For the original GI/M/1/N queuing system was not suitable to model the queue management mechanism,a queuing system GI/M/1/N with randomly dropping packets mechanism was discussed by means of thinning of recurrent flows.

Thus, we adopt sparse optical flow approach by combing that two approaches in this paper.

A short-term load forecasting approach based on imposing sparseness upon LSSVM integrated SMO algorithms;

Compared with SVM,it losses the sparseness of solution,which influences the efficiency of second learning.

For the research of acoustic signal transmission in shallow-water channel, based on the analysis of decision feedback equalizer (DFE) arithmetic, the mean square error (MSE) of sparseness weight DFE equalizer channel estimation and channel sparseness estimation are researched.

From the view of sparsification,an improved algorithm based on extended information filter SLAM is introduced.

For this reason,this paper proposes to seek for the correlation coefficient instead of the high order statistics and apply it to sparsification of training sample set and nonlinear classification with radial basis kernels.

In order to reduce redundancy of training samples and extract the high dimension feature, we present some arithmetic about samples sparsification and classification based on high order correlation in the paper.

CCA sparse least squares support vector machine classifiers;

High sparseness least squares support vector machine classifier;

For lack of sparseness characteristic in support vector machines(SVM) by least squares solution(LSSVM),a density weighted pruning algorithm to improve the sparseness of the LSSVM regression model is investigated.