A Novel Hybrid NN-ABPE-Based Calibration Method for Improving Accuracy of Lateration Positioning System

Abstract

Positioning systems based on the lateration method utilize distance measurements and the knowledge of the location of the beacons to estimate the position of the target object. Although most of the global positioning techniques rely on beacons whose locations are known a priori, miscellaneous factors and disturbances such as obstacles, reflections, signal propagation speed, the orientation of antennas, measurement offsets of the beacons hardware, electromagnetic noise, or delays can affect the measurement accuracy. In this paper, we propose a novel hybrid calibration method based on Neural Networks (NN) and Apparent Beacon Position Estimation (ABPE) to improve the accuracy of a lateration positioning system. The main idea of the proposed method is to use a two-step position correction pipeline that first performs the ABPE step to estimate the perceived positions of the beacons that are used in the standard position estimation algorithm and then corrects these initial estimates by filtering them with a multi-layer feed-forward neural network in the second step. In order to find an optimal neural network, 16 NN architectures with 10 learning algorithms and 12 different activation functions for hidden layers were implemented and tested in the MATLAB environment. The best training outcomes for NNs were then employed in two real-world indoor scenarios: without and with obstacles. With the aim to validate the proposed methodology in a scenario where a fast set-up of the system is desired, we tested eight different uniform sampling patterns to establish the influence of the number of the training samples on the accuracy of the system. The experimental results show that the proposed hybrid NN-ABPE method can achieve a high level of accuracy even in scenarios when a small number of calibration reference points are measured.

Indoor Positioning Based on Bluetooth RSSI Mean Estimator for the Evacuation Supervision System Application

“…As a result, this phenomenon will significantly increase the variance of the distance estimate (14) determined on the basis of the current RSSI value (𝑅𝑆𝑆𝐼 𝑚,𝑛 (𝑘)). Whereas, the use of the estimator (15) of the mean RSSI value will result in a √𝑀 fold reduction of the RSSI variance used to determine the distance (16), which in turn will result in an improvement in the quality of the estimates 𝑑 ̂𝑚,𝑛 (𝑘).…”

“…The values of a = -17.822, b = -61.277 were obtained, which minimized the mean square error of the fit. These values allow the estimation of the distance 𝑑 ̂𝑚,𝑛 (𝑘) between Locm and Pn on the basis of the RSSI using ( 15) and (16).…”

“…The study of the estimation efficiency of the proposed algorithms was carried out based on RSSI measurements obtained in the evacuation monitoring experimental system presented in Figure 7. For this purpose, the distance estimator (15), (16) and the 2D coordinate estimator ( 9) with ( 7), (8) were used. The average height of wearing the wristband was assumed as 𝑧 𝑜 ≈1.2 m. An example of the coordinate estimation process is shown in Figure 11.…”

“…In such cases, the multilateration technique is applied for this reason. It is based on the measurement of the RSSI signal value, the absolute time of the signal arrival from the transmitter to the remote ToA receiver, or the estimation of the differences in the signal arrival times at remotely located transmitting-receiving devices [16], [37].…”