On the difficulty for the current patternrecognition to deal with fuzzy uncertain information, in this paper, the author tries to give a definition of intuitionistic fuzzy relative entropy, and meanwhile introduces t...
详细信息
ISBN:
(纸本)9780769550169
On the difficulty for the current patternrecognition to deal with fuzzy uncertain information, in this paper, the author tries to give a definition of intuitionistic fuzzy relative entropy, and meanwhile introduces the weighted thought into fuzzy patternrecognition, putting forward the method of patternrecognition based on Weighted Intuitionistic Fuzzy Relative Entropy. the new method accurately describes and shows the uncertainty of historical information, effectively realizes the quantitative analysis of patternrecognition, and improves the reliability, accuracy, and the robust performance of the system. Finally, through the examples, the effectiveness and superiority are proved.
Concerning the actual status of protection in the power grid, a new strategy is proposed in this paper to evaluate the cascade tripping. Based on an operating equation of the backup relay protection, the relationship ...
详细信息
ISBN:
(纸本)9781538630136
Concerning the actual status of protection in the power grid, a new strategy is proposed in this paper to evaluate the cascade tripping. Based on an operating equation of the backup relay protection, the relationship between nodal injection power and the cascade tripping is analyzed. the relationship between node injection power and cascade tripping is reconstructed by patternrecognition technology, which is employed to assess the probability of cascading failure in a power network subjected to an initial failure. A certain number of samples are obtained by simulation in IEEE39 system, which are trained and tested based on BP neural network pattern. the validity of the assessment method is verified by the calculation result.
Withthe development of medical treatment, various kinds of medical images become more and more important. the traditional hierarchical structural image representation methods put too much emphasis upon the symmetry o...
详细信息
ISBN:
(纸本)9781424447138
Withthe development of medical treatment, various kinds of medical images become more and more important. the traditional hierarchical structural image representation methods put too much emphasis upon the symmetry of segmentation, they are not the optimal image representation methods. DNAM-based multi-valued image presentation method has not only better compression ability but also has better reconstruction quality. On the basis of the DNAM method, a new storage structure is presented in this paper. By describing dNAM, the coding and decoding algorithms of tag-matrix storage mode are given. the complexity of the algorithm is analyzed. According to the theoretical analysis and the result of the experiment, comparing withthe traditional NAM storage mode, the tag-matrix storage structure has obvious advantages. the method is valuable for the medical image representation.
Syntactic methods in patternrecognition have been used extensively in bioinformatics, and in particular, in the analysis of gene and protein expressions, and in the recognition and classification of biosequences, the...
详细信息
ISBN:
(纸本)9783642040306
Syntactic methods in patternrecognition have been used extensively in bioinformatics, and in particular, in the analysis of gene and protein expressions, and in the recognition and classification of biosequences, these methods are almost universally distance-based. this paper concerns the use of an Optimal and Information theoretic (OIT) probabilistic model [11] to achieve peptide classification using the information residing in their syntactic representations. the latter has traditionally been achieved using the edit distances required in the respective peptide comparisons. We advocate that, one can model the differences between compared strings as a mutation model consisting of random Substitutions, Insertions and Deletions (SID) obeying the OIT model. thus, in this paper, we show that the probability measure obtained. from the OIT model can be perceived as a sequence similarity metric, using which a Support Vector Machine (SVM)-based peptide classifier, referred to as OIT-SVM, can be devised. the classifier, which we have built has been tested for eight different "substitution" matrices and for two different data sets, namely, the HIV-1 Protease Cleavage sites and the T-cell Epitopes. the results show that the OIT model performs significantly better than the one which uses a Needleman-Wunsch sequence alignment score, and the peptide classification methods that previously experimented withthe same two datasets.
the proceedings contain 65 papers. the topics discussed include: inference and learning for active sensing, experimental design and control;large scale online learning of image similarity through ranking;inpainting id...
详细信息
ISBN:
(纸本)3642021719
the proceedings contain 65 papers. the topics discussed include: inference and learning for active sensing, experimental design and control;large scale online learning of image similarity through ranking;inpainting ideas for image compression;smoothed disparity maps for continuous American sign language recognition;human action recognition using optical flow accumulated local histograms;trajectory modeling using mixtures of vector fields;high speed human detection using a multiresolution cascade of histograms of oriented gradients;face-to-face social activity detection using data collected with a wearable device;estimating vehicle velocity using Image profiles on rectified images;kernel based multi-object tracking using gabor functions embedded in a region covariance matrix;and autonomous configuration of parameters in robotic digital cameras.
the paper introduces the,nain principles of automatic interpretation of engineering drawing images, the technology of ED interpretation is proposed based on the introduced principles. the algorithms for automatic reco...
详细信息
ISBN:
(纸本)0818678984;0818678992
the paper introduces the,nain principles of automatic interpretation of engineering drawing images, the technology of ED interpretation is proposed based on the introduced principles. the algorithms for automatic recognition of the main ED entitles: line types, circular arcs, blocks, crosshatched areas, dimensions are proposed. they have been verified experimentally in the whole ED interpretation technology and show good results.
the DARPA Image Understanding Program provides support for a varietY of fundamental research efforts aimed at the derivation of information from images. this paper highlights the research and describes the approach us...
详细信息
the DARPA Image Understanding Program provides support for a varietY of fundamental research efforts aimed at the derivation of information from images. this paper highlights the research and describes the approach used to develop synergism between researchers engaged in complementary sciences contributing to computer vision. Possible applications of image understanding to the Department of Defense are discussed.
the purpose of this paper was to find some feature pattern which may be used in diagnosis of blood stasis syndrome (BSS, a unique concept of traditional Chinese medicine) with myocardial ischemia. After establishing a...
详细信息
ISBN:
(纸本)9781424447138
the purpose of this paper was to find some feature pattern which may be used in diagnosis of blood stasis syndrome (BSS, a unique concept of traditional Chinese medicine) with myocardial ischemia. After establishing an animal model of Chinese experimental miniature swine, 7 indicators in plasma, e.g. troponin T (cTNT), heat shock protein 27 (HSP27), cytochrome C(Cyt C), endothelin-1 (ET-1), calcitonin gene-related peptide (CGRP), thromboxane A2 (TXA(2)) and prostacyclin (PGI(2)) were detected and then least angle regression was performed to discover the correlation between BSS and these 7 indicators. As the results showed, all the 7 indicators were contributed to the diagnosis of BSS and the regression obtained after 110 steps was curacy enough (>90%) in our cases. this pattern may become a supplementary way of traditional diagnostic methods of BBS. And it also demonstrated that least angle regression may be a better algorithm in the mining of feature patterns of syndromes.
In this paper, we propose a novel local feature descriptor for facial expression recognition, referred as local binary covariance matrices (LBCM). the covariance matrix in LBCM is constructed by incorporating location...
详细信息
ISBN:
(纸本)9781849195072
In this paper, we propose a novel local feature descriptor for facial expression recognition, referred as local binary covariance matrices (LBCM). the covariance matrix in LBCM is constructed by incorporating location, intensity and local binary features of each pixel inside a region of interest. Extensive experiments demonstrate the effectiveness of LBCM for FER, even if partial occlusion exists.
暂无评论