{"id":"https://openalex.org/W2116813167","doi":"https://doi.org/10.1109/dcc.2003.1194016","title":"DNA sequence compression using the normalized maximum likelihood model for discrete regression","display_name":"DNA sequence compression using the normalized maximum likelihood model for discrete regression","publication_year":2003,"publication_date":"2003-11-04","ids":{"openalex":"https://openalex.org/W2116813167","doi":"https://doi.org/10.1109/dcc.2003.1194016","mag":"2116813167"},"language":"en","primary_location":{"id":"doi:10.1109/dcc.2003.1194016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc.2003.1194016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Compression Conference, 2003. Proceedings. DCC 2003","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":null,"display_name":"I. Tabus","orcid":null},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"I. Tabus","raw_affiliation_strings":["Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","[Inst. of Signal Process., Tampere Univ. of Technol., Finland]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Inst. of Signal Process., Tampere Univ. of Technol., Finland]","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066920134","display_name":"Gergely Korodi","orcid":null},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"G. Korodi","raw_affiliation_strings":["Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","[Inst. of Signal Process., Tampere Univ. of Technol., Finland]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Inst. of Signal Process., Tampere Univ. of Technol., Finland]","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109212464","display_name":"J. Rissanen","orcid":null},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"J. Rissanen","raw_affiliation_strings":["Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","[Inst. of Signal Process., Tampere Univ. of Technol., Finland]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Inst. of Signal Process., Tampere Univ. of Technol., Finland]","institution_ids":["https://openalex.org/I150589677"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2984,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.8929653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","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/T11269","display_name":"Algorithms and Data Compression","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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9944999814033508,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9937999844551086,"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/minimum-description-length","display_name":"Minimum description length","score":0.733709990978241},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.600967288017273},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.594816267490387},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5693691372871399},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5310020446777344},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5170393586158752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49272826313972473},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4870884418487549},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4668923616409302},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.42681685090065},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.418089359998703},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38654857873916626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24633291363716125},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13643422722816467},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11212697625160217},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09017530083656311},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07182490825653076}],"concepts":[{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.733709990978241},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.600967288017273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.594816267490387},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5693691372871399},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5310020446777344},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5170393586158752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49272826313972473},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4870884418487549},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4668923616409302},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.42681685090065},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.418089359998703},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38654857873916626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24633291363716125},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13643422722816467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11212697625160217},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09017530083656311},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07182490825653076},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dcc.2003.1194016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc.2003.1194016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Compression Conference, 2003. Proceedings. DCC 2003","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":17,"referenced_works":["https://openalex.org/W1603190194","https://openalex.org/W1886627987","https://openalex.org/W1938301739","https://openalex.org/W1976076428","https://openalex.org/W1980569719","https://openalex.org/W2012680439","https://openalex.org/W2034323860","https://openalex.org/W2073097300","https://openalex.org/W2102098892","https://openalex.org/W2117953160","https://openalex.org/W2124871568","https://openalex.org/W2138200515","https://openalex.org/W2146028503","https://openalex.org/W4246382215","https://openalex.org/W4285719527","https://openalex.org/W6635869907","https://openalex.org/W6645321515"],"related_works":["https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W2032414556","https://openalex.org/W2169871401","https://openalex.org/W2057878850"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,18,26,57,95,103,138,142],"normalized":[3],"maximum":[4],"likelihood":[5],"(NML)":[6],"model":[7,29,45,56,125],"for":[8,32,46,108],"encoding":[9,47],"sequences":[10,110],"known":[11],"to":[12,38,99,129],"have":[13],"regularities":[14],"in":[15,51,132],"the":[16,27,48,55,77,101,104,123],"form":[17],"approximate":[19,49],"repetitions":[20],"was":[21,30,36,71],"discussed.":[22],"A":[23],"particular":[24],"version":[25],"NML":[28,124],"presented":[31],"discrete":[33],"regression,":[34],"which":[35,89],"shown":[37],"provide":[39],"a":[40,60,66,86,92,117],"very":[41],"powerful":[42],"yet":[43],"simple":[44,61,87],"repeats":[50,58],"DNA":[52,79,109,139],"sequences.":[53,145],"Combining":[54],"with":[59,76,111],"first":[62],"order":[63],"Markov":[64],"model,":[65,88,122],"fast":[67],"lossless":[68],"compression":[69,80,106],"method":[70],"obtained":[72],"that":[73,85],"compares":[74],"favorably":[75],"existing":[78],"programs.":[81],"It":[82],"is":[83,97],"remarkable":[84],"recursively":[90],"updates":[91],"small":[93],"number":[94],"parameters,":[96],"able":[98],"reach":[100],"state":[102],"art":[105],"ratio":[107],"much":[112],"more":[113],"complex":[114],"models.":[115],"Being":[116],"minimum":[118],"description":[119],"length":[120],"(MDL)":[121],"may":[126],"later":[127],"prove":[128],"be":[130],"useful":[131],"studying":[133],"global":[134],"and":[135],"local":[136],"features":[137],"or":[140],"possibly":[141],"other":[143],"biological":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}