Anomaly Detection in the Internet of Things Using K-Means Clustering and SMO Classifier

Internet of Things is the next generation of internet that physical objects or things interacts with together without human interventions and its presence in different domains and environments, has improved the quality of human lives. But this emerging technology due to the limited sensor’s resources and environmental influences is prone to the existence of abnormal data, accordingly it is week against intrusion. Also, due to the distributed characteristic and its heterogeneous elements, applying complex intrusion detection techniques is very difficult. In this paper a hybrid approach based on K-Means clustering and Sequential Minimal Optimization (SMO) classification has been presented for anomaly detection in the internet of things which despite of very low complexity has a high accuracy in detecting anomalies. This method has been tested on the data collected from sensors in the Intel Berkley research lab which is one of the available free data set in the domain of Internet ofthings. The results show that the proposed technique could achieve an accuracy of 100%, positive detection rate of 100% and reduce false positive rate to 0%.

Keywords:

Internet of Things , Anomaly Detection , Intel Lab , K-Means Clustering , SMO Classifier