Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage Network
Signal features can be obscured in noisy environments, resulting in low accuracy of radar emitter signal recognition based on traditional methods. To improve the ability of learning features from noisy signals, a new radar emitter signal recognition method based on one-dimensional (1D) deep residual...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/7973 |
| _version_ | 1797507248778379264 |
|---|---|
| author | Shengli Zhang Jifei Pan Zhenzhong Han Linqing Guo |
| author_facet | Shengli Zhang Jifei Pan Zhenzhong Han Linqing Guo |
| author_sort | Shengli Zhang |
| collection | DOAJ |
| description | Signal features can be obscured in noisy environments, resulting in low accuracy of radar emitter signal recognition based on traditional methods. To improve the ability of learning features from noisy signals, a new radar emitter signal recognition method based on one-dimensional (1D) deep residual shrinkage network (DRSN) is proposed, which offers the following advantages: (i) Unimportant features are eliminated using the soft thresholding function, and the thresholds are automatically set based on the attention mechanism; (ii) without any professional knowledge of signal processing or dimension conversion of data, the 1D DRSN can automatically learn the features characterizing the signal directly from the 1D data and achieve a high recognition rate for noisy signals. The effectiveness of the 1D DRSN was experimentally verified under different types of noise. In addition, comparison with other deep learning methods revealed the superior performance of the DRSN. Last, the mechanism of eliminating redundant features using the soft thresholding function was analyzed. |
| first_indexed | 2024-03-10T04:45:51Z |
| format | Article |
| id | doaj.art-d550e3efaa994f609e16c3ae144bf033 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:45:51Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d550e3efaa994f609e16c3ae144bf0332023-11-23T03:02:03ZengMDPI AGSensors1424-82202021-11-012123797310.3390/s21237973Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage NetworkShengli Zhang0Jifei Pan1Zhenzhong Han2Linqing Guo3Electronic Countermeasure Institute, National University of Defense Technology, Hefei 230037, ChinaElectronic Countermeasure Institute, National University of Defense Technology, Hefei 230037, ChinaElectronic Countermeasure Institute, National University of Defense Technology, Hefei 230037, ChinaElectronic Countermeasure Institute, National University of Defense Technology, Hefei 230037, ChinaSignal features can be obscured in noisy environments, resulting in low accuracy of radar emitter signal recognition based on traditional methods. To improve the ability of learning features from noisy signals, a new radar emitter signal recognition method based on one-dimensional (1D) deep residual shrinkage network (DRSN) is proposed, which offers the following advantages: (i) Unimportant features are eliminated using the soft thresholding function, and the thresholds are automatically set based on the attention mechanism; (ii) without any professional knowledge of signal processing or dimension conversion of data, the 1D DRSN can automatically learn the features characterizing the signal directly from the 1D data and achieve a high recognition rate for noisy signals. The effectiveness of the 1D DRSN was experimentally verified under different types of noise. In addition, comparison with other deep learning methods revealed the superior performance of the DRSN. Last, the mechanism of eliminating redundant features using the soft thresholding function was analyzed.https://www.mdpi.com/1424-8220/21/23/7973radar emitter signal recognitionhigh noiseone-dimensional residual shrinkage networksoft thresholding |
| spellingShingle | Shengli Zhang Jifei Pan Zhenzhong Han Linqing Guo Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage Network Sensors radar emitter signal recognition high noise one-dimensional residual shrinkage network soft thresholding |
| title | Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage Network |
| title_full | Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage Network |
| title_fullStr | Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage Network |
| title_full_unstemmed | Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage Network |
| title_short | Recognition of Noisy Radar Emitter Signals Using a One-Dimensional Deep Residual Shrinkage Network |
| title_sort | recognition of noisy radar emitter signals using a one dimensional deep residual shrinkage network |
| topic | radar emitter signal recognition high noise one-dimensional residual shrinkage network soft thresholding |
| url | https://www.mdpi.com/1424-8220/21/23/7973 |
| work_keys_str_mv | AT shenglizhang recognitionofnoisyradaremittersignalsusingaonedimensionaldeepresidualshrinkagenetwork AT jifeipan recognitionofnoisyradaremittersignalsusingaonedimensionaldeepresidualshrinkagenetwork AT zhenzhonghan recognitionofnoisyradaremittersignalsusingaonedimensionaldeepresidualshrinkagenetwork AT linqingguo recognitionofnoisyradaremittersignalsusingaonedimensionaldeepresidualshrinkagenetwork |