{"id":"https://openalex.org/W7161850097","doi":"https://doi.org/10.48550/arxiv.2605.19031","title":"KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition","display_name":"KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161850097","doi":"https://doi.org/10.48550/arxiv.2605.19031"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19031","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19031","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19031","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136609781","display_name":"Mengxi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Mengxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066958860","display_name":"Sizhen Bian","orcid":"https://orcid.org/0000-0001-6760-5539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bian, Sizhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120040060","display_name":"V\u00edtor Fortes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fortes, Vitor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136600600","display_name":"Francisco Calatrava Nicolas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas, Francisco Calatrava","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136577480","display_name":"Daniel Gei\u00dfler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gei\u00dfler, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006932634","display_name":"Maximilian Kiefer-Emmanouilidis","orcid":"https://orcid.org/0009-0005-7065-3511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiefer-Emmanouilidis, Maximilian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136577253","display_name":"Bo Zhou","orcid":"https://orcid.org/0000-0002-8316-5673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136610390","display_name":"Paul Lukowicz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukowicz, Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.867900013923645,"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":0.867900013923645,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.03750000149011612,"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/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.024800000712275505,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/robustness","display_name":"Robustness (evolution)","score":0.6782000064849854},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.6381000280380249},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.52920001745224},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5015000104904175},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.42089998722076416},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.40709999203681946},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.39489999413490295},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39010000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717199981212616},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6782000064849854},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.6381000280380249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6089000105857849},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.52920001745224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49309998750686646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4828000068664551},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.42089998722076416},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.3815000057220459},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19031","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19031","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.19031","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19031","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5617947578430176}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Kolmogorov-Arnold":[0],"Networks":[1],"(KANs)":[2],"have":[3],"demonstrated":[4],"an":[5,58,134],"exceptional":[6],"ability":[7],"to":[8,18,37,62],"learn":[9],"complex":[10],"functions":[11],"on":[12,21],"clean,":[13],"low-dimensional":[14],"data":[15],"but":[16],"struggle":[17],"maintain":[19],"performance":[20],"noisy":[22],"and":[23,39,54,70,87,114,150,186],"imperfect":[24],"real-world":[25,191],"datasets.":[26],"In":[27],"contrast,":[28],"conventional":[29,180],"multi-layer":[30],"perceptrons":[31],"(MLPs)":[32],"are":[33],"far":[34],"more":[35,184],"tolerant":[36],"noise":[38,68],"computationally":[40],"efficient.":[41],"Replacing":[42],"all":[43],"MLP":[44,108,151],"components":[45,182],"with":[46,66],"KANs":[47],"in":[48],"HAR":[49,85,127,161,188],"models":[50,189],"often":[51],"degrades":[52],"accuracy":[53],"computation":[55],"efficiency,":[56],"highlighting":[57],"open":[59],"challenge:":[60],"how":[61],"combine":[63],"KANs'":[64],"precision":[65],"MLPs'":[67],"robustness":[69],"efficiency.":[71],"To":[72],"address":[73],"this,":[74],"we":[75],"systematically":[76],"explore":[77],"various":[78],"placements":[79],"of":[80,97,141,175],"KAN":[81,149],"modules":[82],"within":[83],"deep":[84],"networks":[86],"propose":[88],"a":[89,102,116,171],"hybrid":[90,130,156],"architecture":[91],"that":[92,170],"strategically":[93],"synergizes":[94],"the":[95,129],"strengths":[96],"both":[98],"paradigms,":[99],"which":[100],"uses":[101],"KAN-based":[103],"input":[104],"embedding":[105],"layer,":[106],"retains":[107],"layers":[109],"for":[110,120,190],"intermediate":[111],"feature":[112],"mixing,":[113],"introduces":[115],"specialized":[117],"LarctanKAN":[118],"module":[119],"final":[121],"activity":[122],"classification.":[123],"Across":[124],"eight":[125],"public":[126],"datasets,":[128],"KAN-MLP":[131],"model":[132],"achieves":[133],"average":[135],"macro":[136],"F1":[137],"score":[138],"relative":[139],"improvement":[140],"5.33\\%":[142],"compared":[143],"pure-MLP":[144],"model,":[145],"significantly":[146],"outperforming":[147],"standalone":[148],"baselines.":[152],"Furthermore,":[153],"integrating":[154],"this":[155],"strategy":[157],"into":[158],"other":[159,179],"state-of-the-art":[160],"architectures":[162],"consistently":[163],"boosts":[164],"their":[165],"performance.":[166],"Our":[167],"findings":[168],"demonstrate":[169],"carefully":[172],"orchestrated":[173],"combination":[174],"KAN,":[176],"MLP,":[177],"or":[178],"neural":[181],"yields":[183],"robust":[185],"accurate":[187],"wearable":[192],"sensing":[193],"environments.":[194]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-21T00:00:00"}