Skip to Main content Skip to Navigation
Conference papers

Semi-supervised optimal transport methods for detecting anomalies

Abstract : Building upon advances on optimal transport and anomaly detection, we propose a generalization of an unsupervised and automatic method for detection of significant deviation from reference signals. Unlike most existing approaches for anomaly detection, our method is built on a non-parametric framework exploiting the optimal transportation to estimate deviation from an observed distribution. We described the theoretical background of our method and demonstrate its effectiveness on two datasets: an industrial predictive maintenance task based on audio recording and a detection of anomalous breathing relying on brain signals. In this type of problem, no negative or faulty samples are seen during training and the objective is to detect any abnormal sample without raising false alarm. The proposed approach outper-forms all state-of-the-art methods for anomaly detection on the two considered datasets.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.uvsq.fr/hal-02614100
Contributor : Sylvain Chevallier <>
Submitted on : Wednesday, May 20, 2020 - 4:31:56 PM
Last modification on : Wednesday, October 14, 2020 - 4:20:30 AM

File

ICASSP_Amina_AnomalyDetectionO...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02614100, version 1

Collections

Citation

Amina Alaoui-Belghiti, Sylvain Chevallier, Eric Monacelli, Guillaume Bao, Eric Azabou. Semi-supervised optimal transport methods for detecting anomalies. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, Barcelona, Spain. ⟨hal-02614100⟩

Share

Metrics

Record views

29

Files downloads

62