Develop the Hybrid Weighed Quantum Shark Optimization with a Faster Mask Deep Convolutional Neural Network to Improve the Performance Analysis of Predicting Diabetes at an Early Stage

Diabetes is an illness in which the pancreas secretes insulin that is not effective, resulting in a long-term disease. Early diagnosis of diabetes gives patients with diabetes a better opportunity to live healthy lifestyles. Deep learning also removes the need to extract features, unlike traditional methods of analysis that were used. The PIMA Indian diabetic information can be used to identify and predict Type 2 diabetes mellitus through a hybrid machine learning approach to continuous monitoring through publicly available datasets. In order to enhance the accuracy of the diabetic diagnosis at the initial stages, the given study suggests a hybrid model integrating the Weighted Quantum Shark Optimization (WQSO) and Faster Mask Deep Convolutional Neural Network (FMDCNN). The WQSO algorithm combines weighted strategies and Quantum Shark Optimization (QSO) in order to optimize the training of the FMDCNN. FMDCNN is a model that is trained to effectively analyze medical imaging information in order to diagnose diabetes in its early forms. Apply the WQSO solution space calculation and automatically adjust the parameters of the FMDCNN in order to obtain better predictive performance. The proposed system has a good record of accurately predicting early-stage diabetes, as manifested by the comparison of the approach with the current methods and in-depth analysis of the performance. As a result, the proposed system allows doctors to access vital statistics in real-time and obtain comprehensive patient profiles through real-time monitoring.