混沌和神经网络相结合预测短波通信频率参数

为提高短波通信的可靠性 ,提出了一种将混沌和神经网络相结合的方法预测短波通信频率参数。利用混沌方法重构相空间系统吸引子 ,用前向多层神经网络拟合吸引子上的全局整体映射 ,构成混合预测模型。实验结果表明 ,将此混合模型用于预测短波通信频率参数如 F2 层临界频率 ffo F 2 ,能达到较好的预测效果 ,可以应用到实际预测系统中。还将基于奇异值分解的噪声消减滤波算法应用到数据预处理中 ,预测结果表明了这种办法能提高预测精度

Prediction of frequency parameters in short wave radio communications based on chaos and neural networks

The reliability of short wave communication can be improved using a hybrid method for predictions based on chaos phase reconstruction and neural networks to predict frequency parameters. This article presents the use of the chaos method to reconstruct attractors in phase spaces and a multi layer feed forward neural network to fit the attractor's global map, to construct a hybrid prediction model. Experimental results show that the hybrid model provides goods predictions and has promising applications. This article also shows the efficiency of a noise suppressing method based on single value decomposition (SVD).