论文部分内容阅读
在Cohen类时频分布中,为使减小交叉项与保持高的时频聚集性二者之间达到最佳折中,提出了一种基于三阶Rényi熵的核参数优化算法.根据三阶Rényi熵对交叉项的近似不变性,通过搜索三阶Rényi熵随核参数变化曲线下降由快变慢的转折点,可以获得最优核参数.理论分析和仿真结果表明:根据三阶Rényi熵对核参数进行优化,可以使核函数与信号达到最佳匹配,从而得到高性能的时频分布.
In the Cohen-like time-frequency distribution, an optimal kernel parameter optimization algorithm based on the third-order Rényi entropy is proposed to achieve the best compromise between reducing the crossover term and maintaining high time- Rényi entropy to the approximate invariance of the crossover term, the optimal kernel parameters can be obtained by searching the third-order Rényi entropy as the curve of nuclear parameter changes from fast to slow turning point.Theoretical analysis and simulation results show that according to the third-order Rényi entropy to the nucleus The parameters are optimized to match the kernel function with the signal to get the high-performance time-frequency distribution.