旻, 江军, 匡光涛, journalName=自动化学报, refType=null, unstructuredReference=彭睿旻, 江军, 匡光涛, 等. 基于EEG的癫痫自动检测: 综述与展望[J]. 自动化学报, 2022, 48(2): 335-350., articleTitle=基于EEG的癫痫自动检测: 综述与展望, refAbstract=null), Reference(id=1225467185347346774, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=2, pageStart=335, pageEnd=350, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Peng Ruimin, Jiang Jun, Kuang Guangtao, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=Peng Ruimin, Jiang Jun, Kuang Guangtao, et al. EEG-based automatic epilepsy detection: review and outlook[J]. Acta Automatica Sinica, 2022, 48(2): 335-350., articleTitle=EEG-based automatic epilepsy detection: review and outlook, refAbstract=null), Reference(id=1225467185502536039, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=8, issue=null, pageStart=32, pageEnd=41, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Gallotto S, Seeck M, journalName=Clinical Neurophysiology Practice, refType=null, unstructuredReference=Gallotto S, Seeck M. EEG biomarker candidates for the identification of epilepsy[J]. Clinical Neurophysiology Practice, 2023, 8: 32-41., articleTitle=EEG biomarker candidates for the identification of epilepsy, refAbstract=null), Reference(id=1225467187029262717, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=15, pageStart=6097, pageEnd=6104, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=赵倩, 谭浩然, 王西岳, journalName=科学技术与工程, refType=null, unstructuredReference=赵倩, 谭浩然, 王西岳, 等. 脑电采集电极研究进展[J]. 科学技术与工程, 2021, 21(15): 6097-6104., articleTitle=脑电采集电极研究进展, refAbstract=null), Reference(id=1225467187285115280, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=15, pageStart=6097, pageEnd=6104, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zhao Qian, Tan Haoran, Wang Xiyue, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhao Qian, Tan Haoran, Wang Xiyue, et al. Research progress of the electrode for electroencephalogram acquisition[J]. Science Technology and Engineering, 2021, 21(15): 6097-6104., articleTitle=Research progress of the electrode for electroencephalogram acquisition, refAbstract=null), Reference(id=1225467187499024804, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2004, volume=89, issue=1, pageStart=37, pageEnd=40, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Rennie J, Chorley G, Boylan G, journalName=Archives of Disease in Childhood Fetal and Neonatal Edition, refType=null, unstructuredReference=Rennie J, Chorley G, Boylan G, et al. Non-expert use of the cerebral function monitor for neonatal seizure detection[J]. Archives of Disease in Childhood Fetal and Neonatal Edition, 2004, 89(1): 37-40., articleTitle=Non-expert use of the cerebral function monitor for neonatal seizure detection, refAbstract=null), Reference(id=1225467187733905854, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2016, volume=29, issue=8, pageStart=47, pageEnd=57, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Bhattacharyya A, Sharma M, Pachori R B, journalName=Neural Computing and Applications, refType=null, unstructuredReference=Bhattacharyya A, Sharma M, Pachori R B, et al. A novel approach for automated detection of focal EEG signals using empirical wavelet transform[J]. Neural Computing and Applications, 2016, 29(8): 47-57., articleTitle=A novel approach for automated detection of focal EEG signals using empirical wavelet transform, refAbstract=null), Reference(id=1225467187872317902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2016, volume=32, issue=7, pageStart=764, pageEnd=770, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=牛宝东, 马尽文, journalName=信号处理, refType=null, unstructuredReference=牛宝东, 马尽文. 基于希尔伯特黄变换的癫痫自动检测[J]. 信号处理, 2016, 32(7): 764-770., articleTitle=基于希尔伯特黄变换的癫痫自动检测, refAbstract=null), Reference(id=1225467188027507168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2016, volume=32, issue=7, pageStart=764, pageEnd=770, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Niu Baodong, Ma Jinwen, journalName=Journal of Signal Processing, refType=null, unstructuredReference=Niu Baodong, Ma Jinwen. Automatic detection of epileptic seizure through Hilbert-Huang transform[J]. Journal of Signal Processing, 2016, 32(7): 764-770., articleTitle=Automatic detection of epileptic seizure through Hilbert-Huang transform, refAbstract=null), Reference(id=1225467188170113519, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=4, pageStart=1543, pageEnd=1554, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Qureshi M M, Kaleem M, journalName=Signal, Image and Video Processing, refType=null, unstructuredReference=Qureshi M M, Kaleem M. EEG-based seizure prediction with machine learning[J]. Signal, Image and Video Processing, 2023, 17(4): 1543-1554., articleTitle=EEG-based seizure prediction with machine learning, refAbstract=null), Reference(id=1225467188425966082, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2021, volume=33, issue=6, pageStart=668, pageEnd=676, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Harpale V, Bairagi V, journalName=Journal of King Saud University-Computer and Information Sciences, refType=null, unstructuredReference=Harpale V, Bairagi V. An adaptive method for feature selection and extraction for classification of epileptic EEG signal in significant states[J]. Journal of King Saud University-Computer and Information Sciences, 2021, 33(6): 668-676., articleTitle=An adaptive method for feature selection and extraction for classification of epileptic EEG signal in significant states, refAbstract=null), Reference(id=1225467188593738255, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=67, issue=null, pageStart=101943, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Varli M, Ylmaz H, journalName=Journal of Computational Science, refType=null, unstructuredReference=Varli M, Ylmaz H. Multiple classification of EEG signals and epileptic seizure diagnosis with combined deep learning[J]. Journal of Computational Science, 2023, 67: 101943., articleTitle=Multiple classification of EEG signals and epileptic seizure diagnosis with combined deep learning, refAbstract=null), Reference(id=1225467188698595873, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=240, issue=null, pageStart=107680, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Tripathi P M, Kumar A, Kumar M, journalName=Computer Methods and Programs in Biomedicine, refType=null, unstructuredReference=Tripathi P M, Kumar A, Kumar M, et al. Automatic seizure detection and classification using super-resolution superlet transform and deep neural network: a preprocessing-less method[J]. Computer Methods and Programs in Biomedicine, 2023, 240: 107680., articleTitle=Automatic seizure detection and classification using super-resolution superlet transform and deep neural network: a preprocessing-less method, refAbstract=null), Reference(id=1225467188849590834, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=5, pageStart=595, pageEnd=601, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=于永强, 刘健, 孙仁诚, journalName=中国医学物理学杂志, refType=null, unstructuredReference=于永强, 刘健, 孙仁诚, 等. 基于多特征多关系图卷积神经网络的癫痫脑电分类[J]. 中国医学物理学杂志, 2023, 40(5): 595-601., articleTitle=基于多特征多关系图卷积神经网络的癫痫脑电分类, refAbstract=null), Reference(id=1225467189063500360, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=5, pageStart=595, pageEnd=601, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Yu Yongqiang, Liu Jian, Sun Rencheng, journalName=Chinese Journal of Medical Physics, refType=null, unstructuredReference=Yu Yongqiang, Liu Jian, Sun Rencheng, et al. Classification of epileptic electroencephalogram signal using graph convolutional neural network with multiple features and multiple relations[J]. Chinese Journal of Medical Physics, 2023, 40(5): 595-601., articleTitle=Classification of epileptic electroencephalogram signal using graph convolutional neural network with multiple features and multiple relations, refAbstract=null), Reference(id=1225467189369684570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=15, pageStart=6135, pageEnd=6140, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=李玉花, 柳倩, 韦新, journalName=科学技术与工程, refType=null, unstructuredReference=李玉花, 柳倩, 韦新, 等. 基于卷积神经网络的脑电信号分类[J]. 科学技术与工程, 2020, 20(15): 6135-6140., articleTitle=基于卷积神经网络的脑电信号分类, refAbstract=null), Reference(id=1225467189533262438, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=15, pageStart=6135, pageEnd=6140, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=Li Yuhua, Liu Qian, Wei Xin, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Yuhua, Liu Qian, Wei Xin, et al. Classification of electroencephalogram signals based on convolutional neural network[J]. Science Technology and Engineering, 2020, 20(15): 6135-6140., articleTitle=Classification of electroencephalogram signals based on convolutional neural network, refAbstract=null), Reference(id=1225467189692646012, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=1098, pageEnd=1103, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=周嵩, 高天寒, journalName=东北大学学报: 自然科学版, refType=null, unstructuredReference=周嵩, 高天寒. 基于注意力机制RNN模型的癫痫患者脑电信号识别方法[J]. 东北大学学报: 自然科学版, 2023, 44(8): 1098-1103., articleTitle=基于注意力机制RNN模型的癫痫患者脑电信号识别方法, refAbstract=null), Reference(id=1225467189801697926, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=1098, pageEnd=1103, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Zhou Song, Gao Tianhan, journalName=Journal of Northeastern University (Natural Science), refType=null, unstructuredReference=Zhou Song, Gao Tianhan. EEG recognition method for epileptic patients based on RNN model with attention mechanism[J]. Journal of Northeastern University (Natural Science), 2023, 44(8): 1098-1103., articleTitle=EEG recognition method for epileptic patients based on RNN model with attention mechanism, refAbstract=null), Reference(id=1225467189927527061, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=5, pageStart=927, pageEnd=934, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=邓欣, 高红伟, 张家豪, journalName=重庆邮电大学学报: 自然科学版, refType=null, unstructuredReference=邓欣, 高红伟, 张家豪, 等. 基于卷积和注意力机制的癫痫脑电检测模型[J]. 重庆邮电大学学报: 自然科学版, 2023, 35(5): 927-934., articleTitle=基于卷积和注意力机制的癫痫脑电检测模型, refAbstract=null), Reference(id=1225467190053356197, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=5, pageStart=927, pageEnd=934, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=Deng Xin, Gao Hongwei, Zhang Jiahao, journalName=Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), refType=null, unstructuredReference=Deng Xin, Gao Hongwei, Zhang Jiahao, et al. Epileptic EEG detection model based on attention mechanism and convolutional network[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2023, 35(5): 927-934., articleTitle=Epileptic EEG detection model based on attention mechanism and convolutional network, refAbstract=null), Reference(id=1225467191466836658, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2022, volume=26, issue=11, pageStart=5389, pageEnd=5397, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=Chirasani S K R, Manikandan S, journalName=Soft Computing, refType=null, unstructuredReference=Chirasani S K R, Manikandan S. A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism[J]. Soft Computing, 2022, 26(11): 5389-5397., articleTitle=A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism, refAbstract=null), Reference(id=1225467191768826569, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=2, pageStart=442, pageEnd=452, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=仝航, 杨燕, 江永全, journalName=计算机科学与探索, refType=null, unstructuredReference=仝航, 杨燕, 江永全. 检测脑电癫痫的多头自注意力机制神经网络[J]. 计算机科学与探索, 2023, 17(2): 442-452., articleTitle=检测脑电癫痫的多头自注意力机制神经网络, refAbstract=null), Reference(id=1225467192070816473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=2, pageStart=442, pageEnd=452, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=Tong Hang, Yang Yan, Jiang Yongquan, journalName=Journal of Frontiers of Computer Science and Technology, refType=null, unstructuredReference=Tong Hang, Yang Yan, Jiang Yongquan. Multi-head self-attention neural network for detecting EEG epilepsy[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(2): 442-452., articleTitle=Multi-head self-attention neural network for detecting EEG epilepsy, refAbstract=null), Reference(id=1225467192397972210, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2000, volume=101, issue=23, pageStart=215, pageEnd=220, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=Goldberger A L, Amaral L A N, Glass L, journalName=Circulation, refType=null, unstructuredReference=Goldberger A L, Amaral L A N, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals[J]. Circulation, 2000, 101(23): 215-220., articleTitle=PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals, refAbstract=null), Reference(id=1225467192897094411, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2022, volume=30, issue=null, pageStart=915, pageEnd=924, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=Guo Y, Jiang X, Tao L, journalName=IEEE Transactions on Neural Systems and Rehabilitation Engineering, refType=null, unstructuredReference=Guo Y, Jiang X, Tao L, et al. Epileptic seizure detection by cascading isolation forest-based anomaly screening and EasyEnsemble[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 915-924., articleTitle=Epileptic seizure detection by cascading isolation forest-based anomaly screening and EasyEnsemble, refAbstract=null), Reference(id=1225467193027117841, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2021, volume=64, issue=null, pageStart=102215, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=Yao X, Li X, Ye Q, journalName=Biomedical Signal Processing and Control, refType=null, unstructuredReference=Yao X, Li X, Ye Q, et al. A robust deep learning approach for automatic classification of seizures against non-seizures[J]. Biomedical Signal Processing and Control, 2021, 64: 102215., articleTitle=A robust deep learning approach for automatic classification of seizures against non-seizures, refAbstract=null), Reference(id=1225467193400410917, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=2, pageStart=293, pageEnd=300, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=杨涌, 秦小林, 林小光, journalName=生物医学工程学杂志, refType=null, unstructuredReference=杨涌, 秦小林, 林小光, 等. 基于数据增强和深度学习的特定患者癫痫检测分析方法[J]. 生物医学工程学杂志, 2022, 39(2): 293-300., articleTitle=基于数据增强和深度学习的特定患者癫痫检测分析方法, refAbstract=null), Reference(id=1225467193572377389, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=2, pageStart=293, pageEnd=300, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=Yang Yong, Qin Xiaolin, Lin Xiaoguang, journalName=Journal of Biomedical Engineering, refType=null, unstructuredReference=Yang Yong, Qin Xiaolin, Lin Xiaoguang, et al. Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning[J]. Journal of Biomedical Engineering, 2022, 39(2): 293-300., articleTitle=Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning, refAbstract=null), Reference(id=1225467193777898301, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2022, volume=26, issue=11, pageStart=5494, pageEnd=5505, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=Pandey A, Singh S K, Udmale S S, journalName=IEEE Journal of Biomedical and Health Informatics, refType=null, unstructuredReference=Pandey A, Singh S K, Udmale S S, et al. Epileptic seizure classification using battle royale search and rescue optimization-based deep LSTM[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(11): 5494-5505., articleTitle=Epileptic seizure classification using battle royale search and rescue optimization-based deep LSTM, refAbstract=null), Reference(id=1225467194012779341, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2018, volume=23, issue=1, pageStart=83, pageEnd=94, url=null, language=null, rfNumber=[22], rfOrder=30, authorNames=Yuan Y, Xun G, Jia K, journalName=IEEE Journal of Biomedical and Health Informatics, refType=null, unstructuredReference=Yuan Y, Xun G, Jia K, et al. A multi-view deep learning framework for EEG seizure detection[J]. IEEE Journal of Biomedical and Health Informatics, 2018, 23(1): 83-94., articleTitle=A multi-view deep learning framework for EEG seizure detection, refAbstract=null), Reference(id=1225467194268631910, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[23], rfOrder=31, authorNames=Selvakumari R S, Mahalakshmi M, Prashalee P, journalName=Journal of Medical Systems, refType=null, unstructuredReference=Selvakumari R S, Mahalakshmi M, Prashalee P. Patient-specific seizure detection method using hybrid classifier with optimized electrodes[J]. Journal of Medical Systems, 2019, 43: 1-7., articleTitle=Patient-specific seizure detection method using hybrid classifier with optimized electrodes, refAbstract=null), Reference(id=1225467194574816118, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, doi=null, pmid=null, pmcid=null, year=2019, volume=27, issue=10, pageStart=1962, pageEnd=1972, url=null, language=null, rfNumber=[24], rfOrder=32, authorNames=Tian X, Deng Z, Ying W, journalName=IEEE Transactions on Neural Systems and Rehabilitation Engineering, refType=null, unstructuredReference=Tian X, Deng Z, Ying W, et al. Deep multi-view feature learning for EEG-based epileptic seizure detection[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27(10): 1962-1972., articleTitle=Deep multi-view feature learning for EEG-based epileptic seizure detection, refAbstract=null)], funds=[Fund(id=1225467184663675153, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, awardId=20200801035GH, language=CN, fundingSource=吉林省科技发展计划国际科技合作项目(20200801035GH), fundOrder=null, country=null), Fund(id=1225467184835641629, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, awardId=20200802004GH, language=CN, fundingSource=吉林省科技发展计划国际联合研究中心建设项目(20200802004GH), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1225467166116462898, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=1, ext=[AuthorCompanyExt(id=1225467166133240117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China), AuthorCompanyExt(id=1225467166145823032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166116462898, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长春理工大学计算机科学技术学院, 长春 130022)]), AuthorCompany(id=1225467166292623678, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, xref=2, ext=[AuthorCompanyExt(id=1225467166321983809, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166292623678, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Zhongshan Institute, Changchun University of Science and Technology, Zhongshan 528400, China), AuthorCompanyExt(id=1225467166326178114, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, companyId=1225467166292623678, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 长春理工大学中山研究院, 中山 528400)])], figs=[ArticleFig(id=1225467178409968470, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Fig.1, caption=Framework of intelligent-assisted detection for epilepsy, figureFileSmall=ZY5zusMcqSOq5g2E914i2Q==, figureFileBig=EVyC3YYFxK/w4f23M1OSow==, tableContent=null), ArticleFig(id=1225467178586129259, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=图1, caption=癫痫智能辅助检测框架图, figureFileSmall=ZY5zusMcqSOq5g2E914i2Q==, figureFileBig=EVyC3YYFxK/w4f23M1OSow==, tableContent=null), ArticleFig(id=1225467179060085654, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Fig.2, caption=Seizure (specifically marked) and inter-seizure EEG signals of chb01 patient, figureFileSmall=WTjan0c/hknlT9xTd/EGWA==, figureFileBig=HuDVi5ioJfpZvcZCo0AzCw==, tableContent=null), ArticleFig(id=1225467179378852779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=图2, caption=chb01患者的发作期、发作间期脑电信号

特别标注部分为发作期脑电信号

, figureFileSmall=WTjan0c/hknlT9xTd/EGWA==, figureFileBig=HuDVi5ioJfpZvcZCo0AzCw==, tableContent=null), ArticleFig(id=1225467179575985081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Fig.3, caption=Multi-view features, figureFileSmall=cNI8DpGuEaVLtOeuRuOh1g==, figureFileBig=bgIXsK0SQS1sBtuIkYyDcg==, tableContent=null), ArticleFig(id=1225467179781505991, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=图3, caption=多视图特征, figureFileSmall=cNI8DpGuEaVLtOeuRuOh1g==, figureFileBig=bgIXsK0SQS1sBtuIkYyDcg==, tableContent=null), ArticleFig(id=1225467180079301584, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Fig.4, caption=Structure of multi-scale convolution module, figureFileSmall=ieVP5vO01SOiyeJd9K030A==, figureFileBig=Dh5a1XelqD53Eq7bJYYd7w==, tableContent=null), ArticleFig(id=1225467180372902879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=图4, caption=多尺度卷积模块结构图, figureFileSmall=ieVP5vO01SOiyeJd9K030A==, figureFileBig=Dh5a1XelqD53Eq7bJYYd7w==, tableContent=null), ArticleFig(id=1225467180683281397, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Fig.5, caption=View attention module structure, figureFileSmall=XU6NG9h2vqGCzqxV7Kgokg==, figureFileBig=el7pom4ITTP/BDEnjmtycA==, tableContent=null), ArticleFig(id=1225467180909772811, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=图5, caption=视图注意力模块结构图

WvWkWq为3个权重矩阵;VKQ为3个输入向量

, figureFileSmall=XU6NG9h2vqGCzqxV7Kgokg==, figureFileBig=el7pom4ITTP/BDEnjmtycA==, tableContent=null), ArticleFig(id=1225467181098516515, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Fig.6, caption=Variation curve of accuracy and loss value of training set, figureFileSmall=cT3vuN07/tDPZa9Wx8h2pw==, figureFileBig=YzpBz/2qiKgpUAZ3MO43wA==, tableContent=null), ArticleFig(id=1225467182482636852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=图6, caption=训练集准确率和损失值变化曲线, figureFileSmall=cT3vuN07/tDPZa9Wx8h2pw==, figureFileBig=YzpBz/2qiKgpUAZ3MO43wA==, tableContent=null), ArticleFig(id=1225467182633631812, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Table 1, caption=

CHB-MIT dataset details

, figureFileSmall=null, figureFileBig=null, tableContent=
患者 性别 年龄 癫痫
事件/次
癫痫发作
时间/s
记录
时长/h
1 11 7 449 40.55
2 11 3 175 25.3
3 14 7 409 28
4 22 4 382 155.9
5 7 5 563 39
6 1.5 9 147 66.7
7 14.5 3 328 68.1
8 3.5 5 924 20
9 10 4 280 67.8
10 3 7 454 50
11 12 3 809 34.8
12 2 21 1 515 23.7
13 3 12 547 33
14 9 8 117 26
15 16 20 2 012 40
16 7 10 94 19
17 12 3 296 21
18 18 6 323 36
19 19 3 239 30
20 6 8 302 29
21 13 4 203 33
22 9 3 207 31
23 6 7 431 28
24 16 527 22
), ArticleFig(id=1225467182767849557, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=表1, caption=

CHB-MIT数据集详情

, figureFileSmall=null, figureFileBig=null, tableContent=
患者 性别 年龄 癫痫
事件/次
癫痫发作
时间/s
记录
时长/h
1 11 7 449 40.55
2 11 3 175 25.3
3 14 7 409 28
4 22 4 382 155.9
5 7 5 563 39
6 1.5 9 147 66.7
7 14.5 3 328 68.1
8 3.5 5 924 20
9 10 4 280 67.8
10 3 7 454 50
11 12 3 809 34.8
12 2 21 1 515 23.7
13 3 12 547 33
14 9 8 117 26
15 16 20 2 012 40
16 7 10 94 19
17 12 3 296 21
18 18 6 323 36
19 19 3 239 30
20 6 8 302 29
21 13 4 203 33
22 9 3 207 31
23 6 7 431 28
24 16 527 22
), ArticleFig(id=1225467182914650213, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Table 2, caption=

Results of the FAM-MCNN model

, figureFileSmall=null, figureFileBig=null, tableContent=
患者 准确率/% 灵敏度/% 特异度/%
1 99.43 99.15 99.72
2 98.91 100 97.74
3 98.91 98.17 99.68
4 99.67 99.65 99.69
5 99.10 100 98.17
6 99.18 99.17 99.19
7 98.46 98.08 98.84
8 99.25 99.59 98.91
9 98.41 97.77 99.08
10 99.72 99.43 100
11 99.46 99.54 99.37
12 99.45 99.56 99.34
13 97.89 97.81 97.98
14 99.63 99.25 100
15 98.02 98.85 97.27
16 100 100 100
17 97.01 96.12 97.88
18 98.82 99.18 98.48
19 99.47 98.90 100
20 99.15 98.31 100
21 99.06 100 97.96
22 98.77 100 97.59
23 100 100 100
24 98.53 97.09 100
平均值 99.01 98.98 99.04
), ArticleFig(id=1225467183044673659, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=表2, caption=

FAM-MCNN模型的结果

, figureFileSmall=null, figureFileBig=null, tableContent=
患者 准确率/% 灵敏度/% 特异度/%
1 99.43 99.15 99.72
2 98.91 100 97.74
3 98.91 98.17 99.68
4 99.67 99.65 99.69
5 99.10 100 98.17
6 99.18 99.17 99.19
7 98.46 98.08 98.84
8 99.25 99.59 98.91
9 98.41 97.77 99.08
10 99.72 99.43 100
11 99.46 99.54 99.37
12 99.45 99.56 99.34
13 97.89 97.81 97.98
14 99.63 99.25 100
15 98.02 98.85 97.27
16 100 100 100
17 97.01 96.12 97.88
18 98.82 99.18 98.48
19 99.47 98.90 100
20 99.15 98.31 100
21 99.06 100 97.96
22 98.77 100 97.59
23 100 100 100
24 98.53 97.09 100
平均值 99.01 98.98 99.04
), ArticleFig(id=1225467183191474324, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Table 3, caption=

Results of ablation experiments

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 准确率/% 灵敏度/% 特异度/%
a 84.72 82.85 86.50
b 93.77 92.91 94.65
c 97.20 97.15 97.40
d 99.01 98.98 99.04
), ArticleFig(id=1225467183376023710, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=表3, caption=

消融实验的结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 准确率/% 灵敏度/% 特异度/%
a 84.72 82.85 86.50
b 93.77 92.91 94.65
c 97.20 97.15 97.40
d 99.01 98.98 99.04
), ArticleFig(id=1225467183564767407, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Table 4, caption=

Results at different sample sizes

, figureFileSmall=null, figureFileBig=null, tableContent=
训练样本量 准确率/% 灵敏度/% 特异度/%
80% 99.01 98.98 99.04
50% 98.76 98.58 98.93
25% 98.43 98.29 98.57
10% 96.70 95.59 97.82
), ArticleFig(id=1225467183753511098, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=表4, caption=

不同样本量下的结果

, figureFileSmall=null, figureFileBig=null, tableContent=
训练样本量 准确率/% 灵敏度/% 特异度/%
80% 99.01 98.98 99.04
50% 98.76 98.58 98.93
25% 98.43 98.29 98.57
10% 96.70 95.59 97.82
), ArticleFig(id=1225467184080666835, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=EN, label=Table 5, caption=

Effectiveness of different models on the CHB-MIT dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
文献 年份 训练样本量 准确率/% 灵敏度/% 特异度/%
文献[18] 2022 90% 97.74 98.25 97.73
文献[19] 2021 90% 87.80 87.30 88.30
文献[9] 2023 80% 96.23 98.20 94.02
文献[10] 2023 80% 94.30 94.50 94.00
文献[20] 2022 80% 95.47 93.89 96.48
文献[21] 2022 80% 89.88 96.71 89.88
文献[22] 2019 80% 93.97
文献[16] 2023 80% 96.61 96.18 97.04
本文模型 80% 99.01 98.98 99.04
文献[23] 2019 50% 96.28 94.50 97.50
文献[24] 2019 50% 97.16 94.68 98.40
文献[18] 2022 25% 92.62 95.55 92.57
本文模型 25% 98.43 98.29 98.57
), ArticleFig(id=1225467184269410534, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983789705584877, language=CN, label=表5, caption=

不同模型在CHB-MIT数据集上的效果

, figureFileSmall=null, figureFileBig=null, tableContent=
文献 年份 训练样本量 准确率/% 灵敏度/% 特异度/%
文献[18] 2022 90% 97.74 98.25 97.73
文献[19] 2021 90% 87.80 87.30 88.30
文献[9] 2023 80% 96.23 98.20 94.02
文献[10] 2023 80% 94.30 94.50 94.00
文献[20] 2022 80% 95.47 93.89 96.48
文献[21] 2022 80% 89.88 96.71 89.88
文献[22] 2019 80% 93.97
文献[16] 2023 80% 96.61 96.18 97.04
本文模型 80% 99.01 98.98 99.04
文献[23] 2019 50% 96.28 94.50 97.50
文献[24] 2019 50% 97.16 94.68 98.40
文献[18] 2022 25% 92.62 95.55 92.57
本文模型 25% 98.43 98.29 98.57
)], 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.1671-1815.2400599, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2400599, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2400599, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2400599, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
融合注意力机制的多视图卷积网络癫痫智能辅助检测
收藏切换
PDF下载
李奇 1, 2 , 闫旭荣 1 , 武岩 1, 2 , 赵迪 1 , 常立娜 1 , 孙瀚琳 1
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(5): 1988-1995
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(5): 1988-1995
融合注意力机制的多视图卷积网络癫痫智能辅助检测
全屏
李奇1, 2 , 闫旭荣1, 武岩1, 2, 赵迪1, 常立娜1, 孙瀚琳1
作者信息
  • 1 长春理工大学计算机科学技术学院, 长春 130022
  • 2 长春理工大学中山研究院, 中山 528400
  • 李奇(1977—),男,汉族,辽宁葫芦岛人,博士,教授。研究方向:脑机接口技术、神经康复工程、类脑计算、智能感知。E-mail:

Multi-view Convolutional Network with Fused Attention for Intelligent-assisted Epilepsy Detection and Recognition
Qi LI1, 2 , Xu-rong YAN1, Yan WU1, 2, Di ZHAO1, Li-na CHANG1, Han-lin SUN1
Affiliations
  • 1 School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China
  • 2 Zhongshan Institute, Changchun University of Science and Technology, Zhongshan 528400, China
出版时间: 2025-02-18 doi: 10.12404/j.issn.1671-1815.2400599
文章导航
收藏切换

针对单一视图网络癫痫检测识别精度低的问题,提出一种融合注意力机制的多视图卷积网络癫痫智能辅助检测模型(multi-view convolutional network with fused attention mechanism,FAM-MCNN)。该模型从时域、频域、时频域和非线性域提取多视图特征来全面表征脑电信号;采用多尺度卷积捕捉不同层次的细节信息;引入注意力机制分别从视图维度和单个特征向量维度对特征进行加权融合,从而提高对癫痫患者不同类别脑电信号的区分能力。在CHB-MIT癫痫数据集上进行的对比实验结果显示,与单一视图网络相比,FAM-MCNN模型的平均准确率、灵敏度、特异度分别提高了14.29%、16.13%、12.54%。此外,对该模型采用少量训练样本(25%)进行实验,结果显示其检测性能达到了拥有大量训练样本(80%~90%)的对比模型水平。

脑电信号  /  多视图卷积  /  注意力机制  /  癫痫智能辅助检测

In response to the problem of low accuracy in epilepsy detection and recognition using single-view networks, a multi-view convolutional network model with fused attention mechanism (FAM-MCNN) was proposed. Multiple view features were extracted from time domain, frequency domain, time-frequency domain and nonlinear domain to characterize electroencephalogram(EEG) signals comprehensively. Multi-scale convolution was used to capture different levels of detail information. In order to improve the ability to distinguish different types of EEG signals in epileptic patients, the attention mechanism was introduced to combine the features from view dimension and single feature vector dimension respectively. The results of the comparison experiments performed on the CHB-MIT epilepsy dataset show that the average accuracy, sensitivity, and specificity of the FAM-MCNN model are improved by 14.29%, 16.13%, and 12.54%, respectively, when compared to a single-view network. In addition, experiments under a small number of training samples (25%) show that its detection performance reaches the level of the comparison model with a large number of training samples (80%~90%).

electroencephalogram signal  /  multi-view convolution  /  attention mechanisms  /  intelligent auxiliary detection of epilepsy
李奇, 闫旭荣, 武岩, 赵迪, 常立娜, 孙瀚琳. 融合注意力机制的多视图卷积网络癫痫智能辅助检测. 科学技术与工程, 2025 , 25 (5) : 1988 -1995 . DOI: 10.12404/j.issn.1671-1815.2400599
Qi LI, Xu-rong YAN, Yan WU, Di ZHAO, Li-na CHANG, Han-lin SUN. Multi-view Convolutional Network with Fused Attention for Intelligent-assisted Epilepsy Detection and Recognition[J]. Science Technology and Engineering, 2025 , 25 (5) : 1988 -1995 . DOI: 10.12404/j.issn.1671-1815.2400599
癫痫是中国排名第二的神经系统疾病[1],其具有的不可预知性和反复性严重影响患者的日常生活,甚至可能导致患者死亡。目前常用的癫痫检测手段是脑电图(electroencephalogram,EEG)分析[2-3],这项工作不仅烦琐,而且极大地依赖检查者的主观判断[4]。随着智能医疗的不断发展,癫痫智能辅助检测可以在检测与诊断过程中为医生提供有力帮助,大大提升医疗效率。
在癫痫智能辅助检测中,研究人员应用各种信号处理方法从脑电信号中提取特征,其中Bhattacharyya等[5]利用小波变化对脑电信号进行分解得到频域特征,实现癫痫局灶区和非局灶区的分类。牛宝东等[6]通过经验模态分解和希尔伯特变换提取时频域特征,实现癫痫和非癫痫脑电波信号的分类。因为不同癫痫患者的发作类型、发作表现并不相同,并且可能随着时间的推移进行演变,所以单一角度特征已经难以准确表示癫痫患者复杂的脑电信号。于是有研究者提出了从不同角度表达数据的多视图特征。比如,Qureshi等[7]使用离散小波变换提取时频域特征,同时结合峰值、信号频谱导数等时域特征、频域特征,用于检测癫痫发作前期和发作间期的脑电信号,在多通道数据集上实现了94.94%的准确率。Harpale等[8]利用均值、变异系数、功率谱密度等时域特征和频域特征来识别脑电信号的癫痫发作前期和癫痫发作期,达到了96.48%的准确率。因此,有效、合理的特征组合对癫痫智能辅助检测结果具有重要影响。
随着深度学习的发展,神经网络模型在癫痫智能辅助检测领域得到了广泛应用[9-12]。有研究表明在神经网络中加入注意力机制可以提高特征显著性。周嵩等[13]提出了基于注意力机制的循环神经网络模型,在癫痫患者脑电信号识别领域实现了94.4%的准确率。邓欣等[14]采用融合1D-CNN和注意力机制的方法,在癫痫发作自动检测中取得了良好的分类效果。Chirasani等[15]将层次注意力机制嵌入双流卷积中,通过加权特征对健康患者和癫痫患者进行分类,结果显示各项性能均得到显著提高。仝航等[16]将多头注意力机制与双向长短时记忆网络相结合,在癫痫发作间期和发作期脑电信号的检测中实现了96.61%的识别准确率。尽管很多神经网络模型被应用于癫痫检测中,但是忽视了脑电信号不同视图的信息,仍存在较多漏诊、误诊情况,癫痫智能检测的识别精度有待进一步提高。
现提出一种融合注意力机制的多视图卷积网络模型(multi-view convolutional network with fused attention mechanism,FAM-MCNN)进行癫痫智能辅助检测研究。该模型将不同脑电分析方法提取的多视图特征输入多流卷积神经网络中,通过多尺度卷积模块提取不同尺度的特征,以挖掘输入数据中更细节和更全局的信息,再引入视图注意力模块,分别从视图和单个特征向量维度分配权重,强化有用特征、淡化无用特征。同时,临床实践中癫痫发作在时间和空间上具有不可预测性,导致很难收集到足够数量的标记样本。为了验证模型在实际应用中的性能,模拟现实情况进行含有少量标记样本的实验,以期达到更好的检测效果,为癫痫智能辅助检测应用于临床提供新思路。
提出的癫痫智能辅助检测框架如图1所示。首先对原始癫痫患者脑电信号预处理,减少数据不平衡带来的误差,然后通过FAM-MCNN模型进行癫痫智能辅助检测。
CHB-MIT数据集由波士顿儿童医院收集汇编而成,涵盖了23位顽固性癫痫患者的长期连续头皮脑电图记录,每个患者的具体信息如表1所示。因为第21组记录是1号患者时隔1.5年重新采样的数据,所以将24组记录默认为24位患者的数据。该数据集记录包含来自18个电极的数据,分布于前额、顶部和颞部各6个位置,总时长达到了979 h,并且所有头皮脑电图记录均采用国际10-20 EEG电极位置和命名系统方式,信号采样频率为256 Hz,分辨率为16 bit[17]
CHB-MIT中大多数患者脑电图信号是23通道,但存在少数通道不统一的情况。为了便于研究,只保留以下23个通道:FP1-F7、F7-T7、T7-P7、P7-O1、FP1-F3、F3-C3、C3-P3、P3-O1、FP2-F4、F4-C4、C4-P4、P4-O2、FP2-F8、F8-T8、T8-P8、P8-O2、FZ-CZ、CZ-PZ、P7-T7、T7-FT9、FT9-FT10、FT10-T8、T8-P8。该癫痫数据集中患者1的部分发作期与发作间期脑电信号如图2所示。
由于CHB-MIT数据集中每个患者的头皮脑电图数据长度不同,并且包含的癫痫发作信号数量与癫痫不发作信号数量呈现高度的不平衡状态,直接使用这些信号会导致严重的过拟合现象。针对这个问题,对部分不发作信号进行欠采样处理的同时对发作信号进行过采样处理,然后将原本连续的信号划分为多个长度为1 s的信号段,最终得到数量相近的癫痫发作期样本与癫痫发作间期样本。
提出的融合注意力机制的多视图卷积网络,主要由多视图特征模块、多尺度卷积模块和视图注意力模块组成。首先,对癫痫患者的脑电信号使用多种特征提取方法得到4个视图的特征。然后,各个特征视图由双流卷积并行建模。最后,使用注意力机制为各个特征加权,强化关键特征。
通过不同脑电分析方法分别提取时域、频域、时频域、非线性域4个视图的特征来构建多视图特征(multi-view feature,MVF),具体操作如下。
(1) 时域:癫痫患者原始脑电信号是由多个样本点构成的有限、离散时间序列,每个样本点数据代表不同时刻的脑电波幅大小。直接使用原始波形分析(raw waveform analysis,RWA)作为时域特征,如图3(a)所示,其中横轴代表时间,纵轴代表脑电信号的电压。
(2)频域:脑电信号包含不同的频率范围,癫痫发作特征主要出现在4~30 Hz。为了减少不必要特征的干扰,使用4~30 Hz的频段并将频率离散化到间隔为1 Hz的空间中。使用的快速傅里叶变换(fast fourier transform,FFT)如式(1)所示。
$\left\{\begin{array}{l}X\left(k\right)=\sum _{n=0}^{N-1}x\left(n\right){e}^{-j2\pi kn/N}\\ A\left(k\right)=\frac{2\left|X\left(k\right)\right|}{N}\end{array}\right.$
式(1)中:x(n)为第n个采样点的时域信息;X(k)为其在频域上第k个频率分量上的复振幅;N为采样点数;j为虚数单位;A(k)为对应频率上的幅度。对时域信号进行快速傅里叶变换后得到的频域特征如图3(b)所示。
(3)时频域:使用小波包分解(wavelet packet decomposition,WPD)对脑电信号按照频率特性逐层分解。通过使用一组正交、迅速衰减的db4小波函数进行信号拟合。小波包分解算法如式(2)所示。
$\left\{\begin{array}{l}{d}_{l}^{j,2n}={\sum }_{k}^{}{h}_{k-2l}{d}_{k}^{j-1,n}\\ {d}_{l}^{j,2n+1}={\sum }_{k}^{}{g}_{k-2l}{d}_{k}^{j-1,n}\end{array}\right.$
式(2)中:${d}_{l}^{j,2n}$${d}_{l}^{j,2n+1}$为小波包系数,j为尺度参数,控制小波变换的伸缩即频率,lk为平移参数,控制小波变换的平移即时间,n为频率参数;hk-2lgk-2l分别为小波包分解中的低通、高通滤波器组。由于所用数据集的采样频率为256 Hz,根据采样定理知奈奎斯特采样频率是128 Hz。为了综合利用癫痫的时间信息和频率信息,获得与癫痫信号频域特征相同的频段并减少计算量,最终确定将小波包分解的层数设置为6。此时最后一层会产生64个频段,每个频段的频率区间是2 Hz。使用上述小波包分解方法提取的时频域特征如图3(c)所示。
(4)非线性域:排列熵方法(permutation entropy,PE)可以在一定程度上反映癫痫患者脑电信号的自相似性和不规则程度,其计算主要涉及最佳延迟时间τ和嵌入空间的维度m两个参数。对于一维时间序列,使用平均互信息法选取τ(τ>0),使用虚假最近邻点法确定m(m>1),从而组成一个能够使当前序列依次通过的窗口(m,τ)对该一维时间序列进行相空间重构,计算排列熵如式(3)所示。
$H_{\mathrm{pe}}(m)=-\sum_{i=1}^{k} P_{i} \ln P_{i}$
式(3)中:k为相空间重构后的重构分量会产生m!种排列方式;P1,P2,…,Pk为每一种排列情况出现次数的概率。部分时间序列的排列熵值Hpe图3(d)所示。
为了挖掘输入数据不同层次的信息,提出了多尺度卷积模块,该模块结构如图4所示。首先,由于各个视图特征维度不同并且数据量过大,使用全连接层将各个视图Vn的特征从较高维度的空间降到含有23个特征向量的低维空间来避免数据不一致问题。然后,对降维后的数据采用两条通道进行并行卷积操作,其中通道一分别使用3个大小为1×4、1×3、1×3的小卷积核和大步长的池化层提取更具局部特性的特征,可以更好地捕捉细微差异和更具判别性的信息;通道二分别使用3个大小为1×8、1×7、1×7的大卷积核和小步长的池化层提取更具全局特性的特征,防止漏掉或忽视各个视图重要的边缘信息。此外,每次卷积后都使用批量规范化操作将下一层的输入归一化,以此减小内部数据分布偏移的影响。最后,将通道一和通道二提取的不同尺度特征展开为全局特征向量后进行拼接,从而实现单视图多尺度特征的有效整合。
为了增强模型的泛化性和鲁棒性,在单视图多尺度特征矩阵上加入PN-SCS归一化算法来避免各个特征之间的量纲差异,处理过程如式(4)所示。
$\left\{\begin{array}{l}{X}_{ij}=parameters\frac{{x}_{ij}}{\sqrt{\sum _{i=1}^{N}{x}_{ij}^{2}+\epsilon }}\\ {Y}_{ij}={X}_{ij}-\frac{1}{F}\sum _{j=1}^{F}{x}_{ij}\\ i=\mathrm{1,2},\dots,N; j=\mathrm{1,2},\dots,F\end{array}\right.$
式(4)中:对于输入的三维特征张量,x∈RM×N×F,xij为第i个样本的第j个特征向量维度的取值,Xij为对应的结果;M为视图个数;N为批处理样本个数;F为每个视图的特征向量维度;MNF的取值分别是4、30、192;学习参数parameters=1;并且为避免分母为0设置一个小常数ε=1×10-6
将4个单视图多尺度特征的二维矩阵拼接成多视图多尺度特征的三维矩阵之后,结合自注意力机制(self-attention,SA)和通道注意力机制(squeeze-excitation,SE)提出了如图5所示的视图注意力模块来提高特征显著性。首先将多视图多尺度特征的三维矩阵转换成张量大小为(N,M,F)的形式作为输入,然后使用SA捕获输入序列各个视图的内部特征向量之间的关系并得到每个特征向量的权重,同时通过SE自适应地对输入序列的4个视图进行加权,最后将特征向量权值和视图权值相乘,从而进一步提高有用信息的比例。
在模型训练过程中训练15个轮次,数据批处理大小设置为30。使用Adam优化器进行优化,采用L2正则化衰减的交叉熵函数作为损失函数,学习率为1×10-3,权重衰减系数为1×10-3。最后,对加权特征使用全连接层和Softmax层输出癫痫二分类的概率矩阵。
采用准确率、灵敏度、特异度3个指标对所提模型进行分析。准确率(accurary,Acc):正确预测的样本数占总样本数的比例,如式(5)所示;灵敏度(sensitivity,Sen):正确预测的正类样本数占所有正类样本数的比例,如式(6)所示;特异度(specificity,Spe):正确预测的负类样本数占所有负类样本数的比例,如式(7)所示。
Acc=$\frac{TP+TN}{TP+FN+TN+FP}$×100%
Sen=$\frac{TP}{TP+FN}$×100%
Spe=$\frac{TN}{TN+FP}$×100%
式中:TP为被正确预测为患者的患者数量;TN为被正确预测为健康人的健康人数量;FP为被错误预测为患者的健康人数量;FN为被错误预测为健康人的患者数量。
为了分析FAM-MCNN模型的检测性能。采取单被试实验,从每名患者的癫痫脑电数据中选择自身数据的80%作为训练集,其余作为测试集,进行癫痫智能辅助检测的实验结果如表2所示。同时,FAM-MCNN模型训练过程中准确率和损失值的变化曲线如图6所示。
表2可以看出,本文模型对24位患者数据进行实验,获得了99.01%的平均准确率,98.98%的平均灵敏度,99.04%的平均特异性。所有患者的准确率、灵敏度、特异度均达到了97%以上,其中患者17的准确率为97.01%,效果相对较差的原因可能是由于受到了头发和运动等干扰因素的影响。这些结果表明本文模型能够适应不同患者数据并且可以提取有效特征进行癫痫智能辅助检测。
图6可以看出,随着迭代次数的增加,训练集损失值最终达到了一个平稳水平,说明模型已经收敛。此时,FAM-MCNN模型准确率能达到98%以上,与上述结果吻合。
为了验证FAM-MCNN模型的有效性。进行如下消融实验,a模型:单一视图网络;b模型:在a模型上加入多视图特征模块;c模型:在b模型上加入多尺度卷积模块;d模型:在c模型上加入视图注意力模块,即FAM-MCNN模型。各个模型得到的实验结果如表3所示,其中a模型取4个视图中最高的识别精度作为结果。
表3可以看出,加入多视图特征模块后,将单一视图网络的准确率、灵敏度、特异度均提高了8%以上。再次加入多尺度卷积模块,准确率、灵敏度、特异度分别提高3.43%、4.24%、2.7%。最后加入视图注意力模块后,又将各个评价指标平均提高1.7%。表中各个评价指标结果的不断提高,表明本文模型在癫痫智能辅助检测中具有有效性。
目前,大多数癫痫智能辅助检测方法是通过大量癫痫脑电样本训练网络以取得理想效果,当样本数据不足或带标记样本数量过少时,容易出现过拟合现象。然而,在实际检测过程中,由于隐私、安全和伦理等因素,难以获得足够数量的带标记癫痫样本。为了验证FAM-MCNN模型在实际应用中的性能,采用不同癫痫样本量进行实验,即对每位患者的癫痫脑电数据进行如下划分:从每组样本中,分别选择80%、50%、25%、10%的样本作为训练集其余作为测试集,得到的实验结果如表4所示。
表4可以看出,参与本文模型训练的样本量从80%减少到10%的过程中,准确率、灵敏度、特异度随之降低,但是差值保持在3.5%之内。当训练样本量为25%时,各个评价指标已经达到98%以上,在此基础上继续增加样本量,准确率、灵敏度、特异度的增长变得极其缓慢。进一步分析可以看出,使用较少的样本量训练本文模型就可以充分实现癫痫智能辅助检测,能够有效解决临床中癫痫标记样本量不足带来的问题。关于本文模型在少量训练样本下仍能取得高识别精度的原因,提出如下猜测:多个视图和多个尺度可以提供更加丰富和全面的信息,不同视图捕捉不同角度的特征,而不同尺度可以帮助模型对输入信息的整体和局部特征有所了解,从而在少量样本中就可以提取到更具有代表性和区别性的特征,然后引入注意力模块从两个维度动态的调整特征的权重,最终实现了FAM-MCNN模型在少量训练样本下的高性能检测结果。
为了对比FAM-MCNN模型与其他相关文献模型的检测结果,将本文模型与近几年使用CHB-MIT数据集进行癫痫智能辅助检测的主流模型进行比较,结果如表5所示。
可以看出,虽然有一些文献在癫痫检测中取得了不错结果,但是需要大量数据作为训练集训练网络才能取得这样的理想效果,而在实际检测过程中,难以获得足够数量的癫痫带标记样本。另一些文献使用少量数据训练网络,但是得到的灵敏度或特异度较差,无法应用于实际临床中。FAM-MCNN模型不仅在保持较高水平特异度的同时表现出更好的准确率和灵敏度,而且相比较训练集拥有大量样本的其他模型,本文模型在含有少量训练样本的情况下实现了更好的检测性能,大大减少了标记工作量,可以为癫痫智能辅助检测提供有力支持。
提出了一种融合注意力机制的多视图卷积网络模型进行癫痫智能辅助检测。其中,原始信号分析、快速傅里叶变换、小波包分解、排列熵方法用来构建多视图特征,以获取多个角度的信息、增加特征多样性。融合注意力机制的多视图卷积网络从多视图特征中自动学习不同层次的信息,并使用注意力机制从视图维度和单个特征向量维度为特征分配权重,最终提高癫痫智能辅助检测识别精度。FAM-MCNN模型在CHB-MIT数据集的24组癫痫头皮脑电记录上进行了大量实验。结果显示,本文模型的平均准确率、灵敏度、特异度分别为99.01%,98.98%,99.04%,每名患者的特异度和灵敏度均超过了97%,并且在少量训练样本下也能取得较好性能。这些令人满意的结果可以为癫痫辅助检测提供参考。虽然本文模型在准确率和灵敏度上得到了提升,但是该模型还有一些不足和值得进一步深入研究的地方。比如在现实临床环境中,癫痫患者的脑电信号可能会受到各种噪声和干扰的影响,如何提高癫痫智能辅助检测算法的鲁棒性还有待解决。将来的工作中将对上述问题进行深入研究。
  • 吉林省科技发展计划国际科技合作项目(20200801035GH)
  • 吉林省科技发展计划国际联合研究中心建设项目(20200802004GH)
参考文献 引证文献
排序方式:
[1]
彭睿旻, 江军, 匡光涛, 等. 基于EEG的癫痫自动检测: 综述与展望[J]. 自动化学报, 2022, 48(2): 335-350.
Peng Ruimin, Jiang Jun, Kuang Guangtao, et al. EEG-based automatic epilepsy detection: review and outlook[J]. Acta Automatica Sinica, 2022, 48(2): 335-350.
[2]
Gallotto S, Seeck M. EEG biomarker candidates for the identification of epilepsy[J]. Clinical Neurophysiology Practice, 2023, 8: 32-41.
[3]
赵倩, 谭浩然, 王西岳, 等. 脑电采集电极研究进展[J]. 科学技术与工程, 2021, 21(15): 6097-6104.
Zhao Qian, Tan Haoran, Wang Xiyue, et al. Research progress of the electrode for electroencephalogram acquisition[J]. Science Technology and Engineering, 2021, 21(15): 6097-6104.
[4]
Rennie J, Chorley G, Boylan G, et al. Non-expert use of the cerebral function monitor for neonatal seizure detection[J]. Archives of Disease in Childhood Fetal and Neonatal Edition, 2004, 89(1): 37-40.
[5]
Bhattacharyya A, Sharma M, Pachori R B, et al. A novel approach for automated detection of focal EEG signals using empirical wavelet transform[J]. Neural Computing and Applications, 2016, 29(8): 47-57.
[6]
牛宝东, 马尽文. 基于希尔伯特黄变换的癫痫自动检测[J]. 信号处理, 2016, 32(7): 764-770.
Niu Baodong, Ma Jinwen. Automatic detection of epileptic seizure through Hilbert-Huang transform[J]. Journal of Signal Processing, 2016, 32(7): 764-770.
[7]
Qureshi M M, Kaleem M. EEG-based seizure prediction with machine learning[J]. Signal, Image and Video Processing, 2023, 17(4): 1543-1554.
[8]
Harpale V, Bairagi V. An adaptive method for feature selection and extraction for classification of epileptic EEG signal in significant states[J]. Journal of King Saud University-Computer and Information Sciences, 2021, 33(6): 668-676.
[9]
Varli M, Ylmaz H. Multiple classification of EEG signals and epileptic seizure diagnosis with combined deep learning[J]. Journal of Computational Science, 2023, 67: 101943.
[10]
Tripathi P M, Kumar A, Kumar M, et al. Automatic seizure detection and classification using super-resolution superlet transform and deep neural network: a preprocessing-less method[J]. Computer Methods and Programs in Biomedicine, 2023, 240: 107680.
[11]
于永强, 刘健, 孙仁诚, 等. 基于多特征多关系图卷积神经网络的癫痫脑电分类[J]. 中国医学物理学杂志, 2023, 40(5): 595-601.
Yu Yongqiang, Liu Jian, Sun Rencheng, et al. Classification of epileptic electroencephalogram signal using graph convolutional neural network with multiple features and multiple relations[J]. Chinese Journal of Medical Physics, 2023, 40(5): 595-601.
[12]
李玉花, 柳倩, 韦新, 等. 基于卷积神经网络的脑电信号分类[J]. 科学技术与工程, 2020, 20(15): 6135-6140.
Li Yuhua, Liu Qian, Wei Xin, et al. Classification of electroencephalogram signals based on convolutional neural network[J]. Science Technology and Engineering, 2020, 20(15): 6135-6140.
[13]
周嵩, 高天寒. 基于注意力机制RNN模型的癫痫患者脑电信号识别方法[J]. 东北大学学报: 自然科学版, 2023, 44(8): 1098-1103.
Zhou Song, Gao Tianhan. EEG recognition method for epileptic patients based on RNN model with attention mechanism[J]. Journal of Northeastern University (Natural Science), 2023, 44(8): 1098-1103.
[14]
邓欣, 高红伟, 张家豪, 等. 基于卷积和注意力机制的癫痫脑电检测模型[J]. 重庆邮电大学学报: 自然科学版, 2023, 35(5): 927-934.
Deng Xin, Gao Hongwei, Zhang Jiahao, et al. Epileptic EEG detection model based on attention mechanism and convolutional network[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2023, 35(5): 927-934.
[15]
Chirasani S K R, Manikandan S. A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism[J]. Soft Computing, 2022, 26(11): 5389-5397.
[16]
仝航, 杨燕, 江永全. 检测脑电癫痫的多头自注意力机制神经网络[J]. 计算机科学与探索, 2023, 17(2): 442-452.
Tong Hang, Yang Yan, Jiang Yongquan. Multi-head self-attention neural network for detecting EEG epilepsy[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(2): 442-452.
[17]
Goldberger A L, Amaral L A N, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals[J]. Circulation, 2000, 101(23): 215-220.
[18]
Guo Y, Jiang X, Tao L, et al. Epileptic seizure detection by cascading isolation forest-based anomaly screening and EasyEnsemble[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 915-924.
[19]
Yao X, Li X, Ye Q, et al. A robust deep learning approach for automatic classification of seizures against non-seizures[J]. Biomedical Signal Processing and Control, 2021, 64: 102215.
[20]
杨涌, 秦小林, 林小光, 等. 基于数据增强和深度学习的特定患者癫痫检测分析方法[J]. 生物医学工程学杂志, 2022, 39(2): 293-300.
Yang Yong, Qin Xiaolin, Lin Xiaoguang, et al. Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning[J]. Journal of Biomedical Engineering, 2022, 39(2): 293-300.
[21]
Pandey A, Singh S K, Udmale S S, et al. Epileptic seizure classification using battle royale search and rescue optimization-based deep LSTM[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(11): 5494-5505.
[22]
Yuan Y, Xun G, Jia K, et al. A multi-view deep learning framework for EEG seizure detection[J]. IEEE Journal of Biomedical and Health Informatics, 2018, 23(1): 83-94.
[23]
Selvakumari R S, Mahalakshmi M, Prashalee P. Patient-specific seizure detection method using hybrid classifier with optimized electrodes[J]. Journal of Medical Systems, 2019, 43: 1-7.
[24]
Tian X, Deng Z, Ying W, et al. Deep multi-view feature learning for EEG-based epileptic seizure detection[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27(10): 1962-1972.
2025年第25卷第5期
PDF下载
342
140
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2400599
  • 接收时间:2024-01-20
  • 首发时间:2025-07-29
  • 出版时间:2025-02-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-20
  • 修回日期:2024-11-13
基金
吉林省科技发展计划国际科技合作项目(20200801035GH)
吉林省科技发展计划国际联合研究中心建设项目(20200802004GH)
作者信息
    1 长春理工大学计算机科学技术学院, 长春 130022
    2 长春理工大学中山研究院, 中山 528400
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2400599
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