Target Tracking Using Machine Learning and Kalman Filter in Wireless Sensor Networks

Abstract

This paper describes an original method for target tracking in wireless sensor networks. The proposed method combines machine learning with a Kalman filter to estimate instantaneous positions of a moving target. The target's accelerations, along with information from the network, are used to obtain an accurate estimation of its position. To this end, radio-fingerprints of received signal strength indicators (RSSIs) are first collected over the surveillance area. The obtained database is then used with machine learning algorithms to compute a model that estimates the position of the target using only RSSI information. This model leads to a first position estimate of the target under investigation. The kernel-based ridge regression and the vector-output regularized least squares are used in the learning process.The Kalman filter is used afterwards to combine predictions of the target's positions based on acceleration information with the first estimates, leading to more accurate ones. The performance of the method is studied for different scenarios and a thorough comparison to well-known algorithms is also provided.

Modified Iterated Extended Kalman Filter for Mobile Cooperative Tracking System

“…d est (1,2,3) is the distance estimation of the mobile node to the anchor node that was obtained from PLE value eq. (17)(18)(19)(20)(21)(22)(23)(24)(25)(26)(27).…”

“…Another application of WSN is target tracking system that can be viewed as a sequential localization. The target tracking system is estimating directly the object which is requiring a real-time location estimation algorithm [3].…”

“…The methods are RSSI (Received Signal Strength Indicators), AOA (Angle of Arrival), TDOA (Time Difference of Arrival) and TOA (Time of Arrival) [1]- [2], [4]. Although TOA and AOA have more accurate estimation compared to the other methods, this method require high-cost hardware which is making difficult implementation in some application [3]. RSSI-based positioning methods are used as far as they require no complex measurement hardware which is measured the power received from the transmitted radio signal antenna [5].…”

Energy Efficient Target Tracking Scheme for Wireless Sensor Networks

“…In paper [12], author proposed RSSI scheme for target movement detection using the signal strength of sensor nodes. In WSN, sensor nodes continuously communicate with each other by exchanging the messages.…”

RSS-based joint detection and tracking in mixed LOS and NLOS environments

“…In recent years, target tracking in wireless sensor networks (WSN) has received great attention in many fields such as mobile station localization, search-rescue, robotic navigation, and autonomous surveillance [1][2][3][4][5]. Target tracking can be viewed as a sequential localization problem via noisy measurements.…”