Matches in SemOpenAlex for { <https://semopenalex.org/work/W2802904300> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2802904300 abstract "The failures of train wheels account for disruptions of train operations and even a large portion of train derailments. Remaining useful life (RUL) of a wheelset measures the how soon the next failure will arrive, and the failure type reveals how severe the failure will be. RUL prediction is a regression task, whereas failure type is a classification task. In this paper, we propose a multi-task learning approach to jointly accomplish these two tasks by using a common input space to achieve more desirable results. We develop a convex optimization formulation to integrate both least square loss and the negative maximum likelihood of logistic regression, and model the joint sparsity as the L2/L1 norm of the model parameters to couple feature selection across tasks. The experiment results show that our method outperforms the single task learning method by 3% in prediction accuracy." @default.
- W2802904300 created "2018-05-17" @default.
- W2802904300 creator A5010410409 @default.
- W2802904300 creator A5015481671 @default.
- W2802904300 creator A5054724725 @default.
- W2802904300 creator A5073746929 @default.
- W2802904300 date "2021-01-10" @default.
- W2802904300 modified "2023-09-23" @default.
- W2802904300 title "Joint Prediction of Remaining Useful Life and Failure Type of Train Wheelsets: A Multi-task Learning Approach" @default.
- W2802904300 cites W2038569287 @default.
- W2802904300 cites W2109285819 @default.
- W2802904300 doi "https://doi.org/10.48550/arxiv.2101.03497" @default.
- W2802904300 hasPublicationYear "2021" @default.
- W2802904300 type Work @default.
- W2802904300 sameAs 2802904300 @default.
- W2802904300 citedByCount "4" @default.
- W2802904300 countsByYear W28029043002018 @default.
- W2802904300 countsByYear W28029043002020 @default.
- W2802904300 countsByYear W28029043002021 @default.
- W2802904300 crossrefType "posted-content" @default.
- W2802904300 hasAuthorship W2802904300A5010410409 @default.
- W2802904300 hasAuthorship W2802904300A5015481671 @default.
- W2802904300 hasAuthorship W2802904300A5054724725 @default.
- W2802904300 hasAuthorship W2802904300A5073746929 @default.
- W2802904300 hasBestOaLocation W28029043001 @default.
- W2802904300 hasConcept C119857082 @default.
- W2802904300 hasConcept C127413603 @default.
- W2802904300 hasConcept C138885662 @default.
- W2802904300 hasConcept C148483581 @default.
- W2802904300 hasConcept C151956035 @default.
- W2802904300 hasConcept C154945302 @default.
- W2802904300 hasConcept C170154142 @default.
- W2802904300 hasConcept C17744445 @default.
- W2802904300 hasConcept C18555067 @default.
- W2802904300 hasConcept C191795146 @default.
- W2802904300 hasConcept C199539241 @default.
- W2802904300 hasConcept C201995342 @default.
- W2802904300 hasConcept C2776401178 @default.
- W2802904300 hasConcept C2780451532 @default.
- W2802904300 hasConcept C28006648 @default.
- W2802904300 hasConcept C41008148 @default.
- W2802904300 hasConcept C41895202 @default.
- W2802904300 hasConceptScore W2802904300C119857082 @default.
- W2802904300 hasConceptScore W2802904300C127413603 @default.
- W2802904300 hasConceptScore W2802904300C138885662 @default.
- W2802904300 hasConceptScore W2802904300C148483581 @default.
- W2802904300 hasConceptScore W2802904300C151956035 @default.
- W2802904300 hasConceptScore W2802904300C154945302 @default.
- W2802904300 hasConceptScore W2802904300C170154142 @default.
- W2802904300 hasConceptScore W2802904300C17744445 @default.
- W2802904300 hasConceptScore W2802904300C18555067 @default.
- W2802904300 hasConceptScore W2802904300C191795146 @default.
- W2802904300 hasConceptScore W2802904300C199539241 @default.
- W2802904300 hasConceptScore W2802904300C201995342 @default.
- W2802904300 hasConceptScore W2802904300C2776401178 @default.
- W2802904300 hasConceptScore W2802904300C2780451532 @default.
- W2802904300 hasConceptScore W2802904300C28006648 @default.
- W2802904300 hasConceptScore W2802904300C41008148 @default.
- W2802904300 hasConceptScore W2802904300C41895202 @default.
- W2802904300 hasLocation W28029043001 @default.
- W2802904300 hasOpenAccess W2802904300 @default.
- W2802904300 hasPrimaryLocation W28029043001 @default.
- W2802904300 hasRelatedWork W12783365 @default.
- W2802904300 hasRelatedWork W13109368 @default.
- W2802904300 hasRelatedWork W13618705 @default.
- W2802904300 hasRelatedWork W14789944 @default.
- W2802904300 hasRelatedWork W4085024 @default.
- W2802904300 hasRelatedWork W5459358 @default.
- W2802904300 hasRelatedWork W7002624 @default.
- W2802904300 hasRelatedWork W8455802 @default.
- W2802904300 hasRelatedWork W9402503 @default.
- W2802904300 hasRelatedWork W13002482 @default.
- W2802904300 isParatext "false" @default.
- W2802904300 isRetracted "false" @default.
- W2802904300 magId "2802904300" @default.
- W2802904300 workType "article" @default.