Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network
In recent years, neural network algorithms have demonstrated tremendous potential for modulation classification. Deep learning methods typically take raw signals or convert signals into time–frequency images as inputs to convolutional neural networks (CNNs) or recurrent neural networks (RNNs). Howev...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/16/7281 |
| _version_ | 1797583238336610304 |
|---|---|
| author | Dong Wang Meiyan Lin Xiaoxu Zhang Yonghui Huang Yan Zhu |
| author_facet | Dong Wang Meiyan Lin Xiaoxu Zhang Yonghui Huang Yan Zhu |
| author_sort | Dong Wang |
| collection | DOAJ |
| description | In recent years, neural network algorithms have demonstrated tremendous potential for modulation classification. Deep learning methods typically take raw signals or convert signals into time–frequency images as inputs to convolutional neural networks (CNNs) or recurrent neural networks (RNNs). However, with the advancement of graph neural networks (GNNs), a new approach has been introduced involving transforming time series data into graph structures. In this study, we propose a CNN-transformer graph neural network (CTGNet) for modulation classification, to uncover complex representations in signal data. First, we apply sliding window processing to the original signals, obtaining signal subsequences and reorganizing them into a signal subsequence matrix. Subsequently, we employ CTGNet, which adaptively maps the preprocessed signal matrices into graph structures, and utilize a graph neural network based on GraphSAGE and DMoNPool for classification. Extensive experiments demonstrated that our method outperformed advanced deep learning techniques, achieving the highest recognition accuracy. This underscores CTGNet’s significant advantage in capturing key features in signal data and providing an effective solution for modulation classification tasks. |
| first_indexed | 2024-03-10T23:36:01Z |
| format | Article |
| id | doaj.art-d026fe2f743841579e2f5497512cb322 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:36:01Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d026fe2f743841579e2f5497512cb3222023-11-19T02:59:22ZengMDPI AGSensors1424-82202023-08-012316728110.3390/s23167281Automatic Modulation Classification Based on CNN-Transformer Graph Neural NetworkDong Wang0Meiyan Lin1Xiaoxu Zhang2Yonghui Huang3Yan Zhu4Key Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaIn recent years, neural network algorithms have demonstrated tremendous potential for modulation classification. Deep learning methods typically take raw signals or convert signals into time–frequency images as inputs to convolutional neural networks (CNNs) or recurrent neural networks (RNNs). However, with the advancement of graph neural networks (GNNs), a new approach has been introduced involving transforming time series data into graph structures. In this study, we propose a CNN-transformer graph neural network (CTGNet) for modulation classification, to uncover complex representations in signal data. First, we apply sliding window processing to the original signals, obtaining signal subsequences and reorganizing them into a signal subsequence matrix. Subsequently, we employ CTGNet, which adaptively maps the preprocessed signal matrices into graph structures, and utilize a graph neural network based on GraphSAGE and DMoNPool for classification. Extensive experiments demonstrated that our method outperformed advanced deep learning techniques, achieving the highest recognition accuracy. This underscores CTGNet’s significant advantage in capturing key features in signal data and providing an effective solution for modulation classification tasks.https://www.mdpi.com/1424-8220/23/16/7281deep learningmodulation classificationgraph neural networktransformer network |
| spellingShingle | Dong Wang Meiyan Lin Xiaoxu Zhang Yonghui Huang Yan Zhu Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network Sensors deep learning modulation classification graph neural network transformer network |
| title | Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network |
| title_full | Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network |
| title_fullStr | Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network |
| title_full_unstemmed | Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network |
| title_short | Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network |
| title_sort | automatic modulation classification based on cnn transformer graph neural network |
| topic | deep learning modulation classification graph neural network transformer network |
| url | https://www.mdpi.com/1424-8220/23/16/7281 |
| work_keys_str_mv | AT dongwang automaticmodulationclassificationbasedoncnntransformergraphneuralnetwork AT meiyanlin automaticmodulationclassificationbasedoncnntransformergraphneuralnetwork AT xiaoxuzhang automaticmodulationclassificationbasedoncnntransformergraphneuralnetwork AT yonghuihuang automaticmodulationclassificationbasedoncnntransformergraphneuralnetwork AT yanzhu automaticmodulationclassificationbasedoncnntransformergraphneuralnetwork |