Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294804265> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4294804265 abstract "Detecting anomalies in large complex systems is a critical and challenging task. The difficulties arise from several aspects. First, collecting ground truth labels or prior knowledge for anomalies is hard in real-world systems, which often lead to limited or no anomaly labels in the dataset. Second, anomalies in large systems usually occur in a collective manner due to the underlying dependency structure among devices or sensors. Lastly, real-time anomaly detection for high-dimensional data requires efficient algorithms that are capable of handling different types of data (i.e. continuous and discrete). We propose a correlation structure-based collective anomaly detection (CSCAD) model for high-dimensional anomaly detection problem in large systems, which is also generalizable to semi-supervised or supervised settings. Our framework utilize graph convolutional network combining a variational autoencoder to jointly exploit the feature space correlation and reconstruction deficiency of samples to perform anomaly detection. We propose an extended mutual information (EMI) metric to mine the internal correlation structure among different data features, which enhances the data reconstruction capability of CSCAD. The reconstruction loss and latent standard deviation vector of a sample obtained from reconstruction network can be perceived as two natural anomalous degree measures. An anomaly discriminating network can then be trained using low anomalous degree samples as positive samples, and high anomalous degree samples as negative samples. Experimental results on five public datasets demonstrate that our approach consistently outperforms all the competing baselines." @default.
- W4294804265 created "2022-09-06" @default.
- W4294804265 creator A5015318485 @default.
- W4294804265 creator A5052921346 @default.
- W4294804265 creator A5058811939 @default.
- W4294804265 date "2021-05-30" @default.
- W4294804265 modified "2023-10-18" @default.
- W4294804265 title "CSCAD: Correlation Structure-based Collective Anomaly Detection in Complex System" @default.
- W4294804265 doi "https://doi.org/10.48550/arxiv.2105.14476" @default.
- W4294804265 hasPublicationYear "2021" @default.
- W4294804265 type Work @default.
- W4294804265 citedByCount "0" @default.
- W4294804265 crossrefType "posted-content" @default.
- W4294804265 hasAuthorship W4294804265A5015318485 @default.
- W4294804265 hasAuthorship W4294804265A5052921346 @default.
- W4294804265 hasAuthorship W4294804265A5058811939 @default.
- W4294804265 hasBestOaLocation W42948042651 @default.
- W4294804265 hasConcept C101738243 @default.
- W4294804265 hasConcept C108583219 @default.
- W4294804265 hasConcept C117220453 @default.
- W4294804265 hasConcept C121332964 @default.
- W4294804265 hasConcept C124101348 @default.
- W4294804265 hasConcept C12997251 @default.
- W4294804265 hasConcept C138885662 @default.
- W4294804265 hasConcept C153180895 @default.
- W4294804265 hasConcept C154945302 @default.
- W4294804265 hasConcept C162324750 @default.
- W4294804265 hasConcept C165696696 @default.
- W4294804265 hasConcept C176217482 @default.
- W4294804265 hasConcept C21547014 @default.
- W4294804265 hasConcept C2524010 @default.
- W4294804265 hasConcept C26873012 @default.
- W4294804265 hasConcept C2776401178 @default.
- W4294804265 hasConcept C33923547 @default.
- W4294804265 hasConcept C38652104 @default.
- W4294804265 hasConcept C41008148 @default.
- W4294804265 hasConcept C41895202 @default.
- W4294804265 hasConcept C739882 @default.
- W4294804265 hasConcept C83665646 @default.
- W4294804265 hasConceptScore W4294804265C101738243 @default.
- W4294804265 hasConceptScore W4294804265C108583219 @default.
- W4294804265 hasConceptScore W4294804265C117220453 @default.
- W4294804265 hasConceptScore W4294804265C121332964 @default.
- W4294804265 hasConceptScore W4294804265C124101348 @default.
- W4294804265 hasConceptScore W4294804265C12997251 @default.
- W4294804265 hasConceptScore W4294804265C138885662 @default.
- W4294804265 hasConceptScore W4294804265C153180895 @default.
- W4294804265 hasConceptScore W4294804265C154945302 @default.
- W4294804265 hasConceptScore W4294804265C162324750 @default.
- W4294804265 hasConceptScore W4294804265C165696696 @default.
- W4294804265 hasConceptScore W4294804265C176217482 @default.
- W4294804265 hasConceptScore W4294804265C21547014 @default.
- W4294804265 hasConceptScore W4294804265C2524010 @default.
- W4294804265 hasConceptScore W4294804265C26873012 @default.
- W4294804265 hasConceptScore W4294804265C2776401178 @default.
- W4294804265 hasConceptScore W4294804265C33923547 @default.
- W4294804265 hasConceptScore W4294804265C38652104 @default.
- W4294804265 hasConceptScore W4294804265C41008148 @default.
- W4294804265 hasConceptScore W4294804265C41895202 @default.
- W4294804265 hasConceptScore W4294804265C739882 @default.
- W4294804265 hasConceptScore W4294804265C83665646 @default.
- W4294804265 hasLocation W42948042651 @default.
- W4294804265 hasOpenAccess W4294804265 @default.
- W4294804265 hasPrimaryLocation W42948042651 @default.
- W4294804265 hasRelatedWork W2587789887 @default.
- W4294804265 hasRelatedWork W2785535669 @default.
- W4294804265 hasRelatedWork W3160458414 @default.
- W4294804265 hasRelatedWork W4287782143 @default.
- W4294804265 hasRelatedWork W4289653936 @default.
- W4294804265 hasRelatedWork W4296210064 @default.
- W4294804265 hasRelatedWork W4308482784 @default.
- W4294804265 hasRelatedWork W4312721464 @default.
- W4294804265 hasRelatedWork W4313590336 @default.
- W4294804265 hasRelatedWork W4315795808 @default.
- W4294804265 isParatext "false" @default.
- W4294804265 isRetracted "false" @default.
- W4294804265 workType "article" @default.