chapter
The objective of this work is the detection of object classes. An improved method is used for object detection and segmentation in real-world multiple-object scenes. It has two stages. In the first stage this method develops a novel technique to extract class-discriminative boundary fragments and the texture features near the boundary, and then boosting is used to select discriminative boundary fragments...
chapter
Non-rigid registration between CT and ultrasound images is a difficult task due to the low resolution and contrast of ultrasound images. We present a method incorporating the shape information of contours extracted from the image pairs for the registration. Firstly, the shapes are represented by the automatically detected landmarks along the contour of segmented object on CT and ultrasound images...
chapter
In this paper, we discuss a face recognition scheme by subspace analysis of 2D log-Gabor wavelets features. In which, an input face image is firstly decomposed with a set of two dimensional log-Gabor wavelets (2D-LGWs) localized with respect to spatial location, orientation and frequency. Based on complex responses of filters, local energy model (LEM) is used to represent log-Gabor features (LGFs)...
chapter
This paper presents a novel approach to automatically detect the fracture of skull in CT images. The approach consists of 5 steps: 1) skull segmentation, 2) skull extraction, 3) edge detection, 4) noise removal and, 5) image classification. Experiments show that the recognition rate is 99% for 100 images that are randomly chosen from a medical image database contributed by Hospital Putrajaya, Malaysia...
chapter
Segmentation is an important step in fingerprint recognition ystem, in which the region of interest can be extracted. his paper presents a novel fingerprint image segmentation method aiming at dealing with low quality fingerprint images. Firstly the mean and variance of gray level in each divided block is used to differentiate the image coarsely. Then two new features intra-consistency and extra-consistency...
chapter
To determine the main precursory anomalies from intricate earthquake precursors in given area is the important content of earthquake consultation. Based on the dynamic transfer characteristic of elements in S-rough sets theory, and the regional difference and precursory difference of earthquake precursory anomalies, an analytical algorithm of earthquake precursory anomalies based on two direction...
chapter
By using one direction S-rough sets (one direction singular rough sets), the f-attribute interference generation and separation of knowledge, and the f-attribute interference generation and separation of one direction S-rough sets were proposed; on these concepts above, the f-attribute interference theorem, the f-attribute interference lose theorem, the f-attribute interference discernibility theorem,...
chapter
S-rough sets (singular rough sets) theory was proposed by improving Z.Pawlak rough sets theory. S-rough set has dynamic characteristics, since it is defined by R -element equivalence class[x] which has dynamic characteristic. The concept of rough data was presented by employing S-rough sets, and rough data has dynamic characteristic, furthermore, the rough data law generation is given. Based on the...
chapter
In this paper we devote to study some continuous attribute discretization algorithms, and based on them we build a Chinese wines classification system using BP neural network. According to the discretization method based on cluster analysis, we first discretize attributes by using fuzzy c-means cluster analysis guiding by the level of consistency of decision table, and then merge neighboring intervals...
chapter
Reactive power optimization in power system is a complex nonlinear combinatorial optimization problem with multiple constrained conditions. However, direct neural dynamic programming (direct NDP) approach based on on-line measurements can be employed in this situation, which is independent of models. In this paper, on the basis of applicable analysis to reactive power optimization, this algorithm...
chapter
Road safety performance indicators as a comprehensible tool provide a better understanding of current safety conditions and monitor the effect of policy interventions. New insights can be gained in case one road safety index is composed of all risk indicators. The safety performance can be evaluated, and actions can be prioritized by the assigned weights. In this paper, a composite structure of neural...
chapter
From both a neurobiological viewpoint and an implementation perspective, the neuron network is partially-connected. In this paper, we show that associative memory networks with complex topology. Owing to the partial connection in delta distribute network, the associative memory has feature of higher storage capacity, but the basin of attraction is shrunk. The comparison of the performance among the...
chapter
This paper describes an application of artificial neural networks (ANNs) to predict the performance of a ground-water heat pump system (GWHP). In order to gather data for training and testing the proposed ANN model, an experimental GWHP system was operated at steady state conditions. Utilizing some experimental data for training, an ANN model based on a multi-layered perception/back propagation was...
chapter
Mean shift algorithm is a statistics iterative algorithm which is widely used, its increment (namely mean shift vector) of iterative point in each iteration step changes adaptively. This paper presents an extensional mean shift vector, and proves convergence of mean shift algorithm which using the extensional mean shift vector. In addition, we did an experiment - using mean shift algorithm to solve...
chapter
According to a class of discrete time-delay systems with unmatched uncertainties and disturbance, a new chattering free least squares support vector machine grey sliding mode control (LS-SVM-GSMC) law based on Linear Matrix Inequality (LMI) is presented. Estimated value of external disturbance is obtained by grey model, and output of LS-SVM is used for replacing sign function of the reaching law in...
chapter
This paper proposes a novel scheme that we call the opposition based comprehensive learning particle swarm optimizers (OCLPSO), which employs opposition based learning (OBL) for population initialization and also for exemplar selecting. This scheme enables the swarm to explore and exploit with the more diversity and not to be premature convergence. Experiments were conducted on benchmark functions...
chapter
Visible and near infrared (Vis/NIR) transmittance spectroscopy and chemometrics methods were utilized to discriminate red wine. The samples of five varieties of red wine were separated into calibration set and validation set randomly. The principal components (PCs) could be obtained from original spectrum by using Partial least squares (PLS), The PCs (selected by PLS) of each sample in calibration...
chapter
In many machine learning settings, labeled samples are difficult to collect while unlabeled samples are abundant. We investigate in this paper the design of support vector machine classification algorithms learning from positive and unlabeled samples only. We first find the minimum bounding sphere that enclosed all the positive samples, and then use this minimum bounding sphere to pick out the negative...
chapter
In order to deal with time delay in the system and saturation in the input, a new chattering free support vector regression sliding mode control (SVR-SMC) law based on 1(LMIs) is proposed. The sign function of reaching law in conventional sliding mode control (SMC) is replaced by output of SVR. An equivalent matrix is constructed for input saturation condition in the scheme. The feasibility and effectiveness...
chapter
How to deal with the very large database in decision-making applications is a very important issue, which sometimes can be addressed using SVMs. This paper presents a new sample reduction algorithm as a sampling preprocessing for SVM training to improve the scalability. We develop a novel top-down kernel clustering approach which tends to fast produce balanced clusters of similar sizes in the kernel...
