Application of Artificial Neural Network and Gray Level Co-occurrence Matrix to detect blood glucose levels through the skin of the hands.

Abstract

Increased glucose in the blood can cause a buildup so that it cannot be absorbed by all of the body's cells, this problem can cause various disorders in the body's organs. To avoid problems, it is necessary to check the blood glucose level regularly. Monitoring blood sugar levels is currently still using invasive techniques that are painful, non-invasive monitoring is needed. This study develops a non-invasive method to predict blood glucose through image processing. For investigation, several invasive images and glucose levels were taken. Types of samples based on age classification, 20-60 years. For accuracy and simple analysis, 37 images of participants as volunteers, samples were evaluated and investigated under the gray level co-occurrence matrix (GLCM). In this study, an artificial neural network (ANN) was used for all training and hand texture testing to detect glucose levels. The performance of this model is evaluated using Root Mean Square Error (RMSE) and correlation coefficient (r). Clarke Error Grid Analysis (EGA) variance was used in this investigation to determine the accuracy of the method. The results showed that the RMSE was close to the standard value, the regression coefficient was 0.95, and the Clarke EGA analysis: 81.08 % was in the A zone. So that the blood glucose prediction model using the GLCM-ANN method is feasible to apply.