Enhanced efficient outlier detection and classification approach for WSNs

Abstract

Wireless Sensor Networks (WSNs) are one of the main components of the Internet of things (IoT) for gathering information and monitoring the environment in a variety of applications (medical, agricultural, manufacturing, militarily, etc.). However, data collected by sensors and sent to the base station are susceptible to have outliers. These outliers can occur due to sensor nodes themselves or to the harsh environment where they are deployed. Thus, the WSNs have to detect the outliers and take actions to ensure network quality of service (in terms of reliability, latency, etc.) and to avoid further degradation of the application efficiency. In this paper, we propose an enhanced approach of our previous work to achieve better performance for outlier issues in WSNs. The enhancement tackles the clustering phase and the outlier detection phase. The classification phase remains the same as in the EODCA work by using the Inverse Distance Weighting (IDW) method. The enhancement is titled EEODCA for Enhanced Efficient Outlier Detection and Classification Algorithm. For evaluation, we conduct a comparison study between EEODCA, EODCA and another work from the literature and thus for the multivariate data case. Simulation results with both synthetic and real-life datasets showed that the EEODCA outperforms the studied techniques in terms of several metrics like Detection Rate (DR), False Alarm Rate (FAR), Accuracy Rate (ACC), F1_score and Area Under the Curve (AUC).