Real-Time Odor Classification
Through Sequential Bayesian Filtering

Javier G. Monroy

University of Malaga

Javier Gonzalez-Jimenez

University of Malaga

SBF

Abstract:: The classification of volatiles substances with an e-nose is still a challenging problem, particularly when working under real-time, out-of-the-lab environmental conditions where the chaotic and highly dynamic characteristics of the gas transportation induce an almost permanent transient state in the e-nose readings. In this work, a sequential Bayesian filtering (SBF) approach is proposed to efficiently integrate information from previous e-nose observations while updating the belief about the gas class on a real-time basis. We validate our proposal with two real olfaction datasets composed of dynamic time-series experiments (gas transitions are considered, but no mixture of gases), showing an improvement in the classification rate when compared to a stand-alone probabilistic classifier.

Downloads

Paper: PDF(792.2Kb) [BibText]

Slides: Presentation slides

@INPROCEEDINGS{JGMonroy_ISOEN2015_SBF,
    author = {G. Monroy, Javier and Gonz{\'{a}}lez-Jim{\'{e}}nez, Javier},
    title = {Real-Time Odor Classification Through Sequential Bayesian Filtering (Abstract only)},
    booktitle = {16th International Symposium on Olfaction and Electronic Nose (ISOEN)},
    year = {2015},
    location = {Dijon, Burgundy, France},
    url = {http://mapir.isa.uma.es/mapirwebsite/index.php/mapir-downloads/papers/210}
}

Related Publications