Sensor data modeling for data trustworthiness

Abstract

Wireless sensor networks (WSNs) are installed in the terrain for observing the physical and environmental parameters. The nodes in the network are resource constrained in nature and faces several challenges for producing the data from the unfriendly environment. Large amount of data is generated from WSN and suffers from data fault, inaccuracy and inconsistency. To increase the reliability of application, several data trust management schemes are introduced to ensure the trustworthiness of data in decision making process. Apart from these schemes, in the absence of ground truth, sensor data models are used to find the trustiness of the sensor data. The data generated from the simulation of data model is used as a metric to evaluate the degree of trustiness of sensor data. The existing sensor data models suffer from high energy consumption for data trustiness detection and it becomes inaccurate when the data fault rate is high. In this paper, we are proposing an energy efficient sensor data model for evaluating the sensor data trustworthiness and reconstruct the sensor data in case of any data loss and data fault. The proposed data model is hybrid in nature and it works at low level sensor nodes and also at sink node. Results show that the proposed data model is able to detect the untrustworthy data and gives remedy to untrustworthy and missing data with the help of data reconstruction in an energy efficient way and it is able to identify the events in reliable fashion. � 2017 IEEE.