{"id":"https://openalex.org/W7135171445","doi":"https://doi.org/10.1109/jiot.2026.3673750","title":"Diffusion Model-Based Data Augmentation With Mel Spectrogram for Automatic Modulation Recognition in Underwater Acoustic Communication","display_name":"Diffusion Model-Based Data Augmentation With Mel Spectrogram for Automatic Modulation Recognition in Underwater Acoustic Communication","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7135171445","doi":"https://doi.org/10.1109/jiot.2026.3673750"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2026.3673750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3673750","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-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/A5123732201","display_name":"Wenjie Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Huang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0003-0704-7012","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129043739","display_name":"Rong Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Fan","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6703-4844","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123775591","display_name":"Yishan Su","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yishan Su","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6958-0806","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26774565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"11","first_page":"23722","last_page":"23735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.3955000042915344,"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"}},"topics":[{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.3955000042915344,"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"}},{"id":"https://openalex.org/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.30970001220703125,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12131","display_name":"Wireless Signal Modulation Classification","score":0.056299999356269836,"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/spectrogram","display_name":"Spectrogram","score":0.8809000253677368},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.503600001335144},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.49160000681877136},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.487199991941452},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4699999988079071},{"id":"https://openalex.org/keywords/underwater-acoustics","display_name":"Underwater acoustics","score":0.4657000005245209},{"id":"https://openalex.org/keywords/underwater-acoustic-communication","display_name":"Underwater acoustic communication","score":0.42559999227523804}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8809000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836999893188477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5491999983787537},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4699999988079071},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C67467970","wikidata":"https://www.wikidata.org/wiki/Q1292425","display_name":"Underwater acoustics","level":3,"score":0.4657000005245209},{"id":"https://openalex.org/C169111936","wikidata":"https://www.wikidata.org/wiki/Q424098","display_name":"Underwater acoustic communication","level":3,"score":0.42559999227523804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.26919999718666077},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2026.3673750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3673750","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"modulation":[1,90],"recognition":[2],"(AMR)":[3],"in":[4,185],"underwater":[5],"acoustic":[6],"(UWA)":[7],"communications":[8],"is":[9,56,65,75],"limited":[10],"by":[11,142],"scarce":[12],"training":[13],"data":[14,37,152],"and":[15,24,92,128,136,146,160,166,182],"channel":[16,94],"impairments":[17],"such":[18],"as":[19,176],"multipath":[20],"propagation,":[21],"Doppler":[22],"shifts,":[23],"ambient":[25],"noise.":[26],"To":[27],"address":[28],"these":[29],"challenges,":[30],"we":[31],"propose":[32],"Mel-Diffusion,":[33],"a":[34,57,62,98,177],"diffusion":[35,59,107],"model\u2013based":[36],"augmentation":[38],"framework.":[39],"The":[40,51],"method":[41],"first":[42],"converts":[43],"time-domain":[44,80],"signals":[45],"into":[46,105],"Mel":[47],"spectrograms":[48],"for":[49,68,180],"preprocessing.":[50],"proposed":[52],"Mel-Diffusion":[53,87,133,175],"model,":[54],"which":[55],"DDPM-based":[58],"framework":[60],"with":[61],"Transformer":[63],"backbone,":[64],"then":[66],"applied":[67],"feature":[69],"enhancement.":[70],"Finally,":[71],"the":[72,79,106,126,129,154,164,172],"Griffin\u2013Lim":[73],"algorithm":[74],"used":[76],"to":[77,144],"reconstruct":[78],"signals.":[81],"Building":[82],"upon":[83],"this":[84],"processing":[85],"pipeline,":[86],"effectively":[88],"captures":[89],"features":[91],"latent":[93],"characteristics.":[95],"In":[96],"addition,":[97],"Depth-Wise\u2013PointWise":[99],"Feed":[100],"Forward":[101],"Network":[102],"(DPFFN)":[103],"integrated":[104],"model":[108,110],"reduces":[109],"complexity,":[111],"while":[112],"Denoising":[113],"Diffusion":[114],"Implicit":[115],"Model":[116],"(DDIM)":[117],"sampling":[118],"improves":[119],"computational":[120],"efficiency.":[121],"Experiments":[122],"on":[123,163],"datasets":[124],"from":[125],"reservoir":[127,165],"sea":[130,167],"demonstrate":[131],"that":[132],"generates":[134],"realistic":[135],"diverse":[137],"signals,":[138],"improving":[139],"AMR":[140,156,184],"accuracy":[141],"up":[143],"5.51%":[145],"5.27%":[147],"under":[148],"data-scarce":[149],"conditions.":[150],"After":[151],"augmentation,":[153],"highest":[155],"accuracies":[157],"reach":[158],"98.66%":[159],"95.81%,":[161],"respectively,":[162],"datasets.":[168],"These":[169],"results":[170],"highlight":[171],"effectiveness":[173],"of":[174],"practical":[178],"solution":[179],"accurate":[181],"robust":[183],"complex":[186],"UWA":[187],"environments.":[188]},"counts_by_year":[],"updated_date":"2026-05-23T06:10:36.450269","created_date":"2026-03-14T00:00:00"}