work

this file describes and run the blurring of a picture.

fit_ML_normal - Maximum Likelihood fit of the log-normal distribution of i.i.d. samples!. Given the samples of a log-normal distribution, the PDF parameter is found fits data to the probability of the form: p(x) = sqrt(1/(2*pi))/(s*x)*exp(- (log(x-m)^2)/(2*s^2)) with parameters: m,s format: result = fit_ML_log_normal( x,hAx ) input: x - vector, samples with log-normal distribution to be parameterized hAx - handle of an axis, on which the fitted distribution is plotted if h is given empty, a figure is created. output: result - structure with the fields m,s - fitted parameters CRB_m,CRB_s - Cram?r-Rao Bound for the estimator value RMS - RMS error of the estimation type - ML

Multiple kernel learning is a model to merge multiple kernels by linear combination. Mostly solving the models are slow due to explicit computation of kernels. Here, we propose to approximate kernel map function explicitly in finite dimensional space. Then, we use dual coordinate descent to solve the SVM. By storing the solutions in primal, we do not have to compute the kernel explicitly. A group lasso regularization on kernel weights is solved with SVM alternatingly. This is a side-project in my research projects with Dr. Yi-Ren Yeh and Dr. Frank Wang in Academia Sinica.

功率谱估计性能分析及其MATLAB实现，间接法、直接法、改进的周期图法Welch法、Bartlett法 (Power spectrum estimation performance analysis on MATLAB, the indirect method, direct method, improved periodogram the Welch Law, Bartlett method)

动目标参数估计，二范数方法，对目标进行速度方向等的估计(Moving target parameter estimation, two norm method, estimate of the target velocity direction, etc.)

solve distribution powerflow(complex Newton raphsom method to solve distribution powerflow)

huffman encoding for image compression

Introduction to matlab

this code use for matlab

Use Seam Carving for object removal and region filling..