{"id":"https://openalex.org/W4391770533","doi":"https://doi.org/10.1109/ccwc60891.2024.10427575","title":"CMI: Cluster-Centric Missing Value Imputation with Feature Consistency","display_name":"CMI: Cluster-Centric Missing Value Imputation with Feature Consistency","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4391770533","doi":"https://doi.org/10.1109/ccwc60891.2024.10427575"},"language":"en","primary_location":{"id":"doi:10.1109/ccwc60891.2024.10427575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccwc60891.2024.10427575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th Annual Computing and Communication Workshop and Conference (CCWC)","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/A5001513821","display_name":"Megha Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Megha Gupta","raw_affiliation_strings":["San Jose State University,Department of Applied Data Science,San Jose,USA","Department of Applied Data Science, San Jose State University, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"San Jose State University,Department of Applied Data Science,San Jose,USA","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Department of Applied Data Science, San Jose State University, San Jose, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111128723","display_name":"Shripal Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shripal Shah","raw_affiliation_strings":["San Jose State University,Department of Applied Data Science,San Jose,USA","Department of Applied Data Science, San Jose State University, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"San Jose State University,Department of Applied Data Science,San Jose,USA","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Department of Applied Data Science, San Jose State University, San Jose, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083502477","display_name":"Mohammad Masum","orcid":"https://orcid.org/0000-0001-9974-6950"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Masum","raw_affiliation_strings":["San Jose State University,Department of Applied Data Science,San Jose,USA","Department of Applied Data Science, San Jose State University, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"San Jose State University,Department of Applied Data Science,San Jose,USA","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Department of Applied Data Science, San Jose State University, San Jose, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010258542","display_name":"Sai Kosaraju","orcid":"https://orcid.org/0000-0002-4332-6217"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Chandra Kosaraju","raw_affiliation_strings":["University of Nevada,Nevada,USA","University of Nevada, Nevada, USA"],"affiliations":[{"raw_affiliation_string":"University of Nevada,Nevada,USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Nevada, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001513821"],"corresponding_institution_ids":["https://openalex.org/I51504820"],"apc_list":null,"apc_paid":null,"fwci":1.5105,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79785675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"0521","last_page":"0526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9505000114440918,"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/imputation","display_name":"Imputation (statistics)","score":0.8679684400558472},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7906360626220703},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.7273215055465698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6742905378341675},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6207873225212097},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.604590654373169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3490796983242035},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2918757200241089}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.8679684400558472},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7906360626220703},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7273215055465698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6742905378341675},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6207873225212097},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.604590654373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3490796983242035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2918757200241089}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccwc60891.2024.10427575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccwc60891.2024.10427575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th Annual Computing and Communication Workshop and Conference (CCWC)","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":23,"referenced_works":["https://openalex.org/W2064978043","https://openalex.org/W2102720558","https://openalex.org/W2309276681","https://openalex.org/W2574666645","https://openalex.org/W2914652968","https://openalex.org/W2920529430","https://openalex.org/W2977682063","https://openalex.org/W3034536504","https://openalex.org/W3034856749","https://openalex.org/W3046739224","https://openalex.org/W3120740533","https://openalex.org/W3136501774","https://openalex.org/W3181806673","https://openalex.org/W3201081718","https://openalex.org/W3206419906","https://openalex.org/W4200431999","https://openalex.org/W4224920825","https://openalex.org/W4256708289","https://openalex.org/W4285255793","https://openalex.org/W4285391032","https://openalex.org/W4295797491","https://openalex.org/W4366259393","https://openalex.org/W4366813973"],"related_works":["https://openalex.org/W2181530120","https://openalex.org/W4211215373","https://openalex.org/W2024529227","https://openalex.org/W2055961818","https://openalex.org/W2903115227","https://openalex.org/W1574575415","https://openalex.org/W3144172081","https://openalex.org/W3179858851","https://openalex.org/W3028371478","https://openalex.org/W2081476516"],"abstract_inverted_index":{"In":[0],"the":[1,31,92,101,106,115,128],"realm":[2],"of":[3,23,35,83,105,133],"data":[4,8,24,89,165,176],"analysis,":[5,166],"addressing":[6],"missing":[7,58,175],"poses":[9],"a":[10,46,161],"critical":[11],"challenge":[12],"with":[13],"implications":[14],"for":[15,56,173],"both":[16],"research":[17],"and":[18,33,103,121,131,148,170],"practical":[19],"applications.":[20],"The":[21,80,155],"absence":[22],"points":[25,90],"in":[26,60,86,164,177],"datasets":[27],"can":[28],"significantly":[29],"undermine":[30],"reliability":[32],"performance":[34,130],"predictive":[36],"models,":[37],"potentially":[38],"leading":[39],"to":[40,75,136],"erroneous":[41],"conclusions.":[42],"This":[43],"paper":[44],"introduces":[45],"novel":[47],"approach,":[48],"Cluster-Centric":[49],"Missing":[50],"Value":[51],"Imputation":[52,150],"(CMI),":[53],"designed":[54],"specifically":[55],"imputing":[57],"values":[59,74],"numerical":[61],"features":[62],"using":[63],"clustering":[64],"techniques.":[65],"CMI":[66,84,134,159],"is":[67],"augmented":[68],"by":[69,151],"Shapley":[70],"Additive":[71],"Explanations":[72],"(SHAP)":[73],"interpret":[76],"feature":[77],"significance":[78],"post-imputation.":[79],"core":[81],"principle":[82],"lies":[85],"recognizing":[87],"that":[88,158],"within":[91],"same":[93],"cluster":[94],"often":[95],"share":[96],"similar":[97],"key":[98],"attributes,":[99],"enhancing":[100],"transparency":[102],"understandability":[104],"imputation":[107,138],"process.":[108],"Experimental":[109],"evaluation":[110],"on":[111],"two":[112],"medical":[113],"datasets,":[114],"Indian":[116],"Liver":[117],"Patient":[118],"Dataset":[119],"(ILPD)":[120],"Chronic":[122],"Kidney":[123],"Disease":[124],"Data":[125],"(CKD),":[126],"demonstrates":[127],"superior":[129],"interpretability":[132],"compared":[135],"traditional":[137],"methods":[139],"such":[140],"as":[141],"mean":[142],"imputation,":[143,147],"k-nearest":[144],"neighbors":[145],"(KNN)":[146],"Multiple":[149],"Chained":[152],"Equations":[153],"(MICE).":[154],"findings":[156],"suggest":[157],"represents":[160],"significant":[162],"advancement":[163],"providing":[167],"an":[168],"effective":[169],"interpretable":[171],"solution":[172],"handling":[174],"healthcare":[178],"research.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}