微型电脑应用2025，Vol.41Issue(3)：286-290,295,6.
基于BaPCA-CSP的噪声稳健无线电信号识别方法
A Noise Robust Radio Signal Recognition Method Based on BaPCA-CSP
林伟婷1
作者信息
- 1. 惠州工程职业学院,信息工程学院,广东,惠州 516000
- 折叠
摘要
Abstract
Traditional radio signal recognition methods based on single dimensional features have problems such as low recogni-tion accuracy and poor noise robustness.Thus,a noise robust radio signal recognition method based on Bayesian principal com-ponent analysis(BaPCA)combined with common spatial pattern(CSP)is proposed.BaPCA is used to decompose the radio signal to achieve noise suppression and automatically determine the number of principal components,to extract the large eigen-values of the covariance matrix.The principal components obtained by BaPCA are used as the multi-channel input data of CSP for analysis,and the spatial characteristics are extracted.Large eigenvalues and spatial features are combined to form eigenvec-tors,and support vector machine(SVM)is used for classification and judgment.The experimental results based on simulation data show that the proposed method can achieve an average correct recognition rate of better than 93.5％for six radio signals including BPSK,4PSK,8QAM,64QAM,4PAM and 8PAM,and can still achieve recognition results of better than 90％when the SNR is higher than-2dB.关键词
无线电监测/贝叶斯主成分分析/特征提取/模式识别/共空间模式Key words
radio monitoring/Bayesian principal component analysis/feature extraction/pattern recognition/common spatial pattern分类
计算机与自动化引用本文复制引用
林伟婷..基于BaPCA-CSP的噪声稳健无线电信号识别方法[J].微型电脑应用,2025,41(3):286-290,295,6.
