Robust estimation of the number of coherent radar signal sources using deep learning
Abstract A deep‐learning‐based approach to estimating the number of coherent sources in radar is presented. A proper estimate of the number of sources in a signal enables improved angle‐of‐arrival (AoA) estimation common in applications such as radar, sonar, and communication systems. Many AoA estim...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-05-01
|
| Series: | IET Radar, Sonar & Navigation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rsn2.12047 |
| _version_ | 1798001888742866944 |
|---|---|
| author | John Rogers John E. Ball Ali C. Gurbuz |
| author_facet | John Rogers John E. Ball Ali C. Gurbuz |
| author_sort | John Rogers |
| collection | DOAJ |
| description | Abstract A deep‐learning‐based approach to estimating the number of coherent sources in radar is presented. A proper estimate of the number of sources in a signal enables improved angle‐of‐arrival (AoA) estimation common in applications such as radar, sonar, and communication systems. Many AoA estimators utilised in these areas require accurate estimates of the number of sources for enhanced performance. Herein, a robust method that performs well under the existence of coherent sources is developed. The proposed method is based on deep learning and it is shown to perform better than state‐of‐the‐art versions of the Akaike Information Criteria (AIC), Minimum Description Length (MDL), and Exponentially Embedded Families (EEF) estimators, which employ spatial smoothing of the covariance matrix to handle coherent signals. |
| first_indexed | 2024-04-11T11:43:19Z |
| format | Article |
| id | doaj.art-68d26c5a2e41461cbc13f22a2326d34b |
| institution | Directory Open Access Journal |
| issn | 1751-8784 1751-8792 |
| language | English |
| last_indexed | 2024-04-11T11:43:19Z |
| publishDate | 2021-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Radar, Sonar & Navigation |
| spelling | doaj.art-68d26c5a2e41461cbc13f22a2326d34b2022-12-22T04:25:45ZengWileyIET Radar, Sonar & Navigation1751-87841751-87922021-05-0115543144010.1049/rsn2.12047Robust estimation of the number of coherent radar signal sources using deep learningJohn Rogers0John E. Ball1Ali C. Gurbuz2Electrical and Computer Engineering Mississippi State University Starkville Mississippi USAElectrical and Computer Engineering Mississippi State University Starkville Mississippi USAElectrical and Computer Engineering Mississippi State University Starkville Mississippi USAAbstract A deep‐learning‐based approach to estimating the number of coherent sources in radar is presented. A proper estimate of the number of sources in a signal enables improved angle‐of‐arrival (AoA) estimation common in applications such as radar, sonar, and communication systems. Many AoA estimators utilised in these areas require accurate estimates of the number of sources for enhanced performance. Herein, a robust method that performs well under the existence of coherent sources is developed. The proposed method is based on deep learning and it is shown to perform better than state‐of‐the‐art versions of the Akaike Information Criteria (AIC), Minimum Description Length (MDL), and Exponentially Embedded Families (EEF) estimators, which employ spatial smoothing of the covariance matrix to handle coherent signals.https://doi.org/10.1049/rsn2.12047covariance matricesdirection‐of‐arrival estimationestimation theoryradar computingradar signal processingsmoothing methods |
| spellingShingle | John Rogers John E. Ball Ali C. Gurbuz Robust estimation of the number of coherent radar signal sources using deep learning IET Radar, Sonar & Navigation covariance matrices direction‐of‐arrival estimation estimation theory radar computing radar signal processing smoothing methods |
| title | Robust estimation of the number of coherent radar signal sources using deep learning |
| title_full | Robust estimation of the number of coherent radar signal sources using deep learning |
| title_fullStr | Robust estimation of the number of coherent radar signal sources using deep learning |
| title_full_unstemmed | Robust estimation of the number of coherent radar signal sources using deep learning |
| title_short | Robust estimation of the number of coherent radar signal sources using deep learning |
| title_sort | robust estimation of the number of coherent radar signal sources using deep learning |
| topic | covariance matrices direction‐of‐arrival estimation estimation theory radar computing radar signal processing smoothing methods |
| url | https://doi.org/10.1049/rsn2.12047 |
| work_keys_str_mv | AT johnrogers robustestimationofthenumberofcoherentradarsignalsourcesusingdeeplearning AT johneball robustestimationofthenumberofcoherentradarsignalsourcesusingdeeplearning AT alicgurbuz robustestimationofthenumberofcoherentradarsignalsourcesusingdeeplearning |