{"id":"https://openalex.org/W4391678024","doi":"https://doi.org/10.1109/sii58957.2024.10417712","title":"Ego-Noise Prediction Based on Multimodal Learning for Enhanced Discrimination in UAV Hammering Inspection","display_name":"Ego-Noise Prediction Based on Multimodal Learning for Enhanced Discrimination in UAV Hammering Inspection","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4391678024","doi":"https://doi.org/10.1109/sii58957.2024.10417712"},"language":"en","primary_location":{"id":"doi:10.1109/sii58957.2024.10417712","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sii58957.2024.10417712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049771306","display_name":"Koki Shoda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koki Shoda","raw_affiliation_strings":["Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Kashiwa, Chiba,Japan,277-8563"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Kashiwa, Chiba,Japan,277-8563","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051800939","display_name":"Jun Younes Louhi Kasahara","orcid":"https://orcid.org/0000-0002-5924-8858"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Younes Louhi Kasahara","raw_affiliation_strings":["Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Kashiwa, Chiba,Japan,277-8563"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Kashiwa, Chiba,Japan,277-8563","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064103302","display_name":"Hajime Asama","orcid":"https://orcid.org/0000-0002-9482-497X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hajime Asama","raw_affiliation_strings":["Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Kashiwa, Chiba,Japan,277-8563"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo,Department of Precision Engineering,Kashiwa, Chiba,Japan,277-8563","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056335309","display_name":"Qi An","orcid":"https://orcid.org/0000-0001-7641-2632"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Qi An","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa, Chiba,Japan,277-8563"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa, Chiba,Japan,277-8563","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021260328","display_name":"Atsushi Yamashita","orcid":"https://orcid.org/0000-0003-1280-069X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Yamashita","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa, Chiba,Japan,277-8563"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo,Department of Human and Engineered Environmental Studies,Kashiwa, Chiba,Japan,277-8563","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"792","last_page":"797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11309","display_name":"Music and Audio Processing","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6373266577720642},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6338098645210266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5843376517295837},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5230544805526733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3333425521850586},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09338796138763428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373266577720642},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6338098645210266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5843376517295837},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5230544805526733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3333425521850586},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09338796138763428}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii58957.2024.10417712","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sii58957.2024.10417712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G1064255090","display_name":"Domain adaptation for acoustic inspection of concrete structures","funder_award_id":"21K17829","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2944295139","display_name":null,"funder_award_id":"JP21K17829","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2098463040","https://openalex.org/W2146421622","https://openalex.org/W2294801854","https://openalex.org/W2553033130","https://openalex.org/W2785365904","https://openalex.org/W2787822409","https://openalex.org/W2796538318","https://openalex.org/W2810132937","https://openalex.org/W3005641657","https://openalex.org/W3010950195","https://openalex.org/W3183803302","https://openalex.org/W3195556085","https://openalex.org/W4285507689","https://openalex.org/W4323338563","https://openalex.org/W6640212811","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,72,119],"propose":[4,73,120],"an":[5],"ego-noise":[6,29,36,78,88,101,116,129,141,153],"prediction":[7,37,79,138],"method":[8],"applicable":[9,56],"to":[10,26,57,126],"Unmanned":[11],"Aerial":[12],"Vehicles":[13],"(UAVs).":[14],"Sensing":[15],"sound":[16],"using":[17,121,131],"UAV":[18,163],"has":[19,47],"a":[20,74,104,112,122,135,145],"significantly":[21],"reduced":[22],"Signal-to-Noise":[23],"Ratio":[24],"due":[25],"the":[27,31,62,68,86,92,98,108,115,128,149,156],"strong":[28,105],"from":[30],"propellers":[32],"and":[33,90,114,155],"motors.":[34],"Template-based":[35],"for":[38,77,151,160],"robots":[39],"with":[40],"pre-set":[41],"movements,":[42],"such":[43],"as":[44,134],"humanoid":[45],"robots,":[46],"previously":[48],"been":[49],"studied.":[50],"However,":[51],"that":[52,147],"approach":[53],"is":[54],"not":[55],"UAVs":[58],"which":[59,84],"continuously":[60],"adjust":[61],"propeller's":[63],"rotation":[64],"speed":[65],"based":[66],"on":[67,82],"situational":[69],"requirements.":[70],"Here,":[71],"novel":[75],"framework":[76],"by":[80],"focusing":[81],"propellers,":[83],"are":[85,158],"main":[87],"source,":[89],"translating":[91],"modality":[93,99],"of":[94,100,111,140],"propeller":[95,113],"vibrations":[96],"into":[97],"sound.":[102],"Assuming":[103],"relation":[106],"between":[107],"vibration":[109,132],"frequency":[110,133],"it":[117],"generates,":[118],"Recurrent":[123],"Neural":[124],"Network":[125],"predict":[127],"spectrogram,":[130],"feature.":[136],"The":[137],"accuracy":[139],"spectrograms":[142],"was":[143],"at":[144],"level":[146],"suggests":[148],"potential":[150],"effective":[152],"reduction,":[154],"results":[157],"promising":[159],"applications":[161],"in":[162],"hammering":[164],"inspection.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}