Software

OODS : Outlier detection for data streams (including DyCF, DyCG and evaluation). Ducharlet K (2023) URL https://github.com/kyducharlet/odds

Remaining cycle time prediction with Graph Neural Networks for Predictive Process Monitoring. Duong L.T. (2023) URL https://github.com/duongtoan261196/RemainingCycleTimePrediction

DyD2 : Dynamic Double Anomaly Detection DyD2. Dorise A. (2022) URL https://github.com/Adrien-Dorise/DyD2_Dynamic_Double_Anomaly_Detection

DYCLEE : Dyclee implements a dynamic clustering algorithm that efficiently deals with data streams and achieves several important properties which are not generally found together in the same algorithm. The dynamic clustering algorithm operates online in two different time-scale stages, a fast distance-based stage that generates micro-clusters and a density-based stage that groups the micro-clusters according to their density and generates the final clusters. The algorithm achieves novelty detection and concept drift thanks to a forgetting function that allows micro-clusters and final clusters to appear, drift, merge, split or disappear. The algorithm supporting Dyclee has been designed to be able to detect complex patterns even in multi-density distributions and making no assumption of cluster convexity.
Developped by Nathalie Barbosa Roa, Renaud Pons and Louise Travé-Massuyès.

HYDIAG : An analytical redundancy based diagnosis engine for hybrid systems. This diagnosis engine is able to monitor a hybrid system and determines the current fault mode of the underlying system. The input of the software is a mode automaton and a set of analytical redundancy relations for each mode resulting from a system and fault analyses.
Developped by Mehdi Bayoudh and Louise Travé-Massuyès.
 
Causalito : Causal graph generator. This software computes the causal graph of a system, that are the influences between the variables of the system. This causal graph is one of the inputs of a simulator that propagates variations on the input variables. This software tales as input a mathematical model of the system and generates its causal graph. An edge of th graph is labeled as a causal influence between two variables.
Developped by Renaud Pons and Louise Travé-Massuyès.