Increasing pattern recognition accuracy for chemical sensing by evolutionary based drift compensation

Authors:
S. Di Carlo;M. Falasconi;E. Sanchez;A. Scionti;G. Squillero;A. Tonda
Affiliations:
Politecnico di Torino, Control and Computer Engineering Department, Torino, Italy;SENSOR CNR-IDASC, Brescia, Italy and University of Brescia, Department of Chemistry and Physics for Engineering and Materials, Brescia, Italy;Politecnico di Torino, Control and Computer Engineering Department, Torino, Italy;Politecnico di Torino, Control and Computer Engineering Department, Torino, Italy;Politecnico di Torino, Control and Computer Engineering Department, Torino, Italy;Politecnico di Torino, Control and Computer Engineering Department, Torino, Italy
Venue:
Pattern Recognition Letters
Year:
2011

Citing 5
Cited 0

Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES)

Evolutionary Computation
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Completely Derandomized Self-Adaptation in Evolution Strategies

Evolutionary Computation
A stability based validity method for fuzzy clustering

Pattern Recognition
Exploiting evolution for an adaptive drift-robust classifier in chemical sensing

EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I

Quantified Score

Hi-index	0.10

Visualization

Abstract

Artificial olfaction systems, which mimic human olfaction by using arrays of gas chemical sensors combined with pattern recognition methods, represent a potentially low-cost tool in many areas of industry such as perfumery, food and drink production, clinical diagnosis, health and safety, environmental monitoring and process control. However, successful applications of these systems are still largely limited to specialized laboratories. Sensor drift, i.e., the lack of a sensor's stability over time, still limits real industrial setups. This paper presents and discusses an evolutionary based adaptive drift-correction method designed to work with state-of-the-art classification systems. The proposed approach exploits a cutting-edge evolutionary strategy to iteratively tweak the coefficients of a linear transformation which can transparently correct raw sensors' measures thus mitigating the negative effects of the drift. The method learns the optimal correction strategy without the use of models or other hypotheses on the behavior of the physical chemical sensors.