The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Due to standard label propagation algorithm does not use the correct posterior probability of each iteration, and the propagation information of labeled data and unlabeled data are not distinguished during the label propagation process, this paper proposes a multi-level label propagation algorithm Based on data reconstruction. It adds the data which is correctly labeled for each iteration into the...
Document feature extraction and classifier selection are two key problems for document classification approach. To effectively resolve the above two problems, a novel document classification algorithm is proposed by combining the merits of local fisher discriminant analysis and kernel logistic regression. Extensive experiments have been conducted, and the results demonstrate that the proposed algorithm...
Face recognition has become one of the most important research areas of pattern recognition and machine learning due to its potential applications in many fields. To effectively cope with this problem, a novel face recognition algorithm is proposed by using manifold learning and minimax probability machine. Comprehensive comparisons and extensive experiments show that the proposed algorithm achieves...
To cope with performance and accuracy problems with high dimensionality in document classification, a novel dimensionality reduction algorithm called IKDA is proposed in this paper. The proposed IKDA algorithm combines kernel-based learning techniques and direct iterative optimization procedure to deal with the nonlinearity of the document distribution. The proposed algorithm also effectively solves...
Document classification has received extensive attention in the past decade due to its wide range applications. To efficiently deal with this problem, a novel document classification algorithm is proposed by using marginal fisher analysis (MFA) and minimax probability machine(MPM). Experimental results on the WebKB data set show that the proposed algorithm achieves much better performance than other...
To efficiently deal with the curse of dimensionality in the content-based image retrieval (CBIR) system, a novel image retrieval algorithm is proposed by combination of local discriminant embedding (LDE) and least square SVM (LS-SVM) in this paper. LDE aims to achieve good discriminating performance by integrating the local geometrical structure and class relations between image data. LS-SVM classifier...
Document classification has received extensive attention in the past few decades due to its wide applications in many fields. To efficiently deal with this problem, a novel document classification algorithm based on information bottleneck (IB) and least square version of SVM (LS-SVM) is proposed in this paper. Extensive experimental results on the real-word document corpus show that the proposed algorithm...
Face recognition is one of the most challenging research topics in the field of pattern recognition and computer vision. To efficiently deal with this problem, a novel face recognition algorithm is proposed by using marginal manifold learning and SVM classifier. Extensive experiments show that the proposed algorithm performs much better than other well-known face recognition algorithms.
To efficiently deal with spam mail filtering problem, a novel spam filtering algorithm based on locality pursuit projection (LPP) and least square version of SVM(LS-SVM) is proposed in this paper. The mail message features are first extracted by the LPP algorithm, then the LS-SVM classifier is used to classify mails into spam and legitimate. Experimental results demonstrate that the proposed algorithm...
To efficiently tackle document classification problem, a novel document classification algorithm based on kernel neighborhood preserving embedding (KNPE) is proposed in this paper. The discriminant features are first extracted by the KNPE algorithm, then SVM is used to classify the documents into semantically different classes. Experimental results on real document databases have demonstrated the...
Document categorization is one of the most crucial techniques to assign the documents of a corpus to a set of previously fixed categories. To efficiently deal with document categorization problem, an efficient document categorization algorithm based on local discriminant embedding (LDE) and memetic algorithm (MA) is proposed in this paper. Extensive experiments on Reuter-21578 demonstrate that the...
With many potential applications in document management and Web searching, document classification has recently gained more attention. To efficiently resolve this problem, an efficient document classification algorithm based on neighborhood preserving embedding (NPE) and particle swarm optimization (PSO) is proposed in this paper. The document features are first extracted by the NPE algorithm, then...
To efficiently deal with document classification problem, an efficient document classification algorithm based on kernel local discriminant embedding (kernel LDE) is proposed in this paper. The high-dimensional document data are first mapped into lower-dimensional feature space, then the SVM classifier is applied to classify documents. The experimental results demonstrate that the proposed algorithm...
To efficiently cope with document classification problem, an efficient document classification algorithm based on local discriminant embedding (LDE) and SVM classifier is proposed in this paper. The high-dimensional document space are first projected into the lower-dimensional feature space by using LDE algorithm, the SVM classifier is then applied in the reduced document feature space. Extensive...
Face recognition has received growing attention because of its wide applications. In this paper, an efficient face recognition algorithm based on non-negative matrix factorization (NMF) and SVM is proposed. The high dimension face images are first projected into a lower-dimensional subspace using NMF. The SVM classifier is then used to classify the face image into different classes. The experimental...
With the explosive growth in the Web documents, classifying document from the large-scale document database has become one of the most active research fields in data mining communities. Thus, developing an efficient document categorization algorithm to automatically classify Web document is of great importance. In this paper, an efficient document classification algorithm with shuffled frog leaping...
Classification rule mining is one of the important problems in the field of data mining which aims to extract a small set of rules from the training data set with predetermined targets. In this paper, an efficient classification rule mining algorithm is proposed by using memetic algorithm (MA). Experimental results show that the proposed classification algorithm achieves much better performance than...
Dimension reduction is an important data preparation step for face recognition. A new nonlinear dimensionality reduction method called kernel neighborhood preserving embedding (KNPE) is proposed in this paper. This new method extends the well-known neighborhood preserving embedding (NPE) from linear domain to a nonlinear domain with the kernel trick that has been used kernel-based learning algorithms...
The amount of online document has grown greatly in recent years due to the increase in popularity of the World Wide Web. Thus, developing an efficient document classification method to automatically manipulate Web document is of great importance. A novel memetic algorithm (MA)-based document classification algorithm is presented in this paper. The experimental results show that the proposed algorithm...
With the popularization of the Internet, it is challenging to develop spam filters that can effectively eliminate the increasing volumes of unwanted mails automatically before they enter a user's mailbox. To efficiently solve the spam filtering problems, a spam mail filtering method based on neighborhood preserving embedding (NPE) and support vector machines (SVM) classifier is proposed in this paper...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.