bayesleaterror

％ PURPOSE : Demonstrate the differences between the following filters on the same problem: ％ ％ 1) Extended Kalman Filter (EKF) ％ 2) Unscented Kalman Filter (UKF) ％ 3) Particle Filter (PF) ％ 4) PF with EKF proposal (PFEKF) ％ 5) PF with UKF proposal (PFUKF)( PURPOSE: Demonstrate the differences between the following filters on the same problem: 1) Extended Kalman Filter (EKF) 2) Unscented Kalman Filter (UKF) 3) Particle Filter (PF) 4) PF with EKF proposal ( PFEKF) 5) PF with UKF proposal (PFUKF))

基于matlab实现的循环谱估计算法，可以对具有循环平稳特点的信号进行参数估计，如直扩信号和周期调制信号(Matlab-based spectrum estimation algorithm to achieve the cycle, you can have the characteristics of the signal cyclostationary parameter estimation, such as the DS signal and the periodic modulation)

轮轨冲击信号的小波分析matlab程序,程序中H5V20zrail为轮轨冲击信号输入数据。(Wheel-rail impact of wavelet analysis matlab program, the program H5V20zrail impact signal for the wheel-rail input data.)

IndependentComponentanalysis,用法详见文件夹中的content.m，关键能运行(IndependentComponentanalysis, usage see folder content.m, the key to run)

fft program for 512 point with overlap of 50

用matlab编写的程序，关于MATLAB图像处理的中计算图像的欧拉数。(Matlab program, about calculation in matlab image processing of the euler number of image。)

为sinudoidal模型的AIC阶估计.AIC信息准则即Akaike information criterion，是衡量统计模型拟合优良性的一种标准，又由于它为日本统计学家赤池弘次创立和发展的，因此又称赤池信息量准则。它建立在熵的概念基础上，可以权衡所估计模型的复杂度和此模型拟合数据的优良性。 在一般的情况下，AIC可以表示为： AIC=2k-2ln(L) 其中：k是参数的数量，L是似然函数。 假设条件是模型的误差服从独立正态分布。 让n为观察数，RSS为剩余平方和，那么AIC变为： AIC=2k+nln(RSS/n) 增加自由参数的数目提高了拟合的优良性，AIC鼓励数据拟合的优良性但是尽量避免出现过度拟合(Overfitting)的情况。所以优先考虑的模型应是AIC值最小的那一个。赤池信息准则的方法是寻找可以最好地解释数据但包含最少自由参数的模型。(AIC order estimation for sinudoidal model)

用MATLAB进行预测控制的仿真 大家可以参考一下(Using MATLAB simulation to predict the control we can refer to)

说明：  基于matlab语言编写的维纳滤波与自适应滤波中LSM和RLS两种算法的仿真程序(Matlab language based on Wiener filtering and the RLS adaptive filtering in the LSM and the simulation program the two algorithms)

Principle component Analysis based face recognition system