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.
We consider a fully complex-valued radial basis function (RBF) network for regression application. The locally regularised orthogonal least squares (LROLS) algorithm with the D-optimality experimental design, originally derived for constructing parsimonious real-valued RBF network models, is extended to the fully complex-valued RBF network. Like its real-valued counterpart, the proposed algorithm...
This paper presents a simplified primal-dual neural network based on linear variational inequalities (LVI) for online repetitive motion planning of PA10 robot manipulator. To do this, a drift-free criterion is exploited in the form of a quadratic function. In addition, the repetitive-motion-planning scheme could incorporate the joint limits and joint velocity limits simultaneously. Such a scheme is...
A novel approach for data mining of steam turbine based on neural network and genetic algorithm is brought forward, aimed at overcoming shortages of some current knowledge attaining methods. The historical fault data of steam turbine is processed with fuzzy and discrete method firstly, a multiplayer backpropagation neural network is structured secondly, the neural network is trained via teacherpsilas...
The generation of weights is an alternative method of loading a set of weights into an artificial neural network. It is a process that transforms a trained base net by multiplying its weights by symmetric matrices [1]. These weights are then assigned to a derived net. The derived nets map symmetrically related functions. At present, the process is limited because it cannot be applied to one-to-many...
The RoboCup Simulation League is recognized as a test bed for research on multi-agent learning. As an example of multi-agent learning in a soccer game, we dealt with a learning problem between a kicker and a receiver when a direct free kick is awarded just outside the opponentpsilas penalty area. In such a situation, to which point should the kicker kick the ball? We propose a function that expresses...
Identification of nonlinear state space models when no information is available from the state transition or output model has played an important role in the recent research. In this paper, we propose a new approach for modeling a discrete time nonlinear state space system with a multi layer perceptron (MLP) neural network. The expectation maximization (EM) algorithm is used for joint parameter and...
How to choose the optimal parameter is crucial for the kernel method, because kernel parameters perform significantly on the kernel method. In this paper, a novel approach is proposed to choose the kernel parameter for the kernel nearest-neighbor classifier (KNN). The values of the kernel parameter are computed through optimizing an object function designed for measuring the classification reliability...
Representation of knowledge within a neural model is an active field of research involved with the development of alternative structures, training algorithms, learning modes and applications. Radial Basis Function Neural Networks (RBFNNs) constitute an important part of the neural networks research as the operating principle is to discover and exploit similarities between an input vector and a feature...
In this paper, an adaptive edge-based text detection approach in images and video frames is proposed. The proposed approach can adopt different edge detection methods according to the image background complexity. It mainly consists of four stages: Firstly, images are classified into different background complexities. Secondly, different edge detectors are applied on the images according to their background...
Some discrete Fourier kind transforms (DFKT) which include the discrete Fourier transform (DFT), discrete chirp Fourier transform (DCFT), three-order discrete chirp Fourier transform (TDCFT), discrete matched transform based on phase compensation (DMTPC) are studied in the symmetric alpha-stable ( SalphaS ) noise environment. Some DFKTs based on the fractional lower order statistics (FLOS) (DFKT_FLOS)...
This paper presents a one-layer recurrent neural network for solving convex programming problems subject to linear equality and nonnegativity constraints. The number of neurons in the neural network is equal to that of decision variables in the optimization problem. Compared with the existing neural networks for optimization, the proposed neural network has lower model complexity. Moreover, the proposed...
This article studies the usages of texture analysis methods to classify ultrasonic rotator cuff images into the different disease groups that are normal, tendon inflammation, calcific tendonitis and tendon tear. The adopted texture analysis methods include the texture feature coding method, gray-level co-occurrence matrix, fractal dimension and texture spectrum. The texture features of the four methods...
An hybrid particle swarm optimization PSO-based wavelet neural network for modelling the development of fluid dispensing for electronic packaging is presented in this paper. In modelling the fluid dispensing process, it is important to understand the process behaviour as well as determine optimum operating conditions of the process for a high-yield, low cost and robust operation. Modelling the fluid...
A recurrent neural network is proposed to deal with the nonlinear variational inequalities with linear equality and nonlinear inequality constraints. By exploiting the equality constraints, the original variational inequality problem can be transformed into a simplified one with only inequality constraints. Therefore, by solving this simplified problem, the neural network architecture complexity is...
In this paper the path planning for obstacle-avoided pursuit problem (OAP) is studied. The OAP models based on the mixed integer linear programming (MILP) is presented. In the OAP models, the dynamic equation of mass point with linear damping is taken as the state equation of vehiclepsilas motion. Integer variables are used to describe the relative position of vehicle and obstacles. ldquoExpansible...
This study focuses on the design of a dynamic Petri recurrent-fuzzy-neural-network (DPRFNN) control for the path tracking of a nonholonomic mobile robot. In the DPRFNN, the concept of a Petri net (PN) and the recurrent frame of internal feedback loops are incorporated into a traditional fuzzy neural network (FNN) to alleviate the computation burden of parameter learning and to enhance the dynamic...
Based on quaternion, an algorithm for color image de-noising has been proposed in this paper. According to the quaternion singular value decomposition theory, in a color image, the singular values on the diagonal matrix, which were obtained through QSVD, represent the color images in different channels. The additive noise of a color image can be eliminated effectively by keeping the proper singular...
To obtain the inverses of time-varying matrices in real time, a special kind of recurrent neural networks has recently been proposed by Zhang et al. It is proved that such a Zhang neural network (ZNN) could globally exponentially converge to the exact inverse of a given time-varying matrix. To find out the effect of time-derivative term on global convergence as well as for easier hardware-implementation...
In this paper, stochastic control of nonlinear state space models is discussed. After a brief review on nonlinear state space models, a multi layer perceptron (MLP) neural network is considered to represent the general structure of the controller. Then, an expectation maximization (EM) algorithm joint with the particle smoothing framework are proposed for updating parameters of the MLP network. The...
To localize a seen object, the superior colliculus of the barn owl integrates the visual and auditory localization cues which are accessed from the sensory system of the brain. These cues are formed as visual and auditory maps, thus the alignment between visual and auditory maps is very important for accurate localization in prey behavior. Blindness or prism wearing may disturb this alignment. The...
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.