Compressing spectral data using optimised Gaussian basis
Tuomas Kärna, Francesco Corona and Amaury Lendasse
Journal of Chemometrics
High-dimensional data are becoming more and more common, especially in the field of chemometrics. Nevertheless, it is generally known that most of the commonly used prediction models suffer from curse of dimensionality that is the prediction performance degrades as data dimension grows. Therefore it is important to develop methodology for reliable dimensionality reduction. In this paper, we propose a method that is based on functional approximation using Gaussian basis functions. The basis functions are optimised to accurately fit the spectral data using nonlinear Gauss - Newton algorithm. The fitting weights are then used as training data to build a least-squares support vector machine (LS-SVM) model. To utilise the reduced data dimension, relevant variables are further selected using forward--backward (FB) selection. The methodology is experimented with three datasets originating from the food industry. The results show that the proposed method can be used for dimensionality reduction without loss of precision.