الفهرس | Only 14 pages are availabe for public view |
Abstract As there is an urgent need for secure protection against cyber attacks, Cyber Intrusion Detection Systems (CIDSs) have been developed to identify malicious acts with higher efficiency. In this thesis, we propose a new Multi-layer Perception (MLP) algorithm by training a Multilayer Artificial Neural Network using a subset of dataset features through the wrapper feature selection technique. Our goal is to achieve the minimum number of selected features with maximum performance. To achieve this, we utilize the Whale Optimization Algorithm (WOA) is considered to be one of the most competitive nature-inspired metaheuristic optimization algorithms that has been proven effective in solving complex and constrained multi-objective problems, and is also popularly used as a feature selection algorithm while solving NP-hard (non-deterministic polynomial-time hardness) problems. |