Modulation recognition method based on multimodal features
IntroductionAutomatic modulation recognition (AMR) plays a crucial role in modern communication systems for efficient signal processing and monitoring. However, existing modulation recognition methods often lack comprehensive feature extraction and suffer from recognition inaccuracies.MethodsTo over...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-03-01
|
| Series: | Frontiers in Communications and Networks |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frcmn.2025.1453125/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850236161294860288 |
|---|---|
| author | Hu Zhang Yin Kuang Ronghui Huang Sheng Lin Youqiang Dong Min Zhang |
| author_facet | Hu Zhang Yin Kuang Ronghui Huang Sheng Lin Youqiang Dong Min Zhang |
| author_sort | Hu Zhang |
| collection | DOAJ |
| description | IntroductionAutomatic modulation recognition (AMR) plays a crucial role in modern communication systems for efficient signal processing and monitoring. However, existing modulation recognition methods often lack comprehensive feature extraction and suffer from recognition inaccuracies.MethodsTo overcome these challenges, we present a multi-task modulation recognition approach leveraging multimodal features. In this method, a network is proposed to differentiate between multi-domain features for temporal feature extraction. Simultaneously, a network capable of extracting features at multiple scales is utilized for image feature extraction. Subsequently, recognition is conducted by integrating the multimodal features. Due to the inherent differences between 1D signal features and 2D image features, recognizing them collectively may overlook the unique characteristics of each type.ResultsWe examine the merit of the proposed multi-task modulation recognition method and validate their performance with experiments using a public datasets. With an SNR of 0 dB, the proposed algorithm achieves a recognition accuracy of 92.30% on the RadioML2016.10a dataset.DiscussionTherefore, we propose a multi-task modulation recognition approach leveraging multimodal features to enhance accuracy. By integrating temporal and image-based feature extraction, our method outperforms existing techniques in recognition performance. |
| format | Article |
| id | doaj-art-6c98b514569d4324bfbb039e42b2163e |
| institution | OA Journals |
| issn | 2673-530X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Communications and Networks |
| spelling | doaj-art-6c98b514569d4324bfbb039e42b2163e2025-08-20T02:02:01ZengFrontiers Media S.A.Frontiers in Communications and Networks2673-530X2025-03-01610.3389/frcmn.2025.14531251453125Modulation recognition method based on multimodal featuresHu ZhangYin KuangRonghui HuangSheng LinYouqiang DongMin ZhangIntroductionAutomatic modulation recognition (AMR) plays a crucial role in modern communication systems for efficient signal processing and monitoring. However, existing modulation recognition methods often lack comprehensive feature extraction and suffer from recognition inaccuracies.MethodsTo overcome these challenges, we present a multi-task modulation recognition approach leveraging multimodal features. In this method, a network is proposed to differentiate between multi-domain features for temporal feature extraction. Simultaneously, a network capable of extracting features at multiple scales is utilized for image feature extraction. Subsequently, recognition is conducted by integrating the multimodal features. Due to the inherent differences between 1D signal features and 2D image features, recognizing them collectively may overlook the unique characteristics of each type.ResultsWe examine the merit of the proposed multi-task modulation recognition method and validate their performance with experiments using a public datasets. With an SNR of 0 dB, the proposed algorithm achieves a recognition accuracy of 92.30% on the RadioML2016.10a dataset.DiscussionTherefore, we propose a multi-task modulation recognition approach leveraging multimodal features to enhance accuracy. By integrating temporal and image-based feature extraction, our method outperforms existing techniques in recognition performance.https://www.frontiersin.org/articles/10.3389/frcmn.2025.1453125/fullautomatic modulation recognitionfeature extractionmulti-domainmulti-taskdeep learning |
| spellingShingle | Hu Zhang Yin Kuang Ronghui Huang Sheng Lin Youqiang Dong Min Zhang Modulation recognition method based on multimodal features Frontiers in Communications and Networks automatic modulation recognition feature extraction multi-domain multi-task deep learning |
| title | Modulation recognition method based on multimodal features |
| title_full | Modulation recognition method based on multimodal features |
| title_fullStr | Modulation recognition method based on multimodal features |
| title_full_unstemmed | Modulation recognition method based on multimodal features |
| title_short | Modulation recognition method based on multimodal features |
| title_sort | modulation recognition method based on multimodal features |
| topic | automatic modulation recognition feature extraction multi-domain multi-task deep learning |
| url | https://www.frontiersin.org/articles/10.3389/frcmn.2025.1453125/full |
| work_keys_str_mv | AT huzhang modulationrecognitionmethodbasedonmultimodalfeatures AT yinkuang modulationrecognitionmethodbasedonmultimodalfeatures AT ronghuihuang modulationrecognitionmethodbasedonmultimodalfeatures AT shenglin modulationrecognitionmethodbasedonmultimodalfeatures AT youqiangdong modulationrecognitionmethodbasedonmultimodalfeatures AT minzhang modulationrecognitionmethodbasedonmultimodalfeatures |