A new automated procedure able to extract latent chemical information from ToF-SIMS big data sets is presented. A classifier based on a probabilistic neural network able to provide a correct classification of spectra acquired from four different polymers is designed and trained. The procedure is fast and low-demanding in terms of CPU performances, and it is also able to evaluate the similarity/dissimilarity in the Fourier transform domain of very low intensity single pixel spectra without any effort of the analyst.
|Titolo:||Probabilistic neural network-based classifier of ToF-SIMS single-pixel spectra|
|Data di pubblicazione:||2019|
|Appare nelle tipologie:||1.1 Articolo in rivista|