{"id":"https://openalex.org/W2622693244","doi":"https://doi.org/10.23919/inm.2017.7987424","title":"Random access in nondelimited variable-length record collections for parallel reading with Hadoop","display_name":"Random access in nondelimited variable-length record collections for parallel reading with Hadoop","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2622693244","doi":"https://doi.org/10.23919/inm.2017.7987424","mag":"2622693244"},"language":"en","primary_location":{"id":"doi:10.23919/inm.2017.7987424","is_oa":false,"landing_page_url":"https://doi.org/10.23919/inm.2017.7987424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","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/A5017056940","display_name":"Jason Anderson","orcid":"https://orcid.org/0000-0002-1627-3906"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason Anderson","raw_affiliation_strings":["Clemson University"],"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028631069","display_name":"Christopher Gropp","orcid":"https://orcid.org/0000-0002-3697-1218"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Gropp","raw_affiliation_strings":["Clemson University"],"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103239762","display_name":"Linh B. Ngo","orcid":"https://orcid.org/0000-0002-9889-2742"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linh Ngo","raw_affiliation_strings":["Clemson University"],"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004225206","display_name":"Amy Apon","orcid":"https://orcid.org/0000-0001-5617-5334"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amy Apon","raw_affiliation_strings":["Clemson University"],"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017056940"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.07512911,"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":"965","last_page":"970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9994999766349792,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8665145635604858},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.7007268667221069},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6627708673477173},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5991390943527222},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.5493410229682922},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5427787899971008},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5277529358863831},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4970395863056183},{"id":"https://openalex.org/keywords/retransmission","display_name":"Retransmission","score":0.41101759672164917},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3341112732887268},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.29257339239120483},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28216278553009033},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25666147470474243},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.10728737711906433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665145635604858},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.7007268667221069},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6627708673477173},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5991390943527222},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.5493410229682922},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5427787899971008},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5277529358863831},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4970395863056183},{"id":"https://openalex.org/C180611318","wikidata":"https://www.wikidata.org/wiki/Q7316902","display_name":"Retransmission","level":3,"score":0.41101759672164917},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3341112732887268},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.29257339239120483},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28216278553009033},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25666147470474243},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.10728737711906433}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/inm.2017.7987424","is_oa":false,"landing_page_url":"https://doi.org/10.23919/inm.2017.7987424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","raw_type":"proceedings-article"},{"id":"pmh:oai:tigerprints.clemson.edu:computing_pubs-1029","is_oa":false,"landing_page_url":"https://tigerprints.clemson.edu/computing_pubs/29","pdf_url":null,"source":{"id":"https://openalex.org/S4377196397","display_name":"TigerPrints (Clemson University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8078737","host_organization_name":"Clemson University","host_organization_lineage":["https://openalex.org/I8078737"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Publications","raw_type":"text"},{"id":"pmh:oai:open.clemson.edu:computing_pubs-1029","is_oa":false,"landing_page_url":"https://open.clemson.edu/computing_pubs/29","pdf_url":null,"source":{"id":"https://openalex.org/S4377196397","display_name":"TigerPrints (Clemson University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8078737","host_organization_name":"Clemson University","host_organization_lineage":["https://openalex.org/I8078737"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309106","display_name":"Clemson University","ror":"https://ror.org/037s24f05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W854708135","https://openalex.org/W1602874196","https://openalex.org/W1912779191","https://openalex.org/W1981229864","https://openalex.org/W2080680379","https://openalex.org/W2088134864","https://openalex.org/W2117608012","https://openalex.org/W2119738171","https://openalex.org/W2168595508","https://openalex.org/W2173213060","https://openalex.org/W2293413362","https://openalex.org/W2501979949","https://openalex.org/W2995564009","https://openalex.org/W6636211415"],"related_works":["https://openalex.org/W2394308295","https://openalex.org/W2377549730","https://openalex.org/W1981363742","https://openalex.org/W2127624627","https://openalex.org/W2063289542","https://openalex.org/W3046079838","https://openalex.org/W2479247939","https://openalex.org/W4317418679","https://openalex.org/W2163284784","https://openalex.org/W2790740338"],"abstract_inverted_index":{"The":[0],"industry":[1],"standard":[2],"Packet":[3],"CAPture":[4],"(PCAP)":[5],"format":[6],"for":[7,31,55,154],"storing":[8],"network":[9],"packet":[10,38],"traces":[11,39],"is":[12],"normally":[13],"only":[14],"readable":[15],"in":[16,44],"serial":[17,135],"due":[18],"to":[19,126,134],"its":[20],"lack":[21],"of":[22,34,73,75,91,112,120,142,152],"delimiters,":[23],"indexing,":[24],"or":[25],"blocking.":[26],"This":[27],"presents":[28],"a":[29,52,66,70,88,97,101,117,131,140,149],"challenge":[30],"parallel":[32],"analysis":[33],"large":[35],"networks,":[36],"where":[37],"can":[40,84],"be":[41],"many":[42],"gigabytes":[43],"size.":[45],"In":[46],"this":[47],"work":[48],"we":[49,138],"present":[50,139],"RAPCAP,":[51],"novel":[53],"method":[54,95],"random":[56,155],"access":[57,77],"into":[58],"variable-length":[59],"record":[60,67],"collections":[61],"like":[62],"PCAP":[63],"by":[64],"identifying":[65],"boundary":[68],"within":[69],"small":[71],"number":[72,141],"bytes":[74],"the":[76,93,113,121,127],"point.":[78],"Unlike":[79],"related":[80],"heuristic":[81],"methods":[82],"that":[83,146],"limit":[85],"scalability":[86],"with":[87,100,123],"nonzero":[89],"probability":[90],"error,":[92],"new":[94],"offers":[96],"correctness":[98],"guarantee":[99],"well":[102],"formed":[103],"file":[104],"and":[105,130],"does":[106],"not":[107],"rely":[108],"on":[109],"prior":[110],"knowledge":[111],"contents.":[114],"We":[115],"include":[116],"practical":[118],"implementation":[119],"algorithm":[122],"an":[124],"extension":[125],"Hadoop":[128],"framework,":[129],"performance":[132],"comparison":[133],"ingestion.":[136],"Finally,":[137],"similar":[143],"storage":[144],"types":[145],"could":[147],"utilize":[148],"modified":[150],"version":[151],"RAPCAP":[153],"access.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
