Skip to Main content Skip to Navigation
Theses

Variational deep learning for time series modelling and analysis : applications to dynamical system identification and maritime traffic anomaly detection

van Duong Nguyen 1, 2
1 Lab-STICC_IMTA_CID_TOMS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : This thesis work focuses on a class of unsupervised, probabilistic deep learning methods that use variational inference to create high capacity, scalable models for time series modelling and analysis. We present two classes of variational deep learning, then apply them to two specific problems related to the maritime domain. The first application is the identification of dynamical systems from noisy and partially observed data. We introduce a framework that merges classical data assimilation and modern deep learning to retrieve the differential equations that control the dynamics of the system. Using a state space formulation, the proposed framework embeds stochastic components to account for stochastic variabilities, model errors and reconstruction uncertainties. The second application is maritime traffic surveillance using AIS data. We propose a multitask probabilistic deep learning architecture can achieve state-of-the-art performance in different maritime traffic surveillance related tasks, such as trajectory reconstruction, vessel type identification and anomaly detection, while reducing significantly the amount data to be stored and the calculation time. For the most important task—anomaly detection, we introduce a geospatial detector that uses variational deep learning to builds a probabilistic representation of AIS trajectories, then detect anomalies by judging how likely this trajectory is.
Document type :
Theses
Complete list of metadata

https://tel.archives-ouvertes.fr/tel-03185892
Contributor : Abes Star :  Contact
Submitted on : Tuesday, March 30, 2021 - 4:53:16 PM
Last modification on : Tuesday, April 20, 2021 - 10:40:01 AM

File

2020IMTA0227_Nguyen-Duong.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03185892, version 1

Citation

van Duong Nguyen. Variational deep learning for time series modelling and analysis : applications to dynamical system identification and maritime traffic anomaly detection. Machine Learning [cs.LG]. Ecole nationale supérieure Mines-Télécom Atlantique, 2020. English. ⟨NNT : 2020IMTA0227⟩. ⟨tel-03185892⟩

Share

Metrics

Record views

93

Files downloads

95