{"id":"https://openalex.org/W2007090054","doi":"https://doi.org/10.1145/1980422.1980452","title":"Species identification based on approximate matching","display_name":"Species identification based on approximate matching","publication_year":2011,"publication_date":"2011-03-25","ids":{"openalex":"https://openalex.org/W2007090054","doi":"https://doi.org/10.1145/1980422.1980452","mag":"2007090054"},"language":"en","primary_location":{"id":"doi:10.1145/1980422.1980452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1980422.1980452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Annual ACM Bangalore 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/A5040815462","display_name":"Nagamma Patil","orcid":"https://orcid.org/0000-0001-9924-9559"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nagamma Patil","raw_affiliation_strings":["Indian Institute of Technology, Roorkee, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082753354","display_name":"Durga Toshniwal","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Durga Toshniwal","raw_affiliation_strings":["Indian Institute of Technology, Roorkee, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109127163","display_name":"Kumkum Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kumkum Garg","raw_affiliation_strings":["Manipal Institute of Technology, Manipal, India","(Manipal Institute of Technology, Manipal, India)"],"affiliations":[{"raw_affiliation_string":"Manipal Institute of Technology, Manipal, India","institution_ids":["https://openalex.org/I164861460"]},{"raw_affiliation_string":"(Manipal Institute of Technology, Manipal, India)","institution_ids":["https://openalex.org/I164861460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040815462"],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":0.3909,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60848853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965000152587891,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965000152587891,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9954000115394592,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9930999875068665,"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/classifier","display_name":"Classifier (UML)","score":0.6853512525558472},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6543936729431152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6323457956314087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5823706388473511},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5414365530014038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.528583288192749},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4634980857372284},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4377145767211914},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.42925670742988586},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4273113012313843},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.419761061668396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25633153319358826},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1433652937412262},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13047882914543152}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6853512525558472},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6543936729431152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323457956314087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5823706388473511},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5414365530014038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.528583288192749},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4634980857372284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4377145767211914},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.42925670742988586},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4273113012313843},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.419761061668396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25633153319358826},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1433652937412262},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13047882914543152},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1980422.1980452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1980422.1980452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Annual ACM Bangalore Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W208128215","https://openalex.org/W938539187","https://openalex.org/W1610836425","https://openalex.org/W1912123407","https://openalex.org/W1957502337","https://openalex.org/W1990061958","https://openalex.org/W1996640618","https://openalex.org/W2001496424","https://openalex.org/W2068308871","https://openalex.org/W2077096663","https://openalex.org/W2113528688","https://openalex.org/W2123504579","https://openalex.org/W2128757566","https://openalex.org/W2129075788","https://openalex.org/W2134153749","https://openalex.org/W2136241053","https://openalex.org/W2140190241","https://openalex.org/W2140320695","https://openalex.org/W2143533311","https://openalex.org/W2144787334","https://openalex.org/W2322205982","https://openalex.org/W2466512847","https://openalex.org/W2757059711","https://openalex.org/W6624626827"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2394466068","https://openalex.org/W1987683558","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W4387382336","https://openalex.org/W1968695676","https://openalex.org/W4385884940"],"abstract_inverted_index":{"Genomic":[0],"data":[1,86,127],"mining":[2,87],"and":[3,61,95,115,134],"knowledge":[4],"extraction":[5,43],"is":[6],"an":[7],"important":[8],"problem":[9],"in":[10],"bioinformatics.":[11],"Existing":[12],"methods":[13],"for":[14,29,75],"species":[15,130],"identification":[16,30],"are":[17,71,101,136],"based":[18],"on":[19,111],"n-grams.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"a":[26,34],"novel":[27],"approach":[28],"of":[31,36,44,59,78,108,128],"species.":[32],"Given":[33],"database":[35],"genomic":[37],"sequences,":[38],"our":[39],"proposed":[40,140],"work":[41],"includes":[42],"all":[45],"candidate/subsequences":[46],"that":[47,119],"satisfy:":[48],"length":[49],"grater":[50,63],"or":[51,64],"equal":[52,65],"to":[53,66,138],"given":[54,57],"minimum":[55],"length,":[56],"number":[58],"mismatches":[60],"support":[62,92],"user":[67],"threshold.":[68],"These":[69],"patterns":[70],"used":[72,137],"as":[73],"features":[74],"classifier.":[76],"Classification":[77],"genome":[79],"sequences":[80],"has":[81],"been":[82],"done":[83],"by":[84],"using":[85],"techniques":[88],"namely,":[89],"Naive":[90],"Bayes,":[91],"vector":[93],"machine":[94],"nearest":[96],"neighbor.":[97],"Individual":[98],"classifier":[99],"accuracies":[100],"reported.":[102],"We":[103],"also":[104],"show":[105],"the":[106,112],"effect":[107],"sampling":[109,124],"size":[110],"classification":[113,120],"accuracy":[114,121],"it":[116],"was":[117],"observed":[118],"increases":[122],"with":[123],"size.":[125],"Genome":[126],"two":[129],"namely":[131],"E.":[132],"coli":[133],"Yeast":[135],"verify":[139],"method.":[141]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
