Fractional Dynamics Foster Deep Learning of COPD Stage Prediction (Adv. Sci. 12/2023)

Abstract

Deep Learning Analyzing physiological signals with fractional dynamics reduces the learning complexity for automated diagnosis with deep learning. In article number 2203485, Mihai Udrescu, Paul Bogdan, and co-workers show that fractional-order dynamical modeling can extract distinguishing signatures from the physiological signals recorded in COPD patients, then use fractional signatures to develop and train a deep neural network that accurately predicts COPD stages—a robust alternative to spirometry.