Improved automatic modulation recognition using deep learning with additive attention
Automatic Modulation Recognition (AMR) is a critical task in modern communication systems, enabling applications such as cognitive radio, spectrum monitoring, and IoT networks. This paper proposes ICRNNA, a novel deep learning model that integrates Convolutional Neural Networks (CNNs), Bidirectional...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025008606 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850215984052305920 |
|---|---|
| author | Noureddine El-Haryqy Anass Kharbouche Hamza Ouamna Zhour Madini Younes Zouine |
| author_facet | Noureddine El-Haryqy Anass Kharbouche Hamza Ouamna Zhour Madini Younes Zouine |
| author_sort | Noureddine El-Haryqy |
| collection | DOAJ |
| description | Automatic Modulation Recognition (AMR) is a critical task in modern communication systems, enabling applications such as cognitive radio, spectrum monitoring, and IoT networks. This paper proposes ICRNNA, a novel deep learning model that integrates Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an attention mechanism to achieve state-of-the-art performance in AMR tasks. The proposed model is evaluated on the RadioML2016.10a and RadioML2016.10b datasets, demonstrating superior accuracy, computational efficiency, and robustness, particularly in low Signal-to-Noise Ratio (SNR) environments. Through extensive ablation studies, we highlight the contributions of each component, showing that the combination of CNNs, BiLSTMs, and attention mechanisms significantly enhances performance. Comparative experiments against state-of-the-art models, including ResNet, MCLDNN, and CNN-BiLSTM-DNN, reveal that ICRNNA achieves the highest accuracy (63.24% on RadioML2016.10a and 65.39% on RadioML2016.10b) and outperforms baseline models in computational efficiency, with only 48.42 MFLOPs and 0.79 million parameters. The results underscore the model's suitability for real-time applications in dynamic and noisy environments. This work advances the field of AMR by providing a robust, efficient, and high-performing solution for modern communication systems. |
| format | Article |
| id | doaj-art-89bca6106e6144159964bd918625f024 |
| institution | OA Journals |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-89bca6106e6144159964bd918625f0242025-08-20T02:08:27ZengElsevierResults in Engineering2590-12302025-06-012610478310.1016/j.rineng.2025.104783Improved automatic modulation recognition using deep learning with additive attentionNoureddine El-Haryqy0Anass Kharbouche1Hamza Ouamna2Zhour Madini3Younes Zouine4Corresponding author.; Department Electrical and Telecommunication, Laboratory of Advanced Systems Engineering (ISA), National School of Applied Sciences (ENSA), Ibn Tofail University, Kenitra, 14000, MoroccoDepartment Electrical and Telecommunication, Laboratory of Advanced Systems Engineering (ISA), National School of Applied Sciences (ENSA), Ibn Tofail University, Kenitra, 14000, MoroccoDepartment Electrical and Telecommunication, Laboratory of Advanced Systems Engineering (ISA), National School of Applied Sciences (ENSA), Ibn Tofail University, Kenitra, 14000, MoroccoDepartment Electrical and Telecommunication, Laboratory of Advanced Systems Engineering (ISA), National School of Applied Sciences (ENSA), Ibn Tofail University, Kenitra, 14000, MoroccoDepartment Electrical and Telecommunication, Laboratory of Advanced Systems Engineering (ISA), National School of Applied Sciences (ENSA), Ibn Tofail University, Kenitra, 14000, MoroccoAutomatic Modulation Recognition (AMR) is a critical task in modern communication systems, enabling applications such as cognitive radio, spectrum monitoring, and IoT networks. This paper proposes ICRNNA, a novel deep learning model that integrates Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an attention mechanism to achieve state-of-the-art performance in AMR tasks. The proposed model is evaluated on the RadioML2016.10a and RadioML2016.10b datasets, demonstrating superior accuracy, computational efficiency, and robustness, particularly in low Signal-to-Noise Ratio (SNR) environments. Through extensive ablation studies, we highlight the contributions of each component, showing that the combination of CNNs, BiLSTMs, and attention mechanisms significantly enhances performance. Comparative experiments against state-of-the-art models, including ResNet, MCLDNN, and CNN-BiLSTM-DNN, reveal that ICRNNA achieves the highest accuracy (63.24% on RadioML2016.10a and 65.39% on RadioML2016.10b) and outperforms baseline models in computational efficiency, with only 48.42 MFLOPs and 0.79 million parameters. The results underscore the model's suitability for real-time applications in dynamic and noisy environments. This work advances the field of AMR by providing a robust, efficient, and high-performing solution for modern communication systems.http://www.sciencedirect.com/science/article/pii/S2590123025008606Automatic modulation recognitionBidirectional long short-term memory networksConvolutional neural networksDeep learningEnhanced attention mechanismSignal-to-noise ratio |
| spellingShingle | Noureddine El-Haryqy Anass Kharbouche Hamza Ouamna Zhour Madini Younes Zouine Improved automatic modulation recognition using deep learning with additive attention Results in Engineering Automatic modulation recognition Bidirectional long short-term memory networks Convolutional neural networks Deep learning Enhanced attention mechanism Signal-to-noise ratio |
| title | Improved automatic modulation recognition using deep learning with additive attention |
| title_full | Improved automatic modulation recognition using deep learning with additive attention |
| title_fullStr | Improved automatic modulation recognition using deep learning with additive attention |
| title_full_unstemmed | Improved automatic modulation recognition using deep learning with additive attention |
| title_short | Improved automatic modulation recognition using deep learning with additive attention |
| title_sort | improved automatic modulation recognition using deep learning with additive attention |
| topic | Automatic modulation recognition Bidirectional long short-term memory networks Convolutional neural networks Deep learning Enhanced attention mechanism Signal-to-noise ratio |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025008606 |
| work_keys_str_mv | AT noureddineelharyqy improvedautomaticmodulationrecognitionusingdeeplearningwithadditiveattention AT anasskharbouche improvedautomaticmodulationrecognitionusingdeeplearningwithadditiveattention AT hamzaouamna improvedautomaticmodulationrecognitionusingdeeplearningwithadditiveattention AT zhourmadini improvedautomaticmodulationrecognitionusingdeeplearningwithadditiveattention AT youneszouine improvedautomaticmodulationrecognitionusingdeeplearningwithadditiveattention |