基于PSOFS和TSK模糊系统的不平衡心电数据分类算法

التفاصيل البيبلوغرافية
العنوان:	基于PSOFS和TSK模糊系统的不平衡心电数据分类算法
المؤلفون:	李鑫辉, 申情, 张雄涛
المصدر:	大数据, Vol 8, Iss 5, Pp 139-152 (2022)
بيانات النشر:	China InfoCom Media Group, 2022.
سنة النشر:	2022
المجموعة:	LCC:Electronic computers. Computer science
مصطلحات موضوعية:	tsk模糊神经网络, 粒子群优化特征选择, 集成学习, 心电信号分类, 不平衡数据, Electronic computers. Computer science, QA75.5-76.95
الوصف:	提出基于粒子群优化特征选择（PSOFS）算法和TSK（Takagi-Sugeno-Kang）模糊系统的心电信号分类模型，即基于PSOFS和TSK的并行集成模糊神经网络（PE-PT-FN），用于心电图预测。首先对训练集中的各类样本进行随机放回抽样，然后将抽样得到的样本合并在一起，再独立且并行地通过PSOFS算法进行特征选择。PSOFS算法中不同的位置表示不同的特征子集，初始位置随机的粒子经过多次迭代收敛至最佳位置。每个子集得到一个特征子集用于并行训练多组独立的小型TSK模糊神经网络（TSK-FNN）。模糊系统的可解释性和PSOFS算法挑选出来的特征子集能有效地帮助医学研究者找出心电信号数据与不同类型病例之间的关联。实验证明，PE-PT-FN在保留可解释性的前提下，能将预测结果的宏召回率提升至92.35%。
نوع الوثيقة:	article
وصف الملف:	electronic resource
اللغة:	Chinese
تدمد:	2096-0271
Relation:	http://www.infocomm-journal.com/bdr/CN/10.11959/j.issn.2096-0271.2022039; https://doaj.org/toc/2096-0271
DOI:	10.11959/j.issn.2096-0271.2022039
URL الوصول:	https://doaj.org/article/14c7a8f44cf7484dbd480dfce89bab51
رقم الانضمام:	edsdoj.14c7a8f44cf7484dbd480dfce89bab51
قاعدة البيانات:	Directory of Open Access Journals

View record in DOAJ

ResultId	1
Header	edsdoj Directory of Open Access Journals edsdoj.14c7a8f44cf7484dbd480dfce89bab51 978 3 Academic Journal academicJournal 978.45361328125
PLink	https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsdoj&AN=edsdoj.14c7a8f44cf7484dbd480dfce89bab51&custid=s6537998&authtype=sso
FullText	Array ( [Availability] => 0 ) Array ( [0] => Array ( [Url] => https://doaj.org/article/14c7a8f44cf7484dbd480dfce89bab51 [Name] => EDS - DOAJ [Category] => fullText [Text] => View record in DOAJ [MouseOverText] => View record in DOAJ ) )
Items	Array ( [Name] => Title [Label] => Title [Group] => Ti [Data] => 基于PSOFS和TSK模糊系统的不平衡心电数据分类算法 ) Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22李鑫辉%22">李鑫辉</searchLink><br /><searchLink fieldCode="AR" term="%22申情%22">申情</searchLink><br /><searchLink fieldCode="AR" term="%22张雄涛%22">张雄涛</searchLink> ) Array ( [Name] => TitleSource [Label] => Source [Group] => Src [Data] => 大数据, Vol 8, Iss 5, Pp 139-152 (2022) ) Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => China InfoCom Media Group, 2022. ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2022 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => LCC:Electronic computers. Computer science ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22tsk模糊神经网络%22">tsk模糊神经网络</searchLink><br /><searchLink fieldCode="DE" term="%22粒子群优化特征选择%22">粒子群优化特征选择</searchLink><br /><searchLink fieldCode="DE" term="%22集成学习%22">集成学习</searchLink><br /><searchLink fieldCode="DE" term="%22心电信号分类%22">心电信号分类</searchLink><br /><searchLink fieldCode="DE" term="%22不平衡数据%22">不平衡数据</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+computers%2E+Computer+science%22">Electronic computers. Computer science</searchLink><br /><searchLink fieldCode="DE" term="%22QA75%2E5-76%2E95%22">QA75.5-76.95</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => 提出基于粒子群优化特征选择（PSOFS）算法和TSK（Takagi-Sugeno-Kang）模糊系统的心电信号分类模型，即基于PSOFS和TSK的并行集成模糊神经网络（PE-PT-FN），用于心电图预测。首先对训练集中的各类样本进行随机放回抽样，然后将抽样得到的样本合并在一起，再独立且并行地通过PSOFS算法进行特征选择。PSOFS算法中不同的位置表示不同的特征子集，初始位置随机的粒子经过多次迭代收敛至最佳位置。每个子集得到一个特征子集用于并行训练多组独立的小型TSK模糊神经网络（TSK-FNN）。模糊系统的可解释性和PSOFS算法挑选出来的特征子集能有效地帮助医学研究者找出心电信号数据与不同类型病例之间的关联。实验证明，PE-PT-FN在保留可解释性的前提下，能将预测结果的宏召回率提升至92.35%。 ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => article ) Array ( [Name] => Format [Label] => File Description [Group] => SrcInfo [Data] => electronic resource ) Array ( [Name] => Language [Label] => Language [Group] => Lang [Data] => Chinese ) Array ( [Name] => ISSN [Label] => ISSN [Group] => ISSN [Data] => 2096-0271 ) Array ( [Name] => NoteTitleSource [Label] => Relation [Group] => SrcInfo [Data] => http://www.infocomm-journal.com/bdr/CN/10.11959/j.issn.2096-0271.2022039; https://doaj.org/toc/2096-0271 ) Array ( [Name] => DOI [Label] => DOI [Group] => ID [Data] => 10.11959/j.issn.2096-0271.2022039 ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="https://doaj.org/article/14c7a8f44cf7484dbd480dfce89bab51" linkWindow="_blank">https://doaj.org/article/14c7a8f44cf7484dbd480dfce89bab51</link> ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsdoj.14c7a8f44cf7484dbd480dfce89bab51 )
RecordInfo	Array ( [BibEntity] => Array ( [Identifiers] => Array ( [0] => Array ( [Type] => doi [Value] => 10.11959/j.issn.2096-0271.2022039 ) ) [Languages] => Array ( [0] => Array ( [Text] => Chinese ) ) [PhysicalDescription] => Array ( [Pagination] => Array ( [PageCount] => 14 [StartPage] => 139 ) ) [Subjects] => Array ( [0] => Array ( [SubjectFull] => tsk模糊神经网络 [Type] => general ) [1] => Array ( [SubjectFull] => 粒子群优化特征选择 [Type] => general ) [2] => Array ( [SubjectFull] => 集成学习 [Type] => general ) [3] => Array ( [SubjectFull] => 心电信号分类 [Type] => general ) [4] => Array ( [SubjectFull] => 不平衡数据 [Type] => general ) [5] => Array ( [SubjectFull] => Electronic computers. Computer science [Type] => general ) [6] => Array ( [SubjectFull] => QA75.5-76.95 [Type] => general ) ) [Titles] => Array ( [0] => Array ( [TitleFull] => 基于PSOFS和TSK模糊系统的不平衡心电数据分类算法 [Type] => main ) ) ) [BibRelationships] => Array ( [HasContributorRelationships] => Array ( [0] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => 李鑫辉 ) ) ) [1] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => 申情 ) ) ) [2] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => 张雄涛 ) ) ) ) [IsPartOfRelationships] => Array ( [0] => Array ( [BibEntity] => Array ( [Dates] => Array ( [0] => Array ( [D] => 01 [M] => 09 [Type] => published [Y] => 2022 ) ) [Identifiers] => Array ( [0] => Array ( [Type] => issn-print [Value] => 20960271 ) ) [Numbering] => Array ( [0] => Array ( [Type] => volume [Value] => 8 ) [1] => Array ( [Type] => issue [Value] => 5 ) ) [Titles] => Array ( [0] => Array ( [TitleFull] => 大数据 [Type] => main ) ) ) ) ) ) )
IllustrationInfo