ELMAN神经网络

做数据处理，比如做智能诊断样本创建的时候， 如果采集信息有限，但数据量又很大， 可以选择将原始信号就行降采样，来获得更多更可靠的样本(Good collection of information is limited, but the amount of data is so big occasion)

This code for detection cars in traffic in matlab

与“船舶轴系的振动与控制分析”那篇论文相对应的MATLAB程序，其中包含“纵向振动”的，与“扭转振动”的！ (And" the ship shafting vibration analysis and control of" the paper corresponding to the MATLAB program, which contains the" longitudinal", and" torsional vibration"!)

字符识别 用卷积神经网络识别A-Z26个英文字母(Character recognition using convolution neural network A-Z26 letters)

BP神经网络实现测试数据预测(将训练集与测试集数据进行归一化 建立BP神经网络，并训练；利用训练好的BP神经网络对测试集中的23个样本的抗压强度进行预测；输出结果并绘图)(BP neural network to predict the test data (the training set and test data set is normalized the BP neural network and training use of the trained BP neural network on the compressive strength of 23 samples in the test set prediction output results and drawing))

HHT变换中用于边际谱与FFT比较的一个源码。本人亲试，出的图形基本满足要求。你可以下来看看。(HHT marginal spectrum for the transformation of a source compared with the FFT. I pro-test, the graphics basically meet the requirements. You can look down.)

说明：  这是一个基于人脸识别的双边2DLDA程序，其中每人随机选9个做训练，1个做测试，作20次后平均(This is a bilateral 2DLDA procedures based on face recognition, in which each of 9 randomly selected for training, one to do testing for 20 times the average)

针对工业控制过程中的实际问题，对神经网络预测控制进行了深入的研究，提出 了两种新的智能预测控制算法。并结合混合仿真平台，以平台中非线性单变量与多变量系 统为控制对象，将部分算法应用于实际控制中。-For industrial control in the process of practical problems, neural network predictive control of an in-depth research, we propose two new intelligent predictive control algorithm. Combined with hybrid simulation platform to platform non-linear single-variable and multi-variable system for the control of objects, some of the actual control algorithm is applied.

code OFDM Matlab use in MIMO

里面包括matlab界面编程的一些基础知识 很有用 尤其对于初学者(Which includes some basic knowledge of Matlab programming interface is useful especially for beginners)