VT-MCNet: High-Accuracy Automatic Modulation Classification Model Based on Vision Transformer
IEEE Communications Letters · 2024-01 · 28 (1) · 98-102
DOI: 10.1109/lcomm.2023.3336985 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2024-01. Verfasst von Thien-Thanh Dao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 14 Literaturangaben. Gefördert von: “Leaders in INdustry-university Cooperation 3.0” Project, Ministry of Education and National Research Foundation of Korea.
Abstract (Originalsprache)
Cognitive radio networks’ evolution hinges significantly on the use of automatic modulation classification (AMC). However, existing research reveals limitations in attaining high AMC accuracy due to ineffective feature extraction from signals. To counter this, we propose a vision-centric approach employing diverse kernel sizes to augment signal extraction. In addition, we refine the transformer architecture by incorporating a dual-branch multi-layer perceptron network, enabling diverse pattern learning and enhancing the model’s running speed. Specifically, our architecture allows the system to focus on relevant portions of the input sequence, thus, it improves classification accuracy for both high and low signal-to-noise regimes. By utilizing the widely recognized DeepSig dataset, our pioneering deep model, termed as VT-MCNet, outshines prior leading-edge deep networks in terms of classification accuracy and computational costs. Notably, VT-MCNet reaches an exceptional cumulative classification rate of up to 99.24%, while the state-of-the-art method, even with higher computational complexity, can only achieve 99.06%.
Förderung
- “Leaders in INdustry-university Cooperation 3.0” Project
- Ministry of Education and National Research Foundation of Korea
Zitieren
APA
Dao, T., Noh, D., Pham, Q., Hasegawa, M., Sekiya, H., & Hwang, W. (2024). VT-MCNet: High-Accuracy Automatic Modulation Classification Model Based on Vision Transformer. IEEE Communications Letters, 28(1), 98-102. https://doi.org/10.1109/lcomm.2023.3336985
Vancouver
Dao T, Noh D, Pham Q, Hasegawa M, Sekiya H, Hwang W. VT-MCNet: High-Accuracy Automatic Modulation Classification Model Based on Vision Transformer. IEEE Communications Letters. 2024;28(1):98-102. doi:10.1109/lcomm.2023.3336985
BibTeX
@article{Dao2024,
author = {Dao, Thien-Thanh and Noh, Dae-Il and Pham, Quoc-Viet and Hasegawa, Mikio and Sekiya, Hiroo and Hwang, Won-Joo},
title = {VT-MCNet: High-Accuracy Automatic Modulation Classification Model Based on Vision Transformer},
journal = {IEEE Communications Letters},
year = {2024},
volume = {28},
number = {1},
pages = {98--102},
doi = {10.1109/lcomm.2023.3336985}
}
EUVIMED