Robust DoA Estimation Using Denoising Autoencoder and Deep Neural Networks

Chen, Fan; Shi, Shuo; Gu, Xuemai; Shim, Byonghyo

doi:10.1109/access.2022.3164897

Cited by 15 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [2] a CNN is trained to perform Direction of Arrival (DoA) estimation of up to three unknown sources on a grid. Similarly, the authors of [3] also tackle the problem of DoA estimation by combining a denoising autoencoder with a DNN. Both show performance improvement in the low-SNR domain compared to MU-SIC.…”

Section: State-of-the-artmentioning

confidence: 99%

“…We use the signal model introduced in this section to obtain training-and label data for our approach. Please note that our task is similar to the DoA estimation tackled by the previous works [1][2][3][4][5][6].…”

Section: Signal Modelmentioning

confidence: 99%

“…Until recently, available solutions for the task could be loosely divided into three groups: subspace algorithms, iterative maximum likelihood (ML), and Sparse Signal Recovery (SSR). Recent publications [1][2][3][4][5][6] added a fourth category: Deep Neural Networks (DNNs)-based algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Grid-free Harmonic Retrieval and Model Order Selection using Deep Convolutional Neural Networks

Schieler¹,

Semper²,

Faramarzahangari³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper introduces a Deep Learning approach for signal parameter estimation in the context of wireless channel modeling. Our work is capable of multidimensional parameter estimation from a signal containing an unknown number of paths. The signal parameters are estimated relative to a predefined grid, providing quasi gridfree, hence, more accurate estimates than previous grid-limited approaches. It requires no prior knowledge of the number of paths, giving it an advantage in terms of complexity compared to existing solutions. Along with the description, we provide an initial performance analysis and a comparison with State-of-the-Art techniques and discuss future research directions.

show abstract

Section: State-of-the-artmentioning

confidence: 99%

Section: Signal Modelmentioning

confidence: 99%

See 1 more Smart Citation

Grid-free Harmonic Retrieval and Model Order Selection using Deep Convolutional Neural Networks

Schieler¹,

Semper²,

Faramarzahangari³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In [7] a CNN is trained to perform DoA estimation of up to three unknown sources by determining their location on a grid, i.e., solving a classification problem. Similarly, the authors of [8] address the problem of DoA estimation by combining a denoising autoencoder with another DNN for the estimation. As in [6], both approaches show performance improvements in the low-SNR domain compared to MUSIC.…”

Section: Introductionmentioning

confidence: 99%

Grid-free Harmonic Retrieval and Model Order Selection using Convolutional Neural Networks

Schieler,

Semper,

Faramarzahangari

et al. 2024

Preprint

View full text Add to dashboard Cite

Harmonic retrieval techniques are the foundation of radio channel sounding, estimation and modeling. This paper introduces a Deep Learning approach for joint delay-and Doppler estimation from frequency and time samples of a radio channel transfer function. Our work estimates the two-dimensional parameters from a signal containing an unknown number of paths. Compared to existing deep learning-based methods, the signal parameters are not estimated via classification but in a quasi-grid-free manner. This alleviates the bias, spectral leakage, and ghost targets that grid-based approaches produce. The proposed architecture also reliably estimates the number of paths in the measurement. Hence, it jointly solves the model order selection and parameter estimation task. Additionally, we propose a multi-channel windowing of the data to increase the estimator’s robustness. We also compare the performance to other harmonic retrieval methods and integrate it into an existing maximum likelihood estimator for efficient initialization of a gradient-based iteration.

show abstract

“…Furthermore, a DOA estimation algorithm based on a convolutional recurrent neural network (CRNN) [ 25 ] is proposed and can produce high-precision DOA estimation results under different SNR. The denoising autoencoder (DAE) neural network structure [ 26 ] is added to the literature, and the DOA detection accuracy is higher than that of the basic autoencoder by recovering the feature information. Recently, the literature has combined the sum-difference array with deep neural networks [ 21 ], demonstrating that neural networks can better adapt to array defects.…”

Section: Introductionmentioning

confidence: 99%

Direction-of-Arrival Estimation for a Random Sparse Linear Array Based on a Graph Neural Network

Yang,

Zhang,

Peng

et al. 2023

Sensors

View full text Add to dashboard Cite

This article proposes a direction-of-arrival (DOA) estimation algorithm for a random sparse linear array based on a novel graph neural network (GNN). Unlike convolutional layers and fully connected layers, which do not interact well with information between different antennas, the GNN model can adapt to the goniometry problem of non-uniform random sparse linear arrays without any prior information by applying neighbor nodes’ aggregation and update operations. This helps the model in learning signal features under complex environmental conditions. We train the model in an end-to-end way to reduce the complexity of the network. Experiments are conducted on the uniform and sparse linear arrays for various signal-to-noise ratio (SNR) and numbers of snapshots for comparison. We prove that the GNN model has superior angle estimation performance on arrays with large sparsity that cannot be used by traditional algorithms and surpasses existing deep learning models based on convolutional or fully connected structures. The proposed algorithm shows excellent DOA estimation performance under the complex conditions of limited snapshots, low signal-to-noise ratio, and large array sparsity as well. In addition, the algorithm has a low time calculation cost and is suitable for scenarios that require low latency.

show abstract

Robust DoA Estimation Using Denoising Autoencoder and Deep Neural Networks

Cited by 15 publications

References 36 publications

Grid-free Harmonic Retrieval and Model Order Selection using Deep Convolutional Neural Networks

Grid-free Harmonic Retrieval and Model Order Selection using Deep Convolutional Neural Networks

Grid-free Harmonic Retrieval and Model Order Selection using Convolutional Neural Networks

Direction-of-Arrival Estimation for a Random Sparse Linear Array Based on a Graph Neural Network

Contact Info

Product

Resources

About