{"id":"https://openalex.org/W2160447394","doi":"https://doi.org/10.1109/fskd.2012.6233750","title":"Region based data extraction","display_name":"Region based data extraction","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2160447394","doi":"https://doi.org/10.1109/fskd.2012.6233750","mag":"2160447394"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2012.6233750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6233750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","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/A5088121730","display_name":"Pui Leng Goh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143550","display_name":"Taylor's University","ror":"https://ror.org/0498pcx51","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210143550"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Pui Leng Goh","raw_affiliation_strings":["School of Computing and IT, Taylor's University College, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Computing and IT, Taylor's University College, Malaysia","institution_ids":["https://openalex.org/I4210143550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076993574","display_name":"Jer Lang Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143550","display_name":"Taylor's University","ror":"https://ror.org/0498pcx51","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210143550"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jer Lang Hong","raw_affiliation_strings":["School of Computing and IT, Taylor's University College, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Computing and IT, Taylor's University College, Malaysia","institution_ids":["https://openalex.org/I4210143550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087269137","display_name":"Ee Xion Tan","orcid":"https://orcid.org/0000-0003-3338-287X"},"institutions":[{"id":"https://openalex.org/I4210143550","display_name":"Taylor's University","ror":"https://ror.org/0498pcx51","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210143550"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ee Xion Tan","raw_affiliation_strings":["School of Computing and IT, Taylor's University College, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Computing and IT, Taylor's University College, Malaysia","institution_ids":["https://openalex.org/I4210143550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045719777","display_name":"Wei Wei Goh","orcid":"https://orcid.org/0000-0002-8577-8481"},"institutions":[{"id":"https://openalex.org/I4210143550","display_name":"Taylor's University","ror":"https://ror.org/0498pcx51","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210143550"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Wei Wei Goh","raw_affiliation_strings":["School of Computing and IT, Taylor's University College, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Computing and IT, Taylor's University College, Malaysia","institution_ids":["https://openalex.org/I4210143550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088121730"],"corresponding_institution_ids":["https://openalex.org/I4210143550"],"apc_list":null,"apc_paid":null,"fwci":0.734,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83106301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1196","last_page":"1200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":0.9695000052452087,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9574000239372253,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8401539921760559},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6790066361427307},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5465991497039795},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5278223156929016},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5166428685188293},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49653559923171997},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.4949941039085388},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.47953295707702637},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4664776921272278},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43299901485443115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4242200255393982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4051131308078766},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.16181179881095886},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12420877814292908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8401539921760559},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6790066361427307},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5465991497039795},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5278223156929016},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5166428685188293},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49653559923171997},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.4949941039085388},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.47953295707702637},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4664776921272278},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43299901485443115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4242200255393982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4051131308078766},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.16181179881095886},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12420877814292908},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/fskd.2012.6233750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6233750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.1120","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.1120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ibimapublishing.com/journals/CIBIMA/2013/743515/743515.pdf","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":17,"referenced_works":["https://openalex.org/W6578894","https://openalex.org/W2015551056","https://openalex.org/W2035302703","https://openalex.org/W2104086170","https://openalex.org/W2128341918","https://openalex.org/W2133669904","https://openalex.org/W2134907429","https://openalex.org/W2138396769","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W2154872327","https://openalex.org/W2160189941","https://openalex.org/W2168196213","https://openalex.org/W4232071090","https://openalex.org/W6600252591","https://openalex.org/W6675573929","https://openalex.org/W6683516198"],"related_works":["https://openalex.org/W2065605022","https://openalex.org/W3183046488","https://openalex.org/W2367158473","https://openalex.org/W2363029778","https://openalex.org/W4280620143","https://openalex.org/W2355845000","https://openalex.org/W2063800210","https://openalex.org/W2374762067","https://openalex.org/W2379851518","https://openalex.org/W2369251627"],"abstract_inverted_index":{"Wrappers":[0],"are":[1,27,33,59,80,84],"tools":[2],"used":[3],"to":[4,20,42,48,62,67,91,104,115,132],"extract":[5,21,105],"relevant":[6,135,147],"information":[7,46,106],"from":[8,71,107,145],"HTML":[9,108],"pages.":[10,109],"Current":[11],"approaches":[12],"use":[13],"DOM":[14,23],"tree,":[15],"visual":[16,38,69,101,113,150],"cue,":[17],"and":[18,29,87],"ontology":[19],"data.":[22],"tree":[24],"based":[25,39,53,78,102],"techniques":[26],"fast":[28],"simple.":[30],"However,":[31],"they":[32,83],"not":[34],"as":[35,37,127],"accurate":[36],"wrappers":[40,79],"due":[41,61],"lack":[43],"of":[44,124],"additional":[45],"needed":[47,66],"perform":[49],"data":[50,144,163],"extraction.":[51,138,164],"Visual":[52],"wrappers,":[54],"on":[55],"the":[56,63,72,121,134,146],"other":[57],"hand,":[58],"slow":[60,86],"extra":[64],"processing":[65],"obtain":[68],"cue":[70,114],"underlying":[73],"browser":[74],"rendering":[75],"engine.":[76],"Ontology":[77],"accurate,":[81],"but":[82],"also":[85],"need":[88],"manual":[89],"tuning":[90],"operate":[92],"them.":[93],"In":[94],"this":[95],"paper,":[96],"we":[97],"propose":[98],"a":[99],"novel":[100],"wrapper":[103,111,129,141,157,160],"Our":[110],"uses":[112],"eliminate":[116],"unnecessary":[117],"regions,":[118],"hence":[119],"reduces":[120],"running":[122],"time":[123],"extraction":[125],"task":[126],"our":[128,140,156],"only":[130],"needs":[131],"consider":[133],"region":[136,148],"for":[137],"Then,":[139],"removes":[142],"irrelevant":[143],"using":[149],"cue.":[151],"Experiment":[152],"results":[153],"show":[154],"that":[155],"outperforms":[158],"state-of-the-art":[159],"WISH":[161],"in":[162]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
