Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment
The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignm...
Gespeichert in:
| Veröffentlicht in: | Sheng wu yi xue gong cheng xue za zhi 2024-02, Vol.41 (1), p.51-59 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | chi |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 59 |
|---|---|
| container_issue | 1 |
| container_start_page | 51 |
| container_title | Sheng wu yi xue gong cheng xue za zhi |
| container_volume | 41 |
| creator | Xia, Jun Sun, Jing Yang, Hongbo Pan, Jiahua Guo, Tao Wang, Weilian |
| description | The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearra |
| doi_str_mv | 10.7507/1001-5515.202212037 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_proquest_miscellaneous_2932017718</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3075405101</sourcerecordid><originalsourceid>FETCH-LOGICAL-p154t-78b9c4072e42e5c628bedf15080ce2ecc5b3bc94c711892e10a2c6a0bce32d1a3</originalsourceid><addsrcrecordid>eNpdkE1LAzEQhnNQbKn9BYIEvHjZOkk2m-1Ril9QEETPSzY720b3yyRL8S_4q02xingamHnmmZch5IzBQklQVwyAJVIyueDAOeMg1BGZ_nYnZO69LQF4DlmWixMyEXkKIoN0Sj6f0KN2Zkv7jpbavSW1w_cRO_NB_YAmON1Q02NdW2OxC55uIx6o78euoqbRUR1HOti4r5tN72zYttHksdor27EJdmiQ7mxX9TsabIt_TjjcCzZdG9Wn5LjWjcf5oc7Iy-3N8-o-WT_ePayu18nAZBoSlZdLk4LimHKUJuN5iVXNJORgkKMxshSlWaZGMZYvOTLQ3GQaSoOCV0yLGbn89g6ujzF8KFrrDTaN7rAffcGXggNTiuURvfiHvvaj62K6QoCSKUgGLFLnB2osW6yKwdlWu4_i58viC6X0gX0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3075405101</pqid></control><display><type>article</type><title>Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment</title><source>PubMed Central</source><creator>Xia, Jun ; Sun, Jing ; Yang, Hongbo ; Pan, Jiahua ; Guo, Tao ; Wang, Weilian</creator><creatorcontrib>Xia, Jun ; Sun, Jing ; Yang, Hongbo ; Pan, Jiahua ; Guo, Tao ; Wang, Weilian</creatorcontrib><description>The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearra</description><identifier>ISSN: 1001-5515</identifier><identifier>DOI: 10.7507/1001-5515.202212037</identifier><identifier>PMID: 38403604</identifier><language>chi</language><publisher>China: Sichuan Society for Biomedical Engineering</publisher><subject>Algorithms ; Cardiovascular diseases ; Classification ; Deep learning ; Feature extraction ; Filter banks ; Fourier transforms ; Heart ; Heart diseases ; Machine learning ; Neural networks ; Performance evaluation ; Recurrent neural networks ; Segments ; Sound ; Time-frequency analysis</subject><ispartof>Sheng wu yi xue gong cheng xue za zhi, 2024-02, Vol.41 (1), p.51-59</ispartof><rights>Copyright Sichuan Society for Biomedical Engineering 2024</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38403604$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Xia, Jun</creatorcontrib><creatorcontrib>Sun, Jing</creatorcontrib><creatorcontrib>Yang, Hongbo</creatorcontrib><creatorcontrib>Pan, Jiahua</creatorcontrib><creatorcontrib>Guo, Tao</creatorcontrib><creatorcontrib>Wang, Weilian</creatorcontrib><title>Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment</title><title>Sheng wu yi xue gong cheng xue za zhi</title><addtitle>Sheng Wu Yi Xue Gong Cheng Xue Za Zhi</addtitle><description>The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearra</description><subject>Algorithms</subject><subject>Cardiovascular diseases</subject><subject>Classification</subject><subject>Deep learning</subject><subject>Feature extraction</subject><subject>Filter banks</subject><subject>Fourier transforms</subject><subject>Heart</subject><subject>Heart diseases</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Performance evaluation</subject><subject>Recurrent neural networks</subject><subject>Segments</subject><subject>Sound</subject><subject>Time-frequency analysis</subject><issn>1001-5515</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNpdkE1LAzEQhnNQbKn9BYIEvHjZOkk2m-1Ril9QEETPSzY720b3yyRL8S_4q02xingamHnmmZch5IzBQklQVwyAJVIyueDAOeMg1BGZ_nYnZO69LQF4DlmWixMyEXkKIoN0Sj6f0KN2Zkv7jpbavSW1w_cRO_NB_YAmON1Q02NdW2OxC55uIx6o78euoqbRUR1HOti4r5tN72zYttHksdor27EJdmiQ7mxX9TsabIt_TjjcCzZdG9Wn5LjWjcf5oc7Iy-3N8-o-WT_ePayu18nAZBoSlZdLk4LimHKUJuN5iVXNJORgkKMxshSlWaZGMZYvOTLQ3GQaSoOCV0yLGbn89g6ujzF8KFrrDTaN7rAffcGXggNTiuURvfiHvvaj62K6QoCSKUgGLFLnB2osW6yKwdlWu4_i58viC6X0gX0</recordid><startdate>20240225</startdate><enddate>20240225</enddate><creator>Xia, Jun</creator><creator>Sun, Jing</creator><creator>Yang, Hongbo</creator><creator>Pan, Jiahua</creator><creator>Guo, Tao</creator><creator>Wang, Weilian</creator><general>Sichuan Society for Biomedical Engineering</general><scope>NPM</scope><scope>7QO</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope><scope>7X8</scope></search><sort><creationdate>20240225</creationdate><title>Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment</title><author>Xia, Jun ; Sun, Jing ; Yang, Hongbo ; Pan, Jiahua ; Guo, Tao ; Wang, Weilian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p154t-78b9c4072e42e5c628bedf15080ce2ecc5b3bc94c711892e10a2c6a0bce32d1a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>chi</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Cardiovascular diseases</topic><topic>Classification</topic><topic>Deep learning</topic><topic>Feature extraction</topic><topic>Filter banks</topic><topic>Fourier transforms</topic><topic>Heart</topic><topic>Heart diseases</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Performance evaluation</topic><topic>Recurrent neural networks</topic><topic>Segments</topic><topic>Sound</topic><topic>Time-frequency analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Xia, Jun</creatorcontrib><creatorcontrib>Sun, Jing</creatorcontrib><creatorcontrib>Yang, Hongbo</creatorcontrib><creatorcontrib>Pan, Jiahua</creatorcontrib><creatorcontrib>Guo, Tao</creatorcontrib><creatorcontrib>Wang, Weilian</creatorcontrib><collection>PubMed</collection><collection>Biotechnology Research Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Sheng wu yi xue gong cheng xue za zhi</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xia, Jun</au><au>Sun, Jing</au><au>Yang, Hongbo</au><au>Pan, Jiahua</au><au>Guo, Tao</au><au>Wang, Weilian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment</atitle><jtitle>Sheng wu yi xue gong cheng xue za zhi</jtitle><addtitle>Sheng Wu Yi Xue Gong Cheng Xue Za Zhi</addtitle><date>2024-02-25</date><risdate>2024</risdate><volume>41</volume><issue>1</issue><spage>51</spage><epage>59</epage><pages>51-59</pages><issn>1001-5515</issn><abstract>The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearra</abstract><cop>China</cop><pub>Sichuan Society for Biomedical Engineering</pub><pmid>38403604</pmid><doi>10.7507/1001-5515.202212037</doi><tpages>9</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1001-5515 |
| ispartof | Sheng wu yi xue gong cheng xue za zhi, 2024-02, Vol.41 (1), p.51-59 |
| issn | 1001-5515 |
| language | chi |
| recordid | cdi_proquest_miscellaneous_2932017718 |
| source | PubMed Central |
| subjects | Algorithms Cardiovascular diseases Classification Deep learning Feature extraction Filter banks Fourier transforms Heart Heart diseases Machine learning Neural networks Performance evaluation Recurrent neural networks Segments Sound Time-frequency analysis |
| title | Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T16%3A26%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Research%20on%20bark-frequency%20spectral%20coefficients%20heart%20sound%20classification%20algorithm%20based%20on%20multiple%20window%20time-frequency%20reassignment&rft.jtitle=Sheng%20wu%20yi%20xue%20gong%20cheng%20xue%20za%20zhi&rft.au=Xia,%20Jun&rft.date=2024-02-25&rft.volume=41&rft.issue=1&rft.spage=51&rft.epage=59&rft.pages=51-59&rft.issn=1001-5515&rft_id=info:doi/10.7507/1001-5515.202212037&rft_dat=%3Cproquest_pubme%3E3075405101%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3075405101&rft_id=info:pmid/38403604&rfr_iscdi=true |