Abstract

The rapid growth of interconnected devices gives rise to potential exploits and compromise of devices in the Internet of Things environment, this therefore requires an effective checkmate. This study focuses on the detection of threat in an IoTs environment based on ensemble model. In the proposed ensemble model, an outlier analysis was performed to optimize the features in order to enhanced the proposed model’s performance, while Support Vector Machine and Feed Forward Neural Network served as the base learners which were combined using stacking technique to form the proposed ensemble model, to enhance the performance strength in the detection of intrusion threat in IoTs environment. The advantage of the proposed model is its ability to generate an enhanced performance evaluation output; as the result proves an excellent performance for intrusion detection in an Internet of Things environment. The obtained accuracy, precision, F-score, and recall of the proposed ensemble model are 99.96% respectively, and 3.42% False Alarm Rate, thus, outperforming the existing technique. This is a clear distinction of the superiority of the ensemble (Feed Forward Neural Network and Support Vector Machine) model, the proposed ensemble model can serve as a technique in mitigating intrusion threat experienced in IoTs environment.

Key words: SVM, FFNN, Ensemble, IoTs, Accuracy, Recall