{"id":"https://openalex.org/W4415524302","doi":"https://doi.org/10.1109/mlsp62443.2025.11204285","title":"DDL: A Dataset for Drone Detection and Localization From Multi-Channel Audio and a Deep Uncertainty-Aware Framework","display_name":"DDL: A Dataset for Drone Detection and Localization From Multi-Channel Audio and a Deep Uncertainty-Aware Framework","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524302","doi":"https://doi.org/10.1109/mlsp62443.2025.11204285"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5086899221","display_name":"Saeid Safavi","orcid":"https://orcid.org/0000-0002-3000-418X"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Saeid Safavi","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087114343","display_name":"\u00d6zkan \u00c7AYLI","orcid":"https://orcid.org/0000-0002-3389-3867"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"\u00d6zkan \u00c7ayli","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028611929","display_name":"Mohammad Amin Safavi","orcid":"https://orcid.org/0000-0002-7258-0812"},"institutions":[{"id":"https://openalex.org/I1315649409","display_name":"Institute on Taxation and Economic Policy","ror":"https://ror.org/00w9dm031","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1315649409"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Amin Safavi","raw_affiliation_strings":["DeepX Inc,Japan"],"affiliations":[{"raw_affiliation_string":"DeepX Inc,Japan","institution_ids":["https://openalex.org/I1315649409"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110726071","display_name":"Ben Cook","orcid":null},"institutions":[{"id":"https://openalex.org/I884004202","display_name":"National Air Traffic Services (United Kingdom)","ror":"https://ror.org/012mvd861","country_code":"GB","type":"company","lineage":["https://openalex.org/I884004202"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Cook","raw_affiliation_strings":["Airspeed Electronics Ltd,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Airspeed Electronics Ltd,United Kingdom","institution_ids":["https://openalex.org/I884004202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I1315649409","display_name":"Institute on Taxation and Economic Policy","ror":"https://ror.org/00w9dm031","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1315649409"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["DeepX Inc,Japan"],"affiliations":[{"raw_affiliation_string":"DeepX Inc,Japan","institution_ids":["https://openalex.org/I1315649409"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086899221"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17000501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9679999947547913,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9679999947547913,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9605000019073486,"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"}},{"id":"https://openalex.org/T12597","display_name":"Fire Detection and Safety Systems","score":0.9412000179290771,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.9506000280380249},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5856999754905701},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5394999980926514},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.47530001401901245},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.40630000829696655},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.39149999618530273},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38839998841285706},{"id":"https://openalex.org/keywords/euclidean-geometry","display_name":"Euclidean geometry","score":0.35519999265670776}],"concepts":[{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.9506000280380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6500999927520752},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5856999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745999813079834},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38190001249313354},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C101104100","wikidata":"https://www.wikidata.org/wiki/Q1063540","display_name":"Heteroscedasticity","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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":8,"referenced_works":["https://openalex.org/W2082040042","https://openalex.org/W2103235956","https://openalex.org/W2566935005","https://openalex.org/W2612395950","https://openalex.org/W2749920848","https://openalex.org/W2964059111","https://openalex.org/W3097777922","https://openalex.org/W4205221070"],"related_works":[],"abstract_inverted_index":{"Due":[0],"to":[1,16,39,99],"the":[2,17,30,105,136,152],"widespread":[3],"use":[4],"of":[5,19,24,42,66,112,123],"drones":[6,11,25,36],"in":[7],"an":[8,13],"urban":[9,20],"environment,":[10],"present":[12],"increased":[14],"risk":[15],"safety":[18],"life.":[21],"Reliable":[22],"detection":[23],"becomes":[26],"crucial":[27],"for":[28,79,96,161],"countering":[29],"hazard":[31],"introduced":[32],"by":[33,151],"drones.":[34],"However,":[35],"are":[37,130],"difficult":[38],"detect":[40],"because":[41],"their":[43],"size":[44],"and":[45,59,83,94,115,146],"customization.":[46],"This":[47],"paper":[48],"introduces":[49],"DDL,":[50],"a":[51,62,69,73,109,116,158],"dataset":[52,107,160],"aimed":[53],"at":[54],"drone":[55,81,163],"sound":[56],"detection,":[57],"classification,":[58],"localization":[60,98],"via":[61],"specially":[63],"constructed":[64],"set":[65],"microphones.":[67],"As":[68],"baseline,":[70],"we":[71],"propose":[72],"deep":[74],"uncertainty-aware":[75],"framework":[76],"implementing":[77],"Conformer":[78],"joint":[80],"classification":[82,110],"localization.":[84,164],"We":[85],"employ":[86],"heteroscedastic":[87],"loss":[88],"functions":[89],"that":[90],"jointly":[91],"estimate":[92],"means":[93],"variances":[95],"spatial":[97],"model":[100],"prediction":[101],"uncertainty.":[102],"Experiments":[103],"on":[104],"DDL":[106,156],"demonstrate":[108],"accuracy":[111],"99.9":[113],"%":[114],"Euclidean":[117],"distance":[118],"mean":[119],"absolute":[120],"error":[121],"(MAE)":[122],"approximately":[124],"16":[125],"meters.":[126],"The":[127],"uncertainty":[128],"estimates":[129],"well-calibrated,":[131],"with":[132],"coverage":[133],"closely":[134],"matching":[135],"expected":[137],"confidence":[138],"intervals":[139],"(<tex":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$68":[142],"\\%,":[143],"95":[144],"\\%$</tex>,":[145],"99.7":[147],"%)":[148],"as":[149,157],"defined":[150],"empirical":[153],"rule,":[154],"suggesting":[155],"benchmark":[159],"audio-based":[162]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}