Comparison of Linear and Non-Linear Regression Models for Non-Invasive Blood Glucose Measurement

Abstract

This paper deals with a new approach of non-invasive glucose monitoring based on near infrared spectroscopy. The proposed approach is coupled with a regression analysis in order to improve the predictive capacity of the designed device. Basic spectral data is a comparison that has been established between linear and non-linear machine learning regression algorithms. The experimental results show that feed forward backpropagation neural network improves more the performance of the designed prototype than partial least square models. The squared correlation coefficient and the Root Mean Square Error (RMSE) of the Artificial Neural Network (ANN) regression model built were 0.9804 and 0.0784 respectively. The ANN regression model was then used in the validation step using 300 human serums with a concentration range of 08-297 mg/dl. Clarke Error Grid Analysis (EGA) showed that 97% of the measured concentrations fall within the clinically acceptable regions. Results showed that the created model can open a new path to a non-invasive glucose monitoring.