An improved deep bagging convolutional neural network classifier for efficient intrusion detection system

Abstract

In the current trend, the network-based system has substantial jobs, and they have become the targets of attackers. When an intrusion occurs, the security of a computer system is compromised. As a result, we must seek out the best methods for ensuring frameworks. A crucial component of the security management architecture is the intrusion detection system (IDS). To maintain effective network security, the design and implementation of IDS remain an important assessment topic. For intrusion detection, the previous system created an enhanced relevance vector machine (ERVM) classifier. However, intrusion detection is not robust for large-scale intrusion datasets, resulting in a high attack rate. The suggested work developed an improved deep bagging based convolutional neural network (DBCNN) for intrusion detection to address this issue. Preprocessing, feature selection, and classification are three processes included in the proposed framework. The KDD dataset is preprocessed in this stage using the kalman filter method. The feature selection is then carried out using the inertia weight based dragonfly method (IWDA). Finally, the DBCNN classifier successfully identifies interruption assaults. The KDD dataset is used to test the new model. The test results show that the proposed work accomplishes better execution contrasted and the current framework as far as accuracy, precision, recall and f-measure.