{"id":"https://openalex.org/W2803612680","doi":"https://doi.org/10.1145/3233547.3233564","title":"A Practical and Efficient Algorithm for the k-mismatch Shortest Unique Substring Finding Problem","display_name":"A Practical and Efficient Algorithm for the k-mismatch Shortest Unique Substring Finding Problem","publication_year":2018,"publication_date":"2018-08-15","ids":{"openalex":"https://openalex.org/W2803612680","doi":"https://doi.org/10.1145/3233547.3233564","mag":"2803612680"},"language":"en","primary_location":{"id":"doi:10.1145/3233547.3233564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3233547.3233564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://stars.library.ucf.edu/scopus2015/10083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102954773","display_name":"Daniel R. Allen","orcid":"https://orcid.org/0000-0002-2331-928X"},"institutions":[{"id":"https://openalex.org/I159107703","display_name":"Eastern Washington University","ror":"https://ror.org/002g57a93","country_code":"US","type":"education","lineage":["https://openalex.org/I159107703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel R. Allen","raw_affiliation_strings":["Eastern Washington University, Cheney, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Washington University, Cheney, WA, USA","institution_ids":["https://openalex.org/I159107703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049669178","display_name":"Sharma V. Thankachan","orcid":"https://orcid.org/0000-0002-6852-1035"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharma V. Thankachan","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058084642","display_name":"Bojian Xu","orcid":"https://orcid.org/0000-0001-5642-6826"},"institutions":[{"id":"https://openalex.org/I159107703","display_name":"Eastern Washington University","ror":"https://ror.org/002g57a93","country_code":"US","type":"education","lineage":["https://openalex.org/I159107703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bojian Xu","raw_affiliation_strings":["Eastern Washington University, Cheney, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Washington University, Cheney, WA, USA","institution_ids":["https://openalex.org/I159107703"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4527,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65358756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9495999813079834,"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/T10575","display_name":"Wireless Communication Networks Research","score":0.9394999742507935,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/substring","display_name":"Substring","score":0.9394643902778625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6537300944328308},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5156441926956177},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.4211207628250122},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.18982920050621033},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.048792511224746704}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9394643902778625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6537300944328308},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5156441926956177},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.4211207628250122},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.18982920050621033},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.048792511224746704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3233547.3233564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3233547.3233564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:stars.library.ucf.edu:scopus2015-11082","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2015/10083","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2015-2019","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:stars.library.ucf.edu:scopus2015-11082","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2015/10083","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2015-2019","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W212038867","https://openalex.org/W263816278","https://openalex.org/W938539187","https://openalex.org/W1614203862","https://openalex.org/W1962019683","https://openalex.org/W1966552686","https://openalex.org/W1990061958","https://openalex.org/W2002204859","https://openalex.org/W2024147613","https://openalex.org/W2040322457","https://openalex.org/W2149098716","https://openalex.org/W2336925273","https://openalex.org/W2345969517","https://openalex.org/W2533248932"],"related_works":["https://openalex.org/W2393888177","https://openalex.org/W2544423928","https://openalex.org/W2967268719","https://openalex.org/W2115794623","https://openalex.org/W3115392711","https://openalex.org/W2100008676","https://openalex.org/W2360264381","https://openalex.org/W2067173559","https://openalex.org/W1613730747","https://openalex.org/W2541389358"],"abstract_inverted_index":{"This":[0],"paper":[1],"revisits":[2],"the":[3,18,22,36,64,71,79,85,115,148,160,188,202,238,259,337],"k-mismatch":[4,23,90,326],"shortest":[5,91,327],"unique":[6,92,328],"substring":[7,26,93,329],"finding":[8,330],"problem":[9,27],"and":[10,31,106,252,308,322],"demonstrates":[11,107],"that":[12,98,156,195,200,237,318],"a":[13,41,55,132,207,268,286,297],"technique":[14,162],"recently":[15],"presented":[16],"in":[17,40,110,139,166,175,293,342],"context":[19],"of":[20,35,49,84,159,201,221,223,240,271,288,301],"solving":[21],"average":[24],"common":[25],"can":[28,163,283],"be":[29,164,250],"adapted":[30,161],"combined":[32],"with":[33,137,147,212,219,291,296],"parts":[34],"existing":[37],"solution,":[38],"resulting":[39,174],"new":[42,75,100,278,320],"algorithm":[43,101,324],"which":[44,69,303],"has":[45],"expected":[46,317],"time":[47,82,112],"complexity":[48,58,83],"$O(n\u0142og^k":[50],"n":[51,62],")$,":[52],"while":[53,276],"maintaining":[54],"practical":[56,103,178,323],"space":[57],"at":[59],"$O(kn)$,":[60],"where":[61,217],"is":[63,70,102,122,154,235,304,316],"string":[65],"length.":[66],"When":[67],"$k>0$,":[68,275],"hard":[72],"case,":[73],"our":[74,99,129],"proposal":[76],"significantly":[77,245],"improves":[78],"any-case":[80],"$O(n^2)$":[81],"prior":[86,116,149,261],"best":[87,117,150,260],"method":[88,130],"for":[89,228,244,273,312,325],"finding.":[94],"Experimental":[95],"study":[96],"shows":[97],"to":[104,114,125,144,266,334],"implement":[105],"significant":[108,157,177],"improvements":[109],"processing":[111,193,206,247,285],"compared":[113,143],"solution's":[118],"implementation":[119],"when":[120,184,205],"k":[121],"small":[123],"relative":[124],"n.":[126],"For":[127,257],"example,":[128,183,258],"processes":[131],"200KB":[133],"sample":[134,209,270,287],"DNA":[135,210,269],"sequence":[136,211],"$k=1$":[138,292],"just":[140],"0.18":[141],"seconds":[142,146,295],"174.37":[145],"solution.":[151],"Further,":[152],"it":[153,234],"observed":[155],"portions":[158],"executed":[165],"parallel,":[167],"using":[168,185,280,336],"two":[169],"different":[170],"simple":[171],"concurrency":[172],"models,":[173],"further":[176],"performance":[179],"improvement.":[180],"As":[181],"an":[182,215],"8":[186],"cores,":[187,282],"parallel":[189],"implementations":[190],"both":[191,305],"achieved":[192],"times":[194,248],"are":[196,225],"less":[197],"than":[198],"$1/4$":[199],"serial":[203],"implementation,":[204],"10MB":[208],"$k=2$.":[213],"In":[214],"age":[216],"instances":[218],"thousands":[220],"gigabytes":[222],"RAM":[224],"readily":[226],"available":[227,307],"use":[229],"through":[230],"Cloud":[231,311],"infrastructure":[232],"providers,":[233],"likely":[236],"trade-off":[239],"additional":[241],"memory":[242,299],"usage":[243,300],"improved":[246],"will":[249,331],"desirable":[251],"needed":[253],"by":[254],"many":[255,313],"users.":[256,314],"solution":[262],"may":[263],"spend":[264],"years":[265],"finish":[267,284],"200MB":[272],"any":[274],"this":[277,289,319],"proposal,":[279],"24":[281],"size":[290],"$206.376$":[294],"peak":[298],"46GB,":[302],"easily":[306],"affordable":[309],"on":[310,339],"It":[315],"efficient":[321],"prove":[332],"useful":[333],"those":[335],"measure":[338],"long":[340],"sequences":[341],"fields":[343],"such":[344],"as":[345],"computational":[346],"biology.":[347]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}