{"id":"https://openalex.org/W4281759825","doi":"https://doi.org/10.1145/3523286.3524685","title":"Optimization of Big Data Mining Algorithm Based on Spark Framework","display_name":"Optimization of Big Data Mining Algorithm Based on Spark Framework","publication_year":2022,"publication_date":"2022-01-21","ids":{"openalex":"https://openalex.org/W4281759825","doi":"https://doi.org/10.1145/3523286.3524685"},"language":"en","primary_location":{"id":"doi:10.1145/3523286.3524685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523286.3524685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 2nd International Conference on Bioinformatics and Intelligent Computing","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/A5039356009","display_name":"Yan Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zeng","raw_affiliation_strings":["School of Information and Communication Engineering, Hainan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Hainan University, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100691319","display_name":"Jun Li","orcid":"https://orcid.org/0000-0002-6239-2922"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["School of Information and Communication Engineering, Hainan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Hainan University, China","institution_ids":["https://openalex.org/I20942203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20942203"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0700112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9854000210762024,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9854000210762024,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8958632946014404},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8064069747924805},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.8060314655303955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792702913284302},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.717746376991272},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6485506892204285},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5177011489868164},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.5066614747047424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5034472346305847},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4471646547317505},{"id":"https://openalex.org/keywords/efficient-algorithm","display_name":"Efficient algorithm","score":0.41834670305252075},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.26625964045524597}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8958632946014404},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8064069747924805},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.8060314655303955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792702913284302},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.717746376991272},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6485506892204285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5177011489868164},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.5066614747047424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5034472346305847},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4471646547317505},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.41834670305252075},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26625964045524597},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523286.3524685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523286.3524685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 2nd International Conference on Bioinformatics and Intelligent Computing","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":15,"referenced_works":["https://openalex.org/W2752512360","https://openalex.org/W2779294360","https://openalex.org/W2940603449","https://openalex.org/W2947891479","https://openalex.org/W2996591489","https://openalex.org/W2997395344","https://openalex.org/W3001166495","https://openalex.org/W3005195131","https://openalex.org/W3009126327","https://openalex.org/W3042107210","https://openalex.org/W3099698664","https://openalex.org/W3128731422","https://openalex.org/W3159272788","https://openalex.org/W3163005105","https://openalex.org/W6806058506"],"related_works":["https://openalex.org/W3110101717","https://openalex.org/W4287647396","https://openalex.org/W4296965450","https://openalex.org/W3090291499","https://openalex.org/W2361165494","https://openalex.org/W2364229524","https://openalex.org/W2357347077","https://openalex.org/W2385660399","https://openalex.org/W2365953361","https://openalex.org/W2385267502"],"abstract_inverted_index":{"Abstract:":[0],"Frequent":[1],"itemsets":[2,96],"mining":[3,10],"is":[4,32,58,97,107,125],"the":[5,14,19,29,37,42,48,61,89,92,100,105,114,117,122,131],"core":[6],"of":[7,17,47,50,68,71,94,104,116,130],"association":[8],"rule":[9],"data.":[11,145],"However,":[12],"with":[13,88],"continuous":[15],"increase":[16],"data,":[18,56,72],"traditional":[20],"Apriori":[21],"algorithm":[22,30,39,52,106,119],"cannot":[23],"meet":[24],"people's":[25],"daily":[26],"needs,":[27],"and":[28,83,99,134,139],"efficiency":[31,115,138],"low.":[33],"This":[34],"paper":[35],"proposes":[36],"Eclat":[38,118,132],"based":[40,75,120],"on":[41,76,121],"Spark":[43,123],"framework.":[44],"In":[45],"view":[46],"shortcomings":[49],"serial":[51],"in":[53],"processing":[54,143],"big":[55],"it":[57,135],"modified.":[59],"Using":[60],"vertical":[62],"structure":[63],"to":[64],"avoid":[65],"repetitive":[66],"traversal":[67],"large":[69],"amounts":[70],"while":[73],"computing":[74,85,102],"memory":[77],"can":[78],"greatly":[79],"reduce":[80,84],"I/O":[81],"load":[82],"time.":[86],"Combined":[87],"pruning":[90],"strategy,":[91],"calculation":[93],"irrelevant":[95],"reduced,":[98],"parallel":[101],"capability":[103],"improved.":[108],"The":[109],"experimental":[110],"results":[111],"show":[112],"that":[113,129],"framework":[124],"far":[126],"better":[127],"than":[128],"algorithm,":[133],"has":[136],"high":[137],"good":[140],"scalability":[141],"when":[142],"massive":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}