{"id":"https://openalex.org/W3200302774","doi":"https://doi.org/10.1109/tkde.2021.3112520","title":"Spark Rough Hypercuboid Approach for Scalable Feature Selection","display_name":"Spark Rough Hypercuboid Approach for Scalable Feature Selection","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3200302774","doi":"https://doi.org/10.1109/tkde.2021.3112520","mag":"3200302774"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3112520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3112520","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5034187026","display_name":"Chuan Luo","orcid":"https://orcid.org/0000-0002-4021-464X"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Luo","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, Sichuan, China, (e-mail: cluo@scu.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, Sichuan, China, (e-mail: cluo@scu.edu.cn)","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052390626","display_name":"Sizhao Wang","orcid":"https://orcid.org/0000-0002-2577-2643"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sizhao Wang","raw_affiliation_strings":["College of Computer Science, Sichuan University, 12530 Chengdu, Sichuan, China, (e-mail: wangsizhao@stu.scu.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, 12530 Chengdu, Sichuan, China, (e-mail: wangsizhao@stu.scu.edu.cn)","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070559820","display_name":"Tianrui Li","orcid":"https://orcid.org/0000-0001-7780-104X"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Li","raw_affiliation_strings":["School of Information Science and Technology, Southwest Jiaotong University, Chengdu, Sichuan, China, 610031 (e-mail: trli@swjtu.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Southwest Jiaotong University, Chengdu, Sichuan, China, 610031 (e-mail: trli@swjtu.edu.cn)","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358460","display_name":"Hongmei Chen","orcid":"https://orcid.org/0000-0002-7225-5577"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmei Chen","raw_affiliation_strings":["School of Information Science and Technology, Southwest Jiaotong University, Chengdu, Sichuan, China, (e-mail: hmchen@swjtu.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Southwest Jiaotong University, Chengdu, Sichuan, China, (e-mail: hmchen@swjtu.edu.cn)","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055092097","display_name":"Jian Lv","orcid":"https://orcid.org/0000-0001-7633-366X"},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cheng Lv","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, Chengdu, China, (e-mail: lvjiancheng@scu.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, Chengdu, China, (e-mail: lvjiancheng@scu.edu.cn)","institution_ids":["https://openalex.org/I4210125143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103114031","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-0073-3696"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, Sichuan, China, (e-mail: zhangyi@scu.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, Sichuan, China, (e-mail: zhangyi@scu.edu.cn)","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":3.5708,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93505892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9944000244140625,"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/T11106","display_name":"Data Management and Algorithms","score":0.9803000092506409,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8863033056259155},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7405955791473389},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6870436072349548},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6547132134437561},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5248936414718628},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5079427361488342},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49180153012275696},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4273521602153778},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4197264611721039},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3833285868167877},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3073970079421997},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.30426615476608276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19375833868980408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8863033056259155},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7405955791473389},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6870436072349548},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6547132134437561},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5248936414718628},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5079427361488342},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49180153012275696},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4273521602153778},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4197264611721039},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3833285868167877},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3073970079421997},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.30426615476608276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19375833868980408},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2021.3112520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3112520","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2352941459","display_name":null,"funder_award_id":"2018AAA0100201","funder_id":"https://openalex.org/F4320335960","funder_display_name":"National Major Science and Technology Projects of China"},{"id":"https://openalex.org/G3171599357","display_name":null,"funder_award_id":"62076171, 61573292, 61976182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335960","display_name":"National Major Science and Technology Projects of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1969525310","https://openalex.org/W2016929372","https://openalex.org/W2052715156","https://openalex.org/W2057608478","https://openalex.org/W2079680557","https://openalex.org/W2092044939","https://openalex.org/W2092845575","https://openalex.org/W2151257102","https://openalex.org/W2170341854","https://openalex.org/W2200884536","https://openalex.org/W2287696922","https://openalex.org/W2319358180","https://openalex.org/W2568086521","https://openalex.org/W2573426660","https://openalex.org/W2764063895","https://openalex.org/W2766663411","https://openalex.org/W2885790982","https://openalex.org/W2956603593","https://openalex.org/W2959820746","https://openalex.org/W2989196101","https://openalex.org/W2989896841","https://openalex.org/W2994713090","https://openalex.org/W3048584318"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2185094550","https://openalex.org/W2088823210","https://openalex.org/W2135766592"],"abstract_inverted_index":{"Feature":[0],"selection":[1,59],"refers":[2],"to":[3,29,69,85,112,156,168,184],"choose":[4],"an":[5],"optimal":[6],"non-redundant":[7],"feature":[8,58],"subset":[9],"with":[10,92,194],"minimal":[11],"degradation":[12],"of":[13,19,24,33,43,79,141,151,188,197],"learning":[14],"performance":[15],"and":[16,89,106,174,190],"maximal":[17],"avoidance":[18],"data":[20,26,74,100,115,189],"overfitting.":[21],"The":[22],"appearance":[23],"large":[25],"explosion":[27],"leads":[28],"the":[30,40,48,72,93,114,139,142,145,153,158,169,195],"sequential":[31,135],"execution":[32],"algorithms":[34,44,60,129,147],"are":[35,82,109,148],"extremely":[36],"time-consuming,":[37],"which":[38],"necessitates":[39],"scalable":[41],"parallelization":[42,181],"by":[45,62],"efficiently":[46],"exploiting":[47,152],"distributed":[49,87],"computational":[50,198],"capabilities.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"present":[56],"parallel":[57,86],"underpinned":[61],"a":[63,164],"rough":[64,80],"hypercuboid":[65,81],"approach":[66],"in":[67,77],"order":[68],"scale":[70],"for":[71],"growing":[73],"volumes.":[75],"Metrics":[76],"terms":[78],"highly":[83],"suitable":[84],"processing,":[88],"fits":[90],"well":[91,183,193],"Apache":[94],"Spark":[95],"cluster":[96],"computing":[97,119],"paradigm.":[98],"Two":[99],"parallelism":[101],"strategies,":[102],"namely,":[103],"vertical":[104],"partitioning":[105],"horizontal":[107],"partitioning,":[108],"implemented":[110],"respectively":[111],"decompose":[113],"into":[116],"concurrent":[117],"iterative":[118],"streams.":[120],"Experimental":[121],"results":[122],"on":[123,163],"representative":[124],"datasets":[125],"show":[126],"that":[127,161,179],"our":[128,180],"significantly":[130],"faster":[131],"than":[132],"its":[133],"original":[134],"counterpart":[136],"while":[137],"guaranteeing":[138],"quality":[140],"results.":[143],"Furthermore,":[144],"proposed":[146],"perfectly":[149],"capable":[150],"distributed-memory":[154],"clusters":[155],"accomplish":[157],"computation":[159],"task":[160],"fails":[162],"single":[165],"node":[166],"due":[167],"memory":[170],"constraints.":[171],"Parallel":[172],"scalability":[173],"extensibility":[175],"analysis":[176],"have":[177],"confirmed":[178],"extends":[182],"process":[185],"massive":[186],"amount":[187],"can":[191],"scales":[192],"increase":[196],"nodes.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
