Fingerprint-Based Localization for Massive MIMO-OFDM System With Deep Convolutional Neural Networks

Sun, Xiaoyu; Wu, Chi; Gao, Xiqi; Li, Geoffrey Ye

doi:10.1109/tvt.2019.2939209

Cited by 83 publications

(62 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NN-based positioning from CSI measurements requires carefully-designed features, which are robust to small-scale fading as well as system and hardware impairments. The use of beamspace representations to extract the incident angles has been used in [21], [27], [28], [47]. The conversion of subcarrier CSI into the delay domain to extract relative time-of-flight information has been used in [21], [47]- [49].…”

Section: B Contributionsmentioning

confidence: 99%

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

Gönültaş

Lei

Langerman

et al. 2022

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

Channel state information (CSI)-based fingerprinting via neural networks (NNs) is a promising approach to enable accurate indoor and outdoor positioning of user equipments (UEs), even under challenging propagation conditions. In this paper, we propose a positioning pipeline for wireless LAN MIMO-OFDM systems which uses uplink CSI measurements obtained from one or more unsynchronized access points (APs). For each AP receiver, novel features are first extracted from the CSI that are robust to system impairments arising in real-world transceivers. These features are the inputs to a NN that extracts a probability map indicating the likelihood of a UE being at a given grid point. The NN output is then fused across multiple APs to provide a final position estimate. We provide experimental results with realworld indoor measurements under line-of-sight (LoS) and non-LoS propagation conditions for an 80 MHz bandwidth IEEE 802.11ac system using a two-antenna transmit UE and two AP receivers each with four antennas. Our approach is shown to achieve centimeter-level median distance error, an order of magnitude improvement over a conventional baseline.

show abstract

Section: B Contributionsmentioning

confidence: 99%

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

Gönültaş

Lei

Langerman

et al. 2022

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

show abstract

“…Fig. 8 compares the proposed method with the latest triangulation-based DiSouL [12] and DNN-fingerprint [13] methods. As depicted in Fig.…”

Section: Performance In Tracking Location Errormentioning

confidence: 99%

“…Different from the existing methods, this paper develops a high accuracy tracking system by exploring the statistical property, i.e., autocorrelation function (ACFS) of the received signal in massive MIMO systems [12][13][14]. The ACFS is proved to be a stable sinc-like focusing beam around the receiver in which the stability comes from the fact that the received signal in massive MIMO system contains a large number of LOS and NLOS signal components.…”

Section: Introductionmentioning

confidence: 99%

High Accuracy Tracking of Targets Using Massive MIMO

Zeng¹,

Zhang²,

Wang³

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

While high accuracy tracking of targets has been extensively explored because of its wide applications, many exiting methods degenerate in the presence of multipath distortions. This paper proposes an accurate and novel multipath-resilient system to track the targets by leveraging the large number of antennas in massive MIMO systems. We first prove that statistical autocorrelation of the received energy physically shows a sinc-like distribution around the receiver in far-field scenario. Based on such an observation, a novel method is developed to estimate the moving speed of the target with respect to a single base station. The absolute moving speed and direction are further estimated by using the geometrical relationships among multiple base stations and thus we can track the target by dead-reckoning using the consecutive moving speed and moving direction estimations. Numerical simulations show that the proposed system can achieve decimeter-lever accuracy for tracking in various environments, which outperforms the existing methods.

show abstract

“…The experiments in [31] showed the feasibility of using deep learning methods for localization in actual outdoor environments. AI-based fingerprinting methods have alleviated modeling issues and can provide better performance than model-based localization techniques that use geometric relationships by fitting real-life measurements [32], [33]. However, extremely large amounts of training data are required to meet the high requirements of localization accuracy.…”

Section: Introductionmentioning

confidence: 99%

Model-Based Learning Network for 3-D Localization in mmWave Communications

Yang

Jin

Wen

et al. 2021

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

Millimeter-wave (mmWave) cloud radio access networks (CRANs) provide new opportunities for accurate cooperative localization, in which large bandwidths and antenna arrays and increased densities of base stations enhance the delay and angular resolution. This study considers the joint location and velocity estimation of user equipment (UE) and scatterers in a three-dimensional mmWave CRAN architecture. Several existing works have achieved satisfactory results by using neural networks (NNs) for localization. However, the black box NN localization method has limited robustness and accuracy and relies on a prohibitive amount of training data to increase localization accuracy. Thus, we propose a model-based learning network for localization to address these problems. In comparison with the black box NN, we combine NNs with geometric models. Specifically, we first develop an unbiased weighted least squares (WLS) estimator by utilizing hybrid delay and angular measurements, which determine the location and velocity of the UE in only one estimator, and can obtain the location and velocity of scatterers further. The proposed estimator can achieve the Cramér-Rao lower bound under small measurement noise and outperforms other state-of-the-art methods. Second, we establish a NN-assisted localization method called NN-WLS by replacing the linear approximations in the proposed WLS localization model with NNs to learn the higher-order error components, thereby enhancing the performance of the estimator, especially in a large noise environment. The solution possesses the powerful learning ability of the NN and the robustness of the proposed geometric model. Moreover, the ensemble learning is applied to improve the localization accuracy further. Comprehensive simulations show that the proposed NN-WLS is superior to the benchmark methods in terms of localization accuracy, robustness, and required time resources.

show abstract

Fingerprint-Based Localization for Massive MIMO-OFDM System With Deep Convolutional Neural Networks

Cited by 83 publications

References 29 publications

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

High Accuracy Tracking of Targets Using Massive MIMO

Model-Based Learning Network for 3-D Localization in mmWave Communications

Contact Info

Product

Resources

About