This paper describes a new topological map dedicated to clustering under probabilistic constraints. In general, traditional clustering is used in an unsupervised manner. However, in some cases, background information ...
详细信息
ISBN:
(纸本)9783642030697
This paper describes a new topological map dedicated to clustering under probabilistic constraints. In general, traditional clustering is used in an unsupervised manner. However, in some cases, background information about the problem domain is available or imposed in the form of constraints in addition to data instances. In this context, we modify the popular GTM algorithm to take these "soft" constraints into account during the construction of the topology. We present experiments on synthetic known databases with artificial generated constraints for comparison with both GTM and another constrained clustering methods.
There are four main problems that limit application of patternrecognition techniques for recognition of abnormal cardiac left ventricle (LV) wall motion: 1) Normalization of the LV's size, shape, intensity level ...
详细信息
ISBN:
(纸本)9783642042706
There are four main problems that limit application of patternrecognition techniques for recognition of abnormal cardiac left ventricle (LV) wall motion: 1) Normalization of the LV's size, shape, intensity level and position;2) defining a spatial correspondence between phases and Subjects;3) extracting features;4) and discriminating abnormal from normal wall motion. Solving these four problems is required for application of patternrecognition techniques to classify the normal and abnormal LV wall motion. In this work, we introduce a normalization scheme to solve the first and second problems. With this scheme, LVs are normalized to the same position, size, and intensity level. Using the normalized images, we proposed an intra-segment classification criterion based on a con-elation measure to solve the third and fourth problems. Application of the method to recognition of abnormal cardiac MR LV wall motion showed promising results.
We present a new method of computing invariants in videos captured from different views to achieve view-invariant action recognition. To avoid the constraints of collinearity or coplanarity of image points for constru...
详细信息
ISBN:
(纸本)9781424456536
We present a new method of computing invariants in videos captured from different views to achieve view-invariant action recognition. To avoid the constraints of collinearity or coplanarity of image points for constructing invariants, we consider several neighboring frames to compute cross ratios, namely cross ratios across frames (CRAF), as our invariant representation of action. For every five points sampled with different intervals from the trajectories of action, we construct a pair of cross ratios (CRs). Afterwards, we transform the CRs to histograms as the feature vectors for classification. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in effectiveness and stability.
Aiming at the weaknesses of PS-classifier, it is easily trapped into locally optimal solution and slow convergence velocity when it deals with the complex problems, an improved Quantum-behaved particle swarm classifie...
详细信息
ISBN:
(纸本)9781424447541
Aiming at the weaknesses of PS-classifier, it is easily trapped into locally optimal solution and slow convergence velocity when it deals with the complex problems, an improved Quantum-behaved particle swarm classifier has been proposed in the paper. Firstly, It introduce the weighted mean best position to improve the performance of QPSO (Quantum-behaved particle swarm), and use a novel Michigan rule to code speech parameters. Then, a new fitness function is constructed to accomplish the weighted Quantum-behaved particle swarm classifier (WQPS -classifier). Finally it was applied into speaker recognition. Experimental results show that the proposed classifier achieve higher recognition rate in noisy environments compared with other classification algorithms.
Geometric Moment Invariant (GMI) is well known approach in patternrecognition. One of the weaknesses of GMI is in its invarianceness, where data or points concentrated near to the center-of-mass are neglected because...
详细信息
ISBN:
(纸本)9781424441549
Geometric Moment Invariant (GMI) is well known approach in patternrecognition. One of the weaknesses of GMI is in its invarianceness, where data or points concentrated near to the center-of-mass are neglected because of the existence of data or points that are far away from the center-of-mass. To solve this problem, Balslev *** has modified GMI method by adding a weighting function into GMI's formula;thus we called it as Weighted Central Moment (WCM). WCM can increase noise tolerance for rotation/translation independent patternrecognition. In this paper, we present simulation results for characters with adjustable parameter CE equal to 2/R-g. The experiments reveal that WCM yields intra-class results for identifying picture with different orientations. It also illustrates better inter-class distances in recognizing letter "g" and "q" compared to GMI method.
Information technology has become one of the most important infrastructure components of virtually any organization. Although information technology has a crucial impact on the success of organizations it is reported ...
详细信息
ISBN:
(纸本)9783642111631
Information technology has become one of the most important infrastructure components of virtually any organization. Although information technology has a crucial impact on the success of organizations it is reported that IT projects have rather high failure rates. Therefore, it is vitally important for organizations to improve the performance and success rates of IT projects. However, the reasons for failures are versatile and an ongoing very active fields of research especially in information systems and management. An established approach to evaluate IT projects is to define relevant so called critical success factors and analyze IT projects according to these criteria. This analysis is often of a qualitative nature. The objective of our paper is to enrich the analysis of critical success factors by alternative methods in particular rough set theory. We motivate the usage of rough sets to further improve the analysis of critical success factors with the goal to better manage IT projects and increase their success rate.
The theoretic and algorithmic description of the parallel batch pattern back propagation (BP) training algorithm of multilayer perceptron is presented in this paper. The efficiency research of the developed parallel a...
详细信息
ISBN:
(纸本)9783642024801
The theoretic and algorithmic description of the parallel batch pattern back propagation (BP) training algorithm of multilayer perceptron is presented in this paper. The efficiency research of the developed parallel algorithm is fulfilled at progressive increasing of the dimension of parallelized problem on general-purpose parallel Computer NEC TX-7.
An optimization technique is proposed for the outline capture of planar images. The overall technique has various phases including extracting outlines of images, detecting corner points from the detected outline, and ...
详细信息
An optimization technique is proposed for the outline capture of planar images. The overall technique has various phases including extracting outlines of images, detecting corner points from the detected outline, and curve fitting. The idea of multilevel coordinate search has been used to optimize the shape parameters in the description of the generalized conic spline introduced. The spline method ultimately produces optimal results for the approximate vectorization of the digital contour obtained from the generic shapes.
The proceedings contain 85 papers. The topics discussed include: seamless image stitching algorithm using radiometric lens calibration for high resolution optical microscopy;ANFIS supported question classification in ...
ISBN:
(纸本)9781424434282
The proceedings contain 85 papers. The topics discussed include: seamless image stitching algorithm using radiometric lens calibration for high resolution optical microscopy;ANFIS supported question classification in computer adaptive testing (CAT);weighted majority voting for face recognition from low resolution video sequences;an auction based mathematical model and heuristics for resource co-allocation problem in grids and clouds;fault classification in gears using support vector machines (SVMs) and signal processing;constructing robot's model of external environment on basis of linguistic relations and generalized constraints;musical harmonization with words: realizability, potential issues and challenges;principal component based classification for text-independent speaker identification;a new parallel programming language fortress: features and applications;economic order quantity model with backorders using trapezoidal fuzzy numbers;and EOG controlled mobile robot using radial basis function networks.
In the present work an attempt is made to develop a Decision support system (DSS) using the pathological attributes to predict the fetal delivery to be done normal or by surgical procedure. The pathological tests like...
详细信息
ISBN:
(纸本)9781424452446
In the present work an attempt is made to develop a Decision support system (DSS) using the pathological attributes to predict the fetal delivery to be done normal or by surgical procedure. The pathological tests like Blood Sugar (BR), Blood pressure (BP), Resistivity Index (RI) and systolic / Diastolic (SIP) ratio will be recorded at the time of delivery. All attributes lie within a specific range for normal patient. The database consists of the attributes for cases i.e. normal and surgical delivery. softcomputing technique namely Artificial Neural Networks (ANN) are used for simulator. The attributes from dataset are used for training & testing of ANN models. Three models of ANN are trained using Back-Propagation Algorithm (BPA), Radial Basis Function Network (RBFN) and one hybrid approach is Adaptive Neuro-Fuzzy Inference System (ANFIS). The designing factors have been changed to get the optimized model, which gives highest recognition score. The optimized models of BPA, RBFN and ANFIS gave accuracies of 93.75, 99.00 and 99.50 % respectively. Thus ANFIS is the best network for mentioned problem. This system will assist doctor to take decision at the critical time of fetal delivery.
暂无评论