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.
Different from gradient-based dynamics (GD), a special class of neural dynamics has been found, developed, generalized and investigated by Zhang et al, e.g., for online solution of time-varying and/or static nonlinear equations. The resultant Zhang dynamics (ZD) is designed based on the elimination of an indefinite error-function (instead of the elimination of a square-based positive or at least lower-bounded...
In this paper, we investigate monomial reachability and reachability of the special class of discrete-time positive switched systems whose subsystems exhibit the same system matrix A and different input-to-state matrices bi. Necessary and sufficient conditions for these properties to hold, together with some related examples, are provided.
Back-propagation neural network model was developed to predict the coal and gas outburst. After trained, the artificial neural network model was used to predict the coal and gas outburst of several samples. Moreover, ANN model was also used to analyse the quantitative effects of influencing factors on the coal and gas outburst. The prediction performance of ANN model is satisfactory. The prediction...
The statistical analysis of traffic flow is the fundamental of road traffic forecasting with data mining. In the common traffic flow theory, macroscopic flow model and data presentation shows chaos and stochastic distribution. However, in the microscopic based traffic model, it is revealed that in high frequency sampled test, the variables such as flow, density, and lane usage have common trend of...
In this paper, we propose a linear finite difference scheme for the initial-boundary problem of Rosenau-Burgers equation. We not only discuss solvability, stability and convergence of the scheme in detail, but also prove that the numerical solution of the scheme converges to the exact solution of the original problem in the sense of ????????-norm. At last, a numerical example, which compares results...
Height difference between GPS height and normal height is called height anomaly. If height anomaly for a point can be estimated, GPS height above the surface of the WGS-84 ellipsoid can be converted into normal height, which is used in engineering applications. A new robust procedure by using the conicoid fitting method (CFM) with the Huber M-estimation was proposed, to convert GPS height to normal...
The paper introduces the random factor in Particle Swarm Optimization. Comparing with inertia weight, the particle's velocity is determined by previous velocity, own experience, public knowledge and random behavior. The random operator is similar with the mutation operator in the Genetic Algorithms. Simulation results show that the method introducing the random factor is better than inertia weight...
According to mapping relationship of the relative internal efficiency of low pressure cylinder of condensing steam turbine and its affection, a mathematical model based on the Immune system's wavelet network was established. It can be used for calculating the relative internal efficiency of low pressure cylinder of 300 MW steam turbine. The application of the model shows that the proposed method is...
In this paper, a novel function series expansion method based on functional network model is proposed, and a functional network model for functions in several variables series expansion and learning algorithm are given, the learning of parameters of the functional networks is carried out by the solving linear equations. The simulation results show that the proposed approach is more efficient and feasible...
As is known to all, the neutral network has made a great progress in many fields. But due to some strict theoretical system, there are still many defaults in practical application. In this paper, we present an active learning artificial neural network (ALANN). The key issue of this kind of approach is what information can be analysis and forecast about time series(TS). However, the parameters of ALANN...
How to retain the high load precision of a motor-driven load simulator in the case of great change in load gradient is one of its key problems. In the past, the compound PID control method was used to improve its load precision. However, because of the influence of its time-varying character and non-linearity, the method does not produce ideal load speed or precision. Taking the characteristics of...
This paper presents an inverse optimal neural controller, which is constituted by the combination of two well known techniques: (a) inverse optimal control to avoid solving the Hamilton Jacobi Bellman (HJB) equation associated to nonlinear system optimal control, and (b) an on-line neural identifier, which uses a recurrent neural network, trained with the extended Kalman filter (EKF), in order to...
In this paper, a new kind of intelligent PID control method based on BP neural network is presented and a complex neural network PID controller is designed. The NN controller has strong self-adaptability and self-learning abilities. Experimental results on different complex objects prove that, the control method has better performances than traditional PID controller. The system using neural network...
Data association is one of the crucial parts in the reliable objects' tracking system. In this paper, a methodology for data association using an Oriented Bounding Box based object representation is presented. A laser scanner sensor is used for objects perception. A data association algorithm for coalescing objects is described. The algorithm is based on the Nearest Neighbours principle enriched by...
Mine work face gas emission quantity is an important mine design basis, which also has important practical significance for guide mine design, ventilation and safety production. Mine gas emission quantity and work face multi factors have complex non-linear relationship. The paper built the work face gas emission prediction support vector machine (SVM) model. Based on data statistic of a mine work...
This paper investigates the global exponential stability of static neural networks (SNN) with time-varying delays and fixed moments of impulsive effect. Sufficient conditions for the exponential stability are established by using Lyapunov functions and the Razumikhin technique.
Random early detection (RED) is a network congestion control algorithm which calculates the packet-loss ratio according to current length of average queue. This paper describes an improved RED algorithm: Firstly, predicts network flows with RBF neural network in order to forecast queue length much earlier, and then, fits the packet-loss-ratio of RED algorithm according to some special points using...
Traffic congestion is a serious problem which traffic engineers all over the world are trying to solve. Congestion increases the uncertainty in travel times leading to human stress and unsafe traffic situations. Better management of traffic through intelligent transportation systems (ITS) applications, especially by predicting the congestion on various roads and informing the travelers regarding the...
This paper describes an novel approach towards linguistic processing for robots through integration of a motion language module and a natural language module. The motion language module represents association between symbolized motion patterns and words. The natural language module models sentences. The motion language module and the natural language module are graphically integrated. The integration...
In order to eliminate the ambiguity and uncertainty exist in the conventional classification for remote sensing images, the BP neural network was presented. However, the BP network itself also exist some limitations and shortages which are primarily represented in the aspects of network training speed low, optimization for convergence to integer not easy and so on. This paper improves the BP neural...
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.