An automatic acoustic bat identification system based on the audible spectrum
•Recognition of bat locutions obtained automatically from a long recording.•New method of conversion of the locutions to the audible band.•Noise-free spectrogram images.•97.3% of correct rate classification for 7 classes. Nowadays the task of monitoring bat species is a very difficult task because o...
Gespeichert in:
| Veröffentlicht in: | Expert systems with applications 2014-09, Vol.41 (11), p.5451-5465 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 5465 |
|---|---|
| container_issue | 11 |
| container_start_page | 5451 |
| container_title | Expert systems with applications |
| container_volume | 41 |
| creator | Henríquez, Aarón Alonso, Jesús B. Travieso, Carlos M. Rodríguez-Herrera, Bernal Bolaños, Federico Alpízar, Priscilla López-de-Ipina, Karmele Henríquez, Patricia |
| description | •Recognition of bat locutions obtained automatically from a long recording.•New method of conversion of the locutions to the audible band.•Noise-free spectrogram images.•97.3% of correct rate classification for 7 classes.
Nowadays the task of monitoring bat species is a very difficult task because of several factors. The main ones are the difficulty of creating databases automatically and the particularities of the vocalizations of bats. For this reason, it is common to extract bat calls manually from a recording and treat them individually. We propose a new form of identification and labeling process based on adapting bat calls to the audible spectrum and significantly reducing the noise of its spectrogram. This process can be performed automatically from a recording made in a natural area. Our database consists of 189h of recordings obtained in various natural areas in Costa Rica. 50 bats calls of 7 different classes are extracted from this database. We have obtained an average error of 2.7% and 3 of the 7 classes have an error below 1%. |
| doi_str_mv | 10.1016/j.eswa.2014.02.021 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1677997406</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0957417414000840</els_id><sourcerecordid>1567059078</sourcerecordid><originalsourceid>FETCH-LOGICAL-c396t-fc79516c1b9bfebb6df01e05f5fc5ae5fa9006f3abaf86a7d4665d0613e3737e3</originalsourceid><addsrcrecordid>eNqFkE1LAzEQhoMoWD_-gKe9CF62TjabZANeivgFFS96DtnsBFP2oyap4r83pcWjwkAS5nlnyEPIBYU5BSquV3OMX2ZeAa3nUOWiB2RGG8lKIRU7JDNQXJY1lfUxOYlxBUAlgJyR58VYmE2aBpO8LYydNnF7aU0qfIdj8s7b3JrGIn7HhEPuROyK_E7vmJOdb3ss4hptCpvhjBw500c835-n5O3-7vX2sVy-PDzdLpalZUqk0lmpOBWWtqp12Laic0ARuOPOcoPcGQUgHDOtcY0wsquF4B0IypBJJpGdkqvd3HWYPjYYkx58tNj3ZsT8A02FlErJGsT_KBcSuALZZLTaoTZMMQZ0eh38YMK3pqC3mvVKbzXrrWYNVS6aQ5f7-SZa07tgRuvjb7JqatZUssrczY7D7OXTY9DRehwtdj5kebqb_F9rfgCi0pPV</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1567059078</pqid></control><display><type>article</type><title>An automatic acoustic bat identification system based on the audible spectrum</title><source>Access via ScienceDirect (Elsevier)</source><creator>Henríquez, Aarón ; Alonso, Jesús B. ; Travieso, Carlos M. ; Rodríguez-Herrera, Bernal ; Bolaños, Federico ; Alpízar, Priscilla ; López-de-Ipina, Karmele ; Henríquez, Patricia</creator><creatorcontrib>Henríquez, Aarón ; Alonso, Jesús B. ; Travieso, Carlos M. ; Rodríguez-Herrera, Bernal ; Bolaños, Federico ; Alpízar, Priscilla ; López-de-Ipina, Karmele ; Henríquez, Patricia</creatorcontrib><description>•Recognition of bat locutions obtained automatically from a long recording.•New method of conversion of the locutions to the audible band.•Noise-free spectrogram images.•97.3% of correct rate classification for 7 classes.
Nowadays the task of monitoring bat species is a very difficult task because of several factors. The main ones are the difficulty of creating databases automatically and the particularities of the vocalizations of bats. For this reason, it is common to extract bat calls manually from a recording and treat them individually. We propose a new form of identification and labeling process based on adapting bat calls to the audible spectrum and significantly reducing the noise of its spectrogram. This process can be performed automatically from a recording made in a natural area. Our database consists of 189h of recordings obtained in various natural areas in Costa Rica. 50 bats calls of 7 different classes are extracted from this database. We have obtained an average error of 2.7% and 3 of the 7 classes have an error below 1%.</description><identifier>ISSN: 0957-4174</identifier><identifier>EISSN: 1873-6793</identifier><identifier>DOI: 10.1016/j.eswa.2014.02.021</identifier><language>eng</language><publisher>Amsterdam: Elsevier Ltd</publisher><subject>Acoustics ; Aeroacoustics, atmospheric sound ; Applied sciences ; Audio adaptation ; Bat identification ; Bats ; Computer science; control theory; systems ; Data processing. List processing. Character string processing ; Errors ; Exact sciences and technology ; Expert systems ; Feature extraction ; Fundamental areas of phenomenology (including applications) ; Memory organisation. Data processing ; Monitoring ; Physics ; Recording ; Software ; Spectrogram ; Spectrograms ; Tasks</subject><ispartof>Expert systems with applications, 2014-09, Vol.41 (11), p.5451-5465</ispartof><rights>2014 Elsevier Ltd</rights><rights>2015 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c396t-fc79516c1b9bfebb6df01e05f5fc5ae5fa9006f3abaf86a7d4665d0613e3737e3</citedby><cites>FETCH-LOGICAL-c396t-fc79516c1b9bfebb6df01e05f5fc5ae5fa9006f3abaf86a7d4665d0613e3737e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.eswa.2014.02.021$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=28438272$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Henríquez, Aarón</creatorcontrib><creatorcontrib>Alonso, Jesús B.</creatorcontrib><creatorcontrib>Travieso, Carlos M.</creatorcontrib><creatorcontrib>Rodríguez-Herrera, Bernal</creatorcontrib><creatorcontrib>Bolaños, Federico</creatorcontrib><creatorcontrib>Alpízar, Priscilla</creatorcontrib><creatorcontrib>López-de-Ipina, Karmele</creatorcontrib><creatorcontrib>Henríquez, Patricia</creatorcontrib><title>An automatic acoustic bat identification system based on the audible spectrum</title><title>Expert systems with applications</title><description>•Recognition of bat locutions obtained automatically from a long recording.•New method of conversion of the locutions to the audible band.•Noise-free spectrogram images.•97.3% of correct rate classification for 7 classes.
Nowadays the task of monitoring bat species is a very difficult task because of several factors. The main ones are the difficulty of creating databases automatically and the particularities of the vocalizations of bats. For this reason, it is common to extract bat calls manually from a recording and treat them individually. We propose a new form of identification and labeling process based on adapting bat calls to the audible spectrum and significantly reducing the noise of its spectrogram. This process can be performed automatically from a recording made in a natural area. Our database consists of 189h of recordings obtained in various natural areas in Costa Rica. 50 bats calls of 7 different classes are extracted from this database. We have obtained an average error of 2.7% and 3 of the 7 classes have an error below 1%.</description><subject>Acoustics</subject><subject>Aeroacoustics, atmospheric sound</subject><subject>Applied sciences</subject><subject>Audio adaptation</subject><subject>Bat identification</subject><subject>Bats</subject><subject>Computer science; control theory; systems</subject><subject>Data processing. List processing. Character string processing</subject><subject>Errors</subject><subject>Exact sciences and technology</subject><subject>Expert systems</subject><subject>Feature extraction</subject><subject>Fundamental areas of phenomenology (including applications)</subject><subject>Memory organisation. Data processing</subject><subject>Monitoring</subject><subject>Physics</subject><subject>Recording</subject><subject>Software</subject><subject>Spectrogram</subject><subject>Spectrograms</subject><subject>Tasks</subject><issn>0957-4174</issn><issn>1873-6793</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNqFkE1LAzEQhoMoWD_-gKe9CF62TjabZANeivgFFS96DtnsBFP2oyap4r83pcWjwkAS5nlnyEPIBYU5BSquV3OMX2ZeAa3nUOWiB2RGG8lKIRU7JDNQXJY1lfUxOYlxBUAlgJyR58VYmE2aBpO8LYydNnF7aU0qfIdj8s7b3JrGIn7HhEPuROyK_E7vmJOdb3ss4hptCpvhjBw500c835-n5O3-7vX2sVy-PDzdLpalZUqk0lmpOBWWtqp12Laic0ARuOPOcoPcGQUgHDOtcY0wsquF4B0IypBJJpGdkqvd3HWYPjYYkx58tNj3ZsT8A02FlErJGsT_KBcSuALZZLTaoTZMMQZ0eh38YMK3pqC3mvVKbzXrrWYNVS6aQ5f7-SZa07tgRuvjb7JqatZUssrczY7D7OXTY9DRehwtdj5kebqb_F9rfgCi0pPV</recordid><startdate>20140901</startdate><enddate>20140901</enddate><creator>Henríquez, Aarón</creator><creator>Alonso, Jesús B.</creator><creator>Travieso, Carlos M.</creator><creator>Rodríguez-Herrera, Bernal</creator><creator>Bolaños, Federico</creator><creator>Alpízar, Priscilla</creator><creator>López-de-Ipina, Karmele</creator><creator>Henríquez, Patricia</creator><general>Elsevier Ltd</general><general>Elsevier</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20140901</creationdate><title>An automatic acoustic bat identification system based on the audible spectrum</title><author>Henríquez, Aarón ; Alonso, Jesús B. ; Travieso, Carlos M. ; Rodríguez-Herrera, Bernal ; Bolaños, Federico ; Alpízar, Priscilla ; López-de-Ipina, Karmele ; Henríquez, Patricia</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c396t-fc79516c1b9bfebb6df01e05f5fc5ae5fa9006f3abaf86a7d4665d0613e3737e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Acoustics</topic><topic>Aeroacoustics, atmospheric sound</topic><topic>Applied sciences</topic><topic>Audio adaptation</topic><topic>Bat identification</topic><topic>Bats</topic><topic>Computer science; control theory; systems</topic><topic>Data processing. List processing. Character string processing</topic><topic>Errors</topic><topic>Exact sciences and technology</topic><topic>Expert systems</topic><topic>Feature extraction</topic><topic>Fundamental areas of phenomenology (including applications)</topic><topic>Memory organisation. Data processing</topic><topic>Monitoring</topic><topic>Physics</topic><topic>Recording</topic><topic>Software</topic><topic>Spectrogram</topic><topic>Spectrograms</topic><topic>Tasks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Henríquez, Aarón</creatorcontrib><creatorcontrib>Alonso, Jesús B.</creatorcontrib><creatorcontrib>Travieso, Carlos M.</creatorcontrib><creatorcontrib>Rodríguez-Herrera, Bernal</creatorcontrib><creatorcontrib>Bolaños, Federico</creatorcontrib><creatorcontrib>Alpízar, Priscilla</creatorcontrib><creatorcontrib>López-de-Ipina, Karmele</creatorcontrib><creatorcontrib>Henríquez, Patricia</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Expert systems with applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Henríquez, Aarón</au><au>Alonso, Jesús B.</au><au>Travieso, Carlos M.</au><au>Rodríguez-Herrera, Bernal</au><au>Bolaños, Federico</au><au>Alpízar, Priscilla</au><au>López-de-Ipina, Karmele</au><au>Henríquez, Patricia</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An automatic acoustic bat identification system based on the audible spectrum</atitle><jtitle>Expert systems with applications</jtitle><date>2014-09-01</date><risdate>2014</risdate><volume>41</volume><issue>11</issue><spage>5451</spage><epage>5465</epage><pages>5451-5465</pages><issn>0957-4174</issn><eissn>1873-6793</eissn><abstract>•Recognition of bat locutions obtained automatically from a long recording.•New method of conversion of the locutions to the audible band.•Noise-free spectrogram images.•97.3% of correct rate classification for 7 classes.
Nowadays the task of monitoring bat species is a very difficult task because of several factors. The main ones are the difficulty of creating databases automatically and the particularities of the vocalizations of bats. For this reason, it is common to extract bat calls manually from a recording and treat them individually. We propose a new form of identification and labeling process based on adapting bat calls to the audible spectrum and significantly reducing the noise of its spectrogram. This process can be performed automatically from a recording made in a natural area. Our database consists of 189h of recordings obtained in various natural areas in Costa Rica. 50 bats calls of 7 different classes are extracted from this database. We have obtained an average error of 2.7% and 3 of the 7 classes have an error below 1%.</abstract><cop>Amsterdam</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.eswa.2014.02.021</doi><tpages>15</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0957-4174 |
| ispartof | Expert systems with applications, 2014-09, Vol.41 (11), p.5451-5465 |
| issn | 0957-4174 1873-6793 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1677997406 |
| source | Access via ScienceDirect (Elsevier) |
| subjects | Acoustics Aeroacoustics, atmospheric sound Applied sciences Audio adaptation Bat identification Bats Computer science control theory systems Data processing. List processing. Character string processing Errors Exact sciences and technology Expert systems Feature extraction Fundamental areas of phenomenology (including applications) Memory organisation. Data processing Monitoring Physics Recording Software Spectrogram Spectrograms Tasks |
| title | An automatic acoustic bat identification system based on the audible spectrum |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T20%3A27%3A41IST&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=An%20automatic%20acoustic%20bat%20identification%20system%20based%20on%20the%20audible%20spectrum&rft.jtitle=Expert%20systems%20with%20applications&rft.au=Henr%C3%ADquez,%20Aar%C3%B3n&rft.date=2014-09-01&rft.volume=41&rft.issue=11&rft.spage=5451&rft.epage=5465&rft.pages=5451-5465&rft.issn=0957-4174&rft.eissn=1873-6793&rft_id=info:doi/10.1016/j.eswa.2014.02.021&rft_dat=%3Cproquest_cross%3E1567059078%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=1567059078&rft_id=info:pmid/&rft_els_id=S0957417414000840&rfr_iscdi=true |