Secure Communication through MultiAgent System-Based Diabetes Diagnosing and Classification

Abstract

Abstract The main objective of the research is to provide a multi-agent data mining system for diagnosing diabetes. Here, we use multi-agents for diagnosing diabetes such as user agent, connection agent, updation agent, and security agent, in which each agent performs their own task under the coordination of the connection agent. For secure communication, the user symptoms are encrypted with the help of Elliptic Curve Cryptography and Optimal Advanced Encryption Standard. In Optimal Advanced Encryption Standard algorithm, the key values are optimally selected by means of differential evaluation algorithm. After receiving the encrypted data, the suggested method needs to find the diabetes level of the user through multiple kernel support vector machine algorithm. Based on that, the agent prescribes the drugs for the corresponding user. The performance of the proposed technique is evaluated by classification accuracy, sensitivity, specificity, precision, recall, execution time and memory value. The proposed method will be implemented in JAVA platform.