Skip to Main content Skip to Navigation
New interface
Conference papers

Anomaly detection and characterization in smart card logs using NMF and Tweets

Emeric Tonnelier 1 Nicolas Baskiotis 1 Vincent Guigue 1 Patrick Gallinari 1 
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This article describes a novel approach to detect anomalies in smart card logs. In this study, we chose to work on a 24h base for every station in the Parisian metro network. We also consider separately the 7 days of the week. We first build a robust averaged reference for (day,station) couples and then, we focus on the difference between particular situations and references. All experiments are conducted both on the raw data and using an NMF denoised approximation of the log flow. We demonstrate the interest and the robustness of the latter strategy. Then we mine RATP Twitter account to obtain ground truth information about operating incidents. This synchronized flow is used to evaluate our models.
Document type :
Conference papers
Complete list of metadata
Contributor : Vincent Guigue Connect in order to contact the contributor
Submitted on : Tuesday, March 10, 2020 - 9:03:30 AM
Last modification on : Wednesday, January 12, 2022 - 3:47:24 AM


  • HAL Id : hal-02503476, version 1


Emeric Tonnelier, Nicolas Baskiotis, Vincent Guigue, Patrick Gallinari. Anomaly detection and characterization in smart card logs using NMF and Tweets. ESANN 2017 - 25th European Symposium on Artificial Neural Networks, Apr 2017, Bruges, Belgium. ⟨hal-02503476⟩



Record views