Fast Direct Localization for Millimeter Wave MIMO Systems via Deep ADMM Unfolding

Fan, Wenzhe; Liu, Shengheng; Li, Chunguo; Huang, Yongming

doi:10.1109/lwc.2023.3243157

Cited by 8 publications

(2 citation statements)

References 21 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we demonstrate the effectiveness of AoA estimation with existence of hardware impairments using the proposed MoD-DNN, especially in comparison with multiple signal classification (MUSIC) algorithm, DeepMUSIC algorithm (Elbir 2020) and CNN (Liu et al 2023). All novel datasets and codes introduced in this paper will be made publicly available upon publication of the paper with a license that allows free usage for research purposes.…”

Section: Resultsmentioning

confidence: 99%

“…Model-Driven Learning Diverging from pure data-driven neural networks, certain methodologies integrate principled mathematical models with data-driven systems, reaping the strengths of both paradigms (Zhou, Li, and Wang 2020;Zhu et al 2020;Fan et al 2023). Hybrid model-driven deep learning schemes have been advanced to synergize prior statistical models (Merkofer et al 2022;Hasanzade-Zonuzy, Kalathil, and Shakkottai 2021).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Model-Driven Deep Neural Network for Enhanced AoA Estimation Using 5G gNB

Liu,

Li,

Mao

et al. 2024

AAAI

View full text Add to dashboard Cite

High-accuracy positioning has become a fundamental enabler for intelligent connected devices. Nevertheless, the present wireless networks still rely on model-driven approaches to achieve positioning functionality, which are susceptible to performance degradation in practical scenarios, primarily due to hardware impairments. Integrating artificial intelligence into the positioning framework presents a promising solution to revolutionize the accuracy and robustness of location-based services. In this study, we address this challenge by reformulating the problem of angle-of-arrival (AoA) estimation into image reconstruction of spatial spectrum. To this end, we design a model-driven deep neural network (MoD-DNN), which can automatically calibrate the angular-dependent phase error. The proposed MoD-DNN approach employs an iterative optimization scheme between a convolutional neural network and a sparse conjugate gradient algorithm. Simulation and experimental results are presented to demonstrate the effectiveness of the proposed method in enhancing spectrum calibration and AoA estimation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Model-Driven Deep Neural Network for Enhanced AoA Estimation Using 5G gNB

Liu,

Li,

Mao

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

An enhanced direct position determination of non-circular sources via sparse Bayesian inference and grid refinement strategy

Li,

Dong,

Shi

et al. 2024

Digital Signal Processing

View full text Add to dashboard Cite

2D-Localization Based on Tracking Antenna Using Artificial Intelligence Mapping (AIM) Approach

Madany

2023

IEEE Access

View full text Add to dashboard Cite

Many recent low-range applications require only two-dimensional localization. It is more dependable and simpler to use in real-time low-power and range applications because it requires significantly fewer calculations than three dimensions. As antennas can function as sensors in this system, they are regarded as crucial components in the development of localization systems. To avoid a relatively difficult object detection and achieve 360° azimuth plane coverage, the antenna must be as small as possible. The purpose of this study is to design an effective algorithm for the 2D-localization of low-range object positioning using the proposed Artificial Intelligence Mapping (AIM) approach. The proposed AIM approach's modelling and simulation of object localization based on a tracking antenna and the proposed Modified Triangulation Method (MTM) are introduced and analyzed. The design and implementation of the object-localization system were completed. To fulfil the specific aim and suggested AIM approach, the practical 2D-Localization Object System (2D-LOS) uses a commercial identification system. Several trace scenarios for the tracking antenna were illustrated, tested, and compared with samples from other methods in the literature to demonstrate the effectiveness of the proposed localization method for different low-range applications. The proposed AIM approach, which is based on real-world data, has a relatively low resolution and a small error difference.

show abstract

Fast Direct Localization for Millimeter Wave MIMO Systems via Deep ADMM Unfolding

Cited by 8 publications

References 21 publications

Model-Driven Deep Neural Network for Enhanced AoA Estimation Using 5G gNB

Model-Driven Deep Neural Network for Enhanced AoA Estimation Using 5G gNB

An enhanced direct position determination of non-circular sources via sparse Bayesian inference and grid refinement strategy

2D-Localization Based on Tracking Antenna Using Artificial Intelligence Mapping (AIM) Approach

Contact Info

Product

Resources

About