{"id":"https://openalex.org/W2112042392","doi":"https://doi.org/10.1109/bibe.2006.253327","title":"A Tool for Supporting Integration Across Multiple Flat-File Datasets","display_name":"A Tool for Supporting Integration Across Multiple Flat-File Datasets","publication_year":2006,"publication_date":"2006-10-01","ids":{"openalex":"https://openalex.org/W2112042392","doi":"https://doi.org/10.1109/bibe.2006.253327","mag":"2112042392"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2006.253327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5100342938","display_name":"Xuan Zhang","orcid":"https://orcid.org/0000-0003-0520-3934"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuan Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering Ohio State University, Columbus OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Ohio State University, Columbus OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025342178","display_name":"Gagan Agrawal","orcid":"https://orcid.org/0000-0002-2923-5327"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gagan Agrawal","raw_affiliation_strings":["Department of Computer Science and Engineering Ohio State University, Columbus OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Ohio State University, Columbus OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.393,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":3,"citation_normalized_percentile":{"value":0.346678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":72,"max":74},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"148"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9974,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9974,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9889,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9881,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biological-database","display_name":"Biological database","score":0.44094786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86780787},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7142498},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6160461},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.60007346},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5136208},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.50761473},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.47787657},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46057343},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.44094786},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.42387813},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40396175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36229935},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13466227},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11261886},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.10067269},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2006.253327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":26,"referenced_works":["https://openalex.org/W1484496011","https://openalex.org/W1509478745","https://openalex.org/W1556829891","https://openalex.org/W1556897979","https://openalex.org/W156213059","https://openalex.org/W1583245386","https://openalex.org/W1983594585","https://openalex.org/W1997532580","https://openalex.org/W2033229728","https://openalex.org/W2094258495","https://openalex.org/W2098035424","https://openalex.org/W2098601504","https://openalex.org/W2103538877","https://openalex.org/W2104086170","https://openalex.org/W2120057656","https://openalex.org/W2124616944","https://openalex.org/W2131165428","https://openalex.org/W2138067201","https://openalex.org/W2150721933","https://openalex.org/W2153075454","https://openalex.org/W2157058776","https://openalex.org/W2161666572","https://openalex.org/W2413578523","https://openalex.org/W2628074563","https://openalex.org/W4285719527","https://openalex.org/W51398133"],"related_works":["https://openalex.org/W4239016173","https://openalex.org/W2739872940","https://openalex.org/W2541393756","https://openalex.org/W2307569040","https://openalex.org/W2171665518","https://openalex.org/W2145752793","https://openalex.org/W2131941936","https://openalex.org/W2060096282","https://openalex.org/W1983206747","https://openalex.org/W115596161"],"abstract_inverted_index":{"Traditionally,":[0],"biologists":[1],"focused":[2],"on":[3,110],"a":[4,51,143],"single":[5],"research":[6,125],"subject.":[7],"New":[8],"high-throughput":[9],"experimental":[10],"and":[11,17,48,92,134,145],"analytical":[12],"technologies,":[13],"such":[14],"as":[15],"microarray":[16],"BLAST":[18],"programs,":[19],"have":[20,106,130],"changed":[21],"this.":[22],"An":[23],"important":[24],"functionality":[25,133],"required":[26],"now":[27],"is":[28,79],"the":[29,45,66,90,108,132],"ability":[30],"to":[31,87,102],"process":[32],"queries":[33],"about":[34],"multiple":[35],"data":[36,52,94,149],"entries":[37],"with":[38,65,89],"little":[39],"user":[40],"intervention.":[41],"This":[42],"paper":[43],"presents":[44],"design,":[46],"implementation,":[47],"evaluation":[49],"of":[50,115,136],"integration":[53,150],"tool":[54],"that":[55],"supports":[56],"database-like":[57],"query":[58],"operations":[59],"across":[60],"flat-file":[61,152],"biological":[62,112],"datasets.":[63],"Compared":[64],"existing":[67],"solutions,":[68],"our":[69,137,140],"system":[70,78,109],"has":[71],"several":[72],"advantages,":[73],"i.e.,":[74],"no":[75,93],"database":[76],"management":[77],"required,":[80],"users":[81],"can":[82],"still":[83],"use":[84],"declarative":[85],"languages":[86],"communicate":[88],"system,":[91],"parsing,":[95],"loading,":[96],"or":[97],"indexing":[98],"utility":[99],"programs":[100],"need":[101],"be":[103],"written.":[104],"We":[105],"used":[107],"three":[111],"queries,":[113],"each":[114],"which":[116],"was":[117],"inspired":[118],"by":[119],"an":[120],"actual":[121],"study":[122],"from":[123],"bioinformatics":[124],"literature.":[126],"These":[127],"case":[128],"studies":[129],"demonstrated":[131],"scalability":[135],"tool.":[138],"Overall,":[139],"approach":[141],"provides":[142],"light-weight":[144],"scalable":[146],"solution":[147],"for":[148],"over":[151],"datasets":[153]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2112042392","counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2024-12-12T07:15:11.274798","created_date":"2016-06-24"}