SDR-Fi: Deep-Learning-Based Indoor Positioning via Software-Defined Radio

Schmidt, Erick; Inupakutika, Devasena; Mundlamuri, Rahul; Akopian, David

doi:10.1109/access.2019.2945929

Cited by 30 publications

(29 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Applications of CNN and the use of Wi-Fi and magnetic signals for indoor precise positioning were investigated in [31]. Software-defined radio devices and deep learning approaches were leveraged to improve indoor positioning accuracy [32]. Mondal et al evaluated the positioning accuracy of a radio fingerprinting algorithm in commercially deployed LTE networks operating on 800 MHz, 1800 MHz, and 2600 MHz frequency bands [33].…”

Section: Related Workmentioning

confidence: 99%

A Novel Outdoor Positioning Technique Using LTE Network Fingerprints

Lei

Zhang

2020

Sensors

View full text Add to dashboard Cite

In recent years, wireless-based fingerprint positioning has attracted increasing research attention owing to its position-related features and applications in the Internet of Things (IoT). In this paper, by leveraging long-term evolution (LTE) signals, a novel deep-learning-based fingerprint positioning approach is proposed to solve the problem of outdoor positioning. Considering the outstanding performance of deep learning in image classification, LTE signal measurements are converted into location grayscale images to form a fingerprint database. In order to deal with the instability of LTE signals, prevent the gradient dispersion problem, and increase the robustness of the proposed deep neural network (DNN), the following methods are adopted: First, cross-entropy is used as the loss function of the DNN. Second, the learning rate of the proposed DNN is dynamically adjusted. Third, this paper adopted several data enhancement techniques. To find the best positioning fingerprint and method, three types of fingerprint and five positioning models are compared. Finally, by using a deep residual network (Resnet) and transfer learning, a hierarchical structure training method is proposed. The proposed Resnet is used to train with the united fingerprint image database to obtain a positioning model called a coarse localizer. By using the prior knowledge of the pretrained Resnet, feed-forward neural network (FFNN)-based transfer learning is used to train with the united fingerprint database to obtain a better positioning model, called a fine localizer. The experimental results convincingly show that the proposed DNN can automatically learn the location features of LTE signals and achieve satisfactory positioning accuracy in outdoor environments.technologies require additional devices, making these systems impractical. Additionally, in signal NLOS propagation, the performance of the positioning systems will be greatly reduced [5].In contrast, wireless fingerprint positioning technology has received much attention owing to its simplicity and practicality with existing infrastructure and hardware. Many complex LTE signal cues are hidden in the surrounding environment, and the goal of wireless fingerprint-based localization is to discover these cues and use them effectively to determine UE positions [6]. Compared to satellite navigation positioning systems and other wireless positioning technologies, fingerprint-based positioning techniques have many merits. First, low-energy consumption sensors in UE require much less energy. Second, most of the fingerprint-based positioning technologies require no additional devices or infrastructure. Finally, fingerprint-based positioning can be achieved by using ubiquitous smartphones and signals from LTE base stations (BSs) [6,7]. Fingerprint positioning technology works in two phases: an offline training phase and an online matching phase [8]. During the training phase, signal measurements can be used, which are usually received signal strength indicator (RSSI), reference signal receivin...

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Outdoor Positioning Technique Using LTE Network Fingerprints

Lei

Zhang

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Due to the error of the measured signal strength, we assign a lower weight to the RSSI that has propagated a long distance. Then, w i can be calculated by Equations (13) and 14:…”

Section: Virtual Ap Estimationmentioning

confidence: 99%

“…Due to the popularity of Wi-Fi infrastructure and Wi-Fi-embedded mobile equipment, Wi-Fi-based positioning techniques have become increasingly popular. For example, the Channel State Information (CSI) [13] and Received Signal Strength Indication (RSSI) can be extracted from Wi-Fi Access Points (APs), which showed good potential in indoor localization. However, CSI data cannot be collected from current smartphones since it is the signal at the physical level of Wi-Fi networks.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Indoor Wi-Fi Positioning Method Using Virtual Location of AP

Luo

et al. 2020

IJGI

View full text Add to dashboard Cite

Wi-Fi fingerprinting has been widely used for indoor localization because of its good cost-effectiveness. However, it suffers from relatively low localization accuracy and robustness owing to the signal fluctuations. Virtual Access Points (VAP) can effectively reduce the impact of signal fluctuation problem in Wi-Fi fingerprinting. Current techniques normally use the Log-Normal Shadowing Model to estimate the virtual location of the access point. This would lead to inaccurate location estimation due to the signal attenuation factor in the model, which is difficult to be determined. To overcome this challenge, in this study, we propose a novel approach to calculating the virtual location of the access points by using the Apollonius Circle theory, specifically the distance ratio, which can eliminate the attenuation parameter term in the original model. This is based on the assumption that neighboring locations share the same attenuation parameter corresponding to the signal attenuation caused by obstacles. We evaluated the proposed method in a laboratory building with three different kinds of scenes and 1194 test points in total. The experimental results show that the proposed approach can improve the accuracy and robustness of the Wi-Fi fingerprinting techniques and achieve state-of-art performance.

show abstract

“…This sequential mapping of each layer would then be carried out for every added hidden layer in the stacked denoising autoencoder network as each subsequent reconstruction has an accompanied reconstruction loss function similar to those defined in (12) and (15). Observation of the loss function defined in (12) suggests a simplistic alternative input to the conditional probability P(x|l) defined in (7).…”

Section: Deep Learning and Denoising Autoencodermentioning

confidence: 99%

“…To date, minimal research has been conducted in SDR platforms for indoor localization. In [11], RSS was captured for both GSM and WiFi using USRP E310, and a WiFi Pineapple as a least squares (LS) algorithm was employed for distance estimation realizing localization errors on the order of 5 m. Similarly, a USRP device and LS distance estimation approach was employed in [12] for monitoring the uplink RSS of GSM waveforms using openBTS software for realization of GSM base stations. Another physical estimation of location was employed in [13] via time difference of arrival (TDoA) and four spatially distributed receivers.…”

Section: Introductionmentioning

confidence: 99%

SDR Based Indoor Beacon Localization Using 3D Probabilistic Multipath Exploitation and Deep Learning

2019

View full text Add to dashboard Cite

Wireless indoor positioning systems (IPS) are ever-growing as traditional global positioning systems (GPS) are ineffective due to non-line-of-sight (NLoS) signal propagation. In this paper, we present a novel approach to learning three-dimensional (3D) multipath channel characteristics in a probabilistic manner for providing high performance indoor localization of wireless beacons. The proposed system employs a single triad dipole vector sensor (TDVS) for polarization diversity, a deep learning model deemed the denoising autoencoder to extract unique fingerprints from 3D multipath channel information, and a probabilistic k-nearest-neighbor (PkNN) to exploit the 3D multipath characteristics. The proposed system is the first to exploit 3D multipath channel characteristics for indoor wireless beacon localization via vector sensing methodologies, a software defined radio (SDR) platform, and multipath channel estimation.

show abstract

SDR-Fi: Deep-Learning-Based Indoor Positioning via Software-Defined Radio

Cited by 30 publications

References 42 publications

A Novel Outdoor Positioning Technique Using LTE Network Fingerprints

A Novel Outdoor Positioning Technique Using LTE Network Fingerprints

An Efficient Indoor Wi-Fi Positioning Method Using Virtual Location of AP

SDR Based Indoor Beacon Localization Using 3D Probabilistic Multipath Exploitation and Deep Learning

Contact Info

Product

Resources

About