Deep Learning-Aided Off-Grid Channel Estimation for Millimeter Wave Cellular Systems

Wan, Liangtian; Liu, Kaihui; Zhang, Wei

doi:10.1109/twc.2021.3120926

Cited by 29 publications

(12 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, the study of pseudolite/UWB integrated method will be focused on the MIMO pseudolite system [36,37], pseudolite/UWB integrated navigation, and deep learning-aided cycle slip detection and repair [38,39]. It is foreseen that the precise positioning results will be benefit to the high accuracy, low-cost indoor localization.…”

Section: Discussionmentioning

confidence: 99%

An Approach to Improve the Indoor Positioning Performance of Pseudolite/UWB System with Ambiguity Resolution

et al. 2022

Self Cite

View full text Add to dashboard Cite

Indoor localization is still an open challenge, and some pseudolites have been developed to achieve seamless positioning service based on some commercialized GNSS chips. However, most of these indoor localization technologies often fail in a reasonable solution to the key problems such as low cost and highly accurate and efficient for users. In this paper, we propose an indoor location method based on integrated pseudolite and UWB; the virtual pseudo-range measurements of UWB are used to replace the pseudo-range measurements of pseudolite to solve the indoor multipath problem, which is tightly coupled with the corrected carrier phase measurements of pseudolite. Then, the channel-difference observation equation and UWB-aided ambiguity resolution are proposed for precise positioning. In order to test the proposed method, several experiments are conducted. The results show that the virtual pseudo-range errors from UWB are smaller than that of GNSS, and such a small bias will be better for the fast fixing of ambiguity. In addition, the positioning accuracy of the proposed indoor location method is improved from cm-level for the float solution to mm-level for the fixed solution; these performances would be more convincing to users than that given in the most pseudolite and UWB.

show abstract

Section: Discussionmentioning

confidence: 99%

An Approach to Improve the Indoor Positioning Performance of Pseudolite/UWB System with Ambiguity Resolution

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has been widely used in various fields due to its enhanced ability to solve complicated nonlinear problems [14]- [16]. It also provides an advanced solution for conventional DOA estimation.…”

Section: Methodsmentioning

confidence: 99%

“…P ⊥ a(θ) denotes the orthogonal projection matrix of the array steering matrix, and W Root−W SF is the asymptotic-optimum weight matrix. In (16), the expression I is an M × M identity matrix, and σ2 indicates the noise variance. In (17), T is a full rank matrix, and Vn is eigenvectors in a diagonal noise matrix.…”

Section: [•]mentioning

confidence: 99%

Robust DOA Estimation in Satellite Systems in Presence of Coherent Signals Subject to Low SNR

Huang

Ren

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Signal source number detection is an essential issue for the direction of arrival (DOA) estimation in satellite communication systems. The performances of conventional and deep-learning-based signal source number detection methods will deteriorate when the signal-to-noise ratio is low or coherent signals exist. This paper proposes a DOA detection network (DTN) combined with the root weighted subspace fitting (root-WSF) method to tackle this challenge. The DTN uses the constructed deep neural networks (DNN) to denoise the received signals and captures the nonlinear mapping relationship between the received signals and the number of signal sources. The received signals in the complex-valued domain are directly treated as DTN's input, and the label of DTN is the one-hot encoding of the source number. It solves the issue that the classifier cannot well-handle the coherent signals and extends the values of discrete features to Euclidean space. Accordingly, the trained DTN can detect the signal source numbers with an average detection accuracy of 96.6%, and the root-WSF algorithm is applied as the rear stage of DOA estimation. Compared with the traditional DOA methods, the proposed DTN incorporated with the root-WSF algorithm features superior robustness, high DOA estimation accuracy, and enhanced resolution. INDEX TERMS Deep neural network (DNN), direction of arrival (DOA), DOA detection network (DTN), root weighted subspace fitting (root-WSF), satellite communication system.

show abstract

“…In Ref. [26], in view of the large number of antennas, the author proposes a deep learning-assisted channel estimation algorithm, which effectively solves the off-grid channel estimation problem.…”

Section: Introductionmentioning

confidence: 99%

Robust direction‐of‐arrival estimation approach using beamspace‐based deep neural networks with array imperfections and element failure

Wen

Huang

et al. 2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Direction-of-arrival (DOA) estimation is a fundamental functionality of sensor array systems. Previous methods only consider element failure or array imperfections. In fact, the co-existence of element failure and array imperfections is more in line with the realistic operation conditions of an array system. However, the performance of previous methods degrades significantly in the presence of both array imperfections and element failure. To deal with this problem, a robust DOA estimation method is proposed based on a deep neural network (DNN). The proposed DNN consists of a denoising autoencoder (DAE) and a parallel network. The DAE can restore damaged array signals to "non-corrupted" signals, and the parallel network is able to process signals with different levels of loss to improve DOA estimation accuracy. At the training stage, array imperfections are modelled as a spherical distribution, and the training samples are extracted under this distribution to improve the generalisation capability of the proposed network to various array imperfections. In addition, the authors propose to estimate the spatial spectrum in a virtual array beamspace, which can reduce the computational complexity as well as signal-to-noise ratio resolution threshold, and further enhance the robustness to array imperfections. Numerical results show that the proposed DOA estimation approach works well in the presence of both array imperfections and element failure.

show abstract

Deep Learning-Aided Off-Grid Channel Estimation for Millimeter Wave Cellular Systems

Cited by 29 publications

References 60 publications

An Approach to Improve the Indoor Positioning Performance of Pseudolite/UWB System with Ambiguity Resolution

An Approach to Improve the Indoor Positioning Performance of Pseudolite/UWB System with Ambiguity Resolution

Robust DOA Estimation in Satellite Systems in Presence of Coherent Signals Subject to Low SNR

Robust direction‐of‐arrival estimation approach using beamspace‐based deep neural networks with array imperfections and element failure

Contact Info

Product

Resources

About