DNN-based Indoor Fingerprinting Localization with WiFi FTM

Abstract

In this work, we present a deep neural network (DNN)-based indoor fingerprinting localization method with WiFi fine time measurements (FTM). The proposed method leverages the WiFi FTM and its variance as environment features to provide accurate location estimation. An l-th layer DNN structure used in this paper is implemented by back propagation using an Adam optimizer. The weights and the bias of the l-th layer that minimize the loss function is computed in order to minimize the positioning mean squared error (MSE). Experimental results using real-world data obtained in a typical office setting proves the efficiency of the proposed solution. The performance of the system is remarkably improved, using the 600×600 hidden layer size of the DNN, we achieved an average positioning accuracy of 0.7 m and 0.9 m for the 68-th percentiles (1-σ) and 95-th percentiles (2-σ) respectively.

Fingerprinting-Based Indoor Localization With Hybrid Quantum-Deep Neural Network

“…One such technique is fingerprinting, which relies on offline data for accurate online location estimation [1]. Various fingerprinting-based techniques have been proposed, utilizing different signals such as Wi-Fi fine time measurements (FTM) [2], time of arrival (TOA) [3], received signal strength (RSS) [4], ultra-wideband (UWB) [5], and channel state information (CSI) [6], [7]. However, the accuracy of these techniques can fluctuate due to sensor errors, noise, multipath effects, signal interference, and channel inconsistencies [8].…”

“…However, the accuracy of these techniques can fluctuate due to sensor errors, noise, multipath effects, signal interference, and channel inconsistencies [8]. Researchers have explored the use of machine learning (ML) algorithms to improve the accuracy of fingerprinting-based techniques [2], [6], [9]- [15]. Deep neural networks (DNNs) have shown promising results in enhancing localization accuracy among ML algorithms.…”

Improving Fingerprint-Based Positioning by Using IEEE 802.11mc FTM/RTT Observables

“…Recently, the use of IEEE 802.11mc round trip time (RTT), which is also known as a fine time measurement (FTM), as an observable in fingerprinting solutions has been suggested [ 9 , 10 ] and is expected to provide more stable measurements compared to using the RSS [ 11 ]. However, so far, the RTT has been typically used as an observable for multilateration purposes [ 7 ].…”

“…According to the authors in [ 9 ], this similarity approach allows the location system to overcome the typical indoor environment localization challenges, such as multipath interference and NLOS-related transmission problems. In [ 10 ], the authors propose an indoor fingerprinting system based on deep neural networks. This system leverages both the RTT and RSS with a model that addresses the multipath, NLOS, signal attenuation, and interference challenges of the indoor environments.…”

“…This system leverages both the RTT and RSS with a model that addresses the multipath, NLOS, signal attenuation, and interference challenges of the indoor environments. Despite coupling the RTT and the RSS measurements provides good results, the authors in [ 10 ] state that the benefits from RSS observations are scarce. However, there are no data on how the frequency band or the use of simpler (and cheaper) machine learning algorithms could impact an RTT-based fingerprinting system.…”