Title :
Fractal Brownian motion for feature extraction in noisy signals from gas sensors
Author :
Gonschorowski, Juliano S. ; Salcedo, Walter J. ; Quispe, German C S ; Fernandez, Francisco J R ; Peixoto, Nathalia
Author_Institution :
Univ. de Sao Paulo, Sao Paulo
Abstract :
The present work reports on a new pattern recognition method applied to the electrical response of a gas sensor. The sensor is a tin oxide device used as an electronic nose. It yields noisy responses when submitted to organic solvents. Signals were analyzed by the epsilon-blanket fractal dimension associated with the fractal Brownian motion. The classification of features shows close to 100% recognition rate for five different gases.
Keywords :
Brownian motion; electronic noses; feature extraction; fractals; signal processing; tin compounds; SnO2; electrical response; electronic nose; epsilon-blanket fractal dimension; feature extraction; fractal Brownian motion; gas sensors; noisy responses; noisy signals; organic solvents; pattern recognition method; tin oxide device; 1f noise; Brownian motion; Equations; Feature extraction; Fractals; Gas detectors; Gases; Semiconductor device noise; Sensor phenomena and characterization; Signal analysis;
Conference_Titel :
Sensors, 2007 IEEE
Conference_Location :
Atlanta, GA
Print_ISBN :
978-1-4244-1261-7
Electronic_ISBN :
1930-0395
DOI :
10.1109/ICSENS.2007.4388399
