neuronet-BP

Script to use it in Intouch, on estimation plant

sobol 采样方法的matlab程序，全局敏感性分析必备，希望有帮助！~(sobol sampling method matlab program, global sensitivity analysis necessary, Hope that helps! ~)

说明：  本文提出一种在原始视频DCT(离散余弦变换)与SVD(奇异值分解)域自适应嵌入水印的算法。算法首先将视频流分割成一个个场景,场景中的视频图像被变换到DCT-SVD域中,水印量化嵌入在最大奇异上,实现了水印盲检测。同时实验证明该算法在满足透明性要求下也满足一定的鲁棒性要求,能够抵抗低通滤波、中值滤波、椒盐噪声、高斯噪声、H.264压缩攻击以及统计攻击和帧剪切等攻击。(This paper presents an original video in the DCT (Discrete Cosine Transform) and SVD (singular value decomposition) algorithm for adaptive watermark embedding. Firstly, a video stream is divided into scenes, scenes of the video image is converted to the DCT-SVD domain, the watermark embedded in the largest singular quantification, the realization of the watermark signal. Furthermore, the experiments show that the algorithm meet the transparency requirements are met under certain robustness requirements, can resist the low-pass filtering, median filtering, salt and pepper noise, Gaussian noise, H.264 compression attacks and attacks and frame shear statistics attack.)

本程序可实现ARMA的仿真结束估计，用matlab编写(This procedure enables the simulation end of the ARMA estimates prepared using matlab)

BOOT PI CLOSE LOOP CONTOLLER

这是第二能量熵的matlab代码，光纤陀螺输出误差的allan方差分析，小波包分析提取振动信号中的特征频率。( This is the second energy entropy matlab code, allan FOG output error variance analysis, Wavelet packet analysis to extract vibration signal characteristic frequency.)

说明：  几个神经网络的算法实例，及相关优化，希望对了解神经网络有帮助(Several examples of neural network algorithms, and related optimization, we want to understand the neural network has helped)

通过并行压缩进行二维信号压缩，提出了一种利用并行压缩传感技术对二维信号进行压缩的新方案。根据这个原理，译码器的重新构造可以并行进行。通过对二维信号进行某些排列，可以确保所有列具有大致相同的密度级别，并且可以使用相同的测量矩阵进行采样。这样可以避免二维信号的矢量化，从而大大减小测量矩阵的尺寸。我们证明，如果排列良好，重建均方误差的上限会更紧。为了说明这一方案，我们将其应用于视频压缩并使用不同帧的排列有两种：参考帧的基于Z字形扫描的排列和非参考帧的基于块测试的排列。仿真结果表明，在相同的压缩比下，峰值信噪比比比在无置换情况下可提高3-7db左右。(we propose a new scheme to compress 2D signals using parallel compressed sensing. According to this seheme, the reeonstruction at the decoder can be performed in parallel. By performing certain permutation on a 2D signal, all columns are insured to have approximately the same density level and can be sampled using the same measurement matrix. In this way, vectorization of a 2D signal can be avoided, and thus the size of the measurement matrix can be dramatically reduced. We prove that with a good permutation, we can have a tighter upper bound on reconstruction mean square error. To illustrate this scheme, we apply it to video compression and use two kinds of permutations for different frames: the zigzag-scanbased permutation for reference frames and the block-test-based permutation for non-reference frames. Simulation results show that under the same compression ratio, the peak signal-to-noise ratio can be improved by approximately 3-7 dB compared to the case without permutation.)

quantization by matlab

gradient descent in matlab