# TSRuleGrowth : Extraction de r\`egles de pr\'ediction semi-ordonn\'ees \`a partir d'une s\'erie temporelle d'\'el\'ements discrets, application dans un contexte d'intelligence ambiante

## TL;DR

This paper introduces TSRuleGrowth, an algorithm for mining semi-ordered prediction rules from discrete time series, applied to real-world connected environment data to uncover user habits.

## Contribution

The paper proposes a novel algorithm, TSRuleGrowth, that extends rule mining to semi-ordered rules in time series using a new support concept.

## Key findings

- Successfully extracted user habits from connected environment data.
- Demonstrated effectiveness of semi-ordered rule mining in real-world scenarios.
- Extended rule mining principles to temporal data with partial orderings.

## Abstract

This paper presents a new algorithm: TSRuleGrowth, looking for partially-ordered rules over a time series. This algorithm takes principles from the state of the art of rule mining and applies them to time series via a new notion of support. We apply this algorithm to real data from a connected environment, which extract user habits through different connected objects.