仿照着《小波去噪中软硬阈值的一种改良折衷法》一文写的程序，对比了软、硬以及软硬阈值折衷法的信噪比及均方根误差。仿真出来之后，原信号的信噪比是负的，不知道为什么？均方根误差的值也比较大，不知何解？信噪比和均方根误差是参照《基于matlab的小波去噪仿真》：吴伟，《信息与电子工程》 一文写的-Modeled on the written procedures of the hard and soft threshold wavelet de-noising an improved compromise " , compared to the soft and hard compromise between the hard and soft threshold signal-to-noise ratio and root mean square error. Out of the simulation, the signal-to-noise ratio of the original signal is negative, do not know why? The value of the root mean square error is relatively large, do not know why? Signal-to-noise ratio and root mean square error with reference to the wavelet denoising matlab-based simulation: Wu Wei, " Information and Electronic Engineering"　written