{"id":"https://openalex.org/W2366770652","doi":null,"title":"An Effective Approach to Eliminating Noises in HTML Pages","display_name":"An Effective Approach to Eliminating Noises in HTML Pages","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2366770652","mag":"2366770652"},"language":"en","primary_location":{"id":"mag:2366770652","doi":null,"is_oa":false,"landing_page_url":"http://en.cnki.com.cn/Article_en/CJFDTotal-JSJC200708029.htm","pdf_url":null,"source":{"id":"https://openalex.org/S2764825856","display_name":"Jisuanji gongcheng","issn_l":"1000-3428","issn":["1000-3428"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","poland-20"],"host_organization":"https://openalex.org/P4361727472","host_organization_name":"East China Computer Technology Research Institute","host_organization_lineage":["https://openalex.org/P4361727472"],"host_organization_lineage_names":["East China Computer Technology Research Institute"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Jisuanji gongcheng","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5065453511","display_name":"Cheng Luo","orcid":"https://orcid.org/0000-0002-6977-1773","observed_orcids":["https://orcid.org/0000-0002-6977-1773"]},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Luo","raw_affiliation_strings":["Information Engineering Institute,Information Engineering University,Zhengzhou 450002)"],"raw_orcid":"https://orcid.org/0000-0002-6977-1773","affiliations":[{"raw_affiliation_string":"Information Engineering Institute,Information Engineering University,Zhengzhou 450002)","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039649740","display_name":"Bicheng Li","orcid":"https://orcid.org/0000-0003-2218-3146","observed_orcids":["https://orcid.org/0000-0003-2218-3146"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bicheng Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2218-3146","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102756827","display_name":"Xianfei Zhang","orcid":"https://orcid.org/0000-0002-8872-4200","observed_orcids":["https://orcid.org/0000-0002-8872-4200"]},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianfei Zhang","raw_affiliation_strings":["Information Engineering Institute,Information Engineering University,Zhengzhou 450002)"],"raw_orcid":"https://orcid.org/0000-0002-8872-4200","affiliations":[{"raw_affiliation_string":"Information Engineering Institute,Information Engineering University,Zhengzhou 450002)","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9994999766349792,"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":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0003000000142492354,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":9.999999747378752e-05,"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/noise-reduction","display_name":"noise reduction","score":0.42399999499320984},{"id":"https://openalex.org/keywords/html-pages","display_name":"HTML pages","score":0.6050000190734863},{"id":"https://openalex.org/keywords/web-page-classification","display_name":"web page classification","score":0.6480000019073486},{"id":"https://openalex.org/keywords/pattern-tree","display_name":"pattern tree","score":0.8809999823570251},{"id":"https://openalex.org/keywords/tree-structure","display_name":"tree structure","score":0.5680000185966492},{"id":"https://openalex.org/keywords/website-layout","display_name":"web page layout","score":0.578000009059906},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.796999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9067196846008301},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.709077000617981},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5369263887405396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49458548426628113},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4794448912143707},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4561424255371094},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43905457854270935},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.42051151394844055},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10254368185997009},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2366770652","doi":null,"is_oa":false,"landing_page_url":"http://en.cnki.com.cn/Article_en/CJFDTotal-JSJC200708029.htm","pdf_url":null,"source":{"id":"https://openalex.org/S2764825856","display_name":"Jisuanji gongcheng","issn_l":"1000-3428","issn":["1000-3428"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","poland-20"],"host_organization":"https://openalex.org/P4361727472","host_organization_name":"East China Computer Technology Research Institute","host_organization_lineage":["https://openalex.org/P4361727472"],"host_organization_lineage_names":["East China Computer Technology Research Institute"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Jisuanji gongcheng","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1989338554","https://openalex.org/W2019264297","https://openalex.org/W2040075907","https://openalex.org/W2156632103"],"related_works":["https://openalex.org/W2391251053","https://openalex.org/W1555822132","https://openalex.org/W2122001021","https://openalex.org/W7217894119","https://openalex.org/W174477639","https://openalex.org/W2360827827","https://openalex.org/W2390371077","https://openalex.org/W4240344917","https://openalex.org/W2362391441","https://openalex.org/W7100864337"],"abstract_inverted_index":{"Most":[0],"Web":[1,17,36,50,68,94],"pages":[2,64],"usually":[3],"have":[4],"such":[5],"noisy":[6,83],"blocks":[7,84],"as":[8],"navigation":[9],"panels,copyright":[10],"and":[11,24],"advertisements,which":[12],"decreases":[13],"the":[14,32,46,59,63,76,79,86,105,108],"accuracies":[15],"of":[16,35,62,75,85,100,107],"applications":[18,103],"system.So":[19],"eliminating":[20],"noises":[21],"content":[22,48],"accurately":[23],"efficiently":[25],"is":[26,89],"a":[27,41,53,66,92],"key":[28],"technique":[29],"to":[30,44,81],"improve":[31],"service":[33],"qualities":[34],"application":[37],"systems.This":[38],"paper":[39],"proposes":[40],"novel":[42],"approach":[43,88,109],"reduce":[45,82],"noise":[47],"in":[49,65,78,91,102],"pages.It":[51],"uses":[52],"tree":[54],"structure,called":[55],"pattern":[56],"tree(PT),to":[57],"capture":[58],"common":[60],"layout":[61],"given":[67],"site.It":[69],"also":[70],"introduces":[71],"an":[72],"entropy-based":[73],"measure":[74],"node":[77],"PT":[80],"site.The":[87],"applied":[90],"SVM-based":[93],"page":[95],"classification":[96],"system.The":[97],"strong":[98],"evidence":[99],"improvement":[101],"verifies":[104],"validity":[106],"presented.":[110]},"counts_by_year":[],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2016-06-24T00:00:00"}
