Improving underwater localization accuracy with machine learning
Machine learning classification and regression algorithms were applied to calibrate the localization errors of a time-difference-of-arrival (TDOA)-based acoustic sensor array used for tracking salmon passage through a hydroelectric dam on the Snake River, Washington, USA. The locations of stationary...
Gespeichert in:
Veröffentlicht in: | Review of scientific instruments 2018-07, Vol.89 (7), p.074902-074902 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 074902 |
---|---|
container_issue | 7 |
container_start_page | 074902 |
container_title | Review of scientific instruments |
container_volume | 89 |
creator | Rauchenstein, Lynn T. Vishnu, Abhinav Li, Xinya Deng, Zhiqun Daniel |
description | Machine learning classification and regression algorithms were applied to calibrate the localization errors of a time-difference-of-arrival (TDOA)-based acoustic sensor array used for tracking salmon passage through a hydroelectric dam on the Snake River, Washington, USA. The locations of stationary and mobile acoustic tags were first tracked using the approximate maximum likelihood algorithm. Next, ensembles of classification trees successfully identified and filtered data points with large localization errors. This prefiltering step allowed the creation of a machine-learned regression model function, which decreased the median distance error by 50% for the stationary tracks and by 34% for the mobile tracks. It also extended the previous range of sub-meter localization accuracy from 100 m to 250 m horizontal distance from the dam face (the receivers). Median distance errors in the depth direction were especially decreased, falling from 0.49 m to 0.04 m in the stationary tracks and from 0.38 m to 0.07 m in the mobile tracks. These methods would have application to the calibration of error in any TDOA-based sensor network with a steady environment and array configuration. |
doi_str_mv | 10.1063/1.5012687 |
format | Article |
fullrecord | <record><control><sourceid>proquest_osti_</sourceid><recordid>TN_cdi_proquest_miscellaneous_2082092725</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2082092725</sourcerecordid><originalsourceid>FETCH-LOGICAL-c445t-25877743b98fc94e8a5e0067860b26eb6ab7cbde20a47faff350851cfd4051273</originalsourceid><addsrcrecordid>eNp90MtKxDAUBuAgio6XhS8gRTcqVHNPZqeINxDc6DqkaepE2mRM2hF9ejPOqKBgNtl8-XPOD8AugicIcnKKThhEmEuxAkYIynEpOCarYAQhoSUXVG6AzZSeYT4MoXWwQSDkEmE6Ame33TSGmfNPxeBrG191b2PRBqNb9657F3yhjRmiNm_Fq-snRafNxHlbtFZHn59tg7VGt8nuLO8t8Hh1-XBxU97dX99enN-VhlLWl5hJIQQl1Vg2Zkyt1MzmIYTksMLcVlxXwlS1xVBT0eimIQxKhkxT0zwzFmQL7C9yQ-qdSsb11kxM8N6aXiGGKaY0o8MFyju9DDb1qnPJ2LbV3oYhKQwlhmMsMMv04Bd9DkP0eYW5EpyQXF5WRwtlYkgp2kZNo-t0fFMIqnn3Cqll99nuLROHqrP1t_wqO4PjBZhP_9ntt5mF-JOkpnXzH_779QdIm5hv</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2087633034</pqid></control><display><type>article</type><title>Improving underwater localization accuracy with machine learning</title><source>AIP Journals Complete</source><source>Alma/SFX Local Collection</source><creator>Rauchenstein, Lynn T. ; Vishnu, Abhinav ; Li, Xinya ; Deng, Zhiqun Daniel</creator><creatorcontrib>Rauchenstein, Lynn T. ; Vishnu, Abhinav ; Li, Xinya ; Deng, Zhiqun Daniel ; Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)</creatorcontrib><description>Machine learning classification and regression algorithms were applied to calibrate the localization errors of a time-difference-of-arrival (TDOA)-based acoustic sensor array used for tracking salmon passage through a hydroelectric dam on the Snake River, Washington, USA. The locations of stationary and mobile acoustic tags were first tracked using the approximate maximum likelihood algorithm. Next, ensembles of classification trees successfully identified and filtered data points with large localization errors. This prefiltering step allowed the creation of a machine-learned regression model function, which decreased the median distance error by 50% for the stationary tracks and by 34% for the mobile tracks. It also extended the previous range of sub-meter localization accuracy from 100 m to 250 m horizontal distance from the dam face (the receivers). Median distance errors in the depth direction were especially decreased, falling from 0.49 m to 0.04 m in the stationary tracks and from 0.38 m to 0.07 m in the mobile tracks. These methods would have application to the calibration of error in any TDOA-based sensor network with a steady environment and array configuration.</description><identifier>ISSN: 0034-6748</identifier><identifier>EISSN: 1089-7623</identifier><identifier>DOI: 10.1063/1.5012687</identifier><identifier>PMID: 30068124</identifier><identifier>CODEN: RSINAK</identifier><language>eng</language><publisher>United States: American Institute of Physics</publisher><subject>acoustic sensors ; Algorithms ; Artificial intelligence ; Classification ; Damsites ; Data points ; Error detection ; Hydroelectric dams ; hydrophone ; Localization ; Machine learning ; OTHER INSTRUMENTATION ; power plants ; regression analysis ; Regression models ; Salmon ; Scientific apparatus & instruments ; Sensor arrays ; signal processing ; sound-emitting devices ; speed of sound ; telemetry ; water transportation</subject><ispartof>Review of scientific instruments, 2018-07, Vol.89 (7), p.074902-074902</ispartof><rights>Author(s)</rights><rights>2018 Author(s). Published by AIP Publishing.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c445t-25877743b98fc94e8a5e0067860b26eb6ab7cbde20a47faff350851cfd4051273</citedby><cites>FETCH-LOGICAL-c445t-25877743b98fc94e8a5e0067860b26eb6ab7cbde20a47faff350851cfd4051273</cites><orcidid>0000000283008766</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubs.aip.org/rsi/article-lookup/doi/10.1063/1.5012687$$EHTML$$P50$$Gscitation$$H</linktohtml><link.rule.ids>230,314,778,782,792,883,4500,27913,27914,76143</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30068124$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://www.osti.gov/servlets/purl/1524244$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Rauchenstein, Lynn T.</creatorcontrib><creatorcontrib>Vishnu, Abhinav</creatorcontrib><creatorcontrib>Li, Xinya</creatorcontrib><creatorcontrib>Deng, Zhiqun Daniel</creatorcontrib><creatorcontrib>Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)</creatorcontrib><title>Improving underwater localization accuracy with machine learning</title><title>Review of scientific instruments</title><addtitle>Rev Sci Instrum</addtitle><description>Machine learning classification and regression algorithms were applied to calibrate the localization errors of a time-difference-of-arrival (TDOA)-based acoustic sensor array used for tracking salmon passage through a hydroelectric dam on the Snake River, Washington, USA. The locations of stationary and mobile acoustic tags were first tracked using the approximate maximum likelihood algorithm. Next, ensembles of classification trees successfully identified and filtered data points with large localization errors. This prefiltering step allowed the creation of a machine-learned regression model function, which decreased the median distance error by 50% for the stationary tracks and by 34% for the mobile tracks. It also extended the previous range of sub-meter localization accuracy from 100 m to 250 m horizontal distance from the dam face (the receivers). Median distance errors in the depth direction were especially decreased, falling from 0.49 m to 0.04 m in the stationary tracks and from 0.38 m to 0.07 m in the mobile tracks. These methods would have application to the calibration of error in any TDOA-based sensor network with a steady environment and array configuration.</description><subject>acoustic sensors</subject><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Classification</subject><subject>Damsites</subject><subject>Data points</subject><subject>Error detection</subject><subject>Hydroelectric dams</subject><subject>hydrophone</subject><subject>Localization</subject><subject>Machine learning</subject><subject>OTHER INSTRUMENTATION</subject><subject>power plants</subject><subject>regression analysis</subject><subject>Regression models</subject><subject>Salmon</subject><subject>Scientific apparatus & instruments</subject><subject>Sensor arrays</subject><subject>signal processing</subject><subject>sound-emitting devices</subject><subject>speed of sound</subject><subject>telemetry</subject><subject>water transportation</subject><issn>0034-6748</issn><issn>1089-7623</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNp90MtKxDAUBuAgio6XhS8gRTcqVHNPZqeINxDc6DqkaepE2mRM2hF9ejPOqKBgNtl8-XPOD8AugicIcnKKThhEmEuxAkYIynEpOCarYAQhoSUXVG6AzZSeYT4MoXWwQSDkEmE6Ame33TSGmfNPxeBrG191b2PRBqNb9657F3yhjRmiNm_Fq-snRafNxHlbtFZHn59tg7VGt8nuLO8t8Hh1-XBxU97dX99enN-VhlLWl5hJIQQl1Vg2Zkyt1MzmIYTksMLcVlxXwlS1xVBT0eimIQxKhkxT0zwzFmQL7C9yQ-qdSsb11kxM8N6aXiGGKaY0o8MFyju9DDb1qnPJ2LbV3oYhKQwlhmMsMMv04Bd9DkP0eYW5EpyQXF5WRwtlYkgp2kZNo-t0fFMIqnn3Cqll99nuLROHqrP1t_wqO4PjBZhP_9ntt5mF-JOkpnXzH_779QdIm5hv</recordid><startdate>20180701</startdate><enddate>20180701</enddate><creator>Rauchenstein, Lynn T.</creator><creator>Vishnu, Abhinav</creator><creator>Li, Xinya</creator><creator>Deng, Zhiqun Daniel</creator><general>American Institute of Physics</general><general>American Institute of Physics (AIP)</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>7X8</scope><scope>OIOZB</scope><scope>OTOTI</scope><orcidid>https://orcid.org/0000000283008766</orcidid></search><sort><creationdate>20180701</creationdate><title>Improving underwater localization accuracy with machine learning</title><author>Rauchenstein, Lynn T. ; Vishnu, Abhinav ; Li, Xinya ; Deng, Zhiqun Daniel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c445t-25877743b98fc94e8a5e0067860b26eb6ab7cbde20a47faff350851cfd4051273</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>acoustic sensors</topic><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Classification</topic><topic>Damsites</topic><topic>Data points</topic><topic>Error detection</topic><topic>Hydroelectric dams</topic><topic>hydrophone</topic><topic>Localization</topic><topic>Machine learning</topic><topic>OTHER INSTRUMENTATION</topic><topic>power plants</topic><topic>regression analysis</topic><topic>Regression models</topic><topic>Salmon</topic><topic>Scientific apparatus & instruments</topic><topic>Sensor arrays</topic><topic>signal processing</topic><topic>sound-emitting devices</topic><topic>speed of sound</topic><topic>telemetry</topic><topic>water transportation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rauchenstein, Lynn T.</creatorcontrib><creatorcontrib>Vishnu, Abhinav</creatorcontrib><creatorcontrib>Li, Xinya</creatorcontrib><creatorcontrib>Deng, Zhiqun Daniel</creatorcontrib><creatorcontrib>Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>MEDLINE - Academic</collection><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection><jtitle>Review of scientific instruments</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rauchenstein, Lynn T.</au><au>Vishnu, Abhinav</au><au>Li, Xinya</au><au>Deng, Zhiqun Daniel</au><aucorp>Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving underwater localization accuracy with machine learning</atitle><jtitle>Review of scientific instruments</jtitle><addtitle>Rev Sci Instrum</addtitle><date>2018-07-01</date><risdate>2018</risdate><volume>89</volume><issue>7</issue><spage>074902</spage><epage>074902</epage><pages>074902-074902</pages><issn>0034-6748</issn><eissn>1089-7623</eissn><coden>RSINAK</coden><abstract>Machine learning classification and regression algorithms were applied to calibrate the localization errors of a time-difference-of-arrival (TDOA)-based acoustic sensor array used for tracking salmon passage through a hydroelectric dam on the Snake River, Washington, USA. The locations of stationary and mobile acoustic tags were first tracked using the approximate maximum likelihood algorithm. Next, ensembles of classification trees successfully identified and filtered data points with large localization errors. This prefiltering step allowed the creation of a machine-learned regression model function, which decreased the median distance error by 50% for the stationary tracks and by 34% for the mobile tracks. It also extended the previous range of sub-meter localization accuracy from 100 m to 250 m horizontal distance from the dam face (the receivers). Median distance errors in the depth direction were especially decreased, falling from 0.49 m to 0.04 m in the stationary tracks and from 0.38 m to 0.07 m in the mobile tracks. These methods would have application to the calibration of error in any TDOA-based sensor network with a steady environment and array configuration.</abstract><cop>United States</cop><pub>American Institute of Physics</pub><pmid>30068124</pmid><doi>10.1063/1.5012687</doi><tpages>12</tpages><orcidid>https://orcid.org/0000000283008766</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0034-6748 |
ispartof | Review of scientific instruments, 2018-07, Vol.89 (7), p.074902-074902 |
issn | 0034-6748 1089-7623 |
language | eng |
recordid | cdi_proquest_miscellaneous_2082092725 |
source | AIP Journals Complete; Alma/SFX Local Collection |
subjects | acoustic sensors Algorithms Artificial intelligence Classification Damsites Data points Error detection Hydroelectric dams hydrophone Localization Machine learning OTHER INSTRUMENTATION power plants regression analysis Regression models Salmon Scientific apparatus & instruments Sensor arrays signal processing sound-emitting devices speed of sound telemetry water transportation |
title | Improving underwater localization accuracy with machine learning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T09%3A55%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improving%20underwater%20localization%20accuracy%20with%20machine%20learning&rft.jtitle=Review%20of%20scientific%20instruments&rft.au=Rauchenstein,%20Lynn%20T.&rft.aucorp=Pacific%20Northwest%20National%20Laboratory%20(PNNL),%20Richland,%20WA%20(United%20States)&rft.date=2018-07-01&rft.volume=89&rft.issue=7&rft.spage=074902&rft.epage=074902&rft.pages=074902-074902&rft.issn=0034-6748&rft.eissn=1089-7623&rft.coden=RSINAK&rft_id=info:doi/10.1063/1.5012687&rft_dat=%3Cproquest_osti_%3E2082092725%3C/proquest_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2087633034&rft_id=info:pmid/30068124&rfr_iscdi=true |