GMM模型

一维卡尔曼滤波算法，可以直接使用，通过系统噪声和测量噪声调整灵敏度。(One dimensional Calman filtering algorithm can be directly used to adjust the sensitivity through system noise and measurement noise.)

基于Levenberg-Marquardt的曲线/面拟合(C library for Levenberg-Marquardt least-squares minimization and curve fitting)

最小二乘法(LS)仿真三个参考节点定位一个定位节点，包括仿真参数和过程数据收集(Least squares (LS) simulation of three reference nodes positioning a positioning node, including the simulation parameters and process data collection)

自己总结的一些现阶段用得比较多的尾流计算模型(Some of your summary of present with more drafting calculation model)

自己编的最小二乘参数辨识，已经调试，内附详细程序说明。(Their own series of least-squares parameter identification, has been commissioning, containing detailed description of the procedures.)

用mfc实现计算器的基本操作，支持键盘输入，并保留xp风格,可计算平方，幂，时间显示等操作(With mfc achieve the basic operation of the calculator, support for keyboard input, and retain xp style, calculates the square, power, time display and other operations)

全国研究生数学建模竞赛优秀获奖论文(National Graduate School Mathematical Contest in Modeling outstanding thesis award)

some article about Bayes Thinking

共轭梯度法（Conjugate Gradient）是介于最速下降法与牛顿法之间的一个方法，它仅需利用一阶导数信息，但克服了最速下降法收敛慢的缺点，又避免了牛顿法需要存储和计算Hesse矩阵并求逆的缺点，共轭梯度法不仅是解决大型线性方程组最有用的方法之一，也是解大型非线性最优化最有效的算法之一。 在各种优化算法中，共轭梯度法是非常重要的一种。其优点是所需存储量小，具有步收敛性，稳定性高，而且不需要任何外来参数。(Conjugate gradient method (Conjugate Gradient) is between the steepest descent method between the method and Newton' s method, it takes only a first derivative information, but to overcome the steepest descent method convergence slow shortcomings, but also to avoid the Newton method needs to be stored Hesse and disadvantages of computing inverse matrix and the conjugate gradient method is not only one of the most useful methods to solve large linear equations, solution of large-scale nonlinear optimization is one of the most effective algorithm. In various optimization algorithm, conjugate gradient method is a very important one. The advantage is that a small amount of memory required, with step convergence, high stability, and does not require any external parameters.)

薄板样条，一种很好的拟合曲线的方法。是最近比较常用的拟合方法。(thin plate spline is so nice fitting method. Features: (1) support arbitrary control points (2) allow regularization (3) estimate the warp parameters from corresponding pairs )