Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138290087> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3138290087 endingPage "9" @default.
- W3138290087 startingPage "1" @default.
- W3138290087 abstract "Failure of hard disk drives (HDDs) is the most critical reliability issue of data center. Therefore, predicting the failure of the HDD is an important means to ensure the storage security of the data center. However, most current research works had not paid attention to the fact that the self-monitoring, analysis and reporting technology (SMART) data in a returned failed HDD are a long-term sequence that consists of many unlabeled data, as the healthy and faulty data are highly mixed. Because the failure data in the rapid degradation period are less than the health data in the normal state, the mixture of healthy and faulty data results in an extremely data imbalance. This brings a great challenge to find the hidden fault information, and thus failure prediction becomes a difficult task. To cope with the above problems, a multi-instance long-term data classification method based on long short-term memory (LSTM) network and attention mechanism are proposed to predict the failure of HDDs. Regarding long time sequence HDD data as an instance bag, multi-instance learning (MIL) divides it into multiple instances in the subconcept layer, and then studies the connection between instances and bag labels. Based on the analysis of HDD data of a communication company and Backblaze data center, our proposed method can obtain much better results than other methods." @default.
- W3138290087 created "2021-03-29" @default.
- W3138290087 creator A5027287554 @default.
- W3138290087 creator A5039179408 @default.
- W3138290087 creator A5072887757 @default.
- W3138290087 date "2021-01-01" @default.
- W3138290087 modified "2023-10-16" @default.
- W3138290087 title "Multi-Instance Deep Learning Based on Attention Mechanism for Failure Prediction of Unlabeled Hard Disk Drives" @default.
- W3138290087 cites W1519502414 @default.
- W3138290087 cites W1832917778 @default.
- W3138290087 cites W1942954007 @default.
- W3138290087 cites W1965751562 @default.
- W3138290087 cites W2026430219 @default.
- W3138290087 cites W2052643920 @default.
- W3138290087 cites W2064675550 @default.
- W3138290087 cites W2079498338 @default.
- W3138290087 cites W2079735306 @default.
- W3138290087 cites W2110119381 @default.
- W3138290087 cites W2116261113 @default.
- W3138290087 cites W2319441181 @default.
- W3138290087 cites W2533869535 @default.
- W3138290087 cites W2584928005 @default.
- W3138290087 cites W2658572642 @default.
- W3138290087 cites W2752311492 @default.
- W3138290087 cites W2772956929 @default.
- W3138290087 cites W2781712876 @default.
- W3138290087 cites W2791139105 @default.
- W3138290087 cites W2859714231 @default.
- W3138290087 cites W2888477829 @default.
- W3138290087 cites W2892035503 @default.
- W3138290087 cites W2919115771 @default.
- W3138290087 cites W3000870854 @default.
- W3138290087 cites W3010877614 @default.
- W3138290087 cites W3082433520 @default.
- W3138290087 cites W3095103355 @default.
- W3138290087 cites W3115394420 @default.
- W3138290087 cites W3131903265 @default.
- W3138290087 doi "https://doi.org/10.1109/tim.2021.3068180" @default.
- W3138290087 hasPublicationYear "2021" @default.
- W3138290087 type Work @default.
- W3138290087 sameAs 3138290087 @default.
- W3138290087 citedByCount "7" @default.
- W3138290087 countsByYear W31382900872021 @default.
- W3138290087 countsByYear W31382900872022 @default.
- W3138290087 countsByYear W31382900872023 @default.
- W3138290087 crossrefType "journal-article" @default.
- W3138290087 hasAuthorship W3138290087A5027287554 @default.
- W3138290087 hasAuthorship W3138290087A5039179408 @default.
- W3138290087 hasAuthorship W3138290087A5072887757 @default.
- W3138290087 hasConcept C11413529 @default.
- W3138290087 hasConcept C119857082 @default.
- W3138290087 hasConcept C121332964 @default.
- W3138290087 hasConcept C124101348 @default.
- W3138290087 hasConcept C127413603 @default.
- W3138290087 hasConcept C154945302 @default.
- W3138290087 hasConcept C163258240 @default.
- W3138290087 hasConcept C201995342 @default.
- W3138290087 hasConcept C2780451532 @default.
- W3138290087 hasConcept C41008148 @default.
- W3138290087 hasConcept C43214815 @default.
- W3138290087 hasConcept C48103436 @default.
- W3138290087 hasConcept C61797465 @default.
- W3138290087 hasConcept C62520636 @default.
- W3138290087 hasConceptScore W3138290087C11413529 @default.
- W3138290087 hasConceptScore W3138290087C119857082 @default.
- W3138290087 hasConceptScore W3138290087C121332964 @default.
- W3138290087 hasConceptScore W3138290087C124101348 @default.
- W3138290087 hasConceptScore W3138290087C127413603 @default.
- W3138290087 hasConceptScore W3138290087C154945302 @default.
- W3138290087 hasConceptScore W3138290087C163258240 @default.
- W3138290087 hasConceptScore W3138290087C201995342 @default.
- W3138290087 hasConceptScore W3138290087C2780451532 @default.
- W3138290087 hasConceptScore W3138290087C41008148 @default.
- W3138290087 hasConceptScore W3138290087C43214815 @default.
- W3138290087 hasConceptScore W3138290087C48103436 @default.
- W3138290087 hasConceptScore W3138290087C61797465 @default.
- W3138290087 hasConceptScore W3138290087C62520636 @default.
- W3138290087 hasFunder F4320321001 @default.
- W3138290087 hasLocation W31382900871 @default.
- W3138290087 hasOpenAccess W3138290087 @default.
- W3138290087 hasPrimaryLocation W31382900871 @default.
- W3138290087 hasRelatedWork W2081647779 @default.
- W3138290087 hasRelatedWork W2961085424 @default.
- W3138290087 hasRelatedWork W3046775127 @default.
- W3138290087 hasRelatedWork W3170094116 @default.
- W3138290087 hasRelatedWork W4205958290 @default.
- W3138290087 hasRelatedWork W4285260836 @default.
- W3138290087 hasRelatedWork W4286629047 @default.
- W3138290087 hasRelatedWork W4306321456 @default.
- W3138290087 hasRelatedWork W4306674287 @default.
- W3138290087 hasRelatedWork W4224009465 @default.
- W3138290087 hasVolume "70" @default.
- W3138290087 isParatext "false" @default.
- W3138290087 isRetracted "false" @default.
- W3138290087 magId "3138290087" @default.
- W3138290087 workType "article" @default.