{"id":"https://openalex.org/W4404720546","doi":"https://doi.org/10.3390/info15120751","title":"Exploring the Impact of Image-Based Audio Representations in Classification Tasks Using Vision Transformers and Explainable AI Techniques","display_name":"Exploring the Impact of Image-Based Audio Representations in Classification Tasks Using Vision Transformers and Explainable AI Techniques","publication_year":2024,"publication_date":"2024-11-25","ids":{"openalex":"https://openalex.org/W4404720546","doi":"https://doi.org/10.3390/info15120751"},"language":"en","primary_location":{"id":"doi:10.3390/info15120751","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15120751","pdf_url":"https://www.mdpi.com/2078-2489/15/12/751/pdf?version=1732553467","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/15/12/751/pdf?version=1732553467","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011528836","display_name":"Sari Masri","orcid":"https://orcid.org/0009-0000-1592-2540"},"institutions":[{"id":"https://openalex.org/I53620714","display_name":"Arab American University","ror":"https://ror.org/04jmsq731","country_code":"PS","type":"education","lineage":["https://openalex.org/I53620714"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Sari Masri","raw_affiliation_strings":["Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine"],"raw_orcid":"https://orcid.org/0009-0000-1592-2540","affiliations":[{"raw_affiliation_string":"Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine","institution_ids":["https://openalex.org/I53620714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008566898","display_name":"Ahmad Hasasneh","orcid":"https://orcid.org/0000-0002-5794-928X"},"institutions":[{"id":"https://openalex.org/I53620714","display_name":"Arab American University","ror":"https://ror.org/04jmsq731","country_code":"PS","type":"education","lineage":["https://openalex.org/I53620714"]}],"countries":["PS"],"is_corresponding":true,"raw_author_name":"Ahmad Hasasneh","raw_affiliation_strings":["Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine","institution_ids":["https://openalex.org/I53620714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088796061","display_name":"Mohammad Abu Tami","orcid":"https://orcid.org/0009-0003-6634-157X"},"institutions":[{"id":"https://openalex.org/I53620714","display_name":"Arab American University","ror":"https://ror.org/04jmsq731","country_code":"PS","type":"education","lineage":["https://openalex.org/I53620714"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Mohammad Tami","raw_affiliation_strings":["Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine"],"raw_orcid":"https://orcid.org/0009-0003-6634-157X","affiliations":[{"raw_affiliation_string":"Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine","institution_ids":["https://openalex.org/I53620714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058606862","display_name":"Chakib Tadj","orcid":"https://orcid.org/0000-0002-3322-4882"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chakib Tadj","raw_affiliation_strings":["Department of Electrical Engineering, \u00c9cole de Technologie Sup\u00e9rieur, Universit\u00e9 du Qu\u00e9bec, Montreal, QC H3C 1K3, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3322-4882","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, \u00c9cole de Technologie Sup\u00e9rieur, Universit\u00e9 du Qu\u00e9bec, Montreal, QC H3C 1K3, Canada","institution_ids":["https://openalex.org/I9736820","https://openalex.org/I159129438"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008566898"],"corresponding_institution_ids":["https://openalex.org/I53620714"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.8881,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88278912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"15","issue":"12","first_page":"751","last_page":"751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9065999984741211,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9065999984741211,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6628241539001465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6023578643798828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5877716541290283},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5480189919471741},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4425567388534546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3313502371311188},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2216881811618805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19756656885147095},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07748538255691528}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6628241539001465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6023578643798828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5877716541290283},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5480189919471741},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4425567388534546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3313502371311188},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2216881811618805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19756656885147095},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07748538255691528},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info15120751","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15120751","pdf_url":"https://www.mdpi.com/2078-2489/15/12/751/pdf?version=1732553467","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},{"id":"pmh:oai:espace2.etsmtl.ca:30460","is_oa":true,"landing_page_url":null,"pdf_url":"https://espace2.etsmtl.ca/id/eprint/30460/1/Tadj-C-2024-30460.pdf","source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Non \u00e9valu\u00e9 par les pairs"},{"id":"pmh:oai:doaj.org/article:e1b96dd50e6d466090b316b7bdd28abe","is_oa":true,"landing_page_url":"https://doaj.org/article/e1b96dd50e6d466090b316b7bdd28abe","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 15, Iss 12, p 751 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info15120751","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15120751","pdf_url":"https://www.mdpi.com/2078-2489/15/12/751/pdf?version=1732553467","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404720546.pdf","grobid_xml":"https://content.openalex.org/works/W4404720546.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1505110664","https://openalex.org/W2059652044","https://openalex.org/W2087618018","https://openalex.org/W2096623359","https://openalex.org/W2154473523","https://openalex.org/W2415655199","https://openalex.org/W2963451564","https://openalex.org/W2973136764","https://openalex.org/W3010510864","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3097973766","https://openalex.org/W3128592650","https://openalex.org/W3151130473","https://openalex.org/W3158129762","https://openalex.org/W3163243746","https://openalex.org/W3168467966","https://openalex.org/W3176196997","https://openalex.org/W3195830874","https://openalex.org/W4210663539","https://openalex.org/W4220754996","https://openalex.org/W4225871896","https://openalex.org/W4281383881","https://openalex.org/W4281712277","https://openalex.org/W4287022992","https://openalex.org/W4309603539","https://openalex.org/W4317838072","https://openalex.org/W4365135358","https://openalex.org/W4381137386","https://openalex.org/W4385800817","https://openalex.org/W4389401317","https://openalex.org/W4389422989","https://openalex.org/W4396511291"],"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":{"An":[0],"important":[1],"hurdle":[2],"in":[3,42,66,143,186],"medical":[4,187],"diagnostics":[5],"is":[6,105],"the":[7,43,78,89,95,112,149,164],"high-quality":[8],"and":[9,37,45,76,91,135,141,163,189],"interpretable":[10],"classification":[11,68,183],"of":[12,23,47,53,70,86,151,156,197],"audio":[13,26,114,182],"signals.":[14],"In":[15],"this":[16,48,172],"study,":[17],"we":[18],"present":[19],"an":[20,84,194],"image-based":[21],"representation":[22],"infant":[24,31],"crying":[25],"files":[27],"to":[28,138,168],"predict":[29],"abnormal":[30],"cries":[32],"using":[33],"a":[34,67,178],"vision":[35,100],"transformer":[36,101,116],"also":[38],"show":[39],"significant":[40],"improvements":[41],"performance":[44,79],"interpretability":[46],"computer-aided":[49],"tool.":[50],"The":[51,154],"use":[52],"advanced":[54],"feature":[55],"extraction":[56],"techniques":[57,123],"such":[58,124],"as":[59,125,177],"Gammatone":[60],"Frequency":[61],"Cepstral":[62],"Coefficients":[63],"(GFCCs)":[64],"resulted":[65],"accuracy":[69,85,93,155],"96.33%.":[71],"For":[72],"other":[73],"features":[74],"(spectrogram":[75],"mel-spectrogram),":[77],"was":[80,158],"very":[81],"similar,":[82],"with":[83],"93.17%":[87],"for":[88,94,181,193],"spectrogram":[90,115],"94.83%":[92],"mel-spectrogram.":[96],"We":[97,118],"used":[98],"our":[99],"(ViT)":[102],"model,":[103],"which":[104,145],"less":[106],"complex":[107],"but":[108],"more":[109],"effective":[110],"than":[111,160],"proposed":[113],"(AST).":[117],"incorporated":[119],"explainable":[120],"AI":[121],"(XAI)":[122],"Layer-wise":[126],"Relevance":[127],"Propagation":[128],"(LRP),":[129],"Local":[130],"Interpretable":[131],"Model-agnostic":[132],"Explanations":[133],"(LIME),":[134],"attention":[136],"mechanisms":[137],"ensure":[139],"transparency":[140],"reliability":[142],"decision-making,":[144],"helped":[146],"us":[147],"understand":[148],"why":[150],"model":[152],"predictions.":[153],"detection":[157],"higher":[159],"previously":[161],"reported":[162],"results":[165],"were":[166],"easy":[167],"interpret,":[169],"demonstrating":[170],"that":[171],"work":[173],"can":[174],"potentially":[175],"serve":[176],"new":[179],"benchmark":[180],"tasks,":[184],"especially":[185],"diagnostics,":[188],"providing":[190],"better":[191],"prospects":[192],"imminent":[195],"future":[196],"trustworthy":[198],"AI-based":[199],"healthcare":[200],"solutions.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
