Skip to Main content Skip to Navigation
Conference papers

Détection statistique de rupture dans le cadre online

Nassim Sahki 1, 2 Anne Gégout-Petit 1, 2 Sophie Wantz-Mézières 1, 2
1 BIGS - Biology, genetics and statistics
Inria Nancy - Grand Est, IECL - Institut Élie Cartan de Lorraine
Abstract : We introduce the online version of the CUSUM statistics based on a sequential test of the likelihood ratio, which we replace with a score function in the non-parametric case. Change-point detection is based on a stopping rule and the selection of a detection threshold. In our work, we propose an instantaneous detection threshold dependent on time and new stopping rules in order to control the detection parameters given by the instantaneous false alarm rate (IFAR), the mean time between false alarms (MTBFA) and the average detection delay (ADD). Finally, we present simulation results by estimating detection parameters.
Complete list of metadata
Contributor : Nassim Sahki <>
Submitted on : Tuesday, September 17, 2019 - 9:10:34 AM
Last modification on : Thursday, April 22, 2021 - 10:12:02 AM


Nassim SAHKI- JdS 2019.pdf
Files produced by the author(s)


  • HAL Id : hal-02289680, version 1



Nassim Sahki, Anne Gégout-Petit, Sophie Wantz-Mézières. Détection statistique de rupture dans le cadre online. JdS 2019 - 51èmes Journées de Statistique, Jun 2019, Nancy, France. ⟨hal-02289680⟩



Record views


Files downloads