Matches in SemOpenAlex for { <https://semopenalex.org/work/W3116407289> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3116407289 abstract "With the increasing availability of sensory data, inferring the existence of relevant events in the observations is becoming a critical task for smart data service delivery in applications that rely on such data sources. Yet, existing solutions tend to fail when the events that are being inferred are rare, for instance when one attempts to infer seizure events in electroencephalogram (EEG) data. In this paper, we note that multi-variate time series often carry robust localized multi-variate temporal features that could, at least in theory, help identify these events; however, the lack of sufficient data to train for these events make it impossible for neural architectures to identify and make use of these features. To tackle this challenge, we propose an LSTM-based neural architecture, M2N N, with an attention mechanism that leverages robust multivariate temporal features that are extracted a priori and fed into the NN as a side information. In particular, multi-variate temporal features are extracted by simultaneously considering, at multiple scales, temporal characteristics of the time series along with external knowledge, including variate relationships that are known a priori. We then show that a single layer LSTM with dual-layer attention that leverages these multi-scale, multi-variate features provides significant gains in rare seizure detection on EEG data. In addition, in order to illustrate the broader applicability (and reproducibility) of M2N N, we also evaluate it in other publicly available rare event detection tasks, such as anomaly detection in manufacturing. We further show that the proposed M2N N technique is beneficial in tackling more traditional inference problems, such as travel-time prediction, where rare accident events can cause congestions." @default.
- W3116407289 created "2021-01-05" @default.
- W3116407289 creator A5003070145 @default.
- W3116407289 creator A5029316133 @default.
- W3116407289 creator A5043892415 @default.
- W3116407289 date "2020-10-01" @default.
- W3116407289 modified "2023-09-24" @default.
- W3116407289 title "M2NN: Rare Event Inference through Multi-variate Multi-scale Attention" @default.
- W3116407289 cites W2015076179 @default.
- W3116407289 cites W2043317831 @default.
- W3116407289 cites W2064675550 @default.
- W3116407289 cites W2077824338 @default.
- W3116407289 cites W2121553911 @default.
- W3116407289 cites W2131774270 @default.
- W3116407289 cites W2402787549 @default.
- W3116407289 cites W2744757127 @default.
- W3116407289 cites W2780723646 @default.
- W3116407289 cites W2805036854 @default.
- W3116407289 cites W2888556550 @default.
- W3116407289 cites W2915893085 @default.
- W3116407289 cites W2925836809 @default.
- W3116407289 cites W2952091391 @default.
- W3116407289 cites W2963960318 @default.
- W3116407289 cites W2964105864 @default.
- W3116407289 cites W2971893337 @default.
- W3116407289 doi "https://doi.org/10.1109/smds49396.2020.00014" @default.
- W3116407289 hasPublicationYear "2020" @default.
- W3116407289 type Work @default.
- W3116407289 sameAs 3116407289 @default.
- W3116407289 citedByCount "1" @default.
- W3116407289 countsByYear W31164072892022 @default.
- W3116407289 crossrefType "proceedings-article" @default.
- W3116407289 hasAuthorship W3116407289A5003070145 @default.
- W3116407289 hasAuthorship W3116407289A5029316133 @default.
- W3116407289 hasAuthorship W3116407289A5043892415 @default.
- W3116407289 hasConcept C105795698 @default.
- W3116407289 hasConcept C111472728 @default.
- W3116407289 hasConcept C119857082 @default.
- W3116407289 hasConcept C121332964 @default.
- W3116407289 hasConcept C122123141 @default.
- W3116407289 hasConcept C124101348 @default.
- W3116407289 hasConcept C138885662 @default.
- W3116407289 hasConcept C141547133 @default.
- W3116407289 hasConcept C153180895 @default.
- W3116407289 hasConcept C154945302 @default.
- W3116407289 hasConcept C2776214188 @default.
- W3116407289 hasConcept C2778755073 @default.
- W3116407289 hasConcept C2779662365 @default.
- W3116407289 hasConcept C33923547 @default.
- W3116407289 hasConcept C41008148 @default.
- W3116407289 hasConcept C62520636 @default.
- W3116407289 hasConcept C739882 @default.
- W3116407289 hasConcept C75553542 @default.
- W3116407289 hasConceptScore W3116407289C105795698 @default.
- W3116407289 hasConceptScore W3116407289C111472728 @default.
- W3116407289 hasConceptScore W3116407289C119857082 @default.
- W3116407289 hasConceptScore W3116407289C121332964 @default.
- W3116407289 hasConceptScore W3116407289C122123141 @default.
- W3116407289 hasConceptScore W3116407289C124101348 @default.
- W3116407289 hasConceptScore W3116407289C138885662 @default.
- W3116407289 hasConceptScore W3116407289C141547133 @default.
- W3116407289 hasConceptScore W3116407289C153180895 @default.
- W3116407289 hasConceptScore W3116407289C154945302 @default.
- W3116407289 hasConceptScore W3116407289C2776214188 @default.
- W3116407289 hasConceptScore W3116407289C2778755073 @default.
- W3116407289 hasConceptScore W3116407289C2779662365 @default.
- W3116407289 hasConceptScore W3116407289C33923547 @default.
- W3116407289 hasConceptScore W3116407289C41008148 @default.
- W3116407289 hasConceptScore W3116407289C62520636 @default.
- W3116407289 hasConceptScore W3116407289C739882 @default.
- W3116407289 hasConceptScore W3116407289C75553542 @default.
- W3116407289 hasFunder F4320306076 @default.
- W3116407289 hasLocation W31164072891 @default.
- W3116407289 hasOpenAccess W3116407289 @default.
- W3116407289 hasPrimaryLocation W31164072891 @default.
- W3116407289 hasRelatedWork W1971035997 @default.
- W3116407289 hasRelatedWork W2076520961 @default.
- W3116407289 hasRelatedWork W2101929671 @default.
- W3116407289 hasRelatedWork W2120643732 @default.
- W3116407289 hasRelatedWork W2511279186 @default.
- W3116407289 hasRelatedWork W3044458868 @default.
- W3116407289 hasRelatedWork W3106947897 @default.
- W3116407289 hasRelatedWork W4293083511 @default.
- W3116407289 hasRelatedWork W2116305750 @default.
- W3116407289 hasRelatedWork W2183287460 @default.
- W3116407289 isParatext "false" @default.
- W3116407289 isRetracted "false" @default.
- W3116407289 magId "3116407289" @default.
- W3116407289 workType "article" @default.