Improving pattern recognition of electronic nose data with time-delay neural networks
An enhanced time-delay neural network (TDNN), using time series sensor response data, improved pattern recognition ability of an electronic nose (e-nose) in discriminating four different spices. TDNN was used for analysis of e-nose time series sensor data from 0 to 4 min, while two popular pattern r...
Gespeichert in:
| Veröffentlicht in: | Sensors and actuators. B, Chemical Chemical, 2003-11, Vol.96 (1), p.385-389 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 389 |
|---|---|
| container_issue | 1 |
| container_start_page | 385 |
| container_title | Sensors and actuators. B, Chemical |
| container_volume | 96 |
| creator | Zhang, Haoxian Balaban, Murat Ö. Principe, José C. |
| description | An enhanced time-delay neural network (TDNN), using time series sensor response data, improved pattern recognition ability of an electronic nose (e-nose) in discriminating four different spices. TDNN was used for analysis of e-nose time series sensor data from 0 to 4
min, while two popular pattern recognition methods, discriminant function analysis (DFA) and multilayer perceptron (MLP) trained by back-propagation, were used to analyze the “instantaneous” e-nose data obtained from sensor responses only at 4 min. The results showed that DFA and MLP correctly recognized 59.4 and 62.5% of the spices respectively while TDNN correctly recognized all (100%) spices. |
| doi_str_mv | 10.1016/S0925-4005(03)00574-4 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_27856127</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0925400503005744</els_id><sourcerecordid>19226227</sourcerecordid><originalsourceid>FETCH-LOGICAL-c369t-1a1bcdc270a1b8dc9874f7caae1723f262a948b6fdfa49a79fd2ec5c9060ba603</originalsourceid><addsrcrecordid>eNqFkEtLAzEUhYMoWKs_QchKdDF6k3lkZiVSfBQKLrTrkGbu1Og0qUna0n9vbMVtV-cuzjmX8xFyyeCWAavu3qDhZVYAlNeQ3yQRRVYckQGrRZ7lIMQxGfxbTslZCJ8AUOQVDMh0vFh6tzZ2TpcqRvSWetRubk00zlLXUexRR--s0dS6gLRVUdGNiR80mgVmLfZqSy2uvOqTxI3zX-GcnHSqD3jxp0MyfXp8H71kk9fn8ehhkum8amLGFJvpVnMB6ahb3dSi6IRWCpngeccrrpqinlVd26miUaLpWo661A1UMFMV5ENyte9NG75XGKJcmKCx75VFtwqSi7qsGBcHjazh6dvOWO6N2rsQPHZy6c1C-a1kIH9pyx1t-YtSQi53tGWRcvf7HKa5a4NeBm3QamxN4hll68yBhh8sVYiR</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>19226227</pqid></control><display><type>article</type><title>Improving pattern recognition of electronic nose data with time-delay neural networks</title><source>ScienceDirect Journals (5 years ago - present)</source><creator>Zhang, Haoxian ; Balaban, Murat Ö. ; Principe, José C.</creator><creatorcontrib>Zhang, Haoxian ; Balaban, Murat Ö. ; Principe, José C.</creatorcontrib><description>An enhanced time-delay neural network (TDNN), using time series sensor response data, improved pattern recognition ability of an electronic nose (e-nose) in discriminating four different spices. TDNN was used for analysis of e-nose time series sensor data from 0 to 4
min, while two popular pattern recognition methods, discriminant function analysis (DFA) and multilayer perceptron (MLP) trained by back-propagation, were used to analyze the “instantaneous” e-nose data obtained from sensor responses only at 4 min. The results showed that DFA and MLP correctly recognized 59.4 and 62.5% of the spices respectively while TDNN correctly recognized all (100%) spices.</description><identifier>ISSN: 0925-4005</identifier><identifier>EISSN: 1873-3077</identifier><identifier>DOI: 10.1016/S0925-4005(03)00574-4</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Electronic nose ; Multivariate statistics ; Neural network ; Pattern recognition</subject><ispartof>Sensors and actuators. B, Chemical, 2003-11, Vol.96 (1), p.385-389</ispartof><rights>2003 Elsevier B.V.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c369t-1a1bcdc270a1b8dc9874f7caae1723f262a948b6fdfa49a79fd2ec5c9060ba603</citedby><cites>FETCH-LOGICAL-c369t-1a1bcdc270a1b8dc9874f7caae1723f262a948b6fdfa49a79fd2ec5c9060ba603</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/S0925-4005(03)00574-4$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Zhang, Haoxian</creatorcontrib><creatorcontrib>Balaban, Murat Ö.</creatorcontrib><creatorcontrib>Principe, José C.</creatorcontrib><title>Improving pattern recognition of electronic nose data with time-delay neural networks</title><title>Sensors and actuators. B, Chemical</title><description>An enhanced time-delay neural network (TDNN), using time series sensor response data, improved pattern recognition ability of an electronic nose (e-nose) in discriminating four different spices. TDNN was used for analysis of e-nose time series sensor data from 0 to 4
min, while two popular pattern recognition methods, discriminant function analysis (DFA) and multilayer perceptron (MLP) trained by back-propagation, were used to analyze the “instantaneous” e-nose data obtained from sensor responses only at 4 min. The results showed that DFA and MLP correctly recognized 59.4 and 62.5% of the spices respectively while TDNN correctly recognized all (100%) spices.</description><subject>Electronic nose</subject><subject>Multivariate statistics</subject><subject>Neural network</subject><subject>Pattern recognition</subject><issn>0925-4005</issn><issn>1873-3077</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><recordid>eNqFkEtLAzEUhYMoWKs_QchKdDF6k3lkZiVSfBQKLrTrkGbu1Og0qUna0n9vbMVtV-cuzjmX8xFyyeCWAavu3qDhZVYAlNeQ3yQRRVYckQGrRZ7lIMQxGfxbTslZCJ8AUOQVDMh0vFh6tzZ2TpcqRvSWetRubk00zlLXUexRR--s0dS6gLRVUdGNiR80mgVmLfZqSy2uvOqTxI3zX-GcnHSqD3jxp0MyfXp8H71kk9fn8ehhkum8amLGFJvpVnMB6ahb3dSi6IRWCpngeccrrpqinlVd26miUaLpWo661A1UMFMV5ENyte9NG75XGKJcmKCx75VFtwqSi7qsGBcHjazh6dvOWO6N2rsQPHZy6c1C-a1kIH9pyx1t-YtSQi53tGWRcvf7HKa5a4NeBm3QamxN4hll68yBhh8sVYiR</recordid><startdate>20031115</startdate><enddate>20031115</enddate><creator>Zhang, Haoxian</creator><creator>Balaban, Murat Ö.</creator><creator>Principe, José C.</creator><general>Elsevier B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QR</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20031115</creationdate><title>Improving pattern recognition of electronic nose data with time-delay neural networks</title><author>Zhang, Haoxian ; Balaban, Murat Ö. ; Principe, José C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c369t-1a1bcdc270a1b8dc9874f7caae1723f262a948b6fdfa49a79fd2ec5c9060ba603</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Electronic nose</topic><topic>Multivariate statistics</topic><topic>Neural network</topic><topic>Pattern recognition</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Haoxian</creatorcontrib><creatorcontrib>Balaban, Murat Ö.</creatorcontrib><creatorcontrib>Principe, José C.</creatorcontrib><collection>CrossRef</collection><collection>Chemoreception Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Sensors and actuators. B, Chemical</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Haoxian</au><au>Balaban, Murat Ö.</au><au>Principe, José C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving pattern recognition of electronic nose data with time-delay neural networks</atitle><jtitle>Sensors and actuators. B, Chemical</jtitle><date>2003-11-15</date><risdate>2003</risdate><volume>96</volume><issue>1</issue><spage>385</spage><epage>389</epage><pages>385-389</pages><issn>0925-4005</issn><eissn>1873-3077</eissn><abstract>An enhanced time-delay neural network (TDNN), using time series sensor response data, improved pattern recognition ability of an electronic nose (e-nose) in discriminating four different spices. TDNN was used for analysis of e-nose time series sensor data from 0 to 4
min, while two popular pattern recognition methods, discriminant function analysis (DFA) and multilayer perceptron (MLP) trained by back-propagation, were used to analyze the “instantaneous” e-nose data obtained from sensor responses only at 4 min. The results showed that DFA and MLP correctly recognized 59.4 and 62.5% of the spices respectively while TDNN correctly recognized all (100%) spices.</abstract><pub>Elsevier B.V</pub><doi>10.1016/S0925-4005(03)00574-4</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0925-4005 |
| ispartof | Sensors and actuators. B, Chemical, 2003-11, Vol.96 (1), p.385-389 |
| issn | 0925-4005 1873-3077 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_27856127 |
| source | ScienceDirect Journals (5 years ago - present) |
| subjects | Electronic nose Multivariate statistics Neural network Pattern recognition |
| title | Improving pattern recognition of electronic nose data with time-delay neural networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T01%3A34%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improving%20pattern%20recognition%20of%20electronic%20nose%20data%20with%20time-delay%20neural%20networks&rft.jtitle=Sensors%20and%20actuators.%20B,%20Chemical&rft.au=Zhang,%20Haoxian&rft.date=2003-11-15&rft.volume=96&rft.issue=1&rft.spage=385&rft.epage=389&rft.pages=385-389&rft.issn=0925-4005&rft.eissn=1873-3077&rft_id=info:doi/10.1016/S0925-4005(03)00574-4&rft_dat=%3Cproquest_cross%3E19226227%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=19226227&rft_id=info:pmid/&rft_els_id=S0925400503005744&rfr_iscdi=true |