{"id":"https://openalex.org/W2019358701","doi":"https://doi.org/10.1109/bigdata.2013.6691698","title":"Efficient near-duplicate document detection using FPGAs","display_name":"Efficient near-duplicate document detection using FPGAs","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2019358701","doi":"https://doi.org/10.1109/bigdata.2013.6691698","mag":"2019358701"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/A5018696698","display_name":"Xi Luo","orcid":"https://orcid.org/0000-0001-9068-0879"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xi Luo","raw_affiliation_strings":["Computer Science and Engineering, UC Riverside, Riverside, CA, USA","Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033921328","display_name":"Walid Najjar","orcid":"https://orcid.org/0000-0001-6761-6801"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walid Najjar","raw_affiliation_strings":["Computer Science and Engineering, UC Riverside, Riverside, CA, USA","Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113814074","display_name":"Vagelis Hristidis","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vagelis Hristidis","raw_affiliation_strings":["Computer Science and Engineering, UC Riverside, Riverside, CA, USA","Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018696698"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.3216,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56633035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8591539859771729},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6774386167526245},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6511746644973755},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.6213271021842957},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.5992282032966614},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5613289475440979},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5515746474266052},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.506278395652771},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5015244483947754},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.49406102299690247},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45853716135025024},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2579802870750427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21405205130577087},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18169867992401123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591539859771729},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6774386167526245},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6511746644973755},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.6213271021842957},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5992282032966614},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5613289475440979},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5515746474266052},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.506278395652771},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5015244483947754},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.49406102299690247},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45853716135025024},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2579802870750427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21405205130577087},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18169867992401123},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2013.6691698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.428.6157","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.428.6157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucr.edu/~najjar/papers/2013/BPOE-2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W61575366","https://openalex.org/W2010484138","https://openalex.org/W2012833704","https://openalex.org/W2022377611","https://openalex.org/W2054882590","https://openalex.org/W2078242255","https://openalex.org/W2085922539","https://openalex.org/W2108220022","https://openalex.org/W2112795577","https://openalex.org/W2114670894","https://openalex.org/W2115294662","https://openalex.org/W2120058970","https://openalex.org/W2121847343","https://openalex.org/W2142945794","https://openalex.org/W2144799503","https://openalex.org/W2145349611","https://openalex.org/W3128942091","https://openalex.org/W4230940751","https://openalex.org/W4246119624"],"related_works":["https://openalex.org/W1494289317","https://openalex.org/W1531307672","https://openalex.org/W2007540612","https://openalex.org/W2611868502","https://openalex.org/W2416529140","https://openalex.org/W2180288160","https://openalex.org/W2165259681","https://openalex.org/W162676011","https://openalex.org/W2612888708","https://openalex.org/W2888987343"],"abstract_inverted_index":{"Detecting":[0],"duplicate":[1],"and":[2,60,144,170],"near-duplicate":[3,178],"documents":[4,35,47],"is":[5,20,104,114],"critical":[6],"in":[7,42,139,166,176],"applications":[8],"like":[9],"Web":[10],"crawling":[11],"since":[12],"it":[13],"helps":[14],"save":[15],"document":[16,157],"processing":[17],"resources.":[18],"Simhash":[19],"a":[21,26,30,43,134,149,162],"state-of-art":[22],"method":[23],"to":[24,29,88,92,174,183],"assign":[25],"bit-string":[27],"fingerprint":[28,56,136],"document,":[31,59],"such":[32],"that":[33,100,141],"similar":[34,37,65],"have":[36],"fingerprints.":[38],"Finding":[39],"the":[40,54,78,83,90,101,107,115,167],"near-duplicates":[41],"large":[44,154],"collection":[45],"of":[46,49,57,64,86,117,124,164,172],"consists":[48],"two":[50],"stages:":[51],"(a)":[52],"compute":[53,89],"simhash":[55,125,168],"each":[58],"(b)":[61],"find":[62],"pairs":[63],"fingerprints":[66,111],"by":[67,106,132],"computing":[68,137],"their":[69],"Hamming":[70,94],"distance.":[71,95],"Previous":[72],"work":[73],"has":[74],"focused":[75],"on":[76,126,153],"optimizing":[77],"second":[79],"stage,":[80],"i.e.,":[81],"avoiding":[82],"quadratic":[84],"number":[85],"comparisons":[87],"all":[91,93],"However,":[96],"our":[97],"experiments":[98,160],"show":[99,161],"total":[102],"time":[103,181],"dominated":[105],"first":[108],"stage":[109],"(the":[110],"computation),":[112],"which":[113],"focus":[116],"this":[118],"paper.":[119],"We":[120,147],"propose":[121],"an":[122],"implementation":[123],"Field":[127],"Programmable":[128],"Gate":[129],"Arrays":[130],"(FPGAs),":[131],"implementing":[133],"customized":[135],"engine":[138],"hardware":[140],"exploits":[142],"parallelization":[143],"pipelining":[145],"opportunities.":[146],"present":[148],"comprehensive":[150],"experimental":[151],"evaluation":[152],"diverse":[155],"real":[156],"datasets.":[158],"Our":[159],"speedup":[163],"362\u00d7":[165],"computation,":[169],"savings":[171],"up":[173],"98%":[175],"overall":[177],"detection":[179],"execution":[180],"compared":[182],"using":[184],"multi-core":[185],"CPUs.":[186]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}