基于循环平稳PCA和AdaBoost的频谱感知算法

Spectrum Sensing Algorithm Based on Cyclostationary PCA and Ada Boost

针对无线信道环境中各低信噪比情况下主用户信号检测率较低的问题,提出一种基于循环平稳特征主成分分析和Ada Boost的主用户信号频谱感知算法。该算法首先对信号采用循环平稳PCA算法进行特征参数提取,获取信号主成分,并生成训练样本和待测样本,再采用Ada Boost算法分别对有无主用户情况下的信号进行分类检测。仿真实验表明,与人工神经网络和最大最小特征值算法相比较,所提算法在各低信噪比情况下,具有较高的分类检测性能,有效地实现了对主用户信号的感知。

Addressing the low accuracy rate of the primary user detection in the wireless channel environment, a method is proposed based on cy- clostationary principal component analysis （PCA） and AdaBoost for the primary user spectrum sensing of cognitive radio environment in the case of low SNR. In this paper, a set of cyclic spectrum features are first calculated, and the principal component analysis （PCA） is applied to extract the most discriminant feature vector as training samples and testing samples for classification. Finally, the trained AdaBoost is utilized to detect the primary us- er. Test rcsuh shows that the proposed algorithm is not affected by uncertainty factors of noise and has high performance to classification detection com- pared with ANN and maximum-minimum eigen-value （MME）.