{"id":"https://openalex.org/W2012231860","doi":"https://doi.org/10.4304/jcp.5.4.500-507","title":"Efficient Selection and Integration of Hidden Web Database","display_name":"Efficient Selection and Integration of Hidden Web Database","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2012231860","doi":"https://doi.org/10.4304/jcp.5.4.500-507","mag":"2012231860"},"language":"en","primary_location":{"id":"doi:10.4304/jcp.5.4.500-507","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jcp.5.4.500-507","pdf_url":null,"source":{"id":"https://openalex.org/S77894049","display_name":"Journal of Computers","issn_l":"1796-203X","issn":["1796-203X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computers","raw_type":"journal-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/A5032473728","display_name":"Xuefeng Xian","orcid":"https://orcid.org/0000-0002-0918-3128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuefeng Xian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016091616","display_name":"Pengpeng Zhao","orcid":"https://orcid.org/0000-0001-6721-6576"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengpeng Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059710821","display_name":"Yuanfeng Yang","orcid":"https://orcid.org/0000-0003-4881-0523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanfeng Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103572960","display_name":"Jie Xin","orcid":"https://orcid.org/0000-0002-9162-6871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100602190","display_name":"Zhiming Cui","orcid":"https://orcid.org/0000-0002-2960-2051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiming Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7077,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82522704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9966999888420105,"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":0.9966999888420105,"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/T12799","display_name":"Mobile and Web Applications","score":0.9876000285148621,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9830999970436096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7208870053291321},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.6289584040641785},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6085915565490723},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5045684576034546},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3670511543750763},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32867759466171265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22833845019340515},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.14187148213386536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7208870053291321},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.6289584040641785},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6085915565490723},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5045684576034546},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3670511543750763},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32867759466171265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22833845019340515},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.14187148213386536}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4304/jcp.5.4.500-507","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jcp.5.4.500-507","pdf_url":null,"source":{"id":"https://openalex.org/S77894049","display_name":"Journal of Computers","issn_l":"1796-203X","issn":["1796-203X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computers","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.634.5397","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.634.5397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ojs.academypublisher.com/index.php/jcp/article/viewFile/0504500507/1610/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2037906003","https://openalex.org/W2953265498","https://openalex.org/W4378699829","https://openalex.org/W2533455610","https://openalex.org/W4248236804","https://openalex.org/W2028002993","https://openalex.org/W2910532728","https://openalex.org/W1551575434","https://openalex.org/W4300526709"],"abstract_inverted_index":{"Abstract\u2014An":[0],"ever":[1],"increasing":[2],"amount":[3],"of":[4,33,38,73,88,107,127,145,189,209],"valuable":[5],"information":[6,23],"is":[7,57,110],"stored":[8],"in":[9,60,66,161],"web":[10,34,54,62,103,120,157,173,180,190,217],"databases,":[11],"&amp;quot;hidden":[12],"&amp;quot;":[13],"behind":[14],"search":[15],"interfaces.":[16],"A":[17],"new":[18,147],"application":[19],"area":[20],"emerge":[21],"for":[22],"retrieval":[24],"and":[25,84,100,143,171,186],"integration.":[26],"There":[27],"may":[28],"be":[29],"hundreds":[30],"or":[31],"thousands":[32],"databases":[35,63,181,191],"providing":[36],"data":[37,81,148,215],"relevance":[39],"to":[40,51,58,64,97,123,151,164,169],"a":[41,48,111,124,136,201,206],"particular":[42],"domain":[43],"on":[44,140,177],"the":[45,67,71,75,85,119,141,156,184],"web.":[46],"So":[47],"primary":[49],"challenge":[50],"internet-scale":[52],"hidden":[53,179],"database":[55,121,218],"integration":[56,68,129,152,198],"determine":[59],"which":[61],"include":[65],"system":[69,76,130,153,199],"with":[70,200],"aim":[72],"making":[74],"contain":[77],"as":[78,82],"much":[79,117],"high-quality":[80],"possible":[83],"least":[86],"degree":[87],"overlap.":[89],"In":[90],"this":[91,108],"paper,":[92],"we":[93],"present":[94],"an":[95,128,197],"approach":[96,109,168,195],"iteratively":[98],"select":[99,170],"integrate":[101,172],"candidate":[102],"database.":[104,158,174],"The":[105],"core":[106],"benefit":[112,118,137],"function":[113,138],"that":[114,149,183],"evaluates":[115],"how":[116,163],"brings":[122],"given":[125],"status":[126],"by":[131,154,193],"integrating":[132,155],"it.":[133],"We":[134,159],"devise":[135],"based":[139],"volume":[142],"quality":[144],"those":[146],"added":[150],"show":[160],"practice":[162],"efficiently":[165],"apply":[166],"our":[167,194],"Our":[175],"experiments":[176],"real":[178],"indicate":[182],"selected":[185],"integrated":[187],"result":[188],"produced":[192],"yields":[196],"significant":[202],"higher":[203],"utilities":[204],"than":[205],"wide":[207],"range":[208],"other":[210],"strategies.":[211],"Index":[212],"Terms\u2014hidden":[213],"web,":[214],"integration,":[216],"selection.":[219],"I.":[220]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
