{"id":"https://openalex.org/W119234520","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch045","title":"Compression-Based Data Mining","display_name":"Compression-Based Data Mining","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W119234520","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch045","mag":"119234520"},"language":"en","primary_location":{"id":"doi:10.4018/978-1-60566-010-3.ch045","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch045","is_oa":false,"landing_page_url":"https://doi.org/10.4018/978-1-60566-010-3.ch045","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Data Warehousing and Mining, Second Edition","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W2587851609","display_name":"Encyclopedia of Data Warehousing and Mining, Second Edition"},"type":"reference-entry","is_traditional":false,"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/A5078245746","display_name":"Eamonn Keogh","orcid":"https://orcid.org/0000-0002-4188-3968","observed_orcids":["https://orcid.org/0000-0002-4188-3968"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eamonn Keogh","raw_affiliation_strings":["University of California - Riverside, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California - Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004296448","display_name":"Li Keogh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Keogh","raw_affiliation_strings":["Google, Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066344998","display_name":"John C. Handley","orcid":"https://orcid.org/0000-0001-9790-7300","observed_orcids":["https://orcid.org/0000-0001-9790-7300"]},"institutions":[{"id":"https://openalex.org/I4210132870","display_name":"Xerox (United States)","ror":"https://ror.org/03jwzwq24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John C. Handley","raw_affiliation_strings":["Xerox Innovation Group, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Innovation Group, USA","institution_ids":["https://openalex.org/I4210132870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.6371999979019165,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.6371999979019165,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.08950000256299973,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.08070000261068344,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lossless-compression","display_name":"lossless compression","score":0.9129999876022339},{"id":"https://openalex.org/keywords/clustering","display_name":"clustering","score":0.5479999780654907},{"id":"https://openalex.org/keywords/classification","display_name":"classification","score":0.996999979019165},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"anomaly detection","score":0.8379999995231628},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/parameter-free-algorithms","display_name":"parameter-free algorithms","score":0.5910000205039978},{"id":"https://openalex.org/keywords/similarity-measures","display_name":"similarity measures","score":0.5580000281333923},{"id":"https://openalex.org/keywords/information-theory","display_name":"information theory","score":0.5879999995231628}],"concepts":[{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.8227202892303467},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6351123452186584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067205667495728},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5965254306793213},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.581052839756012},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5781867504119873},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.543773353099823},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5276362299919128},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5205339193344116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44448989629745483},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4318598210811615},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.42819347977638245},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42690831422805786},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4008313715457916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3917188048362732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26822707056999207},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08435562252998352},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4018/978-1-60566-010-3.ch045","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch045","is_oa":false,"landing_page_url":"https://doi.org/10.4018/978-1-60566-010-3.ch045","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Data Warehousing and Mining, Second Edition","raw_type":"book-chapter"},{"id":"doi:10.4018/9781605660103.ch045","doi":"https://doi.org/10.4018/9781605660103.ch045","is_oa":false,"landing_page_url":"https://doi.org/10.4018/9781605660103.ch045","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Data Warehousing and Mining, Second Edition","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W58346954","https://openalex.org/W1534506107","https://openalex.org/W1549845211","https://openalex.org/W1971074636","https://openalex.org/W1985556836","https://openalex.org/W2034528422","https://openalex.org/W2064235697","https://openalex.org/W2072994259","https://openalex.org/W2094580724","https://openalex.org/W2100506586","https://openalex.org/W2101460669","https://openalex.org/W2114953535","https://openalex.org/W2117825194","https://openalex.org/W2124871568","https://openalex.org/W2125598538","https://openalex.org/W2134731454","https://openalex.org/W2136467248","https://openalex.org/W2147152072","https://openalex.org/W2162704317","https://openalex.org/W2165340347","https://openalex.org/W2166064672","https://openalex.org/W2171852577","https://openalex.org/W2171886309","https://openalex.org/W2420187884","https://openalex.org/W3020866322","https://openalex.org/W6674998358"],"related_works":["https://openalex.org/W2064235697","https://openalex.org/W7100690612","https://openalex.org/W7100504846","https://openalex.org/W4313395957","https://openalex.org/W1885322152","https://openalex.org/W2792757404","https://openalex.org/W7208388071","https://openalex.org/W71353903","https://openalex.org/W4233393308","https://openalex.org/W1990071908"],"abstract_inverted_index":{"Compression-based":[0],"data":[1,250],"mining":[2],"is":[3,16,35,53,92,118,213,243],"a":[4,84,180],"universal":[5,85],"approach":[6,203],"to":[7,55,216,268],"clustering,":[8],"classification,":[9],"dimensionality":[10],"reduction,":[11],"and":[12,23,133,169,199,211,245],"anomaly":[13,170],"detection.":[14],"It":[15,34],"motivated":[17],"by":[18,48,104],"results":[19],"in":[20,63,179,190],"bioinformatics,":[21],"learning,":[22],"computational":[24],"theory":[25],"that":[26,119,236,255],"are":[27,60,123,188,209,227,237],"not":[28],"well":[29,205],"known":[30],"outside":[31],"those":[32],"communities.":[33],"based":[36],"on":[37],"an":[38],"easily":[39],"computed":[40],"compression":[41,89],"dissimilarity":[42,90,177],"measure":[43,91,178],"(CDM)":[44],"between":[45,68,131,159,231],"objects":[46,71,102,122,208,233],"obtained":[47,82],"compression.":[49],"The":[50,66,88,116,155],"basic":[51],"concept":[52],"easy":[54],"understand,":[56],"but":[57],"its":[58],"foundations":[59],"rigorously":[61],"formalized":[62],"information":[64],"theory.":[65],"similarity":[67],"any":[69],"two":[70,101,121,151,160],"(XML":[72],"files,":[73],"time":[74],"series,":[75],"text":[76],"strings,":[77],"molecules,":[78],"etc.)":[79],"can":[80,173],"be":[81,142,257],"using":[83],"lossless":[86,125],"compressor.":[87],"the":[93,96,100,105,108,114,129,134,138,144,147,150,157,162,232,249],"size":[94,136,145],"of":[95,99,107,111,113,137,146,149,183,186],"compressed":[97,109,152],"concatenation":[98],"divided":[103],"sum":[106],"sizes":[110],"each":[112],"objects.":[115,154],"intuition":[117],"if":[120],"similar,":[124],"compressor":[126],"will":[127],"remove":[128],"redundancy":[130],"them":[132],"resulting":[135],"concatenated":[139],"object":[140],"should":[141],"close":[143],"larger":[148,156],"constituent":[153],"CDM":[158,242],"objects,":[161],"more":[163],"dissimilar":[164],"they":[165],"are.":[166],"Classification,":[167],"clustering":[168],"detection":[171],"algorithms":[172],"then":[174],"use":[175],"this":[176,270],"wide":[181],"variety":[182],"applications.":[184],"Many":[185],"these":[187],"described":[189],"(Keogh":[191,195,259],"et":[192,196,260],"al.,":[193,261],"2004),":[194],"al.":[197],"2007),":[198],"references":[200],"therein.":[201],"This":[202],"works":[204],"when":[206],"(1)":[207],"large":[210],"it":[212],"computationally":[214],"expensive":[215],"compute":[217],"other":[218],"distances":[219,230],"(e.g.,":[220],"very":[221],"long":[222],"strings);":[223],"or":[224,234,251],"(2)":[225],"there":[226],"no":[228],"natural":[229],"none":[235],"reasonable":[238],"from":[239,265],"first":[240],"principles.":[241],"\u201cparameter-free\u201d":[244],"thus":[246],"avoids":[247],"over-fitting":[248],"relying":[252],"upon":[253],"assumptions":[254],"may":[256],"incorrect":[258],"2004).":[262],"Request":[263],"access":[264],"your":[266],"librarian":[267],"read":[269],"chapter's":[271],"full":[272],"text.":[273]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}