{"id":"https://openalex.org/W1905687056","doi":"https://doi.org/10.1109/iccp.2015.7312601","title":"Pre-processing flow for enhancing learning from medical data","display_name":"Pre-processing flow for enhancing learning from medical data","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W1905687056","doi":"https://doi.org/10.1109/iccp.2015.7312601","mag":"1905687056"},"language":"en","primary_location":{"id":"doi:10.1109/iccp.2015.7312601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp.2015.7312601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Intelligent Computer Communication and Processing (ICCP)","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/A5017371225","display_name":"Sebastian Muresan","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Sebastian Muresan","raw_affiliation_strings":["Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","Computer Science Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016255342","display_name":"Ioana Faloba","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Ioana Faloba","raw_affiliation_strings":["Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","Computer Science Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070444955","display_name":"Camelia Lemnaru","orcid":"https://orcid.org/0000-0002-4901-9808"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Camelia Lemnaru","raw_affiliation_strings":["Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","Computer Science Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049230139","display_name":"Rodica Potolea","orcid":"https://orcid.org/0000-0002-7051-3691"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Rodica Potolea","raw_affiliation_strings":["Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","Computer Science Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Computer Science Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.4451,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76317273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9921000003814697,"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/computer-science","display_name":"Computer science","score":0.774025559425354},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.7580414414405823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5599808096885681},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5421908497810364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076617002487183},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49895596504211426},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48035988211631775},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4737692177295685},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4672090411186218},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4371335208415985},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4170069098472595},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.13321146368980408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774025559425354},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.7580414414405823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5599808096885681},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5421908497810364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076617002487183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49895596504211426},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48035988211631775},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4737692177295685},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4672090411186218},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4371335208415985},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4170069098472595},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.13321146368980408},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp.2015.7312601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp.2015.7312601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306239","display_name":"Conquer Cancer Foundation","ror":"https://ror.org/027327e78"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1994410331","https://openalex.org/W1995875735","https://openalex.org/W2017337590","https://openalex.org/W2133462743","https://openalex.org/W2133990480","https://openalex.org/W2148143831","https://openalex.org/W2164330572","https://openalex.org/W4247832998"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W4206637278","https://openalex.org/W2781247653","https://openalex.org/W4386005305","https://openalex.org/W3082051559","https://openalex.org/W1682621979","https://openalex.org/W4386214543","https://openalex.org/W1969988626","https://openalex.org/W2141301039","https://openalex.org/W2389015757"],"abstract_inverted_index":{"Data":[0],"enhancement":[1,83],"is":[2],"an":[3,69],"essential":[4],"operation":[5],"when":[6],"dealing":[7],"with":[8,117],"incomplete":[9],"and":[10,60,79,102],"imbalanced":[11],"data":[12,18,49,58,65,82,113],"sets.":[13],"Further":[14],"classification":[15,136],"on":[16,126],"such":[17,29,85],"might":[19],"prove":[20],"to":[21,67,111],"be":[22],"a":[23,32,103],"difficult":[24],"task.":[25],"This":[26],"paper":[27],"tackles":[28],"issues":[30],"in":[31,115,135],"specific":[33,47],"learning":[34,74],"context":[35],"-":[36],"medical":[37,48,129],"treatment":[38],"prediction":[39],"for":[40,72,88,94],"breast":[41],"cancer.":[42],"We":[43,55],"process":[44],"the":[45,52,73,96,99,107,121,127],"problem":[46],"starting":[50],"from":[51],"preparation":[53],"phase.":[54],"apply":[56,80],"several":[57,81],"cleaning":[59],"selection":[61,93],"steps.":[62],"The":[63],"resulting":[64],"proved":[66],"possess":[68],"insufficient":[70],"quality":[71],"process.":[75],"Therefore,":[76],"we":[77],"propose":[78],"steps,":[84],"as":[86],"imputation":[87],"handling":[89],"missing":[90],"values,":[91],"feature":[92],"reducing":[95],"dimensionality":[97],"of":[98,106,120],"attribute":[100],"space":[101],"modified":[104],"version":[105],"SMOTE":[108],"oversampling":[109],"algorithm":[110],"tackle":[112],"imbalance":[114],"conjunction":[116],"incompleteness.":[118],"Evaluations":[119],"entire":[122],"pre-processing":[123],"flow,":[124],"performed":[125],"available":[128],"data,":[130],"have":[131],"indicated":[132],"significant":[133],"improvements":[134],"performance.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}