{"id":"https://openalex.org/W3140764173","doi":null,"title":"A Novel Approach to Detect Redundant Activity Labels For More Representative Event Logs.","display_name":"A Novel Approach to Detect Redundant Activity Labels For More Representative Event Logs.","publication_year":2021,"publication_date":"2021-03-30","ids":{"openalex":"https://openalex.org/W3140764173","mag":"3140764173"},"language":"en","primary_location":{"id":"mag:3140764173","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.16061.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.16061.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030545939","display_name":"Qifan Chen","orcid":"https://orcid.org/0000-0002-5297-7206","observed_orcids":["https://orcid.org/0000-0002-5297-7206"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qifan Chen","raw_affiliation_strings":["University of Sydney"],"raw_orcid":"https://orcid.org/0000-0002-5297-7206","affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044521860","display_name":"Yang Lu","orcid":"https://orcid.org/0000-0002-9002-8650","observed_orcids":["https://orcid.org/0000-0002-9002-8650"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":["University of Sydney"],"raw_orcid":"https://orcid.org/0000-0002-9002-8650","affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086228954","display_name":"Charmaine S. Tam","orcid":"https://orcid.org/0000-0002-4034-9923","observed_orcids":["https://orcid.org/0000-0002-4034-9923"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Charmaine S. Tam","raw_affiliation_strings":["University of Sydney"],"raw_orcid":"https://orcid.org/0000-0002-4034-9923","affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003933623","display_name":"Simon Kar-Sing Poon","orcid":"https://orcid.org/0000-0003-2726-9109","observed_orcids":["https://orcid.org/0000-0003-2726-9109"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Simon Poon","raw_affiliation_strings":["University of Sydney"],"raw_orcid":"https://orcid.org/0000-0003-2726-9109","affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129604602"],"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14400","display_name":"Medical Coding and Health Information","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/health-information-systems","display_name":"health information systems","score":0.7120000123977661},{"id":"https://openalex.org/keywords/process-mining","display_name":"process mining","score":0.6370000243186951},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.777999997138977},{"id":"https://openalex.org/keywords/label-inconsistency","display_name":"label inconsistency","score":0.4970000088214874},{"id":"https://openalex.org/keywords/sepsis","display_name":"sepsis","score":0.6299999952316284},{"id":"https://openalex.org/keywords/mimic-iii","display_name":"MIMIC-III","score":0.8960000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717792987823486},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6092177033424377},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6014678478240967},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5950132608413696},{"id":"https://openalex.org/C124670913","wikidata":"https://www.wikidata.org/wiki/Q2608526","display_name":"Process mining","level":5,"score":0.5800818800926208},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5515961647033691},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44939687848091125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4488277733325958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4387929439544678},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.24605321884155273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C207505557","wikidata":"https://www.wikidata.org/wiki/Q4374012","display_name":"Business process modeling","level":4,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3140764173","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.16061.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3140764173","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.16061.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W35873499","https://openalex.org/W1043824350","https://openalex.org/W1495107092","https://openalex.org/W1598385458","https://openalex.org/W1945283334","https://openalex.org/W1965481657","https://openalex.org/W1977153588","https://openalex.org/W1992122264","https://openalex.org/W1998871699","https://openalex.org/W2042759024","https://openalex.org/W2061272711","https://openalex.org/W2092898466","https://openalex.org/W2101238481","https://openalex.org/W2101319014","https://openalex.org/W2128061541","https://openalex.org/W2133777675","https://openalex.org/W2143668817","https://openalex.org/W2159904898","https://openalex.org/W2396881363","https://openalex.org/W2468625138","https://openalex.org/W2514759044","https://openalex.org/W2559515863","https://openalex.org/W2594957810","https://openalex.org/W2617759834","https://openalex.org/W2737678507","https://openalex.org/W2796255656","https://openalex.org/W2884507774","https://openalex.org/W2901076221","https://openalex.org/W2979918170","https://openalex.org/W2998446033","https://openalex.org/W3094293898","https://openalex.org/W3094402232"],"related_works":["https://openalex.org/W4281791062","https://openalex.org/W2979918170","https://openalex.org/W3139323298","https://openalex.org/W4408203775","https://openalex.org/W4221138917","https://openalex.org/W3094293898","https://openalex.org/W2514875262","https://openalex.org/W4386315709","https://openalex.org/W3083294935","https://openalex.org/W7140062309"],"abstract_inverted_index":{"The":[0,52,172],"insights":[1],"revealed":[2],"from":[3,16,57,125,158],"process":[4,59,200],"mining":[5,201],"heavily":[6,65],"rely":[7,64],"on":[8,66],"the":[9,21,49,85,159,168,190,204],"quality":[10],"of":[11,36,54,87],"event":[12,94,126,197],"logs.":[13,95,127],"Activities":[14],"extracted":[15],"healthcare":[17,103,205],"information":[18,104],"systems":[19],"with":[20,146],"free-text":[22],"nature":[23],"may":[24],"lead":[25,33],"to":[26,34,41,113,137,189,193],"inconsistent":[27],"labels.":[28,183],"Such":[29],"inconsistency":[30],"would":[31],"then":[32],"redundancy":[35],"activity":[37,77,116,182],"labels,":[38,142],"which":[39,143],"refer":[40],"labels":[42,56,78,117],"that":[43,175],"have":[44,150],"different":[45],"syntax":[46],"but":[47],"share":[48],"same":[50],"behaviours.":[51],"identifications":[53],"these":[55,97],"data-driven":[58],"discovery":[60],"are":[61,79,99],"difficult":[62],"and":[63,121,163],"resource-intensive":[67],"human":[68],"review.":[69],"Existing":[70],"work":[71],"achieves":[72],"low":[73,81],"accuracy":[74],"either":[75],"redundant":[76,115,181],"in":[80,93,102,203],"occurrence":[82],"frequency":[83],"or":[84],"existence":[86],"numerical":[88,122],"data":[89,123,170],"values":[90,124],"as":[91],"attributes":[92],"However,":[96],"phenomena":[98],"commonly":[100],"observed":[101],"systems.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109],"propose":[110],"an":[111],"approach":[112,153,177,185],"detect":[114,180],"using":[118,167],"control-flow":[119],"relations":[120],"Natural":[128],"Language":[129],"Processing":[130],"is":[131],"also":[132],"integrated":[133],"into":[134],"our":[135,152,176],"method":[136],"assess":[138],"semantic":[139],"similarity":[140],"between":[141],"provides":[144],"users":[145],"additional":[147],"insights.":[148],"We":[149],"evaluated":[151],"through":[154],"synthetic":[155],"logs":[156,198],"generated":[157],"real-life":[160],"Sepsis":[161],"log":[162],"a":[164],"case":[165],"study":[166],"MIMIC-III":[169],"set.":[171],"results":[173],"demonstrate":[174],"can":[178,186],"successfully":[179],"This":[184],"add":[187],"value":[188],"preprocessing":[191],"step":[192],"generate":[194],"more":[195],"representative":[196],"for":[199],"tasks":[202],"domain.":[206]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2021-04-13T00:00:00"}