{"id":"https://openalex.org/W3114692355","doi":"https://doi.org/10.1109/ictc49870.2020.9289578","title":"Acoustic Feature based Abnormal Diagnosis Techniques with Capsule Networks","display_name":"Acoustic Feature based Abnormal Diagnosis Techniques with Capsule Networks","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3114692355","doi":"https://doi.org/10.1109/ictc49870.2020.9289578","mag":"3114692355"},"language":"en","primary_location":{"id":"doi:10.1109/ictc49870.2020.9289578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc49870.2020.9289578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","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/A5087454446","display_name":"Nac\u2010Woo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"NacWoo Kim","raw_affiliation_strings":["Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101765146","display_name":"Hyun-Yong Lee","orcid":"https://orcid.org/0000-0002-0615-4241"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"HyunYong Lee","raw_affiliation_strings":["Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690662","display_name":"Sangjun Park","orcid":"https://orcid.org/0000-0003-4975-042X"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SangJun Park","raw_affiliation_strings":["Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027992420","display_name":"Jungi Lee","orcid":"https://orcid.org/0000-0003-4633-0737"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"JunGi Lee","raw_affiliation_strings":["Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000650888","display_name":"Byung\u2010Tak Lee","orcid":"https://orcid.org/0000-0003-1372-4561"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"ByungTak Lee","raw_affiliation_strings":["Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Honam Research Center (HRC), Electronics and Telecommunications Research Institute (ETRI), Gwangju, Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087454446"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46418697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"1147","last_page":"1149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9919999837875366,"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/feature-extraction","display_name":"Feature extraction","score":0.6635124683380127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6626508235931396},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.6395630836486816},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5977879166603088},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5873926281929016},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5701623558998108},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5682854652404785},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5445111989974976},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5316016674041748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4440467655658722},{"id":"https://openalex.org/keywords/capsule","display_name":"Capsule","score":0.4284461438655853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40776562690734863},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14717984199523926}],"concepts":[{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6635124683380127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6626508235931396},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.6395630836486816},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5977879166603088},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5873926281929016},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5701623558998108},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5682854652404785},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5445111989974976},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5316016674041748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4440467655658722},{"id":"https://openalex.org/C2778778583","wikidata":"https://www.wikidata.org/wiki/Q147768","display_name":"Capsule","level":2,"score":0.4284461438655853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40776562690734863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14717984199523926},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":1,"locations":[{"id":"doi:10.1109/ictc49870.2020.9289578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc49870.2020.9289578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W1637570796","https://openalex.org/W2038484192","https://openalex.org/W2889018940","https://openalex.org/W2889943009","https://openalex.org/W2897282582","https://openalex.org/W2936113082","https://openalex.org/W2963703618","https://openalex.org/W2965481041","https://openalex.org/W2967031846","https://openalex.org/W2979923697","https://openalex.org/W6600115225","https://openalex.org/W6636885848","https://openalex.org/W6743446608"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W4317383455","https://openalex.org/W2548511587"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"new":[4],"method":[5],"of":[6,19,100],"converting":[7],"acoustical":[8],"data":[9,75],"into":[10],"mel-frequency":[11,36],"cepstral":[12,37],"coefficient":[13,38],"feature":[14,45],"vector":[15],"and":[16,42,76],"performing":[17],"detection":[18,96],"abnormal":[20,43,84,95],"acoustics":[21],"using":[22,49],"newly":[23],"designed":[24],"capsule":[25,50,86],"network.":[26],"Characteristic":[27],"performance":[28,48,91],"tests":[29],"for":[30,73,80],"extracting":[31],"optimal":[32],"acoustic":[33,44],"characteristics":[34,79],"through":[35],"are":[39],"first":[40],"performed,":[41],"extraction":[46],"model":[47,88],"network":[51,55,66,87],"is":[52],"tested.":[53],"Capsule":[54],"requires":[56],"relatively":[57],"fewer":[58],"training":[59],"sets":[60],"compared":[61,92],"to":[62,93],"the":[63],"convolutional":[64],"neural":[65],"model,":[67],"but":[68],"it":[69],"has":[70,77],"equivariance":[71],"properties":[72],"learning":[74],"strong":[78],"affine":[81],"transformations.":[82],"Our":[83],"detection-based":[85],"shows":[89],"superior":[90],"other":[94],"models":[97],"in":[98],"terms":[99],"accuracy.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}