Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification
Recent advances in deep learning (DL) have led many contemporary automatic modulation classification (AMC) techniques to use deep networks in classifying the modulation type of incoming signals at the receiver. However, current DL-based methods face scalability challenges, particularly when encounte...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10388303/ |
| _version_ | 1797348747630346240 |
|---|---|
| author | Jungik Jang Jisung Pyo Young-Il Yoon Jaehyuk Choi |
| author_facet | Jungik Jang Jisung Pyo Young-Il Yoon Jaehyuk Choi |
| author_sort | Jungik Jang |
| collection | DOAJ |
| description | Recent advances in deep learning (DL) have led many contemporary automatic modulation classification (AMC) techniques to use deep networks in classifying the modulation type of incoming signals at the receiver. However, current DL-based methods face scalability challenges, particularly when encountering unseen modulations or input signals from environments not present during model training, making them less suitable for real-world applications like software-defined radio devices. In this paper, we introduce a scalable AMC scheme that provides flexibility for new modulations and adaptability to input signals with diverse configurations. We propose the Meta-Transformer, a meta-learning framework based on few-shot learning (FSL) to acquire general knowledge and a learning method for AMC tasks. This approach empowers the model to identify new unseen modulations using only a very small number of samples, eliminating the need for complete model retraining. Furthermore, we enhance the scalability of the classifier by leveraging main-sub transformer-based encoders, enabling efficient processing of input signals with diverse setups. Extensive evaluations demonstrate that the proposed AMC method outperforms existing techniques across all signal-to-noise ratios (SNRs) on RadioML2018.01A. The source code and pre-trained models are released at <uri>https://github.com/cheeseBG/meta-transformer-amc</uri>. |
| first_indexed | 2024-03-08T12:09:28Z |
| format | Article |
| id | doaj.art-35d537234ba64720baf5d49b243fb9e0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T12:09:28Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-35d537234ba64720baf5d49b243fb9e02024-01-23T00:01:51ZengIEEEIEEE Access2169-35362024-01-01129267927610.1109/ACCESS.2024.335263410388303Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation ClassificationJungik Jang0https://orcid.org/0000-0003-1036-621XJisung Pyo1https://orcid.org/0009-0008-3696-9223Young-Il Yoon2Jaehyuk Choi3https://orcid.org/0000-0002-4367-3913School of Computing, Gachon University, Seongnam-si, Republic of KoreaSchool of Computing, Gachon University, Seongnam-si, Republic of KoreaResearch and Development Center, LIG Nex1, Seongnam, Republic of KoreaSchool of Computing, Gachon University, Seongnam-si, Republic of KoreaRecent advances in deep learning (DL) have led many contemporary automatic modulation classification (AMC) techniques to use deep networks in classifying the modulation type of incoming signals at the receiver. However, current DL-based methods face scalability challenges, particularly when encountering unseen modulations or input signals from environments not present during model training, making them less suitable for real-world applications like software-defined radio devices. In this paper, we introduce a scalable AMC scheme that provides flexibility for new modulations and adaptability to input signals with diverse configurations. We propose the Meta-Transformer, a meta-learning framework based on few-shot learning (FSL) to acquire general knowledge and a learning method for AMC tasks. This approach empowers the model to identify new unseen modulations using only a very small number of samples, eliminating the need for complete model retraining. Furthermore, we enhance the scalability of the classifier by leveraging main-sub transformer-based encoders, enabling efficient processing of input signals with diverse setups. Extensive evaluations demonstrate that the proposed AMC method outperforms existing techniques across all signal-to-noise ratios (SNRs) on RadioML2018.01A. The source code and pre-trained models are released at <uri>https://github.com/cheeseBG/meta-transformer-amc</uri>.https://ieeexplore.ieee.org/document/10388303/Automatic modulation classificationfew-shot learningmeta-learningtransformerunseen dataset |
| spellingShingle | Jungik Jang Jisung Pyo Young-Il Yoon Jaehyuk Choi Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification IEEE Access Automatic modulation classification few-shot learning meta-learning transformer unseen dataset |
| title | Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification |
| title_full | Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification |
| title_fullStr | Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification |
| title_full_unstemmed | Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification |
| title_short | Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification |
| title_sort | meta transformer a meta learning framework for scalable automatic modulation classification |
| topic | Automatic modulation classification few-shot learning meta-learning transformer unseen dataset |
| url | https://ieeexplore.ieee.org/document/10388303/ |
| work_keys_str_mv | AT jungikjang metatransformerametalearningframeworkforscalableautomaticmodulationclassification AT jisungpyo metatransformerametalearningframeworkforscalableautomaticmodulationclassification AT youngilyoon metatransformerametalearningframeworkforscalableautomaticmodulationclassification AT jaehyukchoi metatransformerametalearningframeworkforscalableautomaticmodulationclassification |