{"id":"https://openalex.org/W2044580197","doi":"https://doi.org/10.1109/bdcloud.2014.79","title":"UDaaS: A Cloud-Based URL-Deduplication-as-a-Service for Big Datasets","display_name":"UDaaS: A Cloud-Based URL-Deduplication-as-a-Service for Big Datasets","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2044580197","doi":"https://doi.org/10.1109/bdcloud.2014.79","mag":"2044580197"},"language":"en","primary_location":{"id":"doi:10.1109/bdcloud.2014.79","doi":"https://doi.org/10.1109/bdcloud.2014.79","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bdcloud.2014.79","pdf_url":null,"source":{"id":"https://openalex.org/S7407088817","display_name":"IEEE International Conference on Big Data and Cloud Computing (BDCloud)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Fourth International Conference on Big Data and Cloud Computing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5004748347","display_name":"Shams Zawoad","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17301866","display_name":"University of Alabama","ror":"https://ror.org/03xrrjk67","country_code":"US","type":"education","lineage":["https://openalex.org/I17301866"]},{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shams Zawoad","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Alabama, Birmingham, AL, USA","Dept. of Comput. & Inf. Sci., Univ. of Alabama at Birmingham, Birmingham, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Alabama, Birmingham, AL, USA","institution_ids":["https://openalex.org/I17301866","https://openalex.org/I32389192"]},{"raw_affiliation_string":"Dept. of Comput. & Inf. Sci., Univ. of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076460405","display_name":"Ragib Hasan","orcid":"https://orcid.org/0000-0001-5248-8341","observed_orcids":["https://orcid.org/0000-0001-5248-8341"]},"institutions":[{"id":"https://openalex.org/I17301866","display_name":"University of Alabama","ror":"https://ror.org/03xrrjk67","country_code":"US","type":"education","lineage":["https://openalex.org/I17301866"]},{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ragib Hasan","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Alabama, Birmingham, AL, USA","Dept. of Comput. & Inf. Sci., Univ. of Alabama at Birmingham, Birmingham, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Alabama, Birmingham, AL, USA","institution_ids":["https://openalex.org/I17301866","https://openalex.org/I32389192"]},{"raw_affiliation_string":"Dept. of Comput. & Inf. Sci., Univ. of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068297866","display_name":"Gary Warner","orcid":"https://orcid.org/0000-0002-5595-9652","observed_orcids":["https://orcid.org/0000-0002-5595-9652"]},"institutions":[{"id":"https://openalex.org/I17301866","display_name":"University of Alabama","ror":"https://ror.org/03xrrjk67","country_code":"US","type":"education","lineage":["https://openalex.org/I17301866"]},{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Warner","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Alabama, Birmingham, AL, USA","Dept. of Comput. & Inf. Sci., Univ. of Alabama at Birmingham, Birmingham, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Alabama, Birmingham, AL, USA","institution_ids":["https://openalex.org/I17301866","https://openalex.org/I32389192"]},{"raw_affiliation_string":"Dept. of Comput. & Inf. Sci., Univ. of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026440046","display_name":"Anthony Skjellum Y","orcid":"https://orcid.org/0000-0001-5252-6600","observed_orcids":["https://orcid.org/0000-0001-5252-6600"]},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Skjellum","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University, USA","Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA#TAB#","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2844,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52308463,"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":"271","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.39500001072883606,"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/T11644","display_name":"Spam and Phishing Detection","score":0.39500001072883606,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.20170000195503235,"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/T11719","display_name":"Data Quality and Management","score":0.14650000631809235,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/malicious-website-detection","display_name":"malicious website detection","score":0.7459999918937683},{"id":"https://openalex.org/keywords/cloud-services","display_name":"cloud services","score":0.6629999876022339},{"id":"https://openalex.org/keywords/distributed-parallel-processing","display_name":"distributed parallel computing","score":0.746999979019165},{"id":"https://openalex.org/keywords/big-datasets","display_name":"big datasets","score":0.9330000281333923},{"id":"https://openalex.org/keywords/storage-reduction","display_name":"storage reduction","score":0.5569999814033508},{"id":"https://openalex.org/keywords/url-analysis","display_name":"URL analysis","score":0.4790000021457672}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.986434817314148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807929277420044},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7585132122039795},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4948698878288269},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.47497814893722534},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42517536878585815},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.381558895111084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3609454035758972},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1364271640777588},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bdcloud.2014.79","doi":"https://doi.org/10.1109/bdcloud.2014.79","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bdcloud.2014.79","pdf_url":null,"source":{"id":"https://openalex.org/S7407088817","display_name":"IEEE International Conference on Big Data and Cloud Computing (BDCloud)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Fourth International Conference on Big Data and Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1993648202","https://openalex.org/W2047319275","https://openalex.org/W2139565456","https://openalex.org/W2139572494","https://openalex.org/W2295731716"],"related_works":["https://openalex.org/W1973990666","https://openalex.org/W2934089203","https://openalex.org/W7164193930","https://openalex.org/W2295858358","https://openalex.org/W7134193715","https://openalex.org/W4410518098","https://openalex.org/W3169377711","https://openalex.org/W4285170126","https://openalex.org/W4285300949","https://openalex.org/W3110938589"],"abstract_inverted_index":{"Since":[0],"the":[1,17,49],"number":[2],"of":[3,20,51,60],"potential":[4],"malicious":[5,21,52],"URLs":[6],"from":[7],"diverse":[8],"sources":[9],"is":[10,14],"large,":[11],"URL":[12,23,31,42],"deduplication":[13,43],"needed":[15],"for":[16],"efficient":[18],"identification":[19],"websites.":[22],"Deduplication-as-a-Service":[24],"(UDaaS)":[25],"was":[26],"developed":[27],"to":[28,33],"help":[29],"a":[30,37],"analyst":[32],"deploy":[34],"and":[35,40,58],"manage":[36],"cloud-based":[38],"distributed":[39],"parallel":[41],"infrastructure":[44],"easily,":[45],"this":[46],"can":[47],"improve":[48],"performance":[50],"websites":[53],"detection":[54],"while":[55],"reducing":[56],"duplication":[57],"quantity":[59],"local":[61],"storage":[62],"requirements.":[63]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
