{"id":"https://openalex.org/W3179062140","doi":"https://doi.org/10.1145/3456529.3456531","title":"Finding Clusters and Patterns in Big Data Applications: State-of-the-Art Methods in Clustering Environments","display_name":"Finding Clusters and Patterns in Big Data Applications: State-of-the-Art Methods in Clustering Environments","publication_year":2021,"publication_date":"2021-02-02","ids":{"openalex":"https://openalex.org/W3179062140","doi":"https://doi.org/10.1145/3456529.3456531","mag":"3179062140"},"language":"en","primary_location":{"id":"doi:10.1145/3456529.3456531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3456529.3456531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 The 5th International Conference on Compute and Data Analysis","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/A5023934242","display_name":"Kehan Zhang","orcid":"https://orcid.org/0000-0001-7030-899X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehan Zhang","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026795459","display_name":"Zhenglin Wang","orcid":"https://orcid.org/0000-0002-5812-2989"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenglin Wang","raw_affiliation_strings":["Huazhong University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100349606","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0002-9995-9080"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Northeastern University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8795,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83612549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.9100064039230347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.778416633605957},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.5799987316131592},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5596985220909119},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5572063326835632},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.5192368626594543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46439865231513977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45911070704460144},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4428543746471405},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.43368563055992126},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.41253963112831116}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9100064039230347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778416633605957},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.5799987316131592},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5596985220909119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5572063326835632},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.5192368626594543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46439865231513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45911070704460144},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4428543746471405},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.43368563055992126},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.41253963112831116}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3456529.3456531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3456529.3456531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 The 5th International Conference on Compute and Data Analysis","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":11,"referenced_works":["https://openalex.org/W85047175","https://openalex.org/W1700132089","https://openalex.org/W1873332500","https://openalex.org/W1966331733","https://openalex.org/W2127218421","https://openalex.org/W2133148918","https://openalex.org/W2137683543","https://openalex.org/W2158703410","https://openalex.org/W2187089797","https://openalex.org/W2913791538","https://openalex.org/W4230962320"],"related_works":["https://openalex.org/W2111119584","https://openalex.org/W2606552659","https://openalex.org/W4301002638","https://openalex.org/W3186815950","https://openalex.org/W2406185607","https://openalex.org/W2163563073","https://openalex.org/W2311450085","https://openalex.org/W3035964814","https://openalex.org/W3124860551","https://openalex.org/W2309230723"],"abstract_inverted_index":{"With":[0],"the":[1,36,41,60,114,125,132,142],"rapid":[2],"development":[3],"of":[4,43,59,113,146],"computation":[5],"power":[6],"and":[7,21,40,64,68,85,104,129,138,144,157],"machine":[8],"learning":[9],"algorithms,":[10],"clustering":[11,62,94,126,148,151],"methods":[12,27,63,127,152],"have":[13],"become":[14],"a":[15,56,75],"powerful":[16,156],"tool":[17],"to":[18,48,74,119,122],"providing":[19],"insights":[20],"detecting":[22],"structures":[23],"in":[24],"datasets.":[25],"Clustering":[26],"are":[28,87,154],"especially":[29],"important":[30],"for":[31,93,135],"big":[32],"data":[33,44],"applications":[34],"where":[35],"dimensionality":[37],"is":[38,45],"high":[39],"amount":[42],"too":[46],"large":[47],"be":[49,117,160],"examined":[50],"by":[51,140],"human.":[52],"This":[53],"paper":[54,115],"provides":[55],"comprehensive":[57],"review":[58],"start-of-the-art":[61],"their":[65,70],"recent":[66],"progresses,":[67],"analyzes":[69],"performances":[71],"when":[72],"applied":[73],"high-dimensional":[76],"expression":[77,98],"level":[78],"dataset":[79],"across":[80],"multiple":[81,147],"environments.":[82],"As":[83],"PCA":[84],"MDS":[86],"very":[88],"commonly":[89],"used":[90],"among":[91],"researchers":[92,121],"environments":[95],"based":[96],"on":[97],"level,":[99],"we":[100],"show":[101],"that":[102,153],"UMAP":[103],"t-SNE":[105],"greatly":[106],"outperforms":[107],"these":[108],"traditional":[109],"methods.":[110],"The":[111],"conclusion":[112],"will":[116],"able":[118],"assist":[120],"understand":[123],"how":[124],"works":[128],"pick":[130],"up":[131],"best":[133],"method":[134],"related":[136],"proposes;":[137],"hopefully,":[139],"combining":[141],"ideas":[143],"advantages":[145],"methods,":[149],"novel":[150],"more":[155],"universal":[158],"can":[159],"developed.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}