Car-theory-programming

一个改进的BP算法的实验的matlab源码，用于体验各参数变化对算法收敛性的影响(An improved BP algorithm matlab source of experiments for the experience of each parameter change on the impact of the convergence algorithm)

是两个综合性较强的实例，分别是Visual C++实现的基于神经网络的文字识别系统和车牌定位系统(Are two examples of more integrated, namely Visual C++ implementation of text based on neural networks and the license plate recognition system positioning systems)

说明：  利用Matlab软件平台对JTC进行了图像识别仿真实验，得到了二维及三维相关输出图像，显示出尖锐的相关峰。仿真实验表明：联合变换进行图像识别中存在强烈的零级干扰，干扰信号是有用信号的7.14倍，输出结果不理想；采用功率谱相减法可以消除零级强干扰，进而提高了图像的识别能力。(Simulations of joint transform correlator (JTC) using Matlab is implemented, and the 2-D and 3-D drawings of the correlation image are obtained. In the simulation experiments, the sharper correlation peaks are showed. The result shows that strong disturbance of zero rank exists in the simulation of JTC, and it is 7.14 times stronger than the useful signal thus, the power spectrum subtraction is used to eliminate the strong disturbance, and the capacity of image recognition is improved.)

Simple Inverted Pendulum with LQR,PID SimMechanics

通过这一算法可以实现二维平面内无人机的路径规划。在该平面内存在已知的障碍，势场法通过给终点添加引力，对障碍增加斥力，使得无人机能够顺利的避障并到达终点。通过对传统势场法的改进，避免了无人机容易陷入极值的问题，使搜索更易实现。(Through this algorithm, the path planning of the UAV in the two-dimensional plane can be realized. There are known obstacles in the plane. The potential field method adds gravity to the terminal to increase the repulsion for obstacles, so that the UAV can avoid obstacles and reach the terminal smoothly. Through the improvement of the traditional potential field method, it avoids the problem that the UAV is easily trapped in the extreme value and makes the search more easy to be realized.)

matlab matlab source code lic lice

UN AUTRE MONDE DE LA VISION.............MATLAB..................SEGMENTATION

关于控制系统多变量分析的一篇文章,提出了多变量分析的一种新的方法(Control system multivariate analysis article proposed a new method for multivariate analysis)

求一维序列x(n)的离散Fourier谱分析，s(0:m)离散功率谱，c(0:m)振幅谱，cta(0:m)位相谱，其中m=[n/2.]。(Discrete Fourier spectrum of one-dimensional series)

In many applications, such as biomedical engineering, it is often required to obtain specific periodic source signals. In this paper, we propose a two-stage based approach for extracting periodic signals. At the first stage, the autocorrelation property of the desired source signal is exploited to roughly extract the desired source signal. At the second stage, the extracted signal is further processed as cleanly as possible, based on the higher-order statistics. Simulations on artificially generated data and real-world ECG data have showed its better performance, compared with many existing extraction algorithms.