.png){kind=icon}
返回
Automatic Modulation Classification Based on a Dynamic Graph Architecture
.png){kind=icon}
OA
AI
DOI：10.3390/app152111782.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As the Internet of Things (IoT) expands and spectrum resources become increasingly scarce, Automatic Modulation Classification (AMC) has become critical for enabling dynamic spectrum access, interference mitigation, and spectrum monitoring without coordination or prior signaling. Most deep learning-based AMC methods (e.g., CNNs, LSTMs, Transformers) operate in Euclidean spaces and therefore overlook the non-Euclidean relationships inherent in modulated signals. We propose KGNN, a graph-based AMC architecture that couples a KNN-driven graph representation with GraphSAGE convolutions for neighborhood aggregation. In the KNN stage, each feature vector is connected to its nearest neighbors, transforming temporal signals into structured graphs, while GraphSAGE extracts relational information across nodes and edges for classification. On the RML2016.10b dataset, KGNN attains an overall accuracy of 64.72%, outperforming strong baselines (including MCLDNN) while using only one-eighth the number of parameters used by MCLDNN and preserving fast inference. These results highlight the effectiveness of graph convolutional modeling for AMC under practical resource constraints and motivate further exploration of graph-centric designs for robust wireless intelligence.
Keyword:
automatic modulation classification
deep learning
KNN graph attention
lightweight
期刊
A
IF:
2.5
论文数:
7.6K
被引数:
4
机构
引用论文
Deep Learning-Based Signal Modulation Identification in OFDM Systems基于深度学习的OFDM系统信号调制识别.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏A novel demodulation system for base band digital modulation signals based on the deep long short-term memory model基于深长短期记忆模型的基带数字调制信号解调系统APPLIED ACOUSTICS
APPLIED ACOUSTICSIF3.6
PREAI
分享收藏分享收藏
查看更多内容