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.
In this work, a new training principle is introduced for unsupervised learning that makes the learned representations more efficient and useful. Using partially corrupted inputs instead, the denoising Auto encoder can obtain more robust and representative pattern of inputs than the traditional learning methods. Besides, this denoising Auto encoder can be stacked to form a deep network. The whole framework...
How to teach computer to classify pictures into different emotional categories automatically as humans? It is a quite interesting and challenging research direction. This paper defines the latent emotional semantic factors and proposes a novel approach for emotional picture categorization. Unlike traditional methods, the latent emotional semantic factor is defined for representing the middle level...
Web Services is an effective way to realize service-oriented architecture. In order to enhance user experience, it is one of the key problems to respond client requests quickly when lots of data is required from the server. Based on modular classification and multi-threading transfer principle, a new method transmitting large data is proposed in this paper after network transmission feature is analyzed...
Mobile search is one of the emerging and promising fields for researchers and practitioners. Nowadays, in consideration of screen size and navigability, current PC web search engines and information retrieval approaches may hardly be transplanted onto mobile search platforms directly. This paper presents an efficient approach to retrieving a compact set of differentiated documents which is information...
Reducing dimension processing is needed in feature samples because the repeated and secondary features would reduce the classification ability and increase computation complexity. In this paper, a feature selection method, named MPSO (Modified Particle Swarm Optimization), is proposed. The original group velocity of a particle swarm was changed into two separate and parallel particle swarm velocity,...
In this paper, the problem of foreground segmentation in videos is considered. The bag of superpixels is proposed to simultaneously model both the foreground and the background. Then it is demonstrated that an image has a hierarchical structure. Based on this observation, the discriminative nature of sparse representations is exploited to segment the foreground in each frame. Experimental results...
SENSC algorithm is a newly proposed stable and efficient NSC algorithm. In this paper the SENSC algorithm is evaluated for the task of image clustering. A series of experiments are conducted on two different kinds of image datasets, including face images and natural images, and SENSC is compared with some other commonly used clustering methods. Experimental results show that SENSC is better suited...
Segmentation is a fundamental issue in synthetic aperture radar (SAR) image analysis. When contrast results against the true landscape, multi-polarization SAR images can provide more information, and obtain more correct segmentation than only single polarization SAR image. This paper presented a new SAR image segmentation method based on the multi-polarization SAR images fusion. The method built the...
In this paper, a simple and efficient method for coarse classification of Chinese characters is presented. In the new approach, a Chinese character is characterized with its outmost and second-peripheral segment features, each of which is expressed as four string vectors. The outmost and second-peripheral segment features of a Chinese word describe the structure of segments in top, bottom, left and...
The remarkable and continuous increase in link speed and application variety of Internet calls for new QoS provision technology that is both efficient and flexible. Being a kind of application-specific processor optimized for network computation, network processor (NP) combines the high performance of hardware and the flexibility of software, which exactly meets the demands of nowadays Internet traffic...
Unrepresentative data samples are likely to reduce the utility of data classifiers in practical application. This study presents a multi-approaches-guided preprocess algorithm in the design of an effective chance discovery model, which bases on data crystallization, clustering and neural network techniques. We used data crystallization to discover unobservable events of the input samples with the...
In recent years, non-negative matrix factorization (NMF) has been widely used in the analysis of gene expression data. However the NMF algorithm has its limitations of little dithering during the iteration process when the initial values are chosen randomly. In this paper, data smoothing is introduced in the iteration to resolve the dithering problem. Both the traditional and the improved NMF algorithm...
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.