Differentiable architecture search-based automatic modulation recognition for multi-carrier signals
Considering the lack of a general multi-carrier signal dataset in urban multipath channels, and the challenge of recognizing the modulation types of distorted signals at low signal-to-noise ratio (SNR), a differentiable architecture search-based (DARTS) automatic modulation recognition algorithm for...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2024-09-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024164/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539221107507200 |
|---|---|
| author | LI Jie LI Jing LYU Lu GONG Fengkui |
| author_facet | LI Jie LI Jing LYU Lu GONG Fengkui |
| author_sort | LI Jie |
| collection | DOAJ |
| description | Considering the lack of a general multi-carrier signal dataset in urban multipath channels, and the challenge of recognizing the modulation types of distorted signals at low signal-to-noise ratio (SNR), a differentiable architecture search-based (DARTS) automatic modulation recognition algorithm for multi-carrier signals was proposed. Firstly, the received signal datasets of commonly used multi-carrier signals, i.e., orthogonal frequency division multiplexing, filter bank multi-carrier, and orthogonal time frequency space, were generated over typical urban multipath channels. The time-frequency images, which were insensitive to modulation parameters, were selected as feature vectors to train the neural network. Secondly, DARTS was employed to automatically search the optimal network architecture. Finally, a joint attention mechanism was introduced into the feature learning process. This mechanism spatially transforming distorted signal features to mitigate the impact of multipath interference, while also calculating and sorting the information weights for each channel of the feature maps to improve the recognition performance of the relevant feature map channels. Simulation results demonstrate that the proposed algorithm improves accuracy in urban multipath channels, especially at low SNR, while simultaneously providing better robustness to modulation parameter variations and small-sample scenarios. |
| format | Article |
| id | doaj-art-a21ba8f4067b46e7ae6ba80511b09683 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2024-09-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-a21ba8f4067b46e7ae6ba80511b096832025-01-14T07:25:08ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-09-0145142573359474Differentiable architecture search-based automatic modulation recognition for multi-carrier signalsLI JieLI JingLYU LuGONG FengkuiConsidering the lack of a general multi-carrier signal dataset in urban multipath channels, and the challenge of recognizing the modulation types of distorted signals at low signal-to-noise ratio (SNR), a differentiable architecture search-based (DARTS) automatic modulation recognition algorithm for multi-carrier signals was proposed. Firstly, the received signal datasets of commonly used multi-carrier signals, i.e., orthogonal frequency division multiplexing, filter bank multi-carrier, and orthogonal time frequency space, were generated over typical urban multipath channels. The time-frequency images, which were insensitive to modulation parameters, were selected as feature vectors to train the neural network. Secondly, DARTS was employed to automatically search the optimal network architecture. Finally, a joint attention mechanism was introduced into the feature learning process. This mechanism spatially transforming distorted signal features to mitigate the impact of multipath interference, while also calculating and sorting the information weights for each channel of the feature maps to improve the recognition performance of the relevant feature map channels. Simulation results demonstrate that the proposed algorithm improves accuracy in urban multipath channels, especially at low SNR, while simultaneously providing better robustness to modulation parameter variations and small-sample scenarios.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024164/differentiable architecture searchmulti-carrier signalautomatic modulation recognitionurban multipath channeljoint attention mechanism |
| spellingShingle | LI Jie LI Jing LYU Lu GONG Fengkui Differentiable architecture search-based automatic modulation recognition for multi-carrier signals Tongxin xuebao differentiable architecture search multi-carrier signal automatic modulation recognition urban multipath channel joint attention mechanism |
| title | Differentiable architecture search-based automatic modulation recognition for multi-carrier signals |
| title_full | Differentiable architecture search-based automatic modulation recognition for multi-carrier signals |
| title_fullStr | Differentiable architecture search-based automatic modulation recognition for multi-carrier signals |
| title_full_unstemmed | Differentiable architecture search-based automatic modulation recognition for multi-carrier signals |
| title_short | Differentiable architecture search-based automatic modulation recognition for multi-carrier signals |
| title_sort | differentiable architecture search based automatic modulation recognition for multi carrier signals |
| topic | differentiable architecture search multi-carrier signal automatic modulation recognition urban multipath channel joint attention mechanism |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024164/ |
| work_keys_str_mv | AT lijie differentiablearchitecturesearchbasedautomaticmodulationrecognitionformulticarriersignals AT lijing differentiablearchitecturesearchbasedautomaticmodulationrecognitionformulticarriersignals AT lyulu differentiablearchitecturesearchbasedautomaticmodulationrecognitionformulticarriersignals AT gongfengkui differentiablearchitecturesearchbasedautomaticmodulationrecognitionformulticarriersignals |