Skip to Main content Skip to Navigation

Détection, anticipation, action face aux risques dans les bâtiments connectés

Abstract : This thesis aims to exploit the future mass of data that will emerge from the large number of connected objects to come. Focusing on data from connected buildings, this work aims to contribute to a generic anomaly detection system. The first year was devoted to defining the problem, the context and identifying the candidate models. The path of autoencoder neural networks has been selected and justified by a first experiment. A second, more consistent experiment, taking more into account the temporal aspect and dealing with all classes of anomalies was conducted in the second year. This experiment aims to study the improvements that recurrence can bring in response to convolution within an autoencoder used in connected buildings. The results of this study were presented and published in an IEEE conference on IoT in Egypt. The last year was devoted to improving the use of auto-encoder by proposing to include an estimate of uncertainty in the original operation of the auto-encoder. These tests, conducted on various known datasets initially and then on a connected building dataset later, showed improved performance and were published in an IEEE IA conference
Document type :
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Friday, June 10, 2022 - 11:41:10 AM
Last modification on : Friday, August 5, 2022 - 11:22:19 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03693152, version 1



Adrien Legrand. Détection, anticipation, action face aux risques dans les bâtiments connectés. Autre [cs.OH]. Université de Picardie Jules Verne, 2019. Français. ⟨NNT : 2019AMIE0058⟩. ⟨tel-03693152⟩



Record views


Files downloads