Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386759712> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4386759712 endingPage "56" @default.
- W4386759712 startingPage "44" @default.
- W4386759712 abstract "Detecting anomalies in massive volumes of multivariate time series data, particularly in the IoT domain, is critical for maintaining stable systems. Existing anomaly detection models based on reconstruction techniques face challenges in distinguishing normal and abnormal samples from unlabeled data, leading to performance degradation. Moreover, accurately reconstructing abnormal values and pinpointing anomalies remains a limitation. To address these issues, we introduce the Adversarial Time-Frequency Reconstruction Network for Unsupervised Anomaly Detection (ATF-UAD). ATF-UAD consists of a time reconstructor, a frequency reconstructor and a dual-view adversarial learning mechanism. The time reconstructor utilizes a parity sampling mechanism to weaken the dependency between neighboring points. Then attention mechanisms and graph convolutional networks (GCNs) are used to update the feature information for each point, which combines points with close feature relationships and dilutes the influence of abnormal points on normal points. The frequency reconstructor transforms the input sequence into the frequency domain using a Fourier transform and extracts the relationship between frequencies to reconstruct anomalous frequency bands. The dual-view adversarial learning mechanism aims to maximize the normal values in the reconstructed sequences and highlight anomalies and aid in their localization within the data. Through dual-view adversarial learning, ATF-UAD minimizes reconstructed value errors and maximizes the identification of residual outliers. We conducted extensive experiments on nine datasets from different domains, and ATF-UAD showed an average improvement of 6.94% in terms of F1 score compared to the state-of-the-art method." @default.
- W4386759712 created "2023-09-16" @default.
- W4386759712 creator A5006977942 @default.
- W4386759712 creator A5049192246 @default.
- W4386759712 creator A5054214235 @default.
- W4386759712 creator A5068538399 @default.
- W4386759712 creator A5077771596 @default.
- W4386759712 creator A5083493334 @default.
- W4386759712 date "2023-11-01" @default.
- W4386759712 modified "2023-10-07" @default.
- W4386759712 title "An Adversarial Time-Frequency Reconstruction Network for Unsupervised Anomaly Detection" @default.
- W4386759712 cites W2034887347 @default.
- W4386759712 cites W2052272843 @default.
- W4386759712 cites W2064675550 @default.
- W4386759712 cites W2116341502 @default.
- W4386759712 cites W2194775991 @default.
- W4386759712 cites W2604247107 @default.
- W4386759712 cites W2743617586 @default.
- W4386759712 cites W2948517885 @default.
- W4386759712 cites W2950361482 @default.
- W4386759712 cites W2962736999 @default.
- W4386759712 cites W2987793235 @default.
- W4386759712 cites W3004207920 @default.
- W4386759712 cites W3027528823 @default.
- W4386759712 cites W3045994189 @default.
- W4386759712 cites W3081497074 @default.
- W4386759712 cites W3086419524 @default.
- W4386759712 cites W3106543020 @default.
- W4386759712 cites W3109457141 @default.
- W4386759712 cites W3114141390 @default.
- W4386759712 cites W3128634608 @default.
- W4386759712 cites W3155567600 @default.
- W4386759712 cites W3169450514 @default.
- W4386759712 cites W3184778778 @default.
- W4386759712 cites W3190748826 @default.
- W4386759712 cites W3194553186 @default.
- W4386759712 cites W3209845259 @default.
- W4386759712 cites W3214635173 @default.
- W4386759712 cites W4224038053 @default.
- W4386759712 cites W4283318673 @default.
- W4386759712 doi "https://doi.org/10.1016/j.neunet.2023.09.018" @default.
- W4386759712 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37741104" @default.
- W4386759712 hasPublicationYear "2023" @default.
- W4386759712 type Work @default.
- W4386759712 citedByCount "0" @default.
- W4386759712 crossrefType "journal-article" @default.
- W4386759712 hasAuthorship W4386759712A5006977942 @default.
- W4386759712 hasAuthorship W4386759712A5049192246 @default.
- W4386759712 hasAuthorship W4386759712A5054214235 @default.
- W4386759712 hasAuthorship W4386759712A5068538399 @default.
- W4386759712 hasAuthorship W4386759712A5077771596 @default.
- W4386759712 hasAuthorship W4386759712A5083493334 @default.
- W4386759712 hasConcept C103824480 @default.
- W4386759712 hasConcept C11413529 @default.
- W4386759712 hasConcept C153180895 @default.
- W4386759712 hasConcept C154945302 @default.
- W4386759712 hasConcept C155512373 @default.
- W4386759712 hasConcept C19118579 @default.
- W4386759712 hasConcept C31972630 @default.
- W4386759712 hasConcept C41008148 @default.
- W4386759712 hasConcept C739882 @default.
- W4386759712 hasConcept C79337645 @default.
- W4386759712 hasConceptScore W4386759712C103824480 @default.
- W4386759712 hasConceptScore W4386759712C11413529 @default.
- W4386759712 hasConceptScore W4386759712C153180895 @default.
- W4386759712 hasConceptScore W4386759712C154945302 @default.
- W4386759712 hasConceptScore W4386759712C155512373 @default.
- W4386759712 hasConceptScore W4386759712C19118579 @default.
- W4386759712 hasConceptScore W4386759712C31972630 @default.
- W4386759712 hasConceptScore W4386759712C41008148 @default.
- W4386759712 hasConceptScore W4386759712C739882 @default.
- W4386759712 hasConceptScore W4386759712C79337645 @default.
- W4386759712 hasFunder F4320321001 @default.
- W4386759712 hasFunder F4320338110 @default.
- W4386759712 hasLocation W43867597121 @default.
- W4386759712 hasLocation W43867597122 @default.
- W4386759712 hasOpenAccess W4386759712 @default.
- W4386759712 hasPrimaryLocation W43867597121 @default.
- W4386759712 hasRelatedWork W1970292246 @default.
- W4386759712 hasRelatedWork W2162306796 @default.
- W4386759712 hasRelatedWork W2295423552 @default.
- W4386759712 hasRelatedWork W2499612753 @default.
- W4386759712 hasRelatedWork W2782295999 @default.
- W4386759712 hasRelatedWork W2946096271 @default.
- W4386759712 hasRelatedWork W2998615029 @default.
- W4386759712 hasRelatedWork W3111802945 @default.
- W4386759712 hasRelatedWork W4247952185 @default.
- W4386759712 hasRelatedWork W3107369729 @default.
- W4386759712 hasVolume "168" @default.
- W4386759712 isParatext "false" @default.
- W4386759712 isRetracted "false" @default.
- W4386759712 workType "article" @default.