Ultra-Fast Accurate AoA Estimation via Automotive Massive-MIMO Radar

Li, Bin; Wang, Shusen; Jun, Zhang; Cao, Xianbin; Zhao, Chenglin

doi:10.1109/tvt.2021.3135910

Cited by 20 publications

(3 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, a small weighting matrix W ∈ R s×s is directly computed by minimizing the residual error [47]- [49], [66]; Y † is the Moore-Penrose pseudo-inverse of Y. When the original space F ∈ R M ×N is rank-restricted, i.e., rank(F) = r ≪ min(M, N ), and the sampling length satisfies s ∼ O{rlog(r/ǫ)}, then the residual error is upper bounded with probability 1 − ǫ [47], [48], i.e.,…”

Section: Reconstructing a Low-rank Representationmentioning

confidence: 99%

Machine Learning-enabled Globally Guaranteed Evolutionary Computation

Wei

et al. 2023

Preprint

View full text Add to dashboard Cite

Evolutionary computation, e.g., particle swarm optimization (PSO), has made impressive achievements in solving complex problems in science and industry. As an important open problem for more than 50 years, there is still no theoretical guarantee on the global optimum and the general reliability, due to lack of a unified representation of diverse problem structures and a generic mechanism to avoid local optimums. The long-standing pitfalls severely impair their trusted applications in a variety of problems. Here, we report a new evolutionary computation framework aided by machine learning, named EVOLER, which for the first time enables the theoretically guaranteed global optimization of complex nonconvex problems. This is achieved by: (1) learning a low-rank representation of problem with the limited samples, which helps to identify one attention subspace; and (2) exploring this small attention subspace via the evolutionary computation method, which allows to reliably avoid local optimums. As validated on 20 challenging benchmarks, it finds the global optimum with probability approaching 1; and moreover, it attains the best results in all cases, thus substantially extending the applicability in diverse problems. We use EVOLER to tackle 2 important problems, dispatch of power grid and inverse design of nano-photonics devices, whereby it consistently gains the optimal results that were rarely achieved by state-of-the-art methods. Our method takes a crucial step forward in globally guaranteed evolutionary computation, overcoming the uncertainty of data-driven black-box methods, offering broad prospects for tackling complex real-world problems.

show abstract

Section: Reconstructing a Low-rank Representationmentioning

confidence: 99%

Machine Learning-enabled Globally Guaranteed Evolutionary Computation

Wei

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Here, a small weighting matrix W ∈ ℝ s×s is directly computed by minimizing the residual error [46][47][48]66 ; Y † is the Moore-Penrose pseudo-inverse of Y. When the original space F ∈ ℝ M×N is rank-restricted, that is, rank (F) = r ≪ min(M, N) , and the sampling length satisfies s ≈ 𝒪𝒪{r log(r/ϵ)}, then the residual error is upper bounded with probability 1 − ϵ (refs.…”

Section: Reconstructing a Low-rank Representationmentioning

confidence: 99%

Machine learning-enabled globally guaranteed evolutionary computation

Wei

et al. 2023

Nat Mach Intell

Self Cite

View full text Add to dashboard Cite

Evolutionary computation, for example, particle swarm optimization, has impressive achievements in solving complex problems in science and industry; however, an important open problem in evolutionary computation is that there is no theoretical guarantee of reaching the global optimum and general reliability; this is due to the lack of a unified representation of diverse problem structures and a generic mechanism by which to avoid local optima. This unresolved challenge impairs trust in the applicability of evolutionary computation to a variety of problems. Here we report an evolutionary computation framework aided by machine learning, named EVOLER, which enables the theoretically guaranteed global optimization of a range of complex non-convex problems. This is achieved by: (1) learning a low-rank representation of a problem with limited samples, which helps to identify an attention subspace; and (2) exploring this small attention subspace via the evolutionary computation method, which helps to reliably avoid local optima. As validated on 20 challenging benchmarks, this method finds the global optimum with a probability approaching 1. We use EVOLER to tackle two important problems: power grid dispatch and the inverse design of nanophotonics devices. The method consistently reached optimal results that were challenging to achieve with previous state-of-the-art methods. EVOLER takes a leap forwards in globally guaranteed evolutionary computation, overcoming the uncertainty of data-driven black-box methods, and offering broad prospects for tackling complex real-world problems.

show abstract

“…Compared to phase-based methods, this approach offers a simpler system configuration and set-up [8][9][10][11]. On the other hand, MUSIC (multiple signal classification) and ESPRIT (estimation of signal parameters via rotation invariance) are typical methods of the angle of arrival estimation using phase, with high estimation accuracy [12][13][14][15]. However, these direction-finding methodologies often require repeated sampling, which is suboptimal for resolving fast-moving targets, supporting large sensor arrays, and minimizing computational time and cost.…”

Section: Introductionmentioning

confidence: 99%

Compact Amplitude-Only Direction Finding Based on a Deep Neural Network with a Single-Patch Multi-Beam Antenna

2023

View full text Add to dashboard Cite

In this paper, a compact direction-finding system based on a deep neural network (DNN) with a single-patch multi-beam antenna is proposed. To achieve multiple beams, the patch is divided into four sectors by metal vias, and the pattern is tilted in the theta direction due to the coupled mode of the divided patch structure. This design allows a single-patch multi-beam antenna to generate eight beams using a combination of four excitation ports assigned to the four-divided sectors. This approach increases the amount of training data required for DNN-based direction finding without requiring multiple antennas, thus improving the accuracy of estimation probability. Furthermore, compared to our previous work, the parasitic elements are applied to improve the estimation probability by reducing the beamwidth of the antenna. The size of the antenna for the proposed direction-finding system is 0.44λ × 0.44λ × 0.008λ with a 97.7% estimation probability. The direction-finding performance has been validated and compared through the experiment to show higher accuracy with compactness than previously studied works.

show abstract

Ultra-Fast Accurate AoA Estimation via Automotive Massive-MIMO Radar

Cited by 20 publications

References 55 publications

Machine Learning-enabled Globally Guaranteed Evolutionary Computation

Machine Learning-enabled Globally Guaranteed Evolutionary Computation

Machine learning-enabled globally guaranteed evolutionary computation

Compact Amplitude-Only Direction Finding Based on a Deep Neural Network with a Single-Patch Multi-Beam Antenna

Contact Info

Product

Resources

About