{"id":"https://openalex.org/W3143573050","doi":"https://doi.org/10.1109/tse.2021.3069958","title":"Improving State-of-the-Art Compression Techniques for Log Management Tools","display_name":"Improving State-of-the-Art Compression Techniques for Log Management Tools","publication_year":2021,"publication_date":"2021-03-31","ids":{"openalex":"https://openalex.org/W3143573050","doi":"https://doi.org/10.1109/tse.2021.3069958","mag":"3143573050"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2021.3069958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3069958","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-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/A5035956071","display_name":"Kundi Yao","orcid":"https://orcid.org/0000-0002-3756-4673"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kundi Yao","raw_affiliation_strings":["Software Analysis and Intelligence Lab (SAIL), School of Computing, Queen&#x0027;s University, Kingston, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3756-4673","affiliations":[{"raw_affiliation_string":"Software Analysis and Intelligence Lab (SAIL), School of Computing, Queen&#x0027;s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023078795","display_name":"Mohammed Sayagh","orcid":"https://orcid.org/0000-0002-2724-0034"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammed Sayagh","raw_affiliation_strings":["Software and IT Engineering Department, ETS (Quebec University), Montreal, QC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2724-0034","affiliations":[{"raw_affiliation_string":"Software and IT Engineering Department, ETS (Quebec University), Montreal, QC, Canada","institution_ids":["https://openalex.org/I9736820","https://openalex.org/I159129438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056378414","display_name":"Weiyi Shang","orcid":"https://orcid.org/0000-0001-6222-7444"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiyi Shang","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Concordia University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Concordia University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091586373","display_name":"Ahmed E. Hassan","orcid":"https://orcid.org/0000-0001-7749-5513"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed E. Hassan","raw_affiliation_strings":["Software Analysis and Intelligence Lab (SAIL), School of Computing, Queen&#x0027;s University, Kingston, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Analysis and Intelligence Lab (SAIL), School of Computing, Queen&#x0027;s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.975,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.86454308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"48","issue":"8","first_page":"2748","last_page":"2760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9861999750137329,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9860000014305115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6964783072471619},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.44106847047805786},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.43953731656074524},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4292503893375397},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3821180462837219},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33733636140823364},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2982787489891052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21818765997886658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964783072471619},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.44106847047805786},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.43953731656074524},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4292503893375397},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3821180462837219},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33733636140823364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2982787489891052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21818765997886658}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tse.2021.3069958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3069958","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:espace2.etsmtl.ca:25172","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/25172/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article publi\u00e9 dans une revue, r\u00e9vis\u00e9 par les pairs"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W185022727","https://openalex.org/W1483021187","https://openalex.org/W1586104616","https://openalex.org/W1946402190","https://openalex.org/W1975523264","https://openalex.org/W2014296507","https://openalex.org/W2027241772","https://openalex.org/W2039114257","https://openalex.org/W2101114896","https://openalex.org/W2102632804","https://openalex.org/W2114379442","https://openalex.org/W2136814173","https://openalex.org/W2152217836","https://openalex.org/W2154091998","https://openalex.org/W2160399108","https://openalex.org/W2161086411","https://openalex.org/W2400577739","https://openalex.org/W2534933448","https://openalex.org/W2560021099","https://openalex.org/W2586066656","https://openalex.org/W2887581501","https://openalex.org/W2898108367","https://openalex.org/W2913254924","https://openalex.org/W2913277370","https://openalex.org/W2955680590","https://openalex.org/W2963999143","https://openalex.org/W2999013495","https://openalex.org/W3004071943","https://openalex.org/W3048902333","https://openalex.org/W3109708056","https://openalex.org/W3147048975","https://openalex.org/W3149943567","https://openalex.org/W3214050560","https://openalex.org/W4239026127","https://openalex.org/W4239854741","https://openalex.org/W6640789038","https://openalex.org/W6728485453","https://openalex.org/W6753589287","https://openalex.org/W6758846591","https://openalex.org/W6758936384"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W3033859939","https://openalex.org/W2847365777","https://openalex.org/W2355048207","https://openalex.org/W3126051647","https://openalex.org/W2750422482","https://openalex.org/W3125827053","https://openalex.org/W3128025644"],"abstract_inverted_index":{"Log":[0,24],"data":[1,41,67],"records":[2],"important":[3],"runtime":[4],"information":[5],"about":[6],"the":[7,87,100,164,201,254,260,265,292,308,315,396],"running":[8],"of":[9,89,102,117,129,256,330,355,399],"a":[10,127,225,275,324,349],"software":[11],"system":[12],"for":[13,274,286],"different":[14],"purposes":[15],"including":[16],"performance":[17],"assurance,":[18],"capacity":[19],"planning,":[20],"and":[21,31,38,51,58,75,145,237,263,343,348,368,385],"anomaly":[22],"detection.":[23],"management":[25,113,248,401],"tools":[26,64],"such":[27,63,228],"as":[28,229],"ELK":[29],"Stack":[30],"Splunk":[32],"are":[33,168,186,243,299],"widely":[34,244],"adopted":[35,245],"to":[36,44,59,216,269,288,303,332,336,340,345,357,361,365,370],"manage":[37],"leverage":[39],"log":[40,49,66,81,92,95,104,112,135,160,219,247,261,266,276,282,400],"in":[42,47],"order":[43],"assist":[45],"DevOps":[46],"real-time":[48],"analytics":[50],"decision":[52],"making.":[53],"To":[54],"enable":[55],"fast":[56],"queries":[57],"save":[60],"storage":[61,397],"space,":[62],"split":[65],"into":[68],"small":[69,103,159,218],"blocks":[70,105,166,203,220,294,311],"(e.g.,":[71,122],"16KB),":[72],"then":[73],"index":[74],"compress":[76],"each":[77],"block":[78,290],"separately.":[79],"Previous":[80],"compression":[82,88,101,108,120,272,317,326,351],"studies":[83],"focus":[84],"on":[85,158,280,300],"improving":[86,99],"either":[90],"large-sized":[91],"files":[93,283],"or":[94,182,197],"streams,":[96],"without":[97,204,312],"considering":[98],"(the":[106],"actual":[107],"need":[109],"by":[110,133,246,258,295],"modern":[111],"tools).":[114],"The":[115],"evaluation":[116,279],"four":[118],"state-of-the-art":[119,316],"approaches":[121,153],"<italic":[123,130,138,142,146,171,175,179,183,213,230,234,238,250,296,319,374,378,382,386,390],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124,131,139,143,147,172,176,180,184,214,231,235,239,251,297,320,375,379,383,387,391],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Logzip</i>":[125,132,173,376],",":[126,141,174,178,233,241,377,381],"variation":[128],"pre-extracting":[134],"templates":[136],"named":[137,212],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Logzip-E</i>":[140,177,380],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LogArchive</i>":[144,181,384],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Cowic</i>":[148,185,388],")":[149],"indicates":[150],"that":[151,167],"these":[152],"do":[154],"not":[155],"perform":[156],"well":[157],"blocks.":[161],"In":[162],"fact,":[163],"compressed":[165,202,293,310],"preprocessed":[169],"using":[170],"even":[187],"larger":[188],"(on":[189],"median":[190,301,329,354],"1.3":[191,339],"times,":[192,194,334,338,359,363],"1.5":[193],"0.2":[195],"times":[196,342,367],"6.6":[198],"times)":[199,347,372],"than":[200,307,373],"any":[205],"preprocessing.":[206],"Hence,":[207],"we":[208],"propose":[209],"an":[210,270],"approach":[211],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LogBlock</i>":[215,252,298,321,392],"preprocess":[217],"before":[221],"compressing":[222],"them":[223],"with":[224],"general":[226],"compressor":[227],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">gzip</i>":[232],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">deflate</i>":[236],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">lz4</i>":[240],"which":[242],"tools.":[249,402],"reduces":[253],"repetitiveness":[255],"logs":[257],"preprocessing":[259,313],"headers":[262],"rearranging":[264],"content":[267],"leading":[268],"improved":[271],"ratio":[273,327],"file.":[277],"Our":[278],"16":[281],"shows":[284],"that,":[285],"16KB":[287],"128KB":[289],"sizes,":[291],"5":[302],"21":[304],"percent":[305],"smaller":[306],"same":[309],"(outperforming":[314],"approaches).":[318],"achieves":[322],"both":[323],"higher":[325],"(a":[328,353],"1.7":[331],"8.4":[333],"1.9":[335,341],"10.0":[337],"6.2":[344],"11.4":[346],"faster":[350],"speed":[352],"30.8":[356],"49.7":[358],"42.6":[360],"53.8":[362],"4.5":[364],"6.0":[366],"2.5":[369],"4.0":[371],".":[389],"can":[393],"help":[394],"improve":[395],"efficiency":[398]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}