Lo studio applica delle tecniche di Machine Learning su immagini all’infrarosso, per la diagnosi differenziale del fenomeno di Raynaud (ISBN 9781326910853).
Today’s computational power makes it possible to apply increasingly high-performance learning algorithms.
Thus, the possibility of applying increasingly efficient procedures in data preprocessing and feature extraction and selection, combined with technological development (offering more precise sensors), lead to unimaginable solutions until a few years ago.
In this framework, this study is applied in a supervised classification approach on the basis of functional infrared (IR) imaging data, for the differential diagnosis of Raynaud’s Phenomenon.
The study also proposes a new features subset selection algorithm, called JSS+E (Jackknifed Stepwise Selection with Exhaustive search), in order to improve the stepwise selection procedure.
The results allow to refine the experimental protocol in a completely new non-invasive way.
Dove trovare il libro
Il Libro è disponibile su piattaforma LULU e Amazon al seguente LINK