Intelligent-based ensemble deep learning model for security improvement in real-time wireless communication

In IoT environment, intrusion detection is the identification of anomalous in the network which is subjected to challenges with the huge volume of data for the training and streaming. This research proposes an intelligent-based security model for the wireless communication. It is an Intelligent based ensemble classifier (IbeC) which comprises of the bagging-based model that creates multiple overlapping bags by sampling data from the training data and the resultant predictions are combined using a heuristic based voting combiner. Data is appropriately pre-processed and passed to the deep learning model for the prediction process and it is evaluated for the three different datasets such as NSL-KDD, KDD CUP 99 and Koyoto 2006+. The deep learning model is appropriately fitted for the given network intrusion data and the final predictions are obtained. The comparative analysis expressed that the proposed IbeC exhibits similar to 2% increased accuracy for the APID and HBM model.