Robust automatic modulation classification under noise mismatch
Abstract Automatic modulation classification plays a critical role in the intelligent reception of unknown wireless signals. In practice, the dynamic wireless environment brings a great challenge, and the actual test model is inconsistent with the training model. Therefore, aiming at the problem of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-06-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13634-023-01036-9 |
| _version_ | 1797778621352378368 |
|---|---|
| author | Lan Guo Rui Gao Yang Cong Lei Yang |
| author_facet | Lan Guo Rui Gao Yang Cong Lei Yang |
| author_sort | Lan Guo |
| collection | DOAJ |
| description | Abstract Automatic modulation classification plays a critical role in the intelligent reception of unknown wireless signals. In practice, the dynamic wireless environment brings a great challenge, and the actual test model is inconsistent with the training model. Therefore, aiming at the problem of noise mismatch, this paper proposes a new modulation classification method based on KD-GoogLeNet and Squeeze-Excitation (KD-GSENet). Using the k-dimensional tree, the complex wireless signals are converted into color images rather than normal constellations, which can enhance the classification features. Considering the attention block has the inherent advantage of assigning more weights to important features, this paper further uses it to improve the GoogLeNet. Finally, extensive experiments are presented including Gaussian noise, non-Gaussian noise, and the scenarios of noise mismatch. Numerical results verify the superior classification performance of the proposed KD-GSENet under different scenarios. |
| first_indexed | 2024-03-12T23:19:19Z |
| format | Article |
| id | doaj.art-2894f5af882c45159c361efb5f58d9c4 |
| institution | Directory Open Access Journal |
| issn | 1687-6180 |
| language | English |
| last_indexed | 2024-03-12T23:19:19Z |
| publishDate | 2023-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-2894f5af882c45159c361efb5f58d9c42023-07-16T11:31:24ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802023-06-012023112110.1186/s13634-023-01036-9Robust automatic modulation classification under noise mismatchLan Guo0Rui Gao1Yang Cong2Lei Yang3Department of Information Engineering, Yangzhou UniversityDepartment of Information Engineering, Yangzhou UniversityDepartment of Information Engineering, Yangzhou UniversityCreatcomm Technology Co., Ltd.Abstract Automatic modulation classification plays a critical role in the intelligent reception of unknown wireless signals. In practice, the dynamic wireless environment brings a great challenge, and the actual test model is inconsistent with the training model. Therefore, aiming at the problem of noise mismatch, this paper proposes a new modulation classification method based on KD-GoogLeNet and Squeeze-Excitation (KD-GSENet). Using the k-dimensional tree, the complex wireless signals are converted into color images rather than normal constellations, which can enhance the classification features. Considering the attention block has the inherent advantage of assigning more weights to important features, this paper further uses it to improve the GoogLeNet. Finally, extensive experiments are presented including Gaussian noise, non-Gaussian noise, and the scenarios of noise mismatch. Numerical results verify the superior classification performance of the proposed KD-GSENet under different scenarios.https://doi.org/10.1186/s13634-023-01036-9Automatic modulation classificationNoise mismatchDeep learningConstellationKD-GSENet |
| spellingShingle | Lan Guo Rui Gao Yang Cong Lei Yang Robust automatic modulation classification under noise mismatch EURASIP Journal on Advances in Signal Processing Automatic modulation classification Noise mismatch Deep learning Constellation KD-GSENet |
| title | Robust automatic modulation classification under noise mismatch |
| title_full | Robust automatic modulation classification under noise mismatch |
| title_fullStr | Robust automatic modulation classification under noise mismatch |
| title_full_unstemmed | Robust automatic modulation classification under noise mismatch |
| title_short | Robust automatic modulation classification under noise mismatch |
| title_sort | robust automatic modulation classification under noise mismatch |
| topic | Automatic modulation classification Noise mismatch Deep learning Constellation KD-GSENet |
| url | https://doi.org/10.1186/s13634-023-01036-9 |
| work_keys_str_mv | AT languo robustautomaticmodulationclassificationundernoisemismatch AT ruigao robustautomaticmodulationclassificationundernoisemismatch AT yangcong robustautomaticmodulationclassificationundernoisemismatch AT leiyang robustautomaticmodulationclassificationundernoisemismatch |