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 order to improve primary energy utilization, achieve economical operation of distribution network, comprehensively consider the concentration / compensation needs of various groups under typical load levels, and to gain understanding of characteristics of different types of user loads, the present paper proposes a hierarchical cluster algorithm to enhance the cohesion of a distribution feeder load...
Network protocol classification plays an important role in modern network security and fine-grained management architectures. The state-of-the-art network protocol classification methods aim to take the advantages of flow statistical features and machine learning techniques. However the classification performance is severely affected by limited supervised information and unknown network protocols...
Aiming at the problem that ViBe (Visual Background extractor) algorithm is sensitive to illumination variation, an improved ViBe algorithm is proposed in this paper. First, a brightness reference image is build, which represents the brightness level of background. Second, adjust the brightness of current frame, which is changed by illumination variation, back to the reference images brightness level...
Satellite information is an important source of the decision-level intelligence in battlefield. Research of the multi-source information decision-level fusion provides a key technical approach for distilling comprehensive satellite information and acquiring decision-level intelligences. A SVMs-DS model adopting statistics theory and uncertainty reasoning method in the article, ensures precision and...
From the functional point of view, a method that employed an Immune Programming algorithm to extract rules from Neural Network (NN) was presented. According to quantifying color feature of landscape images had been marked with emotion values in China Affective Picture System (CAPS), the method clustered outputs of hidden neurons of NN, reduced the searching scale, and the mapping between color and...
In this paper, a hybrid parallel computing framework is proposed for video understanding and retrieval. It is a unified computing architecture based on the Map-Reduce programming model, which supports multi-core and GPU architectures. A key task scheduler is designed for the parallelization of computation tasks. The SVM method is used to train models for video understanding purposes. To effectively...
For improving accuracy and robust property of human detection, fusion of image sequences captured from visible-thermal sensors is lucrative. Instead of performing it in pixel-level directly, we try to fuse object features by a novel image sequence fusion algorithm based on gradient feature (GFIF). The GFIF algorithm calculate gradients of input images to form a joint histograms of Oriented Gradient...
This paper proposes a novel tensor based dimensionality reduction algorithm called Multilinear Isometric Embedding (MIE) based on a representative manifold learning algorithm Isomap. Unlike Isomap that unfolds input data to the vector form, MIE directly works on more general tensor representation and utilizes iterative strategy to seek the low-dimensional equivalence, which best preserves the global...
This paper proposes a novel hierarchical speaker identification method to save the speaker identification and training time, viz. First is to get a coarse decision by a fast scan all registered speakers using PCA classifier to found M possible target speakers; then is to get a final decision by the proposed Multi-Reduced Support Vector Machine (MRSVM). And the MRSVM has two reduction steps to reduce...
Enemy (competition opponent) execute a plan, which has harmful goals for us, this plan is called adversarial plan (opponent plan). To do the answer for the adversarial plan (opponent plan) is called reply plan. The start mechanism of reply plan is the main problem in this paper. In the paper, we introduce a new model: Stress Reaction System Model. We also give the definitions of stress reaction and...
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.