Answers are grounded in this paper and cite their sources.
In vehicle-to-vehicle (V2V) communication systems, the signal-to-noise ratio (SNR) at the receiver vehicle varies significantly owing to dynamic channel conditions. These variations affect the reliability of data transmission, making it essential to adapt the modulation scheme according to the prevailing SNR. Therefore, accurate SNR-Modulation classification has become a promising solution for enabling adaptive modulation in a vehicular communication environment. To address this problem, we propose a deep learning-based approach for the joint classification of SNR ranges and modulation schemes. The proposed framework employs a pre-defined convolutional neural network (CNN), Visual Geometry Group (VGG19) architecture with additional layers to extract discriminative features from constellation diagrams. A CNN-based framework for SNR-Modulation classification was developed, considering digital modulation techniques such as binary phase-shift keying (BPSK) and quadrature PSK (QPSK) under SNR levels ranging from 0 to 10 dB. The proposed CNN model was built using a dataset comprising 8400 constellation diagrams that incorporated various amplitude and phase imbalances to replicate the real-world conditions. The model classified four distinct SNR-Modulation classes: 0 ≤ SNR < 5 dB:BPSK (Class 1), 0 ≤ SNR < 5 dB:QPSK (Class 2), 5 ≤ SNR ≤ 10 dB:BPSK (Class 3), and 5 ≤ SNR ≤ 10 dB:QPSK (Class 4). The proposed model achieved an accuracy of 98.21%, with precision, recall, and F1-score values of 98% and an AUC of 98%.
No takes yet. Share an insight, caveat, or question.
Sairam et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: