A CNN‐BiLSTM–Based Deep Learning Model for CPM Signal Detection
Electronics Letters · 2025-01 · 61 (1)
DOI: 10.1049/ell2.70502 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics Letters, online erschienen am 01.12.2025. Verfasst von Yang He und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
This letter proposes a convolutional neural network–bidirectional long short‐term memory (CNN‐BiLSTM) architecture for continuous phase modulation (CPM) signal detection by optimising the extraction of time‐frequency features and temporal dependencies with reduced complexity. It significantly outperforms the existing maximum likelihood sequence detection (MLSD) and CNN with fully connected layer (CNN‐FC) detectors in higher‐order modulation and multipath scenarios, achieving a 97.99% parameter reduction compared to CNN‐FC. Numerical results confirm its exceptional balance of detection performance and computational efficiency, making it ideal for complex channels and resource‐constrained systems.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
He, Y., Cao, N., Hu, C., & Lu, H. (2025). A CNN‐BiLSTM–Based Deep Learning Model for CPM Signal Detection. Electronics Letters, 61(1). https://doi.org/10.1049/ell2.70502
Vancouver
He Y, Cao N, Hu C, Lu H. A CNN‐BiLSTM–Based Deep Learning Model for CPM Signal Detection. Electronics Letters. 2025;61(1). doi:10.1049/ell2.70502
BibTeX
@article{He2025,
author = {He, Yang and Cao, Ning and Hu, Can and Lu, Hao},
title = {A CNN‐BiLSTM–Based Deep Learning Model for CPM Signal Detection},
journal = {Electronics Letters},
year = {2025},
volume = {61},
number = {1},
doi = {10.1049/ell2.70502}
}
EUVIMED