Why the study?
Anomaly detection is challenging due to limited knowledge of anomalies, and domains like monitoring systems require detectors capable of detecting any alteration.
Proposes a tool to generate anomalies as statistical deviations to aid in the design and testing of unsupervised anomaly detectors.
May aid anomaly detector design and testing; extends unsupervised methods but leaves open clinical validation.
Anomaly Detection is a challenging task due to the limited knowledge about possible anomalies. This issue can be tackled by modeling anomalies through domain expertise or collecting sufficient anomalous data. However, some domains, such as monitoring systems, require detectors that are capable of detecting any potential alteration in the observed phenomenon. Hereby we propose a tool to generate anomalies as a statistical deviation from the characterization of the signal representing the normal behavior. Two families of deviation models are presented, and the effectiveness of the tool is proven using well-known unsupervised detectors. The effects of a possible intermediate data compression stage on the detection capabilities are also considered.
No takes yet. Share an insight, caveat, or question.
Enttsel et al. (2023) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: