Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387366120> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4387366120 abstract "The article touches upon the problem of discovering subsequence anomalies in time series, which is currently in demand in a wide range of subject domains. We propose a new semi-supervised method to detect subsequence anomalies in time series. The method is based on the concepts of discord and snippet, which formalize, respectively, the concepts of anomalous and typical time series subsequences. The proposed method includes a neural network model that calculates the anomaly score of the input subsequence and an algorithm to automatically construct the model’s training set. The model is implemented as a Siamese neural network, where we employ a modification of ResNet as a subnet. To train the model, we proposed a modified contrast loss function. The training set is formed as a representative fragment of the time series from which discords, low-fraction snippets with their nearest neighbors, and outliers within each snippet are removed since they are interpreted as abnormal, atypical activity of the subject, and noise, respectively. Computational experiments over time series from various subject domains showed that the proposed model, compared with analogues, has on average the highest accuracy of anomaly detection with respect to the standard VUS-PR metric. The downside of the high accuracy of the method is the longer time spent on model training and anomaly detection compared to analogues. Nevertheless, in applications of intelligent building heating control, the method provides a speed sufficient to detect subsequence anomalies in real time." @default.
- W4387366120 created "2023-10-06" @default.
- W4387366120 date "2023-08-01" @default.
- W4387366120 modified "2023-10-06" @default.
- W4387366120 title "Detection of Time Series Anomalies Based on Data Mining and Neural Network Technologies" @default.
- W4387366120 doi "https://doi.org/10.14529/cmse230304" @default.
- W4387366120 hasPublicationYear "2023" @default.
- W4387366120 type Work @default.
- W4387366120 citedByCount "0" @default.
- W4387366120 crossrefType "journal-article" @default.
- W4387366120 hasBestOaLocation W43873661201 @default.
- W4387366120 hasConcept C11413529 @default.
- W4387366120 hasConcept C119857082 @default.
- W4387366120 hasConcept C121332964 @default.
- W4387366120 hasConcept C124101348 @default.
- W4387366120 hasConcept C12997251 @default.
- W4387366120 hasConcept C134306372 @default.
- W4387366120 hasConcept C137877099 @default.
- W4387366120 hasConcept C143724316 @default.
- W4387366120 hasConcept C151406439 @default.
- W4387366120 hasConcept C151730666 @default.
- W4387366120 hasConcept C153180895 @default.
- W4387366120 hasConcept C154945302 @default.
- W4387366120 hasConcept C162324750 @default.
- W4387366120 hasConcept C176217482 @default.
- W4387366120 hasConcept C177264268 @default.
- W4387366120 hasConcept C199360897 @default.
- W4387366120 hasConcept C21099817 @default.
- W4387366120 hasConcept C21547014 @default.
- W4387366120 hasConcept C26873012 @default.
- W4387366120 hasConcept C31258907 @default.
- W4387366120 hasConcept C33923547 @default.
- W4387366120 hasConcept C34388435 @default.
- W4387366120 hasConcept C41008148 @default.
- W4387366120 hasConcept C50644808 @default.
- W4387366120 hasConcept C739882 @default.
- W4387366120 hasConcept C79337645 @default.
- W4387366120 hasConcept C86803240 @default.
- W4387366120 hasConceptScore W4387366120C11413529 @default.
- W4387366120 hasConceptScore W4387366120C119857082 @default.
- W4387366120 hasConceptScore W4387366120C121332964 @default.
- W4387366120 hasConceptScore W4387366120C124101348 @default.
- W4387366120 hasConceptScore W4387366120C12997251 @default.
- W4387366120 hasConceptScore W4387366120C134306372 @default.
- W4387366120 hasConceptScore W4387366120C137877099 @default.
- W4387366120 hasConceptScore W4387366120C143724316 @default.
- W4387366120 hasConceptScore W4387366120C151406439 @default.
- W4387366120 hasConceptScore W4387366120C151730666 @default.
- W4387366120 hasConceptScore W4387366120C153180895 @default.
- W4387366120 hasConceptScore W4387366120C154945302 @default.
- W4387366120 hasConceptScore W4387366120C162324750 @default.
- W4387366120 hasConceptScore W4387366120C176217482 @default.
- W4387366120 hasConceptScore W4387366120C177264268 @default.
- W4387366120 hasConceptScore W4387366120C199360897 @default.
- W4387366120 hasConceptScore W4387366120C21099817 @default.
- W4387366120 hasConceptScore W4387366120C21547014 @default.
- W4387366120 hasConceptScore W4387366120C26873012 @default.
- W4387366120 hasConceptScore W4387366120C31258907 @default.
- W4387366120 hasConceptScore W4387366120C33923547 @default.
- W4387366120 hasConceptScore W4387366120C34388435 @default.
- W4387366120 hasConceptScore W4387366120C41008148 @default.
- W4387366120 hasConceptScore W4387366120C50644808 @default.
- W4387366120 hasConceptScore W4387366120C739882 @default.
- W4387366120 hasConceptScore W4387366120C79337645 @default.
- W4387366120 hasConceptScore W4387366120C86803240 @default.
- W4387366120 hasIssue "3" @default.
- W4387366120 hasLocation W43873661201 @default.
- W4387366120 hasOpenAccess W4387366120 @default.
- W4387366120 hasPrimaryLocation W43873661201 @default.
- W4387366120 hasRelatedWork W2295423552 @default.
- W4387366120 hasRelatedWork W2499612753 @default.
- W4387366120 hasRelatedWork W2806741695 @default.
- W4387366120 hasRelatedWork W2946096271 @default.
- W4387366120 hasRelatedWork W2998615029 @default.
- W4387366120 hasRelatedWork W3031281630 @default.
- W4387366120 hasRelatedWork W3111802945 @default.
- W4387366120 hasRelatedWork W3210364259 @default.
- W4387366120 hasRelatedWork W4290647774 @default.
- W4387366120 hasRelatedWork W3107369729 @default.
- W4387366120 hasVolume "12" @default.
- W4387366120 isParatext "false" @default.
- W4387366120 isRetracted "false" @default.
- W4387366120 workType "article" @default.