Network data management model based on Naïve Bayes classifier and deep neural networks in heterogeneous wireless networks

Abstract

A key purpose of a data management system is to monitor and control the large volume of data and other relevant information. Focusing on the data management issues and developing a detection system is necessary for resolving attacks or intrusion in a network. This network instruction detection system helps to identify unseen and unpredictable attacks in management station via loophole to break network security. Conventional instruction detection system has complexities in exploiting, enhancing the security features and this research work focuses on solving above issue. The proposed research work is designed for efficient and flexible network intrusion detection system using Naïve Bayes classifier and deep neural networks. The experimental results show that proposed Deep Neural Network-based Intrusion Detection System is suitable for classification with high accuracy and precision in both binary and multiclass, recall and f- measure values. Compared with other state-of-the-art approaches, the analytic accuracy has been improved.