Network Intrusion Detection Method Using Stacked BILSTM Elastic Regression Classifier with Aquila Optimizer Algorithm for Internet of Things (IoT)

Globally, over the past ten years, computer networks and Internet of Things (IoT) have grown significantly due to increasing amount data that has been collected, ranging from zettabytes petabytes. As a result, as network expanded, security problems also emerged. The large sets involved in these types attacks can make detection difficult. developing are being used for multitude sophisticated purposes, such smart homes, cities, grids, gadgets, objects, well e-commerce, e-banking, e-government. result development numerous intrusion systems (IDS), now protected privacy threats. Data confidentiality, integrity, availability will suffer if IDS prevention efforts fail. Complex can't be handled by traditional methods. There growing interest advanced deep learning techniques detecting intrusions identifying abnormal behavior networks. This research aims propose novel namely stacked BiLSTM elastic regression classifier (Stack_BiLSTM-ERC) with Aquila optimizer algorithm feature selection. optimization method computes use cutting-edge transition function enables it transformed into binary form optimizer. A better solution could secured once number possible solutions found diverse regions search space utilizing method. NSL-KDD UNSW-NB15 two datasets enable characteristics raw order detect harmful prerequisites effective framework patterns. proposed Stack_BiLSTM-ERC achieves 98.l3% accuracy, 95.1% precision, 94.3% recall 95.4 F1-score dataset. Moreover, 98.6% 97.2% 98.5 97.5% F1-score.