4.8 Article

Vehicle Positioning With Deep-Learning-Based Direction-of-Arrival Estimation of Incoherently Distributed Sources

Journal

IEEE INTERNET OF THINGS JOURNAL
Volume 9, Issue 20, Pages 20083-20095

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2022.3171820

Keywords

Direction-of-arrival estimation; Estimation; Antenna arrays; Wireless communication; Internet of Things; Massive MIMO; Perturbation methods; Deep learning (DL); incoherently distributed (ID) sources; Internet of Vehicles (IoVs); transfer learning (TL); two-dimensional (2-D) direction-of-arrival (DOA) estimation; vehicle positioning

Funding

  1. National Natural Science Foundation of China [62001256, 61601398]
  2. Scientific and Technological Achievement Cultivation Project of Guangxi Normal University [RZ200000314]

Ask authors/readers for more resources

In this article, a novel vehicle positioning system architecture based on DOA estimation of ID sources utilizing massive MIMO arrays is proposed. The system employs a D1D-CNN for 2-D DOA estimation and utilizes received SNR information for selecting DOA estimates for positioning. Transfer learning and an attention mechanism are also employed for improving the generalization ability and robustness against array perturbations of the system.
In this article, a novel vehicle positioning system architecture based on direction-of-arrival (DOA) estimation of incoherently distributed (ID) sources is proposed employing massive multiple-input-multiple-output (MIMO) arrays. Such an architecture with the associated signal model is more consistent with the actual array application and multipath transmission scenarios. First, an end-to-end two-dimensional (2-D) DOA estimation of ID sources utilizing a dual one-dimensional (1-D) convolutional neural network (D1D-CNN) under the deep learning (DL) framework is performed, where the normalized covariance matrix data is used for both offline training and online estimation. Then, the received SNR information is exploited to select a set of DOA estimates provided by multiple collaborative BSs for positioning. Moreover, transfer learning and an attention mechanism are employed to promote its generalization ability and achieve robustness against array perturbations. Simulation results are provided to show that the proposed method outperforms the state-of-the-art methods in terms of computational complexity, positioning accuracy, and robustness against array perturbations.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available