DONATE

Publications

by Keyword: Inference mechanisms

Pomareda, Victor, Marco, Santiago, (2011). Chemical plume source localization with multiple mobile sensors using bayesian inference under background signals Olfaction and Electronic Nose: Proceedings of the 14th International Symposium on Olfaction and Electronic Nose AIP Conference Proceedings (ed. Perena Gouma, SUNY Stony Brook), AIP (New York City, USA) 1362, (1), 149-150

This work presents the estimation of a likelihood map for the location of a source of chemical plume using multiple mobile sensors and Bayesian Inference. Previously described methods use a single sensor and just binary detections (concentrations above or below a certain threshold). The main contribution of this work is to extend previous proposals to use concentration information while at the same time being robust against the presence of background signals. The algorithm has two parts. The first part, concerning Adaptive Background Estimation, uses robust statistics measurements to estimate the background level despite the intermittent presence of high concentrations due to plume statistics. The second part of the algorithm estimates likelihood functions for background and for condition plus plume. Then, the algorithm sequentially builds a likelihood probability map for the location of the source. The algorithm allows the use of multiple mobile sensors. The simulation results demonstrate that our algorithm estimates better the source location and is much more robust in the presence of false alarms.

JTD Keywords: Sensors, Inference mechanisms, Probability, Simulation