Аннотация:Due to the sensitivity of the information required to detect network intrusions efficiently, collecting huge amounts of network transactions is inevitable and the volume and details of network transactions available in recent years have been high. The meta-heuristic anomaly based assessment is vital in an exploratory analysis of intrusion related network transaction data. In order to forecast and deliver predictions about intrusion possibility from the available details of the attributes involved in network transaction. In this regard, a meta-heuristic assessment model called the feature correlation analysis and association impact scale is explored to estimate the degree of intrusion scope threshold from the optimal features of network transaction data available for training. With the motivation gained from the model called "network intrusion detection by feature association impact scale" that was explored in our earlier work, a novel and improved meta-heuristic assessment strategy for intrusion prediction is derived. In this strategy, linear canonical correlation for feature optimization is used and feature association impact scale is explored from the selected optimal features. The experimental result indicates that the feature correlation has a significant impact towards minimizing the computational and time complexity of measuring the feature association impact scale.
