Skip to Main content Skip to Navigation
Conference papers

SANDMAN: a Self-Adapted System for Anomaly Detection in Smart Buildings Data Streams

Abstract : Currently, energy management within buildings is essential to mitigate climate change. To this end, buildings are increasingly equipped with sensors to assist the building manager. Yet, the heterogeneity and the large amount of generated data make this task quite difficult. The SANDMAN multi-agent system, described in this paper, aims to assist in the automatic detection, in constrained time, of several types of anomalies using raw and heterogeneous data. SANDMAN features a semisupervised learning by considering some feedback from an expert in the field. The results show that SANDMAN detects different types of anomalies, is resilient to noise and is scalable.
Complete list of metadata
Contributor : Stephanie Combettes <>
Submitted on : Wednesday, November 25, 2020 - 4:28:11 PM
Last modification on : Thursday, March 18, 2021 - 2:22:17 PM
Long-term archiving on: : Friday, February 26, 2021 - 7:36:48 PM


Files produced by the author(s)


  • HAL Id : hal-03024015, version 1


Maxime Houssin, Stéphanie Combettes, Marie-Pierre Gleizes, Bérangère Lartigue. SANDMAN: a Self-Adapted System for Anomaly Detection in Smart Buildings Data Streams. 18th Adaptive Computing (and Agents) for Enhanced Collaboration at IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (ACEC @ WETICE 2020), Jun 2020, Bayonne, France. ⟨hal-03024015⟩



Record views


Files downloads