{"id":"https://openalex.org/W2115615976","doi":"https://doi.org/10.1109/icccn.2002.1043051","title":"An efficient scheme to remove crawler traffic from the Internet","display_name":"An efficient scheme to remove crawler traffic from the Internet","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2115615976","doi":"https://doi.org/10.1109/icccn.2002.1043051","mag":"2115615976"},"language":"en","primary_location":{"id":"doi:10.1109/icccn.2002.1043051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn.2002.1043051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","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/A5061718239","display_name":"Xu Yuan","orcid":"https://orcid.org/0000-0003-3775-3033"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"X. Yuan","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Canada","Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029371742","display_name":"M.H. MacGregor","orcid":"https://orcid.org/0000-0002-2381-1290"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"M.H. MacGregor","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Canada","Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053810473","display_name":"Janelle Harms","orcid":"https://orcid.org/0000-0003-0769-5709"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J. Harms","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Canada","Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta., Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061718239"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.13502915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"90","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983999729156494,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8901678919792175},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7755354642868042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695728600025177},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.63887619972229},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5837523937225342},{"id":"https://openalex.org/keywords/internet-traffic","display_name":"Internet traffic","score":0.4510872960090637},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.390848845243454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06855714321136475}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8901678919792175},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7755354642868042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695728600025177},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.63887619972229},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5837523937225342},{"id":"https://openalex.org/C63969886","wikidata":"https://www.wikidata.org/wiki/Q3536440","display_name":"Internet traffic","level":3,"score":0.4510872960090637},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.390848845243454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06855714321136475},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccn.2002.1043051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn.2002.1043051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W201383773","https://openalex.org/W625975574","https://openalex.org/W1502099332","https://openalex.org/W1566984846","https://openalex.org/W1592975291","https://openalex.org/W1607542842","https://openalex.org/W2046412500","https://openalex.org/W2047421567","https://openalex.org/W2059387258","https://openalex.org/W2066636486","https://openalex.org/W2132581831","https://openalex.org/W2155659292","https://openalex.org/W2165625336","https://openalex.org/W2175110005","https://openalex.org/W6608185717","https://openalex.org/W6634031162","https://openalex.org/W6635453440","https://openalex.org/W6636246886","https://openalex.org/W6667169455"],"related_works":["https://openalex.org/W3005260231","https://openalex.org/W2904469652","https://openalex.org/W4362647146","https://openalex.org/W2383572231","https://openalex.org/W2042034567","https://openalex.org/W3179424333","https://openalex.org/W2782340266","https://openalex.org/W4230722125","https://openalex.org/W2149158941","https://openalex.org/W2937284497"],"abstract_inverted_index":{"We":[0,18],"estimate":[1],"that":[2,39,62],"approximately":[3],"40%":[4],"of":[5],"current":[6,73],"Internet":[7,43],"traffic":[8],"is":[9,65],"due":[10],"to":[11,53,67],"Web":[12],"crawlers":[13],"retrieving":[14],"pages":[15],"for":[16],"indexing.":[17],"address":[19],"this":[20],"problem":[21],"by":[22],"introducing":[23],"an":[24],"efficient":[25,70],"indexing":[26,64],"system":[27],"based":[28],"on":[29],"active":[30,37,63],"networks.":[31],"Our":[32,58],"approach":[33],"employs":[34],"strategically":[35],"placed":[36],"routers":[38],"constantly":[40],"monitor":[41],"passing":[42],"traffic,":[44],"analyze":[45],"it,":[46],"and":[47],"then":[48],"transmit":[49],"the":[50,72],"index":[51],"data":[52],"a":[54],"dedicated":[55],"back-end":[56],"repository.":[57],"simulations":[59],"have":[60],"shown":[61],"up":[66],"30%":[68],"more":[69],"than":[71],"crawler-based":[74],"techniques.":[75]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}