Kalmantestfenxi

This is a simple program to calculate the output of artificial neural network (ANN) using microcontroller ATMega 32. Assume that the neural architecture is : 2 hidden layers with 4 and 2 neurons respectively and 1 layer output with 1 neuron.This program explains the step how to compute the ANN in off-line mode.Means the weights and biases are already exist (microcontroller is not doing the learning steps). These parameters are produced using MATLAB. Therefore, we have already made the appropriate architecture using MATLAB. The tansig function is use in both of hidden layer. Finally, the neural output will be displayed on LCD port C.

基于MATLAB的模式识别的参数估计的最大似然估计，处理水环境分类问题，共分为5类，最后利用贝叶斯决策得出五类总的识别率。 (Maximum likelihood estimation of parameters of pattern recognition of MATLAB estimation based on classification of water environment treatment problem, is divided into 5 categories, the last use of Bayesian decision obtained five types of the total recognition rate. )

对某些点的一维距离像的MATLAB仿真，通过脉冲压缩实现。(The MATLAB simulation of the one-dimensional distance profile of some points is achieved by pulse compression.)

自适应线谱增强算法通过自适应技术减弱噪声，并增强有用信号的功率谱。(This demonstration illustrates the application of adaptive filters to signal separation using a structure called an adaptive line enhancer (ALE). In adaptive line enhancement, a measured signal x(n) contains two signals, an unknown signal of interest v(n), and a nearly-periodic noise signal eta(n). The goal is to remove the noise signal the measured signal to obtain the signal of interest)

the HF principle for calculating diffraction pattern from pinhole.

this program basically implementation of new scheduling algorithm in NS3 for LTE/4G. it is developed in ns3 which is open source platform used cpp.

梯度下降法的matlab版本实例,带收敛轨迹图。(the steepest descent algorithm with matlab )

说明：  据理论中用于求取Jousselme证据距离案例(According to the case of Jousselme Evidence Distance in theory)

blurring and flat region filtering and noisy image

根据不同的概率仍飞镖的问题, 循环多次计算全中的平均时间(Random Dart)