A predictive target tracking framework for IoT using CNN–LSTM

Abstract

This paper addresses the issue of tracking a mobile target, through a data-driven active sensor selection mechanism in the Internet of Things (IoT) sensing applications. IoT networks have proved their usefulness in environmental monitoring applications, including target tracking, thanks to their ease of deployment, scalability, and ability to provide real-time monitoring. Nevertheless, IoT-based target tracking approaches usually sacrifice either the accuracy of the approach or the energy efficiency. In this work, we present a predictive target tracking approach, capable of tracking a mobile target with high accuracy and low overall energy cost. A convolutional long short-term memory (CNN–LSTM) model that can extract both spatial and temporal patterns is proposed to predict the mobility of a source using time-delayed data readings obtained from the IoT sensors. The predicted location is used to dynamically select a set of sensors that can carry out continuous tracking. Moreover, a mechanism to detect possible target loss and its subsequent recovery is also proposed. A use-case of tracking a radioactive source carried by a walking person, in varying settings and for different benchmarks, is used to validate the proposed approach performance. The results demonstrate accurate prediction of the target’s location, and efficient tracking which saves up to 90% of the network’s energy.