{"id":"https://openalex.org/W7140111652","doi":"https://doi.org/10.48550/arxiv.2603.19315","title":"MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification","display_name":"MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7140111652","doi":"https://doi.org/10.48550/arxiv.2603.19315"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.19315","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.19315","pdf_url":"https://arxiv.org/pdf/2603.19315","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.19315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003144307","display_name":"Celal Alag\u00f6z","orcid":"https://orcid.org/0000-0001-9812-1473","observed_orcids":["https://orcid.org/0000-0001-9812-1473"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alag\u00f6z, Celal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130386525","display_name":"Mehmet Kurnaz","orcid":"https://orcid.org/0009-0003-1303-1623","observed_orcids":["https://orcid.org/0009-0003-1303-1623"]},"institutions":[{"id":"https://openalex.org/I4387154028","display_name":"Sivas Bilim ve Teknoloji \u00dcniversitesi","ror":"https://ror.org/05s32j989","country_code":"TR","type":"education","lineage":["https://openalex.org/I4387154028"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Kurnaz, Mehmet","raw_affiliation_strings":["Computer Engineering Sivas Bilim ve Teknoloji \u00dcniversitesi Sivas , T\u00fcrkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Sivas Bilim ve Teknoloji \u00dcniversitesi Sivas , T\u00fcrkiye","institution_ids":["https://openalex.org/I4387154028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058076434","display_name":"Farhan Aadil","orcid":"https://orcid.org/0000-0001-8737-2154","observed_orcids":["https://orcid.org/0000-0001-8737-2154"]},"institutions":[{"id":"https://openalex.org/I4387154028","display_name":"Sivas Bilim ve Teknoloji \u00dcniversitesi","ror":"https://ror.org/05s32j989","country_code":"TR","type":"education","lineage":["https://openalex.org/I4387154028"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Aadil, Farhan","raw_affiliation_strings":["Computer Engineering Sivas Bilim ve Teknoloji \u00dcniversitesi Sivas , T\u00fcrkiye 0000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Sivas Bilim ve Teknoloji \u00dcniversitesi Sivas , T\u00fcrkiye 0000","institution_ids":["https://openalex.org/I4387154028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10320","display_name":"Neural Networks and Applications","score":0.0,"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/time-series-classification","display_name":"time series classification","score":0.9940000176429749},{"id":"https://openalex.org/keywords/multiscale-convolutional-neural-network","display_name":"multi-scale convolutional neural network","score":0.9449999928474426},{"id":"https://openalex.org/keywords/probability-calibration","display_name":"probability calibration","score":0.8870000243186951},{"id":"https://openalex.org/keywords/lightweight-neural-networks","display_name":"lightweight neural networks","score":0.7139999866485596},{"id":"https://openalex.org/keywords/univariate-time-series","display_name":"univariate time series","score":0.777999997138977},{"id":"https://openalex.org/keywords/pareto-analysis","display_name":"Pareto analysis","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7860999703407288},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.7659000158309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541000247001648},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6485000252723694},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46869999170303345},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120999872684479},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.33809998631477356}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.19315","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.19315","pdf_url":"https://arxiv.org/pdf/2603.19315","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2603.19315","doi":"https://doi.org/10.48550/arxiv.2603.19315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19315","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,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.19315","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.19315","pdf_url":"https://arxiv.org/pdf/2603.19315","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140111652.pdf","grobid_xml":"https://content.openalex.org/works/W7140111652.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2306394264","https://openalex.org/W4287865152"],"related_works":["https://openalex.org/W7139037351","https://openalex.org/W2912888010","https://openalex.org/W2306394264","https://openalex.org/W4367047139","https://openalex.org/W4366201698","https://openalex.org/W4390877566","https://openalex.org/W4392090119","https://openalex.org/W3132154052","https://openalex.org/W3115948762","https://openalex.org/W4408667555"],"abstract_inverted_index":{"Time":[0],"series":[1],"classification":[2],"(TSC)":[3],"performance":[4,104],"depends":[5],"not":[6],"only":[7],"on":[8,13,77],"architectural":[9],"design":[10,144],"but":[11],"also":[12],"the":[14,107,115,129],"diversity":[15],"of":[16,174],"input":[17],"representations.":[18],"In":[19,63],"this":[20],"work,":[21],"we":[22,65],"propose":[23],"a":[24,44,56,93,142,164],"scalable":[25,159],"multi-scale":[26,46,139,161],"convolutional":[27,47],"framework":[28],"that":[29,112,137,146],"systematically":[30],"integrates":[31],"structured":[32],"multi-representation":[33,78,138,160],"inputs":[34,73],"for":[35,50,60,71,150,169],"univariate":[36,79],"time":[37],"series.":[38],"We":[39,84],"introduce":[40],"two":[41],"architectures:":[42],"MRMS-Net,":[43],"hierarchical":[45],"network":[48],"optimized":[49],"robustness":[51],"and":[52,54,126,166,176],"calibration,":[53],"LMRMS-Net,":[55],"lightweight":[57],"variant":[58],"designed":[59],"efficiency-aware":[61],"deployment.":[62],"addition,":[64],"adapt":[66],"LiteMV":[67,113],"--":[68,74],"originally":[69],"developed":[70],"multivariate":[72],"to":[75],"operate":[76],"signals,":[80],"enabling":[81],"cross-representation":[82],"interaction.":[83],"evaluate":[85],"all":[86],"models":[87],"across":[88],"142":[89],"benchmark":[90],"datasets":[91],"under":[92],"unified":[94],"experimental":[95],"protocol.":[96],"Critical":[97],"Difference":[98],"(CD)":[99],"analysis":[100,134],"confirms":[101],"statistically":[102],"significant":[103],"differences":[105],"among":[106],"top":[108],"models.":[109],"Results":[110],"show":[111],"achieves":[114],"highest":[116],"mean":[117],"accuracy,":[118],"MRMS-Net":[119,175],"provides":[120],"superior":[121],"probabilistic":[122],"calibration":[123],"(lowest":[124],"NLL),":[125],"LMRMS-Net":[127,177],"offers":[128],"best":[130],"efficiency-accuracy":[131],"tradeoff.":[132],"Pareto":[133],"further":[135],"demonstrates":[136],"modeling":[140],"yields":[141],"flexible":[143],"space":[145],"can":[147],"be":[148],"tuned":[149],"accuracy-oriented,":[151],"calibration-oriented,":[152],"or":[153],"resource-constrained":[154],"settings.":[155],"These":[156],"findings":[157],"establish":[158],"learning":[162],"as":[163],"principled":[165],"practical":[167],"direction":[168],"modern":[170],"TSC.":[171],"Reference":[172],"implementation":[173],"is":[178],"available":[179],"at:":[180],"https://github.com/alagoz/mrmsnet-tsc":[181]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-24T00:00:00"}