{"id":"https://openalex.org/W7160236050","doi":"https://doi.org/10.48550/arxiv.2605.01679","title":"Class-Aware Adaptive Differential Privacy in Deep Learning for Sensor-Based Fall Detection","display_name":"Class-Aware Adaptive Differential Privacy in Deep Learning for Sensor-Based Fall Detection","publication_year":2026,"publication_date":"2026-05-03","ids":{"openalex":"https://openalex.org/W7160236050","doi":"https://doi.org/10.48550/arxiv.2605.01679"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.01679","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.01679","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083767387","display_name":"Joydeb Kumar Sana","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sana, Joydeb Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083767387"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.8981000185012817,"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"}},"topics":[{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.8981000185012817,"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/T10114","display_name":"Balance, Gait, and Falls Prevention","score":0.03009999915957451,"subfield":{"id":"https://openalex.org/subfields/3612","display_name":"Physical Therapy, Sports Therapy and Rehabilitation"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11011","display_name":"Frailty in Older Adults","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/2717","display_name":"Geriatrics and Gerontology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.8720999956130981},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6478000283241272},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6241000294685364},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5401999950408936},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5350000262260437},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5115000009536743},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.49070000648498535}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.8720999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258000016212463},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6478000283241272},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6000000238418579},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5350000262260437},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5115000009536743},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48030000925064087},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C74750220","wikidata":"https://www.wikidata.org/wiki/Q2662197","display_name":"Differential evolution","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.01679","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.01679","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5486065745353699}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fall":[0],"detection":[1,14,226],"is":[2,129],"a":[3,62,71,122],"critical":[4],"task":[5],"in":[6,162,196,227],"healthcare,":[7],"particularly":[8],"for":[9,166],"elderly":[10],"people.":[11],"Timely":[12],"fall":[13,225],"and":[15,36,77,120,139,155,170,187],"treatment":[16],"can":[17,24],"prevent":[18],"severe":[19],"injuries.":[20],"Sensor-based":[21],"activity":[22],"data":[23,32],"be":[25],"used":[26],"to":[27,95,223],"detect":[28],"fall.":[29],"However,":[30],"this":[31,58],"are":[33,193],"highly":[34],"sensitive":[35],"raises":[37],"significant":[38],"privacy":[39,42,108,148,190],"concerns.":[40],"Existing":[41],"approaches":[43],"apply":[44],"uniform":[45],"noise":[46,93],"across":[47],"all":[48],"training":[49],"samples,":[50],"which":[51,192],"affects":[52],"the":[53,90,99,116,146,158,167,180,204,215],"prediction":[54],"performance.":[55],"To":[56],"address":[57],"limitation,":[59],"we":[60],"propose":[61],"Class-Aware":[63],"Adaptive":[64],"Differential":[65],"Privacy":[66,118],"(CA-ADP)":[67],"framework":[68,183,218],"integrated":[69],"with":[70,175],"hybrid":[72],"3D":[73],"Convolutional":[74],"Neural":[75],"Network":[76],"Bidirectional":[78],"Long":[79],"Short-Term":[80],"Memory":[81],"(3D":[82],"CNN-BiLSTM)":[83],"architecture.":[84],"The":[85,126,141],"CA-ADP":[86,217],"mechanism":[87,206],"dynamically":[88],"adjusts":[89],"magnitude":[91],"of":[92,102,152,164],"added":[94],"gradients":[96],"based":[97,182],"on":[98,131],"class":[100],"composition":[101],"each":[103],"mini-batch.":[104],"This":[105],"process":[106],"ensures":[107],"while":[109],"mitigates":[110],"performance":[111,186],"degradation.":[112],"We":[113],"formally":[114],"analyze":[115],"$(\u03b5,\u03b4)$-Differential":[117],"guarantee":[119],"provide":[121],"privacy-utility":[123],"trade-off":[124],"analysis.":[125],"proposed":[127,147,205,216],"method":[128],"evaluated":[130],"three":[132],"public":[133],"benchmark":[134],"datasets,":[135,172],"namely":[136],"SisFall,":[137,168],"UP-Fall,":[138,169],"MobiAct.":[140],"experimental":[142],"results":[143,213],"show":[144,178],"that":[145,179,203],"model":[149,161],"achieves":[150,184],"improvements":[151],"3.3\\%,":[153],"8.5\\%,":[154],"7.5\\%":[156],"over":[157],"conventional":[159,209],"privacy-based":[160],"terms":[163],"F-score":[165],"MobiAct":[171],"respectively.":[173],"Comparisons":[174],"prior":[176],"studies":[177],"CA-AD":[181],"competitive":[185],"provides":[188],"formal":[189],"guarantees,":[191],"largely":[194],"overlooked":[195],"existing":[197],"studies.":[198],"Wilcoxon":[199],"signed-rank":[200],"tests":[201],"confirm":[202],"consistently":[207],"outperforms":[208],"differential":[210],"privacy.":[211],"Those":[212],"establish":[214],"as":[219],"an":[220],"effective":[221],"approach":[222],"privacy-preserving":[224],"real-world":[228],"healthcare":[229],"settings.":[230]},"counts_by_year":[],"updated_date":"2026-05-06T06:10:43.113611","created_date":"2026-05-06T00:00:00"}