PAM_DS_UWB

pattern classification homework 3

说明：  增量式PID的MATLAB实现 有源代码(Incremental PID of the MATLAB source code to achieve)

edge detection using fuzzy and canny operator

对于一幅彩色图像来说，可以对于三个通道进行分别梯度，然后选取最大值组成一幅梯度图像(color gradient matlab)

说明：  一个LDPC的例程使用matlab编写，可直接运行，信道编码程序(a LDPC the use of Matlab routines prepared to be directly run channel coding procedures)

说明：  使用BSCB方法实现对彩色图像的修补，该方法修补效果很好，另附带原文章，改进算法论文和本人总结文档(using BSCB to inpaint the destoryed picture!)

脉冲反向积分发测试混响程序，数据应该为声压时间信号()

本文采用科研领域广泛应用的、功能强大的MATLAB软件及其仿真工具箱Simulink、Real-time Workshop、xPCTarget研究开发了针丈接轮胎压力监测系统(TPMS)的数据采集与处理系统。 首先利用Simulink工具箱建立TPMS系统所需参数的处理方法仿真模型 然后构建了基于MATLAB/xPCTarget的硬件平台,并结合所建立的仿真模型完成了整个数据采集与处理系统的开发 最后,通过实车实验,实时地采集数据,对系统的采集和处理数据功能进行验证。(In this paper, widely used in the field of scientific research, powerful and simulation software MATLAB toolbox Simulink, Real-time Workshop, xPCTarget research and development of a needle then Zhangting Tire Pressure Monitoring System (TPMS) for data acquisition and processing system. First of all, the use of Simulink toolbox parameters required for the establishment of TPMS system simulation model approach then constructed based on MATLAB/xPCTarget hardware platform, combined with simulation models created by the completion of the entire data acquisition and processing system Finally, it is vehicle experiments, real-time data collection, the system of collection and processing of data validation functions.)

采用MATLAB计算fft，并能够消除信号中的直流分量(to calculate the fft and eliminate the dc component)

深度神经网络在函数近似中表现优越，然而需要从头开始训练。另一方面，贝叶斯方法，像高斯过程（GPs），可以利用利用先验知识在测试阶段进行快速推理。然而，高斯过程的计算量很大，也很难设计出合适的先验。本篇论文中我们提出了一种神经模型，条件神经过程（CNPs），可以结合这两者的优点。CNPs受灵活的随机过程的启发，比如GPs，但是结构是神经网络，并且通过梯度下降训练。CNPs通过很少的数据训练后就可以进行准确的预测，然后扩展到复杂函数和大数据集。我们证明了这个方法在一些典型的机器学习任务上面的的表现和功能，比如回归，分类和图像补全(Deep neural networks perform well in function approximation, but they need to be trained from scratch. On the other hand, Bayesian methods, such as Gauss Process (GPs), can make use of prior knowledge to conduct rapid reasoning in the testing stage. However, the calculation of Gauss process is very heavy, and it is difficult to design a suitable priori. In this paper, we propose a neural model, conditional neural processes (CNPs), which can combine the advantages of both. CNPs are inspired by flexible stochastic processes, such as GPs, but are structured as neural networks and trained by gradient descent. CNPs can predict accurately with very little data training, and then extend to complex functions and large data sets. We demonstrate the performance and functions of this method on some typical machine learning tasks, such as regression, classification and image completion.)