{"id":"https://openalex.org/W4251675061","doi":"https://doi.org/10.1109/ideas.2007.4318093","title":"CINDI Robot: an Intelligent Web Crawler Based on Multi-level Inspection","display_name":"CINDI Robot: an Intelligent Web Crawler Based on Multi-level Inspection","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W4251675061","doi":"https://doi.org/10.1109/ideas.2007.4318093"},"language":"en","primary_location":{"id":"doi:10.1109/ideas.2007.4318093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ideas.2007.4318093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th International Database Engineering and Applications Symposium (IDEAS 2007)","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/A5100403681","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0003-1169-7678"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":["Department of Computer Science, Concordia University, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064963422","display_name":"Bipin C. Desai","orcid":"https://orcid.org/0000-0002-9142-7928"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bipin C. Desai","raw_affiliation_strings":["Department of Computer Science, Concordia University, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101668814","display_name":"Cong Zhou","orcid":"https://orcid.org/0000-0003-1875-6335"},"institutions":[{"id":"https://openalex.org/I4210141720","display_name":"Motorola (Canada)","ror":"https://ror.org/047zhzq42","country_code":"CA","type":"company","lineage":["https://openalex.org/I1333370159","https://openalex.org/I4210141720"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cong Zhou","raw_affiliation_strings":["Motorola Canada Software Center, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola Canada Software Center, Canada","institution_ids":["https://openalex.org/I4210141720"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8291,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87999135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"93","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9735999703407288,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9487000107765198,"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/web-crawler","display_name":"Web crawler","score":0.943968653678894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6901992559432983},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6389322876930237},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6344282627105713},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5897186398506165},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5543288588523865},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5155494213104248},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4643478989601135},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4529799222946167},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4506726861000061},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45016297698020935},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3958017826080322},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.36508411169052124},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3513949513435364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19446176290512085}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.943968653678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901992559432983},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6389322876930237},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6344282627105713},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5897186398506165},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5543288588523865},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5155494213104248},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4643478989601135},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4529799222946167},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4506726861000061},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45016297698020935},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3958017826080322},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.36508411169052124},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3513949513435364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19446176290512085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ideas.2007.4318093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ideas.2007.4318093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th International Database Engineering and Applications Symposium (IDEAS 2007)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W127111085","https://openalex.org/W827894772","https://openalex.org/W1563088657","https://openalex.org/W1674850363","https://openalex.org/W1721182246","https://openalex.org/W2007687650","https://openalex.org/W2102942431","https://openalex.org/W2107584622","https://openalex.org/W2124673015","https://openalex.org/W2150827944","https://openalex.org/W2156909104","https://openalex.org/W2325227998","https://openalex.org/W6623266780","https://openalex.org/W6640862754","https://openalex.org/W6675604878","https://openalex.org/W6678701036"],"related_works":["https://openalex.org/W2402678663","https://openalex.org/W2277785728","https://openalex.org/W2368717146","https://openalex.org/W2112685907","https://openalex.org/W2134614621","https://openalex.org/W3201526811","https://openalex.org/W2388966984","https://openalex.org/W4200125296","https://openalex.org/W1994958611","https://openalex.org/W3205049278"],"abstract_inverted_index":{"With":[0],"the":[1,4,22,58,62,66,82],"explosion":[2],"of":[3,61],"Web,":[5],"focused":[6,29],"Web":[7,13,18,30,51,70],"crawlers":[8,14],"are":[9],"gaining":[10],"attention.":[11],"Focused":[12],"aim":[15],"at":[16],"finding":[17,34],"pages":[19],"related":[20],"to":[21,33,48,65],"pre-defined":[23],"topic.":[24],"CINDI":[25],"Robot":[26],"is":[27],"a":[28,44],"crawler":[31],"devoted":[32],"computer":[35],"science":[36],"and":[37,78],"software":[38],"engineering":[39],"academic":[40],"documents.":[41],"We":[42],"propose":[43],"multi-level":[45,55,90],"inspection":[46,56,91],"scheme":[47],"discover":[49],"relevant":[50],"pages.":[52],"Through":[53],"this":[54,89],"scheme,":[57],"text":[59,77],"feature":[60],"content":[63],"contributes":[64],"classification;":[67],"furthermore":[68],"other":[69,94],"characteristics,":[71],"such":[72],"as":[73],"URL":[74],"pattern,":[75],"anchor":[76],"so":[79],"on,":[80],"assist":[81],"decision":[83],"process.":[84],"The":[85],"experiment":[86],"result":[87],"demonstrates":[88],"method":[92],"outperforms":[93],"traditional":[95],"methods.":[96]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
