{"id":"https://openalex.org/W7123337887","doi":"https://doi.org/10.1109/candarw68385.2025.00067","title":"Anomaly Detection in HPC Systems using Time Difference Analysis of Reconstructed Data","display_name":"Anomaly Detection in HPC Systems using Time Difference Analysis of Reconstructed Data","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7123337887","doi":"https://doi.org/10.1109/candarw68385.2025.00067"},"language":null,"primary_location":{"id":"doi:10.1109/candarw68385.2025.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/candarw68385.2025.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Thirteenth International Symposium on Computing and Networking Workshops (CANDARW)","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/A5122879730","display_name":"Seiya Yaguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I165522056","display_name":"Tokyo Denki University","ror":"https://ror.org/01pa62v70","country_code":"JP","type":"education","lineage":["https://openalex.org/I165522056"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Seiya Yaguchi","raw_affiliation_strings":["Tokyo Denki University,Graduate School of Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Denki University,Graduate School of Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I165522056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122895270","display_name":"Ryusuke Egawa","orcid":null},"institutions":[{"id":"https://openalex.org/I165522056","display_name":"Tokyo Denki University","ror":"https://ror.org/01pa62v70","country_code":"JP","type":"education","lineage":["https://openalex.org/I165522056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryusuke Egawa","raw_affiliation_strings":["Tokyo Denki University Cyberscience Center, Tohoku University,Tokyo,Sendai,Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Denki University Cyberscience Center, Tohoku University,Tokyo,Sendai,Japan","institution_ids":["https://openalex.org/I165522056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122879730"],"corresponding_institution_ids":["https://openalex.org/I165522056"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7144297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"351","last_page":"355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.7526999711990356,"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":0.7526999711990356,"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":0.07240000367164612,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.034699998795986176,"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/autoencoder","display_name":"Autoencoder","score":0.7177000045776367},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5896999835968018},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5669999718666077},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43650001287460327},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39570000767707825},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.34290000796318054}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7177000045776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941999793052673},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5896999835968018},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C200749887","wikidata":"https://www.wikidata.org/wiki/Q1165574","display_name":"System monitoring","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/candarw68385.2025.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/candarw68385.2025.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Thirteenth International Symposium on Computing and Networking Workshops (CANDARW)","raw_type":"proceedings-article"}],"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":[],"abstract_inverted_index":{"Detecting":[0],"anomalies":[1,200],"in":[2,198,201,206],"high-performance":[3],"computing":[4],"(HPC)":[5],"systems":[6,20],"is":[7,16,26,164],"essential":[8],"to":[9,66,95,176],"keeping":[10],"them":[11],"reliable.":[12],"However,":[13],"this":[14,97],"task":[15],"difficult":[17],"because":[18],"modern":[19],"are":[21],"very":[22],"complex":[23],"and":[24,79],"there":[25],"little":[27],"labeled":[28],"failure":[29],"data.":[30,45],"Because":[31],"of":[32,77,126,146,180],"this,":[33],"we":[34],"need":[35],"unsupervised":[36,100],"methods":[37,48,115],"that":[38,61,116,159],"can":[39],"learn":[40],"only":[41,80,118,171,197],"from":[42,106,136],"normal":[43],"operating":[44],"Many":[46],"existing":[47],"mainly":[49],"look":[50],"at":[51],"static":[52,173],"system":[53,127],"states.":[54],"They":[55],"often":[56],"ignore":[57],"the":[58,74,124,137,149,178,186],"dynamic":[59,161,187],"behaviors":[60],"show":[62,158],"how":[63,103],"faults":[64],"start":[65],"develop.":[67],"As":[68],"a":[69,90,165],"result,":[70],"they":[71,84],"may":[72,193],"miss":[73],"first":[75],"signs":[76],"problems":[78],"detect":[81],"failures":[82],"after":[83],"have":[85],"grown.":[86],"This":[87,99],"paper":[88],"introduces":[89],"Difference":[91],"Analysis":[92],"(DA)":[93],"method":[94,101,132,153,192],"solve":[96],"problem.":[98],"measures":[102],"reconstructed":[104],"data":[105,135],"an":[107,143],"LSTM-based":[108],"autoencoder":[109],"(RUAD)":[110],"changes":[111,163],"over":[112],"time.":[113],"Unlike":[114],"use":[117],"reconstruction":[119,151,174],"error,":[120],"DA":[121,141],"directly":[122],"models":[123],"instability":[125],"behavior.":[128],"We":[129],"evaluated":[130],"our":[131,191],"on":[133,172],"monitoring":[134],"Marconi":[138],"100":[139],"supercomputer.":[140],"achieved":[142],"ROC":[144],"AUC":[145],"0.881,":[147],"while":[148],"conventional":[150],"error":[152,175],"scored":[154],"0.770.":[155],"These":[156],"results":[157],"studying":[160],"state":[162],"more":[166],"effective":[167],"way":[168],"than":[169],"relying":[170],"improve":[177],"reliability":[179],"large-scale":[181],"HPC":[182],"systems.":[183],"In":[184],"addition,":[185],"patterns":[188],"found":[189],"by":[190],"also":[194,205],"help":[195],"not":[196],"detecting":[199],"real":[202],"time":[203],"but":[204],"predicting":[207],"them.":[208]},"counts_by_year":[],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}