{"id":"https://openalex.org/W4400286658","doi":"https://doi.org/10.3390/rs16132442","title":"A Novel Multi-Feature Fusion Model Based on Pre-Trained Wav2vec 2.0 for Underwater Acoustic Target Recognition","display_name":"A Novel Multi-Feature Fusion Model Based on Pre-Trained Wav2vec 2.0 for Underwater Acoustic Target Recognition","publication_year":2024,"publication_date":"2024-07-03","ids":{"openalex":"https://openalex.org/W4400286658","doi":"https://doi.org/10.3390/rs16132442"},"language":"en","primary_location":{"id":"doi:10.3390/rs16132442","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16132442","pdf_url":"https://www.mdpi.com/2072-4292/16/13/2442/pdf?version=1720002462","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/16/13/2442/pdf?version=1720002462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109742314","display_name":"Zijun Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijun Pu","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027021820","display_name":"Qunfei Zhang","orcid":"https://orcid.org/0000-0003-4500-0779"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunfei Zhang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111122410","display_name":"Yangtao Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangtao Xue","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038915198","display_name":"Peican Zhu","orcid":"https://orcid.org/0000-0002-8389-1093"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peican Zhu","raw_affiliation_strings":["School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi\u2019an 710072, China","School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi'an 710072, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi\u2019an 710072, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi'an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102014288","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0001-5453-7346"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an 710072, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102014288"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":2.5366,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90145831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"16","issue":"13","first_page":"2442","last_page":"2442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.7262642979621887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5992547273635864},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47411563992500305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4722917675971985},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.45551058650016785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44450050592422485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42011046409606934},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.16501504182815552}],"concepts":[{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.7262642979621887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5992547273635864},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47411563992500305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722917675971985},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.45551058650016785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44450050592422485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42011046409606934},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.16501504182815552},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/rs16132442","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16132442","pdf_url":"https://www.mdpi.com/2072-4292/16/13/2442/pdf?version=1720002462","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6a70eed0ed0743a69c2bed835635e266","is_oa":true,"landing_page_url":"https://doaj.org/article/6a70eed0ed0743a69c2bed835635e266","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 16, Iss 13, p 2442 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/rs16132442","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16132442","pdf_url":"https://www.mdpi.com/2072-4292/16/13/2442/pdf?version=1720002462","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400286658.pdf","grobid_xml":"https://content.openalex.org/works/W4400286658.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W2466903746","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2910819494","https://openalex.org/W2920164921","https://openalex.org/W2967719571","https://openalex.org/W2979908286","https://openalex.org/W2980243535","https://openalex.org/W3036601975","https://openalex.org/W3087073077","https://openalex.org/W3118027028","https://openalex.org/W3136465594","https://openalex.org/W3156558703","https://openalex.org/W3158291757","https://openalex.org/W3167369733","https://openalex.org/W3170791017","https://openalex.org/W3176713826","https://openalex.org/W3178690912","https://openalex.org/W4205801124","https://openalex.org/W4210273080","https://openalex.org/W4285101935","https://openalex.org/W4290712918","https://openalex.org/W4291801713","https://openalex.org/W4292962639","https://openalex.org/W4295037267","https://openalex.org/W4308822662","https://openalex.org/W4309918509","https://openalex.org/W4313118584","https://openalex.org/W4313133614","https://openalex.org/W4313855655","https://openalex.org/W4320913149","https://openalex.org/W4323794421","https://openalex.org/W4365514660","https://openalex.org/W4376278471","https://openalex.org/W4381746030","https://openalex.org/W4385408259","https://openalex.org/W4385444203","https://openalex.org/W4388204522","https://openalex.org/W4388465379","https://openalex.org/W4390510266","https://openalex.org/W4390684568","https://openalex.org/W4390893022","https://openalex.org/W4391432318","https://openalex.org/W4391938812","https://openalex.org/W4398255119","https://openalex.org/W6739901393","https://openalex.org/W6780218876","https://openalex.org/W6848935649"],"related_works":["https://openalex.org/W4388412763","https://openalex.org/W1999583034","https://openalex.org/W3217214504","https://openalex.org/W3168963531","https://openalex.org/W2591930867","https://openalex.org/W2953138830","https://openalex.org/W2773822314","https://openalex.org/W3176162126","https://openalex.org/W2891537746","https://openalex.org/W4386159726"],"abstract_inverted_index":{"Although":[0],"recent":[1],"data-driven":[2],"Underwater":[3],"Acoustic":[4],"Target":[5],"Recognition":[6],"(UATR)":[7],"methods":[8],"have":[9,32],"played":[10],"a":[11,87],"dominant":[12],"role":[13],"in":[14,37],"marine":[15],"acoustics,":[16],"they":[17],"suffer":[18],"from":[19],"complex":[20],"ocean":[21],"environments":[22],"and":[23,54,121,155,165],"rather":[24],"small":[25],"datasets.":[26],"To":[27],"tackle":[28],"such":[29],"challenges,":[30],"researchers":[31],"resorted":[33],"to":[34,40,66,76,139,167,195,198],"transfer":[35],"learning":[36],"an":[38],"effort":[39],"fulfill":[41],"UATR":[42,82,89,231],"tasks.":[43],"However,":[44],"existing":[45],"pre-trained":[46,100],"models":[47,75],"are":[48,55],"trained":[49,191],"on":[50,70,192,205,229],"audio":[51],"speech":[52,193],"data,":[53,194],"not":[56],"suitable":[57,79],"for":[58,80,107],"underwater":[59,199],"acoustic":[60,200],"data.":[61,201],"Therefore,":[62],"it":[63],"is":[64,190],"necessary":[65],"make":[67,77],"further":[68],"optimization":[69],"the":[71,81,110,128,133,148,156,170,174,179,203,206,224,230],"basis":[72],"of":[73,114,217,226],"these":[74],"them":[78],"task.":[83,232],"Here,":[84],"we":[85],"propose":[86],"novel":[88],"framework":[90],"called":[91],"Attention":[92,124],"Layer":[93],"Supplement":[94],"Integration":[95],"(ALSI),":[96],"which":[97,189],"integrates":[98],"large":[99],"neural":[101],"networks":[102],"with":[103,173],"customized":[104],"attention":[105,180],"modules":[106],"acoustic.":[108],"Specifically,":[109],"ALSI":[111],"model":[112,212,228],"consists":[113],"two":[115],"important":[116,142],"modules,":[117],"namely":[118],"Scale":[119,129,161],"ResNet":[120,130,162],"Residual":[122],"Hybrid":[123],"Fusion":[125],"(RHAF).":[126],"First,":[127],"module":[131,184],"takes":[132,147],"Constant-Q":[134],"transform":[135],"feature":[136,150,158,176],"as":[137,163],"input":[138,164],"obtain":[140],"relatively":[141],"frequency":[143,157],"information.":[144],"Next,":[145],"RHAF":[146,183],"temporal":[149,175],"extracted":[151,159],"by":[152,160,177],"wav2vec":[153,187],"2.0":[154],"aims":[166],"better":[168,196],"integrate":[169],"time\u2013frequency":[171],"features":[172],"using":[178],"mechanism.":[181],"The":[182],"can":[185,213],"help":[186],"2.0,":[188],"adapt":[197],"Finally,":[202],"experiments":[204,222],"ShipsEar":[207],"dataset":[208],"demonstrated":[209],"that":[210],"our":[211,227],"achieve":[214],"recognition":[215],"accuracy":[216],"96.39%.":[218],"In":[219],"conclusion,":[220],"extensive":[221],"confirm":[223],"effectiveness":[225]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-10-10T00:00:00"}
