Hyperbolic decision-making based on RBF for diabetic/COVID-19 iris

The Iris is the most complex tissue of the body that shows thousands of nerves, blood vessels, muscles, and other tissues. This study presents techniques for searching points on the iris by visual query language based on the Gaussian radial basis function (GRBF) and Hyperbolic decision tree; there are several types of iris belonging to diabetic patients; we consider the behavior of COVID-19 on diabetes; our solution detects similarities in symptoms for two different conditions. It can estimate signs of new patterns of diseases on the next cycle of the time interval of illness for virus mutation. It can match the zones in the iris by Delaunay triangulation in d3. js. Then it can design colored models with the same color for spatial diseases. The best algorithm is used for community detection for a group of signs clustered and reducing the error with K-NN by neo4j on the Cypher platform. It detects congestion of infection and inflammation of chronic diseases as a background disease; Covid-19 disorder is illustrated with a centrality algorithm based on a shared relationship for two diseases graph. Our techniques calculate the accuracy of our query design for the target shared symptoms model for new diseases. We reduced complexity algorithms and search time by decreasing the redundancy of data points. We provide the abstract layer in the target model to reduce the dimensionality of data. We present a model from a graph with a description of knowledge that it can generate to determine the target user. Algorithms optimize this model. This model can map the points of the circle into the query and hyperbolic tree, and decide for their classification in the next mutation of diseases. Our solution improved the performance by about 97% in memory usage and time-consuming of search data in complex mixed diseases with different colors and signs.