基于相空间优化近邻点的跳频预测方法研究

Study on Prediction of Frequency-hopping Pattern Based on Optimal Neighbor Pointsin Phase Space

提出了一种基于混沌相空间重构理论的优化近邻点局部线性化跳频预测方法。根据相点的总体分布情况以及预测点与周围相点的加权距离确定近邻点，同时剔除“伪近邻点”，进而确定跳频预测方程。实验结果表明：该方法精度高且稳健，性能显著优于一般的预测方法。

Based on the theory of chaos phase space reconstruction, a local linear forecasting approach on selecting the optimal neighbor points is presented in this paper. Optimal neighbor points are acquired according to general distribution of space points and weighted distances between forecast points and their neighbor points. At the same time, false neighbor points are eliminated, then forecasting expression is gained. Experimental results show that proposed approach is robust and possesses higher prediction precision than that of other methods.