Dependable Object Stalking Model Employing Modified Kalman Filter (MKF) in WSNs

Abstract

The Wireless Sensor Networks (WSNs) advances a variety of ground-breaking applications, including localization, target tracking, etc. The bulk of these applications make use of a large number of sensor devices that are linked to the base station, which functions as a gateway to link cloud computing environments and other settings. The primary functions of WSNs are data gathering, data sensing, and data transmission; however, sensor devices collect data and communicate it episodically across the intermediate node in order to make wise decisions from time to time. The main goal of target tracking applications using WSNs is to increase tracking prediction accuracy, network reliability, and lifetime performance for data collected. This study proposes a model for dependable target tracking (RTT) that makes use of WSNs. First, a modified Kalman Filter (MKF) is implemented to increase forecast accuracy. Next, multi-objective-based route optimization and better CH selection are demonstrated. The findings of the experiment demonstrate that the RTT model outperforms the current target tracking approach using WSNs in terms of energy efficiency, tracking accuracy, latency reduction, and communication overhead