Title :
A study in the application of multilayer perceptrons to the analysis of chemical sensors systems data
Author :
Pardo, Matteo ; Sberveglieri, Giorgio
Author_Institution :
Dept. of Chem. & Phys., Brescia Univ., Italy
Abstract :
In this paper, we address two aspects, which influence the performance of multilayer perceptrons (MLP). 1) dimensionality reduction with PCA: the number of principal components are optimized; 2) complexity control: we investigate three different methods: model order selection, early stopping and regularization. We considered two electronic nose datasets of different size and learning difficulty. Measurements have been performed with the pico electronic nose based on thin film gas sensors. It turns out that: 1) (test set) performance depends strongly on the number of principal components and that even components with less than 1% of the global variance enhance classification; 2) if complexity control is performed with early stopping or regularization, then overfitting is avoided whatever the number of hidden units (and hence of network weights) is.
Keywords :
chemical sensors; data analysis; multilayer perceptrons; principal component analysis; chemical sensors systems data; complexity control; dimensionality reduction; early stopping; electronic nose datasets; global variance; model order selection; multilayer perceptrons; network weights; principal components; regularization; thin film gas sensors; Chemical analysis; Chemical sensors; Electronic noses; Gas detectors; Multilayer perceptrons; Optimization methods; Performance evaluation; Principal component analysis; Testing; Thin film sensors;
Conference_Titel :
Sensors, 2002. Proceedings of IEEE
Print_ISBN :
0-7803-7454-1
DOI :
10.1109/ICSENS.2002.1037306