Sine hunter prey optimization enabled deep residual network for diabetes mellitus detection using tongue image

Abstract

Background: Many people suffer from Diabetes Mellitus (DM), a disease caused by high blood glucose levels. In real-time, many methods are implemented to diagnose DM to obtain a good accuracy level, but those methods remain costlier. Objective: To develop a method for DM detection with good accuracy and minimum cost. Materials and methods: In this research, DM is detected using tongue image based on DL model, named Deep Residual Network (DRN) that is trained by proposed Sine Hunter Prey Optimization (SHPO). Here, an adaptive median filter is used for the pre-processing phase, and image segmentation is done using ResUNet++, which is trained by Exponential Anti Corona Virus Optimization (ExpACVO). Here, ExpACVO integrates Anti Corona Virus Optimization (ACVO) and Exponential Weighted Moving Average (EWMA). Further, image augmentation and appropriate feature extraction stages are carried out, leading to DM detection by DRN. Moreover, SHPO is formed by combining the Sine Cosine Algorithm (SCA) and Hunter Prey Optimization (HPO). The performance of the proposed method is analyzed using the Tongue image dataset and the Diabetic images dataset. Results: The performance of SHPO_DRN is found using four evaluation metrics: accuracy, sensitivity, specificity, and f-measure. Here, these metrics exhibit superior performance with high-range values of 0.961, 0.970, 0.948, and 0.961. Conclusion: The proposed method detects the DM at earlier stages with a good accuracy.