Transformer Model Embedding Dual Stream for Modulation Classification of Short Signal Samples
ACM Transactions on Intelligent Systems and Technology · 30.06.2026 · 17 (3) · 1-25
DOI: 10.1145/3770082 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 20.03.2026. Verfasst von Thien-Thanh Dao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land Infrastructure and Transport, National Research Foundation of Korea (NRF) grant funded by the Korea government, Institute of Information & Communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Deve….
Abstract (Originalsprache)
Automatic modulation classification (AMC) is a critical task in modern communication systems, particularly under diverse signal conditions and limited data scenarios. Existing transformer-based AMC models often rely on single-stream architectures and uniform input formats, which limit their effectiveness in capturing rich signal features. To address these limitations, we propose DTNet, a novel transformer-based dual-stream network designed for efficient and accurate modulation classification. DTNet introduces two key innovations: (1) a scale feature and extension (SFE) block that applies a scaling function to transform signals into a structured output map, followed by an extension module that reconstructs the signal into a square matrix and integrates a response map using adaptive filters; and (2) a convolutional stream that extracts discriminative features from multi-scale signal representations. Furthermore, a modified feature embedding to leverage the transformer architecture is introduced to capture global dependencies and contextual information from the input signal, thereby enhancing the modulation classification accuracy. Experimental results show that DTNet achieves superior performance on benchmark datasets, reaching classification accuracies of 93.4% on RML2016.10A and 94.4% on RML2016.10B, outperforming state-of-the-art deep learning methods while maintaining lower computational complexity. The source code is available at https://github.com/daothanh2011/DTNet .
Förderung
- Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land Infrastructure and Transport
- National Research Foundation of Korea (NRF) grant funded by the Korea government
- Institute of Information & Communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Deve…
- grant funded by the Korea government
- Institute of Information & Communications Technology Planning & Evaluation (IITP)-ITRC (Information Technology Research Center) grant funded by the Korea gover…
Zitieren
APA
Dao, T., Pham, Q., Huynh-The, T., & Hwang, W. (2026). Transformer Model Embedding Dual Stream for Modulation Classification of Short Signal Samples. ACM Transactions on Intelligent Systems and Technology, 17(3), 1-25. https://doi.org/10.1145/3770082
Vancouver
Dao T, Pham Q, Huynh-The T, Hwang W. Transformer Model Embedding Dual Stream for Modulation Classification of Short Signal Samples. ACM Transactions on Intelligent Systems and Technology. 2026;17(3):1-25. doi:10.1145/3770082
BibTeX
@article{Dao2026,
author = {Dao, Thien-Thanh and Pham, Quoc-Viet and Huynh-The, Thien and Hwang, Won-Joo},
title = {Transformer Model Embedding Dual Stream for Modulation Classification of Short Signal Samples},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2026},
volume = {17},
number = {3},
pages = {1--25},
doi = {10.1145/3770082}
}
EUVIMED