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.
The following topics are dealt with: neural networks and applications; machine learning; multimedia systems and applications; speech processing; image processing; video signal processing; computer aided network design; intelligent robots; intelligent circuits and systems; industrial applications; intelligent control; wireless computing.
This paper presents a character segmentation method of vehicle license plate using modified vertical projection. After analyzing the reason of failure of traditional segmentation methods, the paper gives some methods to deal with character adhesion and segmentation mistakes, which improves the success probability of segmentation obviously. The most valuable feature of this new algorithm is that it...
A successful rough set methodology based on discernibility of objects and Boolean reasoning has been developed for computing decision rules. However, the requirement of an equivalent relation seems to be a stringent condition that may limit the application domain of the Pawlak rough set model, especially when the data describing objects is imprecise or when small differences are meaningless in the...
This paper presents a new real-time path planning algorithm in dynamic uncertainty environment, and it has well real-time and high applicability. This algorithm is composed by two parts. The first part is the analysis and interpretation of the environment information by searching the characteristic information (double safe edges DSE), so the algorithm can catch the dynamic obstacle and estimate the...
To enhance its global optimization speed, the basic ant colony optimization (ACO) is modified, then it is used to optimize the neural networks (NN), and the optimized NN is applied to the direct torque control (DTC) system, so that the rotate speed can be observed. The DTC with speed sensorless is implemented at last. The research of simulation shows that, the modified ACO has eminent global optimization...
The method was studied about traffic flow prediction by using subtractive clustering for fuzzy neural network model of phase-space reconstruction. The prediction model of traffic flow must be established to satisfy the intelligent need of high precision through analyzing problems of the existing predicting methods in chaos traffic flow time series and the demand of uncertain traffic system. Based...
In this paper, an integer pixel search algorithm based on prediction (PIS) is proposed. The primary characteristic of this algorithm is using quadrangle and flat hexagon as search pattern. To strengthen the flexibility and precision of this algorithm, early termination strategy is adopted. And to prove the validity of the PIS algorithm, besides some theories and computation analysis, several experiments...
A special kind of recurrent neural network has recently been proposed by Zhang et al for matrix inversion. Then, for possible hardware and digital-circuit realization, the corresponding discrete-time model of Zhang neural network (ZNN) is proposed for constant matrix inversion, which reduces exactly to Newton iteration when linear activation functions and constat step-size 1 are used. In this paper,...
A special kind of recurrent neural networks (RNN), i.e., Zhang neural networks (ZNN), has recently been proposed for online time-varying problems solving. In this paper, we generalize and investigate the Matlab Simulink modeling and verification of a ZNN model for online time-varying matrix pseudoinverse solving. Based on click-and-drag mouse operations, Simulink could be easily and conveniently used...
The work of how to measure the difference, or deviation, between two models is an important studied problem. Venkatesh Ganti has developed the FOCUS framework for computing an interpretable, qualifiable deviation measure between two datasets in terms of the models they induce. In this paper, we propose a novel method to measure the deviation for cluster models making use of CF-tree based on the FOCUS...
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.