CMX469

Predication with RBF neural network BY hossein dehghan

固定个数，不动点ICA算法的语音信号盲源分离(A fixed number of fixed point ICA algorithm speech signal blind source separation)

BP神经网络：是一种按误差逆传播算法训练的多层前馈网络，是目前应用最广泛的神经网络模型之一。BP网络能学习和存贮大量的输入-输出模式映射关系，而无需事前揭示描述这种映射关系的数学方程。它的学习规则是使用最速下降法，通过反向传播来不断调整网络的权值和阈值，使网络的误差平方和最小。BP神经网络模型拓扑结构包括输入层（input）、隐层(hide layer)和输出层(output layer)。(BP neural network: a Press the front back propagation algorithm to train multilayer feedforward network is one of the most widely used neural network model. BP network can learn and store large amounts of input- output mode mappings without prior reveal mathematical equations that describe this map. It' s learning rule is to use the steepest descent method, through a reverse spread to constantly adjust the network weights and thresholds, so that the minimum squared error of the network. BP neural network topology, including the input layer (input), hidden layer (hide layer) and output layer (output layer).)

关于智能天线music算法的matlab仿真代码(About the intelligent antenna music of matlab simulation algorithm code )

Fiber Optic Telecommunication

由磁悬浮小球的状态空间模型计算出其鲁棒控制器，并在simulink模型中对鲁棒控制器的性能进行了验证。(Magnetic levitation ball from the state-space model to calculate the robust controller and in simulink model for robust controller performance is verified.)

说明：  MATLAB tutorial (1) introduction, interface and help, basic commands and statements, M files and M functions (teacher zhou luwen

matlab 程序函数列表 内涵常用数学、绘图的呢过分析函数名称(Matlab function list)

我下的一本关于机械故障诊断的电子书，对初学者入门比较好(I was under a mechanical fault diagnosis on the books, started better for beginners)

说明：  广义S变换，具有良好的分析特性和局部的时频的特性，而谱白化和反褶积也是高分辨处理中的一种有效的频率补偿手段，本文利用他们的他们的各自优点，使二者结合起来，该方法对地震信号用广义S变换分解，进行频率补偿再进行重构，得到高分辨率时间信号。  理论模型试算和实际地震处理结果证明了该方法的正确性和有效性。  关键词：广义S变换，谱白化，高分辨处理(Generalized S transformation (GST) has good analyzing feature and good Time-frequency localization,. spectrum whitening and deconvolution is an Effective tool for frequency compensation , Utilizing both their advantages , The method first conducts GST decomposition to seismic data,. doing high frequency compensation and then reconstruction to get high resolution seismic to get a high-resolution time signal. Theoretic modeling and field seismic data processing results has proved this method corrected and effective . )