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.
A new search algorithm based on the hydrogen bond shape complementarity and relaxation labeling for fast protein-ligand docking is proposed. Given that the protein-ligand binding sites are demonstrated to relate with the cavities in the protein structure, Fpocket was used to identify the pockets on the proteins. Then based on the hydrogen bond model, the protein pockets as well as the ligand can be...
Formal decision context is a formal context with condition attributes and decision attributes, it is a generalization of formal context. For a weakly consistent formal decision context, we propose two methods to compress the condition lattice based on two new formal contexts, M-T class context and M-T extent context, respectively. These two compression methods are both based on decision lattice, and...
Formal concept analysis has been applied as a tool for knowledge expression and acquisition. However, the huge concept lattice makes the hidden knowledge difficult to understand. This paper proposes a method to compress a concept lattice using K-means clustering. Firstly, the similarity measure between formal concepts is obtained through the importance degree of each attribute and object, and then,...
In this paper, we present a Support Vector Regression (SVR) system to measure the semantic similarity of short texts by combining multiple similarity measurements, i.e., string similarity, knowledge-based similarity, corpus-based similarity, syntactic dependency similarity, number similarity and machine translation similarity. Experiments on the five data sets of SemEval 2012 Semantic Text Similarity...
In the area of Information Retrieval, user queries often mismatch the documents users exactly want. We regard this problem as a Query Rewriting task from user queries to document space. Using query logs containing query-keywords-CTR pairs, we trained a state-of-the-art statistical machine translation model to translate the user query to keywords of a web document. Using this method we successfully...
Relevance feedback (RF) based on support vector machine (SVM) has been widely used in content-based image retrieval (CBIR) to bridge the semantic gap between low-level visual features and high-level human perception. However, the conventional SVM based RF uses only the labeled images for learning, which gives rise to the small sample problem, i.e., when the training data is insufficient, the performance...
When unlabeled data is selected for updating classifier, it is easy to introduce noise or unreliable data. In this paper, a semi-supervised collaboration-training based on genetic algorithm (SCGA) is proposed. This algorithm uses optimization function of genetic algorithm to help collaboration-training algorithm to select valuable unlabeled data. Experiments on UCI datasets prove that the algorithm...
Feature weighting, which is considered as an extension of feature selection techniques, has been successfully applied to improve the performance of clustering. Focusing on the clustering based on a similarity matrix, we design an optimization model to minimize the fuzziness of similarity matrix by learning feature weights. The objective of this model is to get a more reasonable result of clustering...
Network clustering is receiving increasing attention in many application areas. However, as the size of data increases, traditional algorithms fail to deal with the large-scale data. Using distributed computers to handle such a problem in a parallel manner is an ideal solution. Many parallel clustering algorithms have been proposed, however, few are proposed for networks with the clustering criteria...
Almost all researches are carried out in two-dimensional space in the field of meteorology. However these researches are in lack of intuitive traits and have a low degree of visualization. This work is dedicated to the researches on three-dimensional reconstruction of the strong convective cell. Firstly, the contours in correlated faultage were extracted from meteorological radar base data. Then they...
In this paper, an image gray level statistics and region properties based iris localization method has been proposed. The proposed method starts by finding the coarse pupil region, reducing the effect of the eyelashes connected to pupil region, and tracing the boundary of pupil. Once the pupil is localized, we use a modified Intergrodifferential operator to localize the iris coarsely and finally use...
A new hybrid fast mode decision method for H.264/AVC intra coding is proposed in this paper. In the proposed algorithm, edge based filters are applied to some samples distributed in the block and each directional mode is related to a filtering result. After that, the absolute sum of Hadamard Transformed coefficients of the filtering results is utilized to help selecting the candidate prediction modes...
Target representation has great influence on the results of object tracking algorithms. This paper presents a new approach for target representation that applies image patches extracted from image sequences to target detection phase. In this approach, the initial image frame is split into small image patches, which are quantized and clustered to form a texture dictionary. Instead of using the statistical...
Abnormal behavior detection is an important issue in video surveillance. This paper presents an approach for abnormal behavior detection based on spatial-temporal features. First, the proposed method extracts moving objects from video sequence. Then, it tracks moving objects to detect their overlapping. Finally, a clutter-model is built up based on the changes of spatial-temporal feature to detect...
It is intractable problem to segment the fluorescence image of T-cells with different sizes, irregular shape, and severe overlapping by conventional marker-based watershed segmentation. In this paper, Adaptive Marker-controlled Watershed method (AMWS) will be proposed. The Otsu strategy firstly is performed twice in a row to capture as many T-cells as possible. Then based on T-cells' roundish shape,...
The unsharp masking filter (UMF) has been widely used in image processing front ends for contrast enhancement. The filter, being easy to implement, is based on the concept of augmenting a scaled and high-passed version of the image to itself. The UMF performance is critically dependent on the generation of the high-passed signal to be added as well as its associated scale factor. However, the optimal...
The key of a computer-assisted diagnosis system for screening of cervical cancer is the accurate segmentation of cells. In this paper, an adaptive segmentation algorithm based on GVF Snake model is proposed to separate the nucleus from cervical smear model. We set the parameters of the model, and then use the model to segment the cervical cells based on the initial contour of nuclei. The segmentation...
Storm cell is the fundamental element of forming varieties of strong convective disastrous weather. It is usually difficult to distinguish the cell because in an echo image the shapes of storm cells are complicated and the distributions are different inside while intertwined outside. This paper grasps the distribution that the storm cell's intensity decreases from inside to outside. Then get to start...
Electrical resistance tomography (ERT) techniques have increasing gained importance during the past several decades as a process visualization tool. Most of the existing ERT methods work in term of an optimization process and assume the optimized objective function be differentiable. But this assumption doesn't hold in noisy conditions and leads to an infeasible optimization process. In this paper,...
Noise reduction and contrast enhancement are the two fundamental procedures in most image processing applications. Their effectiveness often play crucial roles in the success of subsequent image operations such as feature segmentation or object recognition. In order to obtain high quality images, the bilateral filer (BF) and the unsharp masking filter (UMF) have often been used as attractive candidates...
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.