A Framework Model for Data Reliability in Wireless Sensor Networks

Abstract

In this study a model for data reliability in wireless sensor networks is proposed in which machine learning methods are used. Proposed framework includes data modelling missing data prediction anomaly detection data fusion and trust mechanism phases. Thus temporal analysis is performed on the preprocessed sensor data and missing data are predicated. Then outliers on collected data are detected on the cluster head nodes by using Eta one-class Support Vector Machines. If an event is detected data are fused and then send to sink. If an anomaly is detected for a node's data the trust weight of the node is decreased.