Skip to Main content Skip to Navigation
Conference papers

SANDMAN : un système auto-adaptatif pour la détection d’anomalies dans le flux des données des bâtiments intelligents

Abstract : Currently, energy management within buildings is essentialto participate in the green transition. To this end, buildingsare increasingly equipped with sensors to assist the buil-ding manager. But the heterogeneity and the large amountof data generated makes this task quite difficult. The SAND-MAN multi-agent system, described in this paper, aims toassist in the automatic detection, in real time, of seve-ral types of anomalies using raw and heterogeneous data.SANDMAN features a semi-supervised learning by consi-dering some feedbacks from an expert in the field. The re-sults show that SANDMAN, after a learning phase, detectsthe different types of anomalies, is resistant to noise and isscalable.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03024002
Contributor : Stephanie Combettes <>
Submitted on : Wednesday, November 25, 2020 - 4:23:17 PM
Last modification on : Tuesday, March 30, 2021 - 5:04:02 PM
Long-term archiving on: : Friday, February 26, 2021 - 7:35:28 PM

File

RJCIA_2020_Paper20.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03024002, version 1

Citation

Maxime Houssin, Stéphanie Combettes, Marie-Pierre Gleizes, Bérangère Lartigue. SANDMAN : un système auto-adaptatif pour la détection d’anomalies dans le flux des données des bâtiments intelligents. Rencontres des Jeunes Chercheur·ses en Intelligence Artificielle (RJCIA 2020 @ PFIA), PFIA : Plate-Forme IA, Jun 2020, Angers, France. ⟨hal-03024002⟩

Share

Metrics

Record views

40

Files downloads

27