基于启发式集成特征选择的人体活动识别

TP391; 针对人为提取的冗余特征集和无关特征集导致可穿戴传感器的人体活动识别分类性能降低的问题,提出一种基于启发式集成特征选择的人体活动识别方法.该方法首先选取了包含功率谱密度(Power spectrum density,PSD)的特征集用于识别易混淆的活动,在此基础上借助皮尔逊系数法(Pearson correlation coefficient,PCC)筛选出低相关的特征子集,然后使用改进的正余弦优化算法(Sine cosine algorithm,SCA)进行特征优化,通过两次特征筛选得到最优特征子集.实验结果表明,在实验室采集的数据集中使用该方法后的特征子集维数为34,识别准确率...

Full description

Saved in:
Bibliographic Details
Published in数据采集与处理 Vol. 37; no. 4; pp. 860 - 871
Main Authors 戴健威, 李瑞祥, 陈金瑶, 乐燕芬, 施伟斌
Format Journal Article
LanguageChinese
Published 上海理工大学光电信息与计算机工程学院,上海 200093 01.07.2022
Subjects
特征选择
可穿戴传感器
正余弦算法
人体活动识别
功率谱密度
Online AccessGet full text
ISSN1004-9037
DOI10.16337/j.1004-9037.2022.04.014

Cover

Abstract TP391; 针对人为提取的冗余特征集和无关特征集导致可穿戴传感器的人体活动识别分类性能降低的问题,提出一种基于启发式集成特征选择的人体活动识别方法.该方法首先选取了包含功率谱密度(Power spectrum density,PSD)的特征集用于识别易混淆的活动,在此基础上借助皮尔逊系数法(Pearson correlation coefficient,PCC)筛选出低相关的特征子集,然后使用改进的正余弦优化算法(Sine cosine algorithm,SCA)进行特征优化,通过两次特征筛选得到最优特征子集.实验结果表明,在实验室采集的数据集中使用该方法后的特征子集维数为34,识别准确率达到了98.21％.在公开的SCUT-NAA数据集中进行对比实验,特征子集维数为39,低于以往基于该数据集研究方法的特征维数,并且识别准确率达到了96.51％.
AbstractList TP391; 针对人为提取的冗余特征集和无关特征集导致可穿戴传感器的人体活动识别分类性能降低的问题,提出一种基于启发式集成特征选择的人体活动识别方法.该方法首先选取了包含功率谱密度(Power spectrum density,PSD)的特征集用于识别易混淆的活动,在此基础上借助皮尔逊系数法(Pearson correlation coefficient,PCC)筛选出低相关的特征子集,然后使用改进的正余弦优化算法(Sine cosine algorithm,SCA)进行特征优化,通过两次特征筛选得到最优特征子集.实验结果表明,在实验室采集的数据集中使用该方法后的特征子集维数为34,识别准确率达到了98.21％.在公开的SCUT-NAA数据集中进行对比实验,特征子集维数为39,低于以往基于该数据集研究方法的特征维数,并且识别准确率达到了96.51％.
Author 戴健威
乐燕芬
陈金瑶
施伟斌
李瑞祥
AuthorAffiliation 上海理工大学光电信息与计算机工程学院,上海 200093
AuthorAffiliation_xml – name: 上海理工大学光电信息与计算机工程学院,上海 200093
Author_FL LI Ruixiang
DAI Jianwei
SHI Weibin
CHEN Jinyao
LE Yanfen
Author_FL_xml – sequence: 1
  fullname: DAI Jianwei
– sequence: 2
  fullname: LI Ruixiang
– sequence: 3
  fullname: CHEN Jinyao
– sequence: 4
  fullname: LE Yanfen
– sequence: 5
  fullname: SHI Weibin
Author_xml – sequence: 1
  fullname: 戴健威
– sequence: 2
  fullname: 李瑞祥
– sequence: 3
  fullname: 陈金瑶
– sequence: 4
  fullname: 乐燕芬
– sequence: 5
  fullname: 施伟斌
BookMark eNo9j7tKA0EYRqeIYIx5B0ubXf-57D-ZUoI3CNhoHWYnM-ISNuAiYqcgIVEwETstbBWLNDaul6fZ2Zi3MKJYHfiK83GWSCXtpZaQFQohRc7lWhJSABEo4DJkwFgIIgQqKqT6vy-SepYdxsA4CqQKqwT9Q17k13488aMb_z6a3ffLwXg6fPWf57OzYXn1NL27KPK8-LgtX9785ePXpO8Hz8tkweluZut_rJH9zY295nbQ2t3aaa63gowCF0EjNhSdcU5JZ6EhWUcoZjVKKik36NBGrhEZpgSPmIm56qBkOrbaAkqFitfI6q_3RKdOpwftpHd8lM4f21liklPT_QkFMc_k34rwXaQ
ClassificationCodes TP391
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.16337/j.1004-9037.2022.04.014
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Human Activity Recognition Based on Heuristic Integrated Feature Selection
EndPage 871
ExternalDocumentID sjcjycl202204014
GrantInformation_xml – fundername: 国家自然科学基金
  funderid: (51705324)
GroupedDBID 2B.
4A8
92I
93N
ADMLS
ALMA_UNASSIGNED_HOLDINGS
PSX
TCJ
ID FETCH-LOGICAL-s1034-8bc16fcff97fe0872d492ea671713c6f6e5f85c294352cb39d672abeae0679693
ISSN 1004-9037
IngestDate Thu May 29 04:00:12 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 4
Keywords 特征选择
可穿戴传感器
正余弦算法
人体活动识别
功率谱密度
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1034-8bc16fcff97fe0872d492ea671713c6f6e5f85c294352cb39d672abeae0679693
PageCount 12
ParticipantIDs wanfang_journals_sjcjycl202204014
PublicationCentury 2000
PublicationDate 2022-07-01
PublicationDateYYYYMMDD 2022-07-01
PublicationDate_xml – month: 07
  year: 2022
  text: 2022-07-01
  day: 01
PublicationDecade 2020
PublicationTitle 数据采集与处理
PublicationTitle_FL Journal of Data Acquisition & Processing
PublicationYear 2022
Publisher 上海理工大学光电信息与计算机工程学院,上海 200093
Publisher_xml – name: 上海理工大学光电信息与计算机工程学院,上海 200093
SSID ssib023646196
ssib001102757
ssib000459638
ssib001164671
ssib006568634
ssib002264227
ssib036439733
ssib057620134
ssib023167944
ssib051372606
Score 2.3496294
Snippet TP391; 针对人为提取的冗余特征集和无关特征集导致可穿戴传感器的人体活动识别分类性能降低的问题,提出一种基于启发式集成特征选择的人体活动识别方法.该方法首先选取了包...
SourceID wanfang
SourceType Aggregation Database
StartPage 860
Title 基于启发式集成特征选择的人体活动识别
URI https://d.wanfangdata.com.cn/periodical/sjcjycl202204014
Volume 37
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Inspec with Full Text
  issn: 1004-9037
  databaseCode: ADMLS
  dateStart: 20180901
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  omitProxy: false
  ssIdentifier: ssib057620134
  providerName: EBSCOhost
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV29b9QwFI9Ku7AgECC-VSQ8Xkmc-Gt07nKqEGWhlbpVF18CVOgq0XagE0ioakGiRWwwsIIYurBwfAz8LU1L_wvec3xJKEUqSKfI53t5H7-X2M8--9nzbvTCXh6mEWsZKWGAIljQ6onMtIzpQzxOs5TZUyJm7vDpuejWPJsfO_GjsWppdSWdMmtH7iv5H69CHfgVd8n-g2crplABZfAvXMHDcD2Wj0nCiOqSWJMkwqtMbI1PdBcLsktUgIW4jeVEERUTyUnCiZRIlggiFYmVpUkgqEQa6WMl0sREK6RRwDlyIpysDlEh0sRQjq0sTbQkiUTRKIKhCB03Y1-kVyDIt8w7RCdWnMBPrRswlM4QHVm5AlWV1QyiUx8ko5CAaGZp4aagSaI6lotACJQtAKFmNQlIVMio1AGBste4IShCbBxOAnUH-9DQdnOuhNbrasune2SDtgCBwaKywQItRipHRAtbACxKyJiFHogjvBH5dIkOrMWBdWqFjkT4tFUaCkpYk9vWPZUIYVGJGyKszZrCe_Wnkphc0i_PkXS9FK4eUn6ZLWfUjblvD5pzNGVAUx7YUIU3wZE9Jw9t8oXFqYr5FCJo8wCX23wP5SVfXjSLj81DJIKOAM-Sn6DQs_rj3oTuzNy-2xw0_NbKQ8BJReO_9gBT3DUGJbi1m9Lm7mcueZ3EkGLuhsZubjwBgQd10sjQxtj1IIYFoYBBe_U7QyXdcpORqW6JH2Jw8y8I2E19g7w3uNeIP2dPe6fcwHFSl63AGW9s7f5ZjxfvhrvDl8X2TrH1qvi6dfB2fW9je3_zc_H96cGTzb0XH_bfPNsdDne_vd779KV4_v7nznqx8fGcN9dNZtvTLXcSSms58MOoJVMT8NzkuRJ55ktB-9iO9gA1EYSG5zxjuWSGKhj8UJOGqs8F7aVZL7PzxCo8740PlgbZBW-SpVzmRvZziC6ikIqUGjzBws_ylGM2x4vedWfngmvplhcOu_rSMWgueyfrN_CKN77yaDW7CvH7SnrNPSC_APYOqWw
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E5%90%AF%E5%8F%91%E5%BC%8F%E9%9B%86%E6%88%90%E7%89%B9%E5%BE%81%E9%80%89%E6%8B%A9%E7%9A%84%E4%BA%BA%E4%BD%93%E6%B4%BB%E5%8A%A8%E8%AF%86%E5%88%AB&rft.jtitle=%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E5%A4%84%E7%90%86&rft.au=%E6%88%B4%E5%81%A5%E5%A8%81&rft.au=%E6%9D%8E%E7%91%9E%E7%A5%A5&rft.au=%E9%99%88%E9%87%91%E7%91%B6&rft.au=%E4%B9%90%E7%87%95%E8%8A%AC&rft.date=2022-07-01&rft.pub=%E4%B8%8A%E6%B5%B7%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E5%85%89%E7%94%B5%E4%BF%A1%E6%81%AF%E4%B8%8E%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E4%B8%8A%E6%B5%B7+200093&rft.issn=1004-9037&rft.volume=37&rft.issue=4&rft.spage=860&rft.epage=871&rft_id=info:doi/10.16337%2Fj.1004-9037.2022.04.014&rft.externalDocID=sjcjycl202204014
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fsjcjycl%2Fsjcjycl.jpg