Performance of multilayer perceptrons for classification of LIBS protein spectra

We investigate performance of neural networks for classification of laser-induced breakdown spectroscopic data of four proteins: Bovine Serum Albumin, Osteopontin, Leptin and Insulin-like Growth Factor II. We utilize principal component analysis algorithm for feature extraction and multilayer perceptrons algorithms with one and two hidden layers. We employ leave-one-out procedure for classifier evaluation. Our experimental results indicate that methods with linear convergence can provide classification accuracy superior to methods with quadratic convergence.