{"id":"https://openalex.org/W2594608325","doi":"https://doi.org/10.3233/978-1-61499-484-8-541","title":"Anomaly Detection in Hadoop Clusters Using PCA and DBSCAN","display_name":"Anomaly Detection in Hadoop Clusters Using PCA and DBSCAN","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2594608325","doi":"https://doi.org/10.3233/978-1-61499-484-8-541","mag":"2594608325"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-484-8-541","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-541","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5033410733","display_name":"Xiao Yang","orcid":"https://orcid.org/0000-0003-1105-6686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Yan","raw_affiliation_strings":["China University of Geosciences, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu Zunhe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu Zunhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Cao Buyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao Buyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34139747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9959999918937683,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9959999918937683,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9947999715805054,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.944599986076355,"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/anomaly-detection","display_name":"Anomaly detection","score":0.7366766929626465},{"id":"https://openalex.org/keywords/dbscan","display_name":"DBSCAN","score":0.6437668204307556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5534670948982239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46150946617126465},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4176562428474426},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38273632526397705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33295440673828125},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.313442587852478},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08992978930473328}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7366766929626465},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.6437668204307556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5534670948982239},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46150946617126465},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4176562428474426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38273632526397705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33295440673828125},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.313442587852478},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08992978930473328},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.0},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-484-8-541","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-541","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3176449234","https://openalex.org/W2353158678","https://openalex.org/W2767235736","https://openalex.org/W2045002201","https://openalex.org/W4225278791","https://openalex.org/W4377236448","https://openalex.org/W2806741695","https://openalex.org/W4322502698","https://openalex.org/W4290647774","https://openalex.org/W3189286258"],"abstract_inverted_index":{"With":[0],"the":[1,72,151,156,170],"widely":[2],"adoption":[3],"of":[4,65,71,125,150,172],"Hadoop-based":[5],"big":[6],"data":[7,99,141],"platfom":[8],"in":[9,82,97,155,174],"industry,":[10],"monitoring":[11,40],"and":[12,31,43,61,69,114,128],"maintaining":[13],"Hadoop":[14,41,57,102,145],"clusters":[15,42,58,146],"has":[16,119],"become":[17],"increasingly":[18],"critical,":[19],"which":[20,76],"also":[21],"brings":[22],"high":[23],"demands":[24],"on":[25,63,122,138],"automatic":[26,47],"or":[27],"semi-automatic":[28],"health":[29],"checking":[30],"diagonostics.":[32],"Anomaly":[33],"detection":[34,55,107],"plays":[35],"an":[36],"essential":[37],"role":[38],"for":[39,46,53,56,79],"provides":[44],"basis":[45],"alerts":[48],"generation.":[49],"Most":[50],"existing":[51],"methods":[52],"anomaly":[54,106],"are":[59,131],"rule-based":[60],"relies":[62],"characterizing":[64],"anomalies":[66,167,173],"with":[67],"domain-knowledge":[68],"understanding":[70],"specific":[73],"target":[74,126],"system,":[75],"bring":[77],"barriers":[78],"practical":[80],"application":[81],"complex":[83],"business":[84],"platform.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"leverage":[90],"statistical":[91],"analysis":[92],"to":[93,133,165],"discover":[94],"critical":[95],"components":[96],"execution":[98,140],"collected":[100,142],"through":[101],"JobTracker.":[103],"A":[104],"two-stage":[105],"method":[108,118,162],"is":[109,163],"proposed":[110],"by":[111,148],"integrating":[112],"PCA":[113],"DBSCAN.":[115],"This":[116],"new":[117],"no":[120],"requirements":[121],"prior":[123],"knowledge":[124],"nodes":[127],"jobs.":[129],"Experiments":[130],"conducted":[132],"detect":[134,166],"buggy":[135],"jobs":[136],"based":[137],"real":[139],"from":[143],"three":[144],"provided":[147],"one":[149],"largest":[152],"E-Commerce":[153],"company":[154],"world.":[157],"The":[158],"results":[159],"show":[160],"our":[161],"effective":[164],"without":[168],"specifying":[169],"features":[171],"advance.":[175]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2017-03-16T00:00:00"}