jiaoyanshe2

含约束的优化问题求解案例，算法简单，求解很方便实用(Constrained optimization problem solving case, the algorithm is simple, easy to solve, practical)

随机森林的代码实现，如何使用学会只用随机森林进行学习(Random forest code implementation, how to use learning to learn only random forest)

一个案例代码，用最小二乘支持向量机的，预测煤炭量(A case code, using the least squares support vector machine to predict the volume of coal)

LS_SVM 偏最小二乘结合支持向量机(The LS SVM partial least squares and Support Vector Machine)

说明：  通过模型决定系数完成支持向量机参数优化，并建立基于大数据的支持向量机模型实现回归拟合(The parameters of SVM are optimized by the coefficient determined by the model, and the regression fitting is realized by the support vector machine model based on big data)

based classification (SRC) has been widely used for face recognition (FR). SRC first codes a testing sample as a sparse linear combination of all the training samples, and then classifies the testing sample by evaluating which class leads to the minimum representation error. While the importance of sparsity is much emphasized in SRC and many related works, the use of collaborative representation (CR) in SRC is ignored by most literature.

说明：  本实验是利用卡尔曼滤波器实现一维匀加速运动的轨迹跟踪。卡尔曼滤波是一种时域滤波方法，它采用状态空间方法描述系统，算法采用递推机制，数据存储量小，在导航领域有成功的应用。(This experiment is the use of Kalman filter to achieve a one-dimensional constant acceleration of the trajectory tracking. Kalman filter is a time-domain filtering method, which uses state-space description of systems, algorithms using recursive mechanisms, data storage a small amount of success in the navigation area of the application.)

说明：  主要用于Fluent 中风剖面、湍流剖面以及耗散率剖面的开发，应用的是日本的规范。(It is mainly used for the development of fluent stroke profile, turbulence profile and dissipation rate profile, and it is applied to the specifications of Japan.)

替代数据方法（基于相位随机化方法），检验续写的非线性(Surrogate data method (based on random-phase method), non-linear write test)

说明：  在科学与工程计算中，经常遇到求解非线性方程组的问题；非线性方程组在收敛速度及收敛性比线性方程组要差，特别对于非凸的非线性方程组，其求解更是困难。下面简要介绍非线性方程组的三种解法——牛顿法、拟牛顿法、同伦算法，分析三种解法的适用性，并附Matlab原程序。(Scientific and engineering computing, often encounter the problem of solving nonlinear equations speed of convergence of nonlinear equations and linear equations worse than convergence, especially for non-convex nonlinear equations, which is even more difficult to solve . The following briefly describes three solutions to nonlinear equations- Newton method, quasi-Newton method, homotopy method, the applicability of the three solutions, along with Matlab original program.)