Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams
Оценка отношения сигнал/шум на основе глубокого обучения с использованием диаграмм созвездий
2020-11-06
SCID: 54.1/ymjuuevk
Discuss with AI
AlexNetInceptionV1SNR estimationVGG16constellation diagramsdeep learninglow SNR scenarios
Figures from the paper
Abstract (AI)
Signal-to-noise ratio (SNR) estimation is a fundamental task of spectrum management and data transmission. Existing methods for SNR estimation usually suffer from significant estimation errors when SNR is low. This paper proposes a deep learning (DL) based SNR estimation algorithm using constellation diagrams. Since the constellation diagrams exhibit different patterns at different SNRs, the proposed algorithm achieves SNR estimation via constellation diagram recognition, which can be easily handled based on DL. Three DL networks, AlexNet, InceptionV1, and VGG16, are utilized for DL based SNR estimation. Experimental results show that the proposed algorithm always performs well, especially in low SNR scenarios.
Key Findings
1
A deep learning-based algorithm for SNR estimation using constellation diagrams is proposed, leveraging pattern differences across SNRs for recognition.
2
Framing SNR estimation as constellation diagram recognition enables handling the task easily with existing deep learning models.
3
The proposed DL-based method consistently performs well across conditions and shows particularly strong performance in low SNR scenarios.
4
Three CNN architectures—AlexNet, InceptionV1, and VGG16—are applied to perform SNR estimation from constellation diagrams.
Research Object
Constellation diagrams of received communication signals used for SNR estimation
Research Subject
Deep-learning-based estimation of signal-to-noise ratio (SNR) by recognizing constellation diagram patterns, including performance in low-SNR scenarios using AlexNet, InceptionV1, and VGG16
Publication Details
Publication Date
2020-11-06
Journal
Publisher
ISSN
Cited by
32
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest