CRB Weighted Source Localization Method Based on Deep Neural Networks in Multi-UAV Network

Cong, Jingyu; Wang, Xianpeng; Yan, Chenggang; Yang, Laurence T.; Dong, Mianxiong; Ota, Kaoru

doi:10.1109/jiot.2022.3150794

Cited by 41 publications

(22 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the parameter of AN is chosen to be 0.001. Essentially, the effectiveness of noise reconstruction can be assessed by the level of sidelobe in the spatial spectrum, the number and amplitude of pseudo-peaks, and the RMSE of DOA estimation, defined as follows [51]:…”

Section: Simulation Resultsmentioning

confidence: 99%

A Generalized Noise Reconstruction Approach for Robust DOA Estimation

Cong¹,

Wang²,

Liu³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

<p>The performance of direction-of-arrival (DOA) estimation is severely affected by noise and clutter, and conventional methods fail to simultaneously cope with different situations because of the difficulties to predict noise and clutter. In order to solve this problem, a generalized robust framework for noise reconstruction in the received data domain is proposed to enhance DOA estimation performance. First, based on the Doppler information of the source, an approximate noise difference is obtained and, based on its cumulative sum, a coarse estimation of the received domain noise is then calculated. In particular, the optimal initial value is obtained using the generalized pattern search algorithm, where the objective function, constructed with the distance between the normalized Capon spatial spectrum peaks and the desired spatial spectrum peaks, is minimized. Then, exact reconstruction of the received data-domain noise is realized by a new cumulative sum formed using the solution from the previous step. Finally, using the denoised data, the spatial spectrum is obtained via the Capon algorithm. The effectiveness of the proposed framework is verified by simulations, both in terms of accuracy of DOA estimation and effectiveness in suppressing sidelobe and pseudo-peaks, for different cases, including white Gaussian noise, non-uniform noise, colored noise, impulsive noise, and K-distribution sea clutter. The relevant codes are available online: https://github.com/CJYLostviews/Robust-Noise-Reconstruction/</p>

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

A Generalized Noise Reconstruction Approach for Robust DOA Estimation

Cong¹,

Wang²,

Liu³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…DOA estimation is the preliminary purpose of beamforming and localization. DOA-based cooperative positioning applications been the subject of extensive interested in the past few years [ 10 , 11 , 12 , 13 , 14 , 15 ]. The cooperative positioning principle is depicted in Figure 2 .…”

Section: Signal Model Of Doa Estimationmentioning

confidence: 99%

DOA Estimation in B5G/6G: Trends and Challenges

Ruan

Wang

Wen

et al. 2022

Sensors

View full text Add to dashboard Cite

Direction-of-arrival (DOA) estimation is the preliminary stage of communication, localization, and sensing. Hence, it is a canonical task for next-generation wireless communications, namely beyond 5G (B5G) or 6G communication networks. Both massive multiple-input multiple-output (MIMO) and millimeter wave (mmW) bands are emerging technologies that can be implemented to increase the spectral efficiency of an area, and a number of expectations have been placed on them for future-generation wireless communications. Meanwhile, they also create new challenges for DOA estimation, for instance, through extremely large-scale array data, the coexistence of far-field and near-field sources, mutual coupling effects, and complicated spatial-temporal signal sampling. This article discusses various open issues related to DOA estimation for B5G/6G communication networks. Moreover, some insights on current advances, including arrays, models, sampling, and algorithms, are provided. Finally, directions for future work on the development of DOA estimation are addressed.

show abstract

“…2), it can be seen that the accuracy of DOA estimation for the same SNR differs significantly. In addition, this problem also exists in neural network-based denoising algorithms [14], [35], [57]. Therefore, considering the incompatibility of datadriven methods to data with dynamic range, such methods are not the best solution for dealing with noise.…”

Section: A Previous Work: Doa Estimation With Different Noise Typesmentioning

confidence: 99%

A Generalized Noise Reconstruction Framework for DOA Estimation in Received Data Domain

Cong¹,

Wang²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>The performance of direction-of-arrival (DOA) estimation algorithms is affected by noise and clutter, but conventional noise reduction methods are difficult to adapt a variety of DOA estimation algorithms in different noise/clutter environments. To address this issue, a generalized robust framework for noise reconstruction in the received data domain is proposed to enhance DOA estimation performance. The problem of noise reconstruction is formulated as an optimization problem, whose objective function kernel may consist of many different DOA estimation algorithms. First, based on the cumulative sum of an approximate noise first order finite difference, a coarse estimation of the received domain noise is then calculated. In particular, the optimal initial value is obtained using the generalized pattern search algorithm, where the objective function, constructed with the distance between the normalized spatial spectrum peaks and the desired spatial spectrum peaks or the total noise power estimated by least squares (LS), is minimized. Then, exact reconstruction of the received data-domain noise is realized by a new cumulative sum formed using the solution from the previous step. Finally, using the denoised data, the DOA estimation is obtained via different algorithms. The effectiveness of the proposed framework is verified by simulations, with the objective function kernel of the propagator method (PM), Capon, sparse Bayesian learning (SBL), and parallel factorization (PARAFAC), both in terms of accuracy of DOA estimation and effectiveness in suppressing sidelobe and pseudo-peaks, for different cases, including white Gaussian noise, non-uniform noise, colored noise, impulsive noise, and K-distribution sea clutter. In addition, the effectiveness of the proposed framework is verified on the FMCW MIMO radar real-world data. The relevant codes are available online: https://github.com/CJYLostviews/Robust-Noise-Reconstruction/</p>

show abstract

CRB Weighted Source Localization Method Based on Deep Neural Networks in Multi-UAV Network

Cited by 41 publications

References 32 publications

A Generalized Noise Reconstruction Approach for Robust DOA Estimation

A Generalized Noise Reconstruction Approach for Robust DOA Estimation

DOA Estimation in B5G/6G: Trends and Challenges

A Generalized Noise Reconstruction Framework for DOA Estimation in Received Data Domain

Contact Info

Product

Resources

About