{"id":"https://openalex.org/W2101023181","doi":"https://doi.org/10.1145/2513456.2513488","title":"Efficient representation of DNA data for pattern recognition using failure factor oracles","display_name":"Efficient representation of DNA data for pattern recognition using failure factor oracles","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2101023181","doi":"https://doi.org/10.1145/2513456.2513488","mag":"2101023181"},"language":"en","primary_location":{"id":"doi:10.1145/2513456.2513488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513456.2513488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference","raw_type":"proceedings-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/A5043799147","display_name":"Loek Cleophas","orcid":"https://orcid.org/0000-0002-7221-3676"},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Loek Cleophas","raw_affiliation_strings":["University of Pretoria, Hatfield, Pretoria, Republic of South Africa"],"affiliations":[{"raw_affiliation_string":"University of Pretoria, Hatfield, Pretoria, Republic of South Africa","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106185216","display_name":"Derrick G. Kourie","orcid":null},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Derrick G. Kourie","raw_affiliation_strings":["University of Pretoria, Hatfield, Pretoria, Republic of South Africa"],"affiliations":[{"raw_affiliation_string":"University of Pretoria, Hatfield, Pretoria, Republic of South Africa","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027422026","display_name":"Bruce W. Watson","orcid":"https://orcid.org/0000-0003-0511-1837"},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Bruce W. Watson","raw_affiliation_strings":["University of Pretoria, Hatfield, Pretoria, Republic of South Africa"],"affiliations":[{"raw_affiliation_string":"University of Pretoria, Hatfield, Pretoria, Republic of South Africa","institution_ids":["https://openalex.org/I69552723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043799147"],"corresponding_institution_ids":["https://openalex.org/I69552723"],"apc_list":null,"apc_paid":null,"fwci":0.9888,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83219678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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/T12029","display_name":"DNA and Biological Computing","score":0.9987000226974487,"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/T11567","display_name":"semigroups and automata theory","score":0.9984999895095825,"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/sequence","display_name":"Sequence (biology)","score":0.6732888221740723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6079832315444946},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5716332793235779},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.505657434463501},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48146525025367737},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.47800126671791077},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.45617103576660156},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45448610186576843},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4154006242752075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23243772983551025}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6732888221740723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6079832315444946},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5716332793235779},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.505657434463501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48146525025367737},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.47800126671791077},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.45617103576660156},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45448610186576843},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4154006242752075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23243772983551025},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/2513456.2513488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513456.2513488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/029bbf09-6496-4891-8d9f-2a1a115c8e70","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/029bbf09-6496-4891-8d9f-2a1a115c8e70","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cleophas, L, Kourie, D G & Watson, B W 2013, Efficient representation of DNA data for pattern recognition using failure factor oracles. in SAICSIT '13 : Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference, 7-9 October 2013, East London, South Africa. Association for Computing Machinery, Inc., New York, pp. 369-377, 2013 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2013), East London, South Africa, 7/10/13. https://doi.org/10.1145/2513456.2513488","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:888839","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=888839","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:841341","is_oa":false,"landing_page_url":"http://repository.tue.nl/841341","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:888839","is_oa":false,"landing_page_url":"http://repository.tue.nl/888839","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:tue:oai:pure.tue.nl:publications/029bbf09-6496-4891-8d9f-2a1a115c8e70","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/029bbf09-6496-4891-8d9f-2a1a115c8e70","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SAICSIT '13 : Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference, 7-9 October 2013, East London, South Africa, 369 - 377","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W642038236","https://openalex.org/W1515839227","https://openalex.org/W1543564942","https://openalex.org/W1983788629","https://openalex.org/W1985108724","https://openalex.org/W2067216917","https://openalex.org/W2096375120","https://openalex.org/W2099964107","https://openalex.org/W2105459732","https://openalex.org/W2136740376","https://openalex.org/W2171909603","https://openalex.org/W2890091142","https://openalex.org/W2915973606","https://openalex.org/W6680202756"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3024364549","https://openalex.org/W3110702597","https://openalex.org/W4206019083","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2913469389"],"abstract_inverted_index":{"In":[0],"indexing":[1],"of":[2,12,105,111,116,123,151,173],"and":[3,66,101],"pattern":[4],"matching":[5],"on":[6,103,138],"DNA":[7,109],"sequences,":[8],"representing":[9],"all":[10],"factors":[11],"a":[13,40,57,69,75],"sequence":[14,139],"is":[15,21,90],"important.":[16],"One":[17],"efficient,":[18],"compact":[19,59],"representation":[20],"the":[22,27,63,98,165,171],"factor":[23,71,177],"oracle":[24,72],"(FO).":[25],"At":[26],"same":[28],"time,":[29],"any":[30],"classical":[31],"deterministic":[32],"finite":[33],"automata":[34],"(DFA)":[35],"can":[36],"be":[37,149,183],"transformed":[38],"to":[39,50,80,85,118,148,161],"so-called":[41],"failure":[42,48,70,126],"one":[43],"(FDFA),":[44],"which":[45],"may":[46,182],"use":[47,172],"transitions":[49,106,127],"replace":[51],"multiple":[52],"symbol":[53,134],"transitions,":[54,124],"potentially":[55],"yielding":[56],"more":[58],"representation.":[60],"We":[61,95],"combine":[62],"two":[64],"ideas":[65],"directly":[67],"construct":[68],"(FFO)":[73],"from":[74],"given":[76],"sequence,":[77],"in":[78,120],"contrast":[79],"ex":[81],"post":[82],"facto":[83],"transformation":[84],"an":[86],"FDFA.":[87],"The":[88],"algorithm":[89],"suitable":[91],"for":[92,107,170,175],"long":[93],"sequences.":[94],"empirically":[96],"compared":[97],"resulting":[99],"FFOs":[100,144,174],"FOs":[102],"number":[104,122],"many":[108],"sequences":[110],"lengths":[112],"4--512,":[113],"showing":[114],"gains":[115],"up":[117,130],"10%":[119],"total":[121],"with":[125],"also":[128],"taking":[129],"less":[131,184],"space":[132],"than":[133,186],"transitions.":[135],"Preliminary":[136],"results":[137,166],"processing":[140],"runtimes":[141],"when":[142,153],"using":[143,154],"originally":[145],"showed":[146],"these":[147],"multiples":[150],"those":[152],"FOs,":[155],"but":[156],"partial":[157],"memoization":[158],"already":[159],"leads":[160],"drastic":[162],"improvements.":[163],"Altogether":[164],"are":[167],"promising,":[168],"particularly":[169],"(repeated)":[176],"detection,":[178],"where":[179],"recognition":[180],"speed":[181],"important":[185],"memory":[187],"use.":[188]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
