在网络异常检测中,为了提高对异常状态的检测率，降低对正常状态的误判率,本文提出一种基于量子粒子群优化算法训练小波神经网络进行网络异常检测的新方法。利用用量子粒子群优化算法(QPSO)训练小波神经网络,将小波神经网络(WNN)中的参数组合作为优化算法中的一个粒子,在全局空间中搜索具有最优适应值的参数向量。

-This paper presents a new method of network anomaly detection based on quantum particle swarm optimization algorithm to train the wavelet neural network in order to improve the rate of detection of the abnormal state and reduce the false positive rate for normal state in the network anomaly detection. Quantum particle swarm optimization algorithm (QPSO) training wavelet neural network, the combination of parameters of the wavelet neural network (WNN) as a particle optimization algorithm search parameter vector with the best fitness value in the global space.