Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN
This paper proposes a joint estimation method for source number and DOA based on an improved convolutional neural network for unknown source number and undetermined DOA estimation. By analyzing the signal model, the paper designs a convolutional neural network model based on the existence of a mappi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/6/3100 |
| _version_ | 1827747748131110912 |
|---|---|
| author | Fangzheng Zhao Guoping Hu Hao Zhou Shuhan Guo |
| author_facet | Fangzheng Zhao Guoping Hu Hao Zhou Shuhan Guo |
| author_sort | Fangzheng Zhao |
| collection | DOAJ |
| description | This paper proposes a joint estimation method for source number and DOA based on an improved convolutional neural network for unknown source number and undetermined DOA estimation. By analyzing the signal model, the paper designs a convolutional neural network model based on the existence of a mapping relationship between the covariance matrix and both the source number and DOA estimation. The model, which discards the pooling layer to avoid data loss and introduces the dropout method to improve generalization, takes the signal covariance matrix as input and the two branches of source number estimation and DOA estimation as outputs, and achieves the unfixed number of DOA estimation by filling in invalid values. Simulation experiments and analysis of the results show that the algorithm can effectively achieve the joint estimation of source number and DOA. Under the conditions of high SNR and a large snapshot number, both the proposed algorithm and the traditional algorithm have high estimation accuracy, while under the conditions of low SNR and a small snapshot, the algorithm is better than the traditional algorithm, and under the underdetermined conditions, where the traditional algorithm often fails, the algorithm can still achieve the joint estimation. |
| first_indexed | 2024-03-11T05:56:38Z |
| format | Article |
| id | doaj.art-cfc6a361fbd7479cb488941dac2a5a00 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:56:38Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cfc6a361fbd7479cb488941dac2a5a002023-11-17T13:45:59ZengMDPI AGSensors1424-82202023-03-01236310010.3390/s23063100Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNNFangzheng Zhao0Guoping Hu1Hao Zhou2Shuhan Guo3Graduate School, Air Force Engineering University, Xi’an 710043, ChinaAir and Missile Defense College, Air Force Engineering University, Xi’an 710043, ChinaAir and Missile Defense College, Air Force Engineering University, Xi’an 710043, ChinaGraduate School, Air Force Engineering University, Xi’an 710043, ChinaThis paper proposes a joint estimation method for source number and DOA based on an improved convolutional neural network for unknown source number and undetermined DOA estimation. By analyzing the signal model, the paper designs a convolutional neural network model based on the existence of a mapping relationship between the covariance matrix and both the source number and DOA estimation. The model, which discards the pooling layer to avoid data loss and introduces the dropout method to improve generalization, takes the signal covariance matrix as input and the two branches of source number estimation and DOA estimation as outputs, and achieves the unfixed number of DOA estimation by filling in invalid values. Simulation experiments and analysis of the results show that the algorithm can effectively achieve the joint estimation of source number and DOA. Under the conditions of high SNR and a large snapshot number, both the proposed algorithm and the traditional algorithm have high estimation accuracy, while under the conditions of low SNR and a small snapshot, the algorithm is better than the traditional algorithm, and under the underdetermined conditions, where the traditional algorithm often fails, the algorithm can still achieve the joint estimation.https://www.mdpi.com/1424-8220/23/6/3100convolutional neural networkssource number estimationunderdetermined DOA estimationuniform linear arraysparse array |
| spellingShingle | Fangzheng Zhao Guoping Hu Hao Zhou Shuhan Guo Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN Sensors convolutional neural networks source number estimation underdetermined DOA estimation uniform linear array sparse array |
| title | Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN |
| title_full | Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN |
| title_fullStr | Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN |
| title_full_unstemmed | Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN |
| title_short | Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN |
| title_sort | research on underdetermined doa estimation method with unknown number of sources based on improved cnn |
| topic | convolutional neural networks source number estimation underdetermined DOA estimation uniform linear array sparse array |
| url | https://www.mdpi.com/1424-8220/23/6/3100 |
| work_keys_str_mv | AT fangzhengzhao researchonunderdetermineddoaestimationmethodwithunknownnumberofsourcesbasedonimprovedcnn AT guopinghu researchonunderdetermineddoaestimationmethodwithunknownnumberofsourcesbasedonimprovedcnn AT haozhou researchonunderdetermineddoaestimationmethodwithunknownnumberofsourcesbasedonimprovedcnn AT shuhanguo researchonunderdetermineddoaestimationmethodwithunknownnumberofsourcesbasedonimprovedcnn |