{"id":"https://openalex.org/W2020080418","doi":"https://doi.org/10.1145/2247596.2247624","title":"Towards \"intelligent compression\" in streams","display_name":"Towards \"intelligent compression\" in streams","publication_year":2012,"publication_date":"2012-03-27","ids":{"openalex":"https://openalex.org/W2020080418","doi":"https://doi.org/10.1145/2247596.2247624","mag":"2020080418"},"language":"en","primary_location":{"id":"doi:10.1145/2247596.2247624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","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/A5053023517","display_name":"Sourav Dutta","orcid":"https://orcid.org/0000-0002-8934-9166"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sourav Dutta","raw_affiliation_strings":["IBM Research, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021010333","display_name":"Souvik Bhattacherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Souvik Bhattacherjee","raw_affiliation_strings":["IBM Research, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109064591","display_name":"Ankur Narang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankur Narang","raw_affiliation_strings":["IBM Research, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053023517"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":2.4822,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89404064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"228","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.82768714427948},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.652982771396637},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.496938019990921},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.45830798149108887},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.4442511200904846},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.42601072788238525},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.41644641757011414},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.410917192697525},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3836343288421631},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35322052240371704},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3136816918849945},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.21384045481681824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82768714427948},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.652982771396637},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.496938019990921},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.45830798149108887},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.4442511200904846},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42601072788238525},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.41644641757011414},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.410917192697525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3836343288421631},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35322052240371704},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3136816918849945},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21384045481681824},{"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:10.1145/2247596.2247624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W41415572","https://openalex.org/W200233886","https://openalex.org/W1558092379","https://openalex.org/W1564712904","https://openalex.org/W1565494300","https://openalex.org/W1575097427","https://openalex.org/W1576397915","https://openalex.org/W1588030505","https://openalex.org/W1613836731","https://openalex.org/W1993284846","https://openalex.org/W1993482412","https://openalex.org/W2023797161","https://openalex.org/W2025051251","https://openalex.org/W2053154469","https://openalex.org/W2053449578","https://openalex.org/W2056049383","https://openalex.org/W2062652918","https://openalex.org/W2063743738","https://openalex.org/W2064379477","https://openalex.org/W2065290081","https://openalex.org/W2065610969","https://openalex.org/W2067432306","https://openalex.org/W2080330461","https://openalex.org/W2081189989","https://openalex.org/W2081533422","https://openalex.org/W2082553115","https://openalex.org/W2108084305","https://openalex.org/W2111549955","https://openalex.org/W2116967744","https://openalex.org/W2117098909","https://openalex.org/W2119885577","https://openalex.org/W2121133177","https://openalex.org/W2123845384","https://openalex.org/W2125763460","https://openalex.org/W2126540423","https://openalex.org/W2132627996","https://openalex.org/W2134786002","https://openalex.org/W2135955253","https://openalex.org/W2136986825","https://openalex.org/W2140733653","https://openalex.org/W2142808699","https://openalex.org/W2151823597","https://openalex.org/W2164456230","https://openalex.org/W2164855881","https://openalex.org/W2322524800","https://openalex.org/W2511894128","https://openalex.org/W4237219250","https://openalex.org/W6634463810","https://openalex.org/W6671428793"],"related_works":["https://openalex.org/W3008420177","https://openalex.org/W2942719460","https://openalex.org/W2371981271","https://openalex.org/W3113874423","https://openalex.org/W2806950186","https://openalex.org/W2605169415","https://openalex.org/W2082671441","https://openalex.org/W180351855","https://openalex.org/W2538312128","https://openalex.org/W2904574017"],"abstract_inverted_index":{"With":[0],"the":[1,102,111],"explosion":[2],"of":[3,16,22,27,53,85,99,114],"information":[4],"stored":[5],"world-wide,":[6],"data":[7,28,36,104,115],"intensive":[8],"computing":[9],"has":[10,59],"emerged":[11],"as":[12,33],"a":[13,61,107,126,133],"central":[14],"area":[15,84],"research.":[17],"Efficient":[18],"management":[19],"and":[20,74,80,97,138],"processing":[21,79],"this":[23,123],"massively":[24],"exponential":[25],"amount":[26],"from":[29,65,101,132],"diverse":[30],"sources,":[31],"such":[32,66],"telecommunication":[34],"call":[35],"records,":[37,42],"telescope":[38],"imagery,":[39],"online":[40],"transaction":[41],"web":[43],"pages,":[44],"stock":[45],"markets,":[46],"medical":[47],"records":[48],"(monitoring":[49],"critical":[50],"health":[51],"conditions":[52],"patients),":[54],"climate":[55],"warning":[56],"systems,":[57],"etc.,":[58],"become":[60],"necessity.":[62],"Removing":[63],"redundancy":[64],"huge":[67],"(multi-billion":[68],"records)":[69],"datasets":[70],"results":[71],"in":[72,91],"resource":[73],"compute":[75],"efficiency":[76],"for":[77,94,146],"downstream":[78],"constitutes":[81],"an":[82],"important":[83],"study.":[86],"\"Intelligent":[87],"compression\"":[88],"or":[89],"deduplication":[90],"streaming":[92],"scenarios,":[93],"precise":[95],"identification":[96],"elimination":[98],"duplicates":[100],"unbounded":[103],"stream":[105],"is":[106],"greater":[108],"challenge":[109],"given":[110],"real-time":[112],"nature":[113],"arrival.":[116],"Stable":[117],"Bloom":[118],"Filters":[119],"(SBF)":[120],"[13]":[121],"address":[122],"problem":[124],"to":[125],"certain":[127],"extent.":[128],"However,":[129],"SBF":[130],"suffers":[131],"high":[134],"false":[135,150],"negative":[136,151],"rate":[137,152],"slow":[139],"convergence":[140],"rate,":[141],"thereby":[142],"rendering":[143],"it":[144],"inefficient":[145],"applications":[147],"with":[148],"low":[149],"tolerance.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}