{"id":"https://openalex.org/W2614329789","doi":"https://doi.org/10.1109/wocc.2017.7928973","title":"Decision tree rule-based feature selection for large-scale imbalanced data","display_name":"Decision tree rule-based feature selection for large-scale imbalanced data","publication_year":2017,"publication_date":"2017-04-01","ids":{"openalex":"https://openalex.org/W2614329789","doi":"https://doi.org/10.1109/wocc.2017.7928973","mag":"2614329789"},"language":"en","primary_location":{"id":"doi:10.1109/wocc.2017.7928973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wocc.2017.7928973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 26th Wireless and Optical Communication Conference (WOCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101731302","display_name":"Haoyue Liu","orcid":"https://orcid.org/0000-0003-1379-7648"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyue Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081318069","display_name":"MengChu Zhou","orcid":"https://orcid.org/0000-0002-5408-8752"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MengChu Zhou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":0.6921,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73308771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9785000085830688,"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/feature-selection","display_name":"Feature selection","score":0.769168496131897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7410751581192017},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.73410964012146},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6065858602523804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6017521619796753},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5923928022384644},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5813158750534058},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5496717691421509},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5174968242645264},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4959429204463959},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.4657600224018097},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4488145709037781},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4440305233001709},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36994439363479614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14216628670692444},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1298331618309021},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11740955710411072},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07253685593605042}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.769168496131897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410751581192017},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.73410964012146},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6065858602523804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6017521619796753},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5923928022384644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5813158750534058},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5496717691421509},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5174968242645264},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4959429204463959},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.4657600224018097},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4488145709037781},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4440305233001709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36994439363479614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14216628670692444},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1298331618309021},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11740955710411072},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07253685593605042},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wocc.2017.7928973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wocc.2017.7928973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 26th Wireless and Optical Communication Conference (WOCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1560107318","https://openalex.org/W1594031697","https://openalex.org/W1975664724","https://openalex.org/W1979680481","https://openalex.org/W2016544456","https://openalex.org/W2023450550","https://openalex.org/W2026458067","https://openalex.org/W2102708620","https://openalex.org/W2109283550","https://openalex.org/W2118978333","https://openalex.org/W2131987814","https://openalex.org/W2141014056","https://openalex.org/W2144024248","https://openalex.org/W2149620660","https://openalex.org/W2254005892","https://openalex.org/W2291437667","https://openalex.org/W2295598076","https://openalex.org/W2327530886","https://openalex.org/W2340877487","https://openalex.org/W2569168369","https://openalex.org/W3102476541","https://openalex.org/W4399647672","https://openalex.org/W6633497745","https://openalex.org/W6675953175","https://openalex.org/W6681543018","https://openalex.org/W6681822384","https://openalex.org/W6869608176"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"A":[0],"class":[1],"imbalance":[2],"problem":[3],"often":[4],"appears":[5],"in":[6],"many":[7],"real":[8],"world":[9],"applications,":[10],"e.g.":[11],"fault":[12],"diagnosis,":[13],"text":[14],"categorization,":[15],"fraud":[16],"detection.":[17],"When":[18],"dealing":[19],"with":[20,85],"a":[21,28,37,43,57],"large-scale":[22,58],"imbalanced":[23],"dataset,":[24],"feature":[25,38,87],"selection":[26,39,88],"becomes":[27],"great":[29],"challenge.":[30],"To":[31],"confront":[32],"it,":[33],"this":[34],"work":[35],"proposes":[36],"approach":[40,52,68],"based":[41],"on":[42],"decision":[44],"tree":[45],"rule.":[46],"The":[47,63,94],"effectiveness":[48],"of":[49],"the":[50,74],"proposed":[51],"is":[53],"verified":[54],"by":[55],"classifying":[56],"dataset":[59],"from":[60],"Santander":[61],"Bank.":[62],"results":[64,95],"show":[65,96],"that":[66,97],"our":[67],"can":[69],"achieve":[70],"higher":[71],"Area":[72],"Under":[73],"Curve":[75],"(AUC)":[76],"and":[77,92],"less":[78],"computational":[79,105],"time.":[80],"We":[81],"also":[82],"compare":[83],"it":[84,98],"filter-based":[86],"approaches,":[89],"i.e.,":[90],"Chi-Square":[91],"F-statistic.":[93],"outperforms":[99],"them":[100],"but":[101],"needs":[102],"slightly":[103],"more":[104],"efforts.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}