Paper Title
ANN-Based Whale Sine Algorithm: A Promising Approach to Improve Intrusion Detection

Abstract
Network anomaly detection systems enable monitoring the computer networks behaving in a different way from the protocol of the network and it’s implemented mainly in a variety of the areas. IDS (Intrusion Detection Systems) is extensively used to secure and monitor the networks. Concurrently, ML (Machine Learning) is commonly deployed to provide potential solutions for attack detection in existing studies. By using ML, the present study aims to increase the efficiency of intrusion detection by checking the presence of intrusion in the network. An efficient feature selection approach always directly influences on the performance styles such as computational information and integrity. Two techniques are proposed in this study, in order to detect the malicious activities that exists in the network–Optimal Whale Sine Algorithm (OWSA) for feature selection and ANN Weighted Random Forest (AWRF) for classification. The present study improves the IDS which is evaluated by using the UNSW-BoT dataset. These proposed model in the present study obtains better results in accordance with performance metrics such as precision, recall, f1-score and accuracy and there by increases the efficiency of IDS. The proposed model produces more attractive outcomes that exposes the performance of the algorithm in order to select the best features and perform optimal intrusion detection. Keywords - Intrusion Detection, Machine Learning, Sine Cosine Algorithm, Whale Optimization Algorithm, Random Forest