{"id":"https://openalex.org/W3107683761","doi":"https://doi.org/10.1109/iicaiet49801.2020.9257865","title":"Acoustic Event Detection with MobileNet and 1D-Convolutional Neural Network","display_name":"Acoustic Event Detection with MobileNet and 1D-Convolutional Neural Network","publication_year":2020,"publication_date":"2020-09-26","ids":{"openalex":"https://openalex.org/W3107683761","doi":"https://doi.org/10.1109/iicaiet49801.2020.9257865","mag":"3107683761"},"language":"en","primary_location":{"id":"doi:10.1109/iicaiet49801.2020.9257865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iicaiet49801.2020.9257865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","raw_type":"proceedings-article"},"type":"article","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/A5018784339","display_name":"Pooi Shiang Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Pooi Shiang Tan","raw_affiliation_strings":["Faculty of Information & Technology, Multimedia University, Melaka, Malaysia","Multimedia University,Faculty of Information & Technology,Melaka,Malaysia,75450"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information & Technology, Multimedia University, Melaka, Malaysia","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"Multimedia University,Faculty of Information & Technology,Melaka,Malaysia,75450","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017532046","display_name":"Kian Ming Lim","orcid":"https://orcid.org/0000-0003-1929-7978"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kian Ming Lim","raw_affiliation_strings":["Faculty of Information & Technology, Multimedia University, Melaka, Malaysia","Multimedia University,Faculty of Information & Technology,Melaka,Malaysia,75450"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information & Technology, Multimedia University, Melaka, Malaysia","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"Multimedia University,Faculty of Information & Technology,Melaka,Malaysia,75450","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086127398","display_name":"Chin Poo Lee","orcid":"https://orcid.org/0000-0003-3679-8977"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Chin Poo Lee","raw_affiliation_strings":["Faculty of Information & Technology, Multimedia University, Melaka, Malaysia","Multimedia University,Faculty of Information & Technology,Melaka,Malaysia,75450"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information & Technology, Multimedia University, Melaka, Malaysia","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"Multimedia University,Faculty of Information & Technology,Melaka,Malaysia,75450","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006047624","display_name":"Cheah Heng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I14637135","display_name":"Motorola (South Korea)","ror":"https://ror.org/00y09zk14","country_code":"KR","type":"company","lineage":["https://openalex.org/I1333370159","https://openalex.org/I14637135"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Cheah Heng Tan","raw_affiliation_strings":["Motorola Solutions Malaysia Sdn. Bhd., Pulau, Pinang, Malaysia","Motorola Solutions Malaysia Sdn. Bhd.,Pulau,Pinang,Malaysia,11900"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola Solutions Malaysia Sdn. Bhd., Pulau, Pinang, Malaysia","institution_ids":["https://openalex.org/I14637135"]},{"raw_affiliation_string":"Motorola Solutions Malaysia Sdn. Bhd.,Pulau,Pinang,Malaysia,11900","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6083,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68118967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spectrogram","display_name":"Spectrogram","score":0.9513981938362122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7511152625083923},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7278527021408081},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6852689981460571},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.645129919052124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5390083193778992},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5382935404777527},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5317790508270264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.508920431137085},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4921833574771881},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.45664119720458984},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.4367865025997162},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.431335985660553},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.36785998940467834},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36114561557769775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24427935481071472},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07056215405464172}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9513981938362122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511152625083923},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7278527021408081},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6852689981460571},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.645129919052124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5390083193778992},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5382935404777527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5317790508270264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.508920431137085},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4921833574771881},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.45664119720458984},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.4367865025997162},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.431335985660553},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.36785998940467834},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36114561557769775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24427935481071472},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07056215405464172},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.1109/iicaiet49801.2020.9257865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iicaiet49801.2020.9257865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","raw_type":"proceedings-article"},{"id":"pmh:oai:shdl.mmu.edu.my:8056","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/9257865","pdf_url":null,"source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1533561824","https://openalex.org/W1836465849","https://openalex.org/W2034215399","https://openalex.org/W2038484192","https://openalex.org/W2063491684","https://openalex.org/W2065529590","https://openalex.org/W2074764925","https://openalex.org/W2092318512","https://openalex.org/W2101949174","https://openalex.org/W2105068979","https://openalex.org/W2125324924","https://openalex.org/W2165320399","https://openalex.org/W2341412280","https://openalex.org/W2407542046","https://openalex.org/W2509065397","https://openalex.org/W2571520038","https://openalex.org/W2612445135","https://openalex.org/W2763761345","https://openalex.org/W2884011836","https://openalex.org/W2889351461","https://openalex.org/W2949117887","https://openalex.org/W2963158330","https://openalex.org/W3096841046","https://openalex.org/W3098357269","https://openalex.org/W4289329167","https://openalex.org/W4297775537","https://openalex.org/W6632323398","https://openalex.org/W6678788828","https://openalex.org/W6684354967","https://openalex.org/W6785333363"],"related_works":["https://openalex.org/W3128220493","https://openalex.org/W4298017035","https://openalex.org/W3026913501","https://openalex.org/W2792147139","https://openalex.org/W4226354336","https://openalex.org/W3110700750","https://openalex.org/W2998675825","https://openalex.org/W4318954401","https://openalex.org/W2736804899","https://openalex.org/W2897443685"],"abstract_inverted_index":{"Sound":[0],"waves":[1],"are":[2,42,173,230],"a":[3,9,119,142,164,176,200],"form":[4],"of":[5,183,186],"energy":[6],"produced":[7],"by":[8,128],"vibrating":[10],"object":[11],"that":[12,17,45],"travels":[13],"through":[14],"the":[15,22,43,48,78,91,104,125,130,135,206,236,239],"medium":[16],"can":[18],"be":[19],"heard.":[20],"Generally,":[21],"sound":[23,79],"is":[24,58,74,122,139,160,195,209,223],"used":[25],"in":[26,47],"human":[27],"communication,":[28],"music,":[29],"alert,":[30],"and":[31,50,114,188,197,221,233,245,251],"so":[32],"on.":[33],"Furthermore,":[34],"it":[35],"also":[36,85],"helps":[37],"us":[38,53],"to":[39,55,66,89,146,162,204,211],"understand":[40,56,71],"what":[41,57,72],"events":[44],"occurring":[46,75],"moment,":[49],"thereby,":[51],"provide":[52],"hints":[54],"happening":[59],"around":[60],"us.":[61],"This":[62,100],"has":[63],"prompt":[64],"researchers":[65,84],"study":[67,86,101],"on":[68,77,87,103],"how":[69,88],"humans":[70],"event":[73,98,106,168],"based":[76],"waves.":[80],"In":[81,151],"recent":[82],"years,":[83],"equip":[90],"machine":[92],"with":[93,218,226],"this":[94,152],"ability,":[95],"i.e.":[96],"acoustic":[97,105,126,167],"detection.":[99,169],"focuses":[102],"detection":[107],"which":[108,229],"leverage":[109],"both":[110],"frequency":[111,131,137,216],"spectrogram":[112,120,132,138,217],"technique":[113],"deep":[115],"learning":[116],"methods.":[117],"Initially,":[118],"image":[121],"generated":[123,136],"from":[124,175],"data":[127],"using":[129],"technique.":[133],"Then,":[134],"fed":[140,198],"into":[141,199],"pre-trained":[143,177,219],"MobileNet":[144,220],"model":[145,165],"extract":[147],"robust":[148],"features":[149],"representations.":[150],"work,":[153],"1":[154],"Dimensional":[155],"Convolutional":[156],"Neural":[157],"Network":[158],"(1D-CNN)":[159],"adopted":[161],"train":[163],"for":[166,248],"The":[170,179,191,214],"feature":[171],"representations":[172],"extracted":[174],"MobileNet.":[178],"proposed":[180,215,240],"1D-CNN":[181,222],"consist":[182],"several":[184],"alternatives":[185],"convolution":[187],"pooling":[189,193],"layers.":[190],"last":[192],"layer":[194,203],"flattened":[196],"fully":[201],"connected":[202],"classify":[205],"events.":[207],"Dropout":[208],"employed":[210],"prevent":[212],"overfitting.":[213],"then":[224],"evaluated":[225],"three":[227],"datasets,":[228],"Soundscapes1,":[231,249],"Soundscapes2,":[232,250],"UrbanSound8k.":[234],"From":[235],"experimental":[237],"results,":[238],"method":[241],"obtained":[242],"81,":[243],"86,":[244],"70":[246],"F1-score,":[247],"UrbanSound8k,":[252],"respectively.":[253]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}