In this research, we exploit the regularize framework and proposed an associative classification algorithm for uncertain data. The major recompense of SVM(support vector machine) are: recurrent item sets capture every dominant associations between items in a dataset. These classifiers naturally handle missing values and outliers as they only deal with statistically significant associations whic...

The radiosity method is a very demanding process in terms of computing and memory resources. To cope with these problems, parallel solutions have been proposed in the literature. These solutions are outlined and classiied in this paper. A new parallel solution, based on the use of a shared virtual memory (SVM), is proposed. It will be shown that this concept of SVM greatly simpliies the impleme...

This paper is concerned with the development of a novel classifier for automatic mass detection of mammograms, based on contourlet feature extraction in conjunction with statistical and fuzzy classifiers. In this method, mammograms are segmented into regions of interest (ROI) in order to extract features including geometrical and contourlet coefficients. The extracted features benefit from...

Human face recognition has become an active area of research over the last decade. The major problem of face recognition is the classification. In this paper, a new face recognition algorithm based on fusion of 2DPCA and Gabor features with SVM classifier is presented. The method first extracts features by employing Gabor wavelets followed by a face recognition algorithm 2DPCA and the SVM metho...

One of the main drawbacks of Support Vector Machines (SVM) is their high computational cost for large data sets. We propose the use of the Leader algorithm as a preprocessing procedure for SVM with large data sets, so that the obtained leaders are used as the training set for the SVM. The result is an algorithm where the Leader algorithm allows to construct a sample of the data set whose granul...

This paper proposes two methods which take advantage of k -mean clustering algorithm to decrease the number of support vectors (SVs) for the training of support vector machine (SVM). The first method uses k -mean clustering to construct a dataset of much smaller size than the original one as the actual input dataset to train SVM. The second method aims at reducing the number of SVs by which the...

This paper presents a new approach for the probability density function estimation using the Support Vector Machines (SVM) and the Expectation Maximization (EM) algorithms. In the proposed approach, an advanced algorithm for the SVM density estimation which incorporates the Mean Field theory in the learning process is used. Instead of using ad-hoc values for the parameters of the kernel functio...

In this paper, a new SVM classification algorithm is proposed, this algorithm is applied in Quantified Boolean Formulas (QBF) hybrid solving and a new QBF hybrid solver is designed. This solver apply SVM algorithm to construct inductive models and classify the formulae. At the same time, the reinforcement learning technology is applied to realize the dynamic algorithm selection. The relationshi...