TDOA-based Localization via Stochastic Gradient Descent Variants

TL;DR

This paper compares classical and modern stochastic gradient descent variants for TDOA-based source localization, introducing RMSProp+AF, which enhances convergence and stability in signal processing applications.

Contribution

It introduces RMSProp+AF, a novel optimization method with adaptive decay, and demonstrates its superior performance in TDOA localization compared to existing techniques.

Findings

RMSProp+AF outperforms classical SGD and other variants in convergence speed.

The proposed method achieves higher stability in localization tasks.

Simulations confirm improved accuracy and robustness of RMSProp+AF.

Abstract

Source localization is of pivotal importance in several areas such as wireless sensor networks and Internet of Things (IoT), where the location information can be used for a variety of purposes, e.g. surveillance, monitoring, tracking, etc. Time Difference of Arrival (TDOA) is one of the well-known localization approaches where the source broadcasts a signal and a number of receivers record the arriving time of the transmitted signal. By means of computing the time difference from various receivers, the source location can be estimated. On the other hand, in the recent few years novel optimization algorithms have appeared in the literature for $(i)$ processing big data and for $(ii)$ training deep neural networks. Most of these techniques are enhanced variants of the classical stochastic gradient descent (SGD) but with additional features that promote faster convergence. In this paper, we compare the performance of the classical SGD with the novel techniques mentioned above. In addition, we propose an optimization procedure called RMSProp+AF, which is based on RMSProp algorithm but with the advantage of incorporating adaptation of the decaying factor. We show through simulations that all of these techniques---which are commonly used in the machine learning domain---can also be successfully applied to signal processing problems and are capable of attaining improved convergence and stability. Finally, it is also shown through simulations that the proposed method can outperform other competing approaches as both its convergence and stability are superior.