SOM

CVPR2008一篇判别训练，多尺度，变形部分建模的实现作者P. Felzenszwalb等，运行于windows环境。(This is an windows implementation of the system described in:P. Felzenszwalb, D. McAllester, D. Ramaman.A Discriminatively Trained, Multiscale, Deformable Part Model.To appear in CVPR 2008.)

Fisherface方法的实现是在PCA数据重构的基础上完成的，首先利用PCA将高维数据投影到低维特征脸子空间，然后再在这个低维特征脸子空间上用LDA特征提取方法得到Fisherface。程序中使用参数寻优的方法来寻找最佳投影维数，以达到比较理想的识别效果。 (The Fisherface method implemented in the PCA data reconstruction based on the completion of the first use of PCA projection of high-dimensional data to a low dimensional feature subspace, and then on the characteristics of low-dimensional subspace LDA feature extraction methods to get the Fisherface. Program parameter optimization method is used to find the best projection dimension, in order to achieve the ideal identification.)

说明：  通过Matlab仿真，对有无信道估计对系统误码率的影响进行了比较，对LS和MMSE估计算法进行比较(Matlab simulation, whether the channel estimation system bit error rate compared with LS and MMSE estimation algorithm compares)

运用firls设计的滤波器进行滤波 运用remez设计的滤波器进行滤波(The use of the filter design firls filter designed to filter the use of Remez filter)

该段matlab可实现自由摆系统的演示。(The segment can be realized matlab free pendulum system demonstration.)

矩形排样的剩余矩形优化算法。在matlab中的实现。(The rectangle layout of the remaining algorithm, MATLAB optimization and efficient use of raw materials )

最近在学习决策树，一个简单的决策树预测模型(Recently in the learning decision tree,A simple decision tree prediction model)

用来判断样本是否线性可分的 用来判断样本是否线性可分的 (ll)

Implementation of Quadrature Amplitude Modulation-Demodulation

三相SVPWM整流逆变，波形还ok，仅供参考，欢迎拍砖(three phase svpwm converter ，it‘s good)