Recherche de motifs partiellement ordonnés clos discriminants pour caractériser l'état des milieux aquatiques

Abstract : This paper presents a data mining process implemented to extract original knowledge from hydro-ecological data. The approach is based on closed partially ordered patterns used as discriminant features to link physico-chemistry with biology in river sampling sites. For each bio-indicator quality value, we obtain a set of significant discriminant features. We use them to identify the impact of physico-chemical characteristics on the biological dimensions. The approach has been experimented on a dataset of several thousands river sites.
Document type :
Other publications
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01102784
Contributor : Florence Le Ber <>
Submitted on : Tuesday, January 13, 2015 - 2:58:28 PM
Last modification on : Wednesday, September 18, 2019 - 4:04:05 PM
Long-term archiving on: Tuesday, April 14, 2015 - 11:05:40 AM

File

anaenv2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01102784, version 1

Citation

Mickaël Fabrègue, Agnès Braud, Sandra Bringay, Florence Le Ber, Maguelonne Teisseire. Recherche de motifs partiellement ordonnés clos discriminants pour caractériser l'état des milieux aquatiques. 2014. ⟨hal-01102784⟩

Share

Metrics

Record views

573

Files downloads

256