基于LSTM的短波频率参数预测

针对现有短波通信频率参数预测方法操作繁琐、预测精度不足的缺点,首次提出一种基于长短期记忆型循环神经网络（LSTM RNN）的预测方法。通过对电离层参数f0F2数据的分析，利用LSTM在处理时序相关数据时可以长期记忆网络历史数据的优势，对f0F2值进行预测。对比反向传播神经网络（BPNN），LSTM将误差降低了7%，并将均方误差控制在2%以下。研究结果表明：基于LSTM搭建的提前预报5天的f0F2值的模型是可行的且比BP神经网络更适合预测电离层的f0F2值。

A Prediction of Frequency Parameters Based on LSTM for High Frequency Communication

Aimed at the problems that in the existing high frequency communication, the frequency parameter prediction methods are tedious formalities in operation and shortage in precision, this paper presents a prediction model of frequency parameters of short wave communication based on long short term memory recurrent neural networks. This neural network can break through the limitations of traditional neural networks and establish long term correlations on data sequences. The experimental results show that the mean square error (MSE) can be control below 2% and the model reduced the error by 7%. And this method is effective and superior to the traditional prediction method.