Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

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 outperforms all state-of-the-art methods for anomaly detection on the two considered datasets.

up
0 users have voted:

Paper Details

Authors:
Amina Alaoui-Belghiti, Sylvain Chevallier, Eric Monacelli, Guillaume Bao, Eric Azabou
Submitted On:
20 May 2020 - 8:36am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Sylvain Chevallier
Paper Code:
IDSP-L1.3
Document Year:
2020
Cite

Document Files

Presentation slides

(14)

Subscribe

[1] Amina Alaoui-Belghiti, Sylvain Chevallier, Eric Monacelli, Guillaume Bao, Eric Azabou, "Semi-Supervised Optimal Transport Methods for Detecting Anomalies", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5406. Accessed: Jul. 10, 2020.
@article{5406-20,
url = {http://sigport.org/5406},
author = { Amina Alaoui-Belghiti; Sylvain Chevallier; Eric Monacelli; Guillaume Bao; Eric Azabou },
publisher = {IEEE SigPort},
title = {Semi-Supervised Optimal Transport Methods for Detecting Anomalies},
year = {2020} }
TY - EJOUR
T1 - Semi-Supervised Optimal Transport Methods for Detecting Anomalies
AU - Amina Alaoui-Belghiti; Sylvain Chevallier; Eric Monacelli; Guillaume Bao; Eric Azabou
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5406
ER -
Amina Alaoui-Belghiti, Sylvain Chevallier, Eric Monacelli, Guillaume Bao, Eric Azabou. (2020). Semi-Supervised Optimal Transport Methods for Detecting Anomalies. IEEE SigPort. http://sigport.org/5406
Amina Alaoui-Belghiti, Sylvain Chevallier, Eric Monacelli, Guillaume Bao, Eric Azabou, 2020. Semi-Supervised Optimal Transport Methods for Detecting Anomalies. Available at: http://sigport.org/5406.
Amina Alaoui-Belghiti, Sylvain Chevallier, Eric Monacelli, Guillaume Bao, Eric Azabou. (2020). "Semi-Supervised Optimal Transport Methods for Detecting Anomalies." Web.
1. Amina Alaoui-Belghiti, Sylvain Chevallier, Eric Monacelli, Guillaume Bao, Eric Azabou. Semi-Supervised Optimal Transport Methods for Detecting Anomalies [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5406