Improved Scheme for Fast Approximation to Least Squares Support Vector Regression

The solution of normal least squares support vector regression(LSSVR)is lack of sparseness,which limits the real-time and hampers the wide applications to a certain degree.To overcome this obstacle,a scheme,named I2FSA-LSSVR,is proposed.Compared with the previously approximate algorithms,it not only adopts the partial reduction strategy but considers the influence between the previously selected support vectors and the willselected support vector during the process of computing the supporting weights.As a result,I2FSA-LSSVR reduces the number of support vectors and enhances the real-time.To confirm the feasibility and effectiveness of the proposed algorithm,experiments on benchmark data sets are conducted,whose results support the presented I2FSA-LSSVR.

Facial Feature Extraction Method Based on Coefficients of Variances

Principal Component Analysis （PCA） and Linear Discriminant Analysis （LDA） are two popular feature extraction techniques in statistical pattern recognition field. Due to small sample size problem LDA cannot be directly applied to appearance-based face recognition tasks. As a consequence, a lot of LDA-based facial feature extraction techniques are proposed to deal with the problem one after the other. Nullspace Method is one of the most effective methods among them. The Nullspace Method tries to find a set of discriminant vectors which maximize the between-class scatter in the null space of the within-class scatter matrix. The calculation of its discriminant vectors will involve performing singular value decomposition on a high-dimensional matrix. It is generally memory- and time-consuming. Borrowing the key idea in Nullspace method and the concept of coefficient of variance in statistical analysis we present a novel facial feature extraction method, i.e., Discriminant based on Coefficient of Variance （DCV） in this paper. Experimental results performed on the FERET and AR face image databases demonstrate that DCV is a promising technique in comparison with Eigenfaces, Nullspace Method, and other state-of-the-art facial feature extraction methods.

X-ray fluorescence spectra quantitative analysis based on characteristic spectra optimization of partial least-squares method

The quantitative analysis of X-ray fluorescence （XRF） spectra is studied using the partial least-squares （PLS） method. The characteristic variables of spectra matrix of PLS are optimized by genetic algorithm. The subset of multi-component characteristic spectra matrix is established which is corresponding to their concentration. The individual fitness is calculated which combines the crossover validation parameters （prediction error square summation） and correlation coefficients （R^2）. The experimental result indicates that the predicated values improve using the PLS model of characteristic spectra optimization. Compared to the nonoptimized XRF spectra, the linear dependence of processed spectra averagely decreases by about 7%, root mean square error of calibration averagely increases by about 79.32, and root mean square error of cross-validation avera^elv increases by about 14.2.

Joint User Selection and Rate Adaptation Scheme in a Coordinated Multipoint Transmission System for Power Minimization

In a coordinated multipoint transmission system with centralized architecture for saving power consumption, total power metric is minimized while completely using the backhaul capacity and maintaining the minimum target data rate. The problem is formulated as a mixed integer optimization problem, which is difficult to solve. To overcome this problem, a joint user selection and rate adaptation scheme is developed based on the water-filling rate adaptation with the given user set and the power saving criterion with the allocated rates.Numerical results demonstrate that compared with the norm-based and semi-orthogonal user selection algorithms,the proposed algorithm can significantly reduce the total power consumption. The proposed algorithm can also achieve near-optimal performance compared with the performance achieved by the exhaustive search-based method. In addition, the computational complexity of the proposed algorithm is reduced by heuristic iteration and search scope shrinking.