A Hybrid Slime Mould Meta Heuristic Algorithm and Machine Learning Technique for Intrusion Detection System

Network anomaly prediction is a crucial aspect of network security, as it helps identify unusual or potentially malicious activities within a computer network. There are several approaches and techniques used for network anomaly prediction, and Machine Learning (ML) is often employed due to its ability to detect patterns and anomalies in large datasets. In this research, network anomaly detection is carried out by three stages. In first stage, data set from IEEE data port is collected and LRC, RFC models are trained for prediction. In second stage, dimension reduction algorithm PCA is used for preprocessing and ML models are trained for prediction. In third stage, the hybrid PCA +SMA is proposed along with ML models for prediction. From this analysis, the hybrid PCA+SMA+ML provide better performance (accuracy 96) compared with previous three stages. Finally, the hybrid PCA+SMA+RFC is selected for final deployment.