Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization
We propose a complex LeDIM-net (C-LeDIM-net) convolutional neural network (CNN) that employs a newly-formulated complex phasor normalization for gridless direction-of-arrival (DOA) estimation. Unlike existing deep learning (DL) approaches, C-LeDIM-net extracts explicit phase information in its inter...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171213 |
| _version_ | 1811692436491075584 |
|---|---|
| author | Tan, Zhi-Wei Liu, Yuan Khong, Andy Wai Hoong Nguyen, Anh H. T. |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Tan, Zhi-Wei Liu, Yuan Khong, Andy Wai Hoong Nguyen, Anh H. T. |
| author_sort | Tan, Zhi-Wei |
| collection | NTU |
| description | We propose a complex LeDIM-net (C-LeDIM-net) convolutional neural network (CNN) that employs a newly-formulated complex phasor normalization for gridless direction-of-arrival (DOA) estimation. Unlike existing deep learning (DL) approaches, C-LeDIM-net extracts explicit phase information in its intermediate complex-valued feature maps to estimate unknown source DOAs. Given its explicit phase representation, the proposed complex phasor normalization leverages the phase-to-sensor relationship of the feature maps which, as a consequence, improves the robustness of C-LeDIM-net to array imperfections when operating with limited number of snapshots. Simulation results show that the proposed method outperforms the existing methods, including the subspace-based and DL-based methods. |
| first_indexed | 2024-10-01T06:35:45Z |
| format | Journal Article |
| id | ntu-10356/171213 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:35:45Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1712132023-10-17T05:48:12Z Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization Tan, Zhi-Wei Liu, Yuan Khong, Andy Wai Hoong Nguyen, Anh H. T. School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Array Imperfections Complex Neural Network We propose a complex LeDIM-net (C-LeDIM-net) convolutional neural network (CNN) that employs a newly-formulated complex phasor normalization for gridless direction-of-arrival (DOA) estimation. Unlike existing deep learning (DL) approaches, C-LeDIM-net extracts explicit phase information in its intermediate complex-valued feature maps to estimate unknown source DOAs. Given its explicit phase representation, the proposed complex phasor normalization leverages the phase-to-sensor relationship of the feature maps which, as a consequence, improves the robustness of C-LeDIM-net to array imperfections when operating with limited number of snapshots. Simulation results show that the proposed method outperforms the existing methods, including the subspace-based and DL-based methods. Agency for Science, Technology and Research (A*STAR) Thiswork was supported in part by A*STAR through IAF-ICP Programme, Project WP6 within the Delta-NTU Corporate Lab under Grant I2201E0013 and in partby Delta Electronics Inc. 2023-10-17T05:48:12Z 2023-10-17T05:48:12Z 2023 Journal Article Tan, Z., Liu, Y., Khong, A. W. H. & Nguyen, A. H. T. (2023). Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization. IEEE Signal Processing Letters, 30, 813-817. https://dx.doi.org/10.1109/LSP.2023.3292037 1070-9908 https://hdl.handle.net/10356/171213 10.1109/LSP.2023.3292037 2-s2.0-85164447842 30 813 817 en I2201E0013 IEEE Signal Processing Letters © 2023 IEEE. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Array Imperfections Complex Neural Network Tan, Zhi-Wei Liu, Yuan Khong, Andy Wai Hoong Nguyen, Anh H. T. Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization |
| title | Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization |
| title_full | Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization |
| title_fullStr | Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization |
| title_full_unstemmed | Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization |
| title_short | Gridless DOA estimation using complex-valued convolutional neural network with phasor normalization |
| title_sort | gridless doa estimation using complex valued convolutional neural network with phasor normalization |
| topic | Engineering::Electrical and electronic engineering Array Imperfections Complex Neural Network |
| url | https://hdl.handle.net/10356/171213 |
| work_keys_str_mv | AT tanzhiwei gridlessdoaestimationusingcomplexvaluedconvolutionalneuralnetworkwithphasornormalization AT liuyuan gridlessdoaestimationusingcomplexvaluedconvolutionalneuralnetworkwithphasornormalization AT khongandywaihoong gridlessdoaestimationusingcomplexvaluedconvolutionalneuralnetworkwithphasornormalization AT nguyenanhht gridlessdoaestimationusingcomplexvaluedconvolutionalneuralnetworkwithphasornormalization |