基于PCA与主动学习AdaBoost的频谱感知算法

针对认知网络中各低信噪比环境下主用户信号检测率偏低的问题,提出一种基于主成分分析和主动学习AdaBoost的主用户信号频谱感知算法.该算法首先采用主成分分析算法对信号特征参数进行提取,获得信号的主成分,之后利用主动学习算法通过多次迭代抽样,获取有利于提高分类性能的样本,并对AdaBoost分类器进行训练,最后利用训练完成的AdaBoost分类器对待测信号进行分类检测.仿真实验表明,在各低信噪比情况下与ANN和MME算法相比较,所提算法具有较高的分类感知性能,有效地实现了对主用户信号的频谱感知.

Spectrum Sensing Algorithm Based on PCA and Active Learning AdaBoost

In order to solve the problem of the low accuracy rate of the primary user detection in the wireless channel environment,a method based on principal component analysis (PCA) and active learning AdaBoost for the primary user spectrum sensing of cognitive radio environment in the case of low SNR(signal noise ratio) is proposed.First a set of cyclic spectrum features are calculated,and the principal component analysis (PCA) is applied to extract the most discriminant feature vector.Then the samples that help to improve classification performance can be obtained and training samples are formed through repetitious iteration sampling by utilizing the active learning algorithm.AdaBoost classifiers are generated by repetitious training using the training samples.Finally,the trained AdaBoost is used to detect the primary user.Test result shows that the proposed algorithm is not affected by uncertainty factors of noise and has high performance to classification detection compared with ANN and maximum-minimum eigenvalue (MME).