Results of the "Ensembles of offline changepoint detection methods" research to reproduce

Documentation for the ruptures package.

Assessing the computational reproducibility of Kim et al. 2021 as part of STARS.

A repository for a user friendly environment to make offline change point detections using an optimisation approach and Bayesian statistics.

This project was undertaken as part of my work with the Internet Equity Initiative at the Data Science Institute, University of Chicago. More details about the initiative are here http://internetequity.uchicago.edu/about/the-initiative/.

L’objectif de ce projet est d’appliquer la classification non supervisée dans le cadre de la segmentation d’un ensemble de séries temporelles qui représentent la consommation d’électricité de 100 appartements/ménages observée toutes les 30 minutes durant 91 jours consécutifs. Il s’agit en particulier de détecter de manière automatique des ruptures

Seismic monitoring of urban noise and change point detection.

Unsupervised learning for the detection of patterns in human activity sensor data