back-propagation

QAM信号调制解调的仿真以及解调误码率的比较。(QAM signal modulation and demodulation of the demodulation error rate simulation and comparison.)

The cross-entropy (CE) method attributed to Reuven Rubinstein is a general Monte Carlo approach to combinatorial and continuous multi-extremal optimization and importance sampling. The method originated from the field of rare event simulation, where very small probabilities need to be accurately estimated, for example in network reliability analysis, queueing models, or performance analysis of telecommunication systems. The CE method can be applied to static and noisy combinatorial optimization problems such as the traveling salesman problem, the quadratic assignment problem, DNA sequence alignment, the max-cut problem and the buffer allocation problem, as well as continuous global optimization problems with many local extrema.

说明：  以truetime-1.5为例说明truetime工具箱的安装方法，很实用！！(An example to truetime-1.5 truetime toolbox installation method, it works! !)

image fusion using particle of swarm optimastion

1) 已知x=[1:15], y=[12 34 56 78 99 123 165 198 243 277 353 345 303 288 275], 用多项式进行拟合，给出拟合多项式，(所选拟合多项式阶数不同，拟合结果不同，请你选择适当的阶数进行拟合)，并绘出原始数据点、拟合曲线和95％置信区间（confidence bounds）的图形 . 2) 根据下面数学模型建立仿真模型，并在一个示波器中把它们的波形仿真出来。 (1) are known to x = [1:15], y = [12 34 56 78 99 123 165 198 243 277 353 345 303 288 275], with polynomial fitting, given the polynomial fitting, (the election order polynomial fitting different fitting results to differ, please select the appropriate order of fit), and draw original data points, fitting curve and 95 confidence interval (confidence bounds) graphics .2 ) In accordance with the following mathematical model for the establishment of simulation model, and in an oscilloscope waveform in their simulation out.)

实现fisher判别方法，对标准变量建立判别函数，然后判别位置的变量的类别(Achieve fisher discriminant analysis, discriminant function to establish the standard variables, and then determine the type of the variable position)

运用matlab编写，可用于一维信号压缩，经验证应用效果较好。(Using matlab prepared for one-dimensional signal compression, proven applications better.)

time domain symptom extraction

用黄金分割法来求解函数的极小点，不用求函数的导数，只需进行迭代即可,非精确线搜索技术用于解决极值区间(Golden section method to solve the minimum point of the function, do not seek the derivative of a function, simply iteration can be inexact line search techniques for solving extremal interval)

Channel estimation techniques for OFDM systems based on a pilot arrangement are investigated. Channel estimation based on a comb type pilot arrangement is studied through different algorithms for both estimating the channel at pilot frequencies and interpolating the channel. Channel estimation at pilot frequencies is based on LS and LMS methods while channel interpolation is done using linear interpolation, second order interpolation, low-pass interpolation, spline cubic interpolation, and time domain interpolation. Time-domain interpolation is obtained by passing to the time domain by means of IDFT (inverse discrete Fourier transform), zero padding and going back to the frequency domain by DFT (discrete Fourier transform). In addition, channel estimation based on a block type pilot arrangement is performed by sending pilots in every sub-channel and using this estimation for a