The Unscented Kalman Filter for Real-Time Target Localization and Tracking in WSN Using Hybrid NPO-ANN Method.

Utilizing received signal strength indicators (RSSIs) is one of the most widely used cost-effective techniques for the localization and tracking of mobile targets using wireless sensor networks (WSNs). Significant estimation errors in target localization are caused by the noise variability in received signal strength indicator (RSSI) readings, particularly in indoor environments. In this paper, a new method is proposed based on a Nomadic People Optimizer (NPO) and Artificial Neural Network (ANN) to overcome the weaknesses of the traditional method, which is called NPO+ANN algorithm to improve the accuracy of target localization and tracking. This study presents a novel method for estimating the initial location of a single target moving in a 2-D space within a wireless sensor network (WSN) that combines hybrid NPO+ANN as a substitute for the common RSSI-based method. The Unscented Kalman Filter (UKF) is then used to improve and fine-tune these preliminary estimations to increase target localization accuracy, the research suggests NPO+ANN+UKF. The simulation outcome validates the NPO+ANN+UK architecture's capability for solving the real-time target tracking issue in WSN utilizing RSSI. The NPO+ANN+UKF provides a remarkable improvement of 98.2%, and 88% over the traditional RSSI, and NPO+ANN, respectively. [ABSTRACT FROM AUTHOR]