Evolutionary Neural Architecture Search for Type 2 Diabetes Mellitus Diagnosis from Salivary ATR-FTIR Spectroscopy

Abstract

The blood diagnosis of diabetes mellitus (DM) is accurate, but invasive. Attenuated Total Reflectance by Fourier Transform Infrared Spectroscopy (ATR-FTIR) is a green technology adopted in the detection of several diseases resulting in a non-invasive and accurate diagnosis. The analysis of ATR-FTIR data using deep learning techniques like Convolutional Neural Network (CNN) is promising. However, the challenges to find optimized architectures are barely explored in the ATR-FTIR literature. In this paper, we propose an Evolutionary Neural Architecture Search technique able to find optimized CNN architectures for salivary ATR-FTIR spectra for type 2 DM diagnosis using Genetic Algorithm as optimization approach.