Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network
This paper introduces an off-grid DoA estimation via two-stage cascaded network which can resolve a mismatch between true direction-of-arrival (DoA) and discrete angular grid. In the first-stage network, the initial DoAs are estimated with a convolutional neural network (CNN), where initial DoAs are...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/1/228 |
| _version_ | 1797542434179121152 |
|---|---|
| author | Hyeonjin Chung Hyeongwook Seo Jeungmin Joo Dongkeun Lee Sunwoo Kim |
| author_facet | Hyeonjin Chung Hyeongwook Seo Jeungmin Joo Dongkeun Lee Sunwoo Kim |
| author_sort | Hyeonjin Chung |
| collection | DOAJ |
| description | This paper introduces an off-grid DoA estimation via two-stage cascaded network which can resolve a mismatch between true direction-of-arrival (DoA) and discrete angular grid. In the first-stage network, the initial DoAs are estimated with a convolutional neural network (CNN), where initial DoAs are mapped on the discrete angular grid. To deal with the mismatch between initially estimated DoAs and true DoAs, the second-stage network estimates a tuning vector which represents the difference between true DoAs and nearest discrete angles. By using tuning vector, the final DoAs are estimated by moving initially estimated DoAs as much as the difference between true DoAs and nearest discrete angles. The limitation on estimation accuracy induced by the discrete angular grid can be resolved with the proposed two-stage network so that the estimation accuracy can be further enhanced. Simulation results show that adding the second-stage network after the first-stage network helps improve the estimation accuracy by resolving mismatch induced by the discretized grid. In the aspect of the implementation of machine learning, results also show that using CNN and using PReLU as the activation function is the best option for accurate estimation. |
| first_indexed | 2024-03-10T13:30:27Z |
| format | Article |
| id | doaj.art-da250e48f46d4c1f9fc9778232186d2f |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T13:30:27Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-da250e48f46d4c1f9fc9778232186d2f2023-11-21T08:10:20ZengMDPI AGEnergies1996-10732021-01-0114122810.3390/en14010228Off-Grid DoA Estimation via Two-Stage Cascaded Neural NetworkHyeonjin Chung0Hyeongwook Seo1Jeungmin Joo2Dongkeun Lee3Sunwoo Kim4Department of Electronics and Computer Engineering, Hanyang University, Seoul 04763, KoreaDepartment of Electronics and Computer Engineering, Hanyang University, Seoul 04763, KoreaAgency for Defense Development, Yuseong P.O. Box 35, Daejeon 34186, KoreaAgency for Defense Development, Yuseong P.O. Box 35, Daejeon 34186, KoreaDepartment of Electronics and Computer Engineering, Hanyang University, Seoul 04763, KoreaThis paper introduces an off-grid DoA estimation via two-stage cascaded network which can resolve a mismatch between true direction-of-arrival (DoA) and discrete angular grid. In the first-stage network, the initial DoAs are estimated with a convolutional neural network (CNN), where initial DoAs are mapped on the discrete angular grid. To deal with the mismatch between initially estimated DoAs and true DoAs, the second-stage network estimates a tuning vector which represents the difference between true DoAs and nearest discrete angles. By using tuning vector, the final DoAs are estimated by moving initially estimated DoAs as much as the difference between true DoAs and nearest discrete angles. The limitation on estimation accuracy induced by the discrete angular grid can be resolved with the proposed two-stage network so that the estimation accuracy can be further enhanced. Simulation results show that adding the second-stage network after the first-stage network helps improve the estimation accuracy by resolving mismatch induced by the discretized grid. In the aspect of the implementation of machine learning, results also show that using CNN and using PReLU as the activation function is the best option for accurate estimation.https://www.mdpi.com/1996-1073/14/1/228off-grid direction-of-arrival (DoA) estimationmachine learningcascaded neural networkconvolutional neural network (CNN)deep neural network (DNN)sparse representation |
| spellingShingle | Hyeonjin Chung Hyeongwook Seo Jeungmin Joo Dongkeun Lee Sunwoo Kim Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network Energies off-grid direction-of-arrival (DoA) estimation machine learning cascaded neural network convolutional neural network (CNN) deep neural network (DNN) sparse representation |
| title | Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network |
| title_full | Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network |
| title_fullStr | Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network |
| title_full_unstemmed | Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network |
| title_short | Off-Grid DoA Estimation via Two-Stage Cascaded Neural Network |
| title_sort | off grid doa estimation via two stage cascaded neural network |
| topic | off-grid direction-of-arrival (DoA) estimation machine learning cascaded neural network convolutional neural network (CNN) deep neural network (DNN) sparse representation |
| url | https://www.mdpi.com/1996-1073/14/1/228 |
| work_keys_str_mv | AT hyeonjinchung offgriddoaestimationviatwostagecascadedneuralnetwork AT hyeongwookseo offgriddoaestimationviatwostagecascadedneuralnetwork AT jeungminjoo offgriddoaestimationviatwostagecascadedneuralnetwork AT dongkeunlee offgriddoaestimationviatwostagecascadedneuralnetwork AT sunwookim offgriddoaestimationviatwostagecascadedneuralnetwork |