Abstract
Recently, Internet of things (IoT) is invading our daily life, which make it very attractive to industry as well as research community. the functionality of devices is prone to many failures. Discovering these failures is challenging problem due to field of devices deployment or due to device itself as resource constrained. We propose, in this paper, a novel IoT fault detection method. Feature extraction and classification is done by Support Vector Machines. Grey Wolf Optimiser (GWO) is added to the scheme for eliminating the irrelevant and redundant features. GWO optimizer is used to maximize the classification accuracy and to evaluate the selected features for the SVM classifier. This added component reflects the robustness of the proposed solution that has achieved very satisfying results. The overall accuracy is improved reaching 90.28 %.