Cluster-based Ensemble Classification Approach for Anomaly Detection in the Internet of Things

Background & Objective: The next generation of the internet where physical things or objects are going to interact with each other without human interventions is called the Internet of Things (IoT). Its presence can improve the quality of human lives in different domains and environments such as agriculture, smart homes, intelligent transportation systems, and smart grids. In the lowest layer of the IoT architecture (i.e., the perception layer), there are a variety of sensors which are responsible for gathering data from their environment to provide service for customers. However, these collected data are not always accurate and may be infected with anomalies for some reasons such as limited sensor’s resources and environmental influences. Accordingly, anomaly detection can be used as a preprocessing phase to prevent sending inappropriate data for the processing. Methods: Since distributed characteristic and its heterogeneous elements complicate the application of anomaly detection techniques, in this paper, a cluster-based ensemble classification approach has been presented. > Results & Conclusion: Will possessing low complexity, the proposed method has high accuracy in detecting anomalies. This method has been tested on the data collected from sensors in the Intel Berkley research laboratory which is one of the free and available datasets in the domain of IoT. The results indicated that the proposed technique could achieve an accuracy of 99.9186%, a positive detection rate of 99.7459%, while reducing false positive rate and misclassification rate to 0.0025% and 0.0813% respectively.