基于量子粒子群优化极限学习机的频谱感知算法

A Spectrum Sensing Algorithm Based on QuantumParticle Swarm Optimization and ExtremeLearning Machine

针对无线信道环境中低信噪比情况下主用户信号检测率较低的问题,提出了一种基于量子粒子群优化极限学习机(ELM)算法的认知无线电网络频谱感知方法。针对极限学习机算法的特点通过量子粒子群算法(QPSO)优化极限学习机参数,并构建引入结构风险思想的QPSO-ELM模型,降低算法的经验风险提高模型的泛化能力,提高算法的频谱感知性能。仿真实验表明,与人工神经网络(ANN)、支持向量机(SVM)和极限学习机(ELM)三种机器学习算法,在信噪比为-15 dB时的频谱感知性能进行比较,分别提高了16%、28%、9%,仿真证明所提算法在低信噪比情况下具有较高的性能,可有效地实现对主用户信号的频谱感知。

A spectrum sensing method for cognitive radio networks based on quantum particle swarm optimization(QPSO)and extreme learning machine(ELM)algorithm is proposed to solve the problem of low detection rate of primary user signals in low SNR wireless channel environment.According to the characteristics of extreme learning machine algorithm,the parameters of extreme learning machine are optimized by quantum particle swarm optimization;and a QPSO-ELM model with structural risk is constructedto reduce the empirical risk of the algorithm and improve the generalization ability of the model,thereby improving the spectrum sensing performance of the algorithm.The simulation results show that comparing the three machine learning algorithms of ANN,SVM and ELM,the performance of spectrum sensing is improved by 16%,28%and 9%respectivelyas SNR is-15 dB.The simulation results show that the proposed algorithm has high performance in low SNR and can effectively realize spectrum sensing of primary user signals.