Investigation of LSSVM and RBFNN-based Techniques for Intrusion Detection Systems for IoT Networks

As more and more devices become internet-enabled, it's no longer possible to imagine modern life without them. In particular, Internet of Things (IoT) devices have become widespread and indispensable. But there are issues that appear to be worsening and for which there are currently no good solutions. The safety of Internet of Things (IoT) devices and other connected gadgets is a growing concern. There has been a lot of development in the area of safeguarding IoT networks, but there is always room for improvement. The proposed methodology consists of three stages: preprocessing the data, selecting the features to use, and training the model. In data preprocessing, normalization and standardization techniques are utilized. The use of particle swarm optimization helps improve feature selection. Models are trained with SVM-RBFNN after information gain is used to choose relevant features. The proposed method achieves better results than both SVM and LSSVM, two widely usedalternatives.