Examining the longevity of dental restoration using Hebbian adversarial networks clustering with gradient boosting recurrent neural network

Abstract Dental restoration is one of the crucial methods that used to avoid the teeth loss and damage by filling teeth with restorative materials. During this process, longevity of dental restoration is difficult to predict due to the type of filling, characteristics of cavity and patient health. The less lifetime of dental restoration process leads to causes the teeth loss and creates more damage to teeth. For overcoming these issues, case based reasoning evolutionary algorithm called Hebbian adversarial networks clustering with gradient boosting recurrent neural network (GBRNN). The method collects the different case based restorative materials details from patients, the collected information is processed and similar details are clustered using above defined clustering approach after removing inconsistent data. At the time of clustering process, quantitative and quality of restoration materials are examined for each case and similar cases are grouped together. After that, the grouped information is analyzed by defined classifier that predicts the quality restorative materials which used to predict the longevity of restoration process. Finally the performance of system is evaluated using MATLAB tool based experimental results.