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.
Feature extractors are used to get mathematical features that can be machine readable. In this paper we proposed a novel feature extraction and similarity measurement method based on RBF neural network one-step deviation prediction, which is different from traditional time series researches. The method converts time series similarity to feature vectors similarity comparison, while feature vectors...
The lateral acceleration of railway coach is chaotic time series with certain law when it passes the curve. The passing curve unbalanced acceleration can be predicted with the law and the experiment data in certain time. And the predicted values can be used as the input reference signals of the active control system of the vehicle. The center and normalizing parameters of the active function of the...
Real earthquake time series were analyzed and studied by chaos theory. Through the quantitative identification of time series, the results show that seismic time series performance deterministic chaotic characteristics. Considering the problems of slow convergence speed and low efficiency and local optimum caused by Gradient descent method, a method which momentum term with adaptive momentum factor...
It is significant to control network congestion by time series forecasting research for network flow. The hybrid method of particle swarm optimization algorithm and RBF neural network is applied to predict network flow and gain the desirable network flow prediction results. In the hybrid method, particle swarm optimization algorithm is selected and adjusted to the connection weights and the center...
Time series forecasting is the main method in network flow prediction. RBF neural network is capable of universal approximation, which not only has fast training velocity, but also can solve the local minima problem. Thus, network flow prediction technology based on genetic algorithm and RBF neural network is presented in the paper. And the training parameters are adjusted by genetic algorithm. Network...
This paper discusses a method for chaotic time series prediction based on radial basis function (RBF) neural network. The number of input nodes for RBF is determined by embedding dimension based on chaotic phase-space reconstruction. Both Grassberger--Procaccia algorithm and Takens' method are employed to calculate minimal embedding dimension of chaotic time series. Finally, the prediction accuracy...
A new disaster monitor and forecast system based on RBF neural networks is proposed. This disaster forecast system consists of disaster spatial monitor subsystem that is pre-trained by off-line learning algorithms and disaster time forecast subsystem developed by online learning algorithms. The disaster spatial monitor subsystem aims to detect trend of the objective behavior, once the unstable condition...
Rainfall prediction is a key question in the study field of hydrology and water resources. Point to non-linear, chaotic character and with the noise characteristics Run-off signals, we propose a new model based on empirical mode decomposition (EMD) and the RBF neural network (RBF). First, rainfall time series will be broken down into a series of different scales intrinsic mode function imf by EMD,...
Automobile sells system plays an important role in automobile sales area, through the whole produce and management. Some forecast models have had unilateralism in some side nowadays, such as ARMA model. For example, the data of non-linearity has some error by ARMA model. This paper, assembles curve -regression model, Time Series Decomposition Model and RBF neural networks according to the weight distribution...
The original electrical signals in Crassula portulacea were tested by a touching test used platinum sensors in a system of self-made double shields. Tested data of the electrical signals were denoised by the wavelet soft threshold and using Gaussian radial base function (RBF) as the time series at a delayed input window chosen at 50. An intelligent RBF forecasting system was set up to forecast the...
Economic growth forecasting is important to make the policy on national economic development. Support vector machine (SVM) is a new machine learning method, which seeks to minimize an upper bound of the generalization error instead of the empirical error as in conventional neural networks. In the study, support vector machine and particle swarm optimization is applied in economic growth forecasting,...
The CNY exchange rates can be viewed as financial time series which are charactered by high uncertainty, nonlinearity and time-varying behavior. Predictions for exchange rates of GBP-CNY and USD-CNY were carried respectively by means of RBF neural network forecasters. The detailed designs for architectures of RBF neural network models, transfer functions of the hidden layer nodes, input vectors and...
Since 2007, CPI in our country has reached new high repeatedly, causes attention closely in society. Using data published by State Statistical Bureau, this article, after process, applies RBF neural network with momentum item to forecast separately CPI in 2008 and in 2009 will be respectively 109.4733 and 106.4275, and also puts forward some corresponding policy proposals.
Landslide is a kind of genetic type of slope and has the same characteristics with slope. The major external motivation factor of landslide displacement is groundwater and it is under the control of remedial measures at the same time after its remediation. Chaotic time series of landslide displacement and its influential factors could reflect the history of landslide displacement of dynamic system,...
The following topics are dealt with: shape reliability; software reliability engineering; software product characteristics; software safety; defect content prediction; RBF neural network; program bugs; JavaScript vulnerabilities; computer security; time series models; QoS-aware middleware; fault tolerant Web services; operating system robustness; system logs; OS device drivers; runtime test case generation;...
Because of some advantages obtained from non-cooperative passive detection system, such as anti-surveillance, anti-interference, anti-stealth, anti-radiation missile and so on, it will become a crucial trend of radar systems in the future. The key problem in this system is the detection of weak echo signal, which is submerged in interference and noise. In this paper, the echo signal in non-cooperative...
In order to improve the energy-saving efficiency, a novel heat load prediction method based on radial basis function neural network (RBF NN) and time series crossover is proposed according to the characteristics of heat supply process. The dimension of the input vector in the RBF NN model is established with autocorrelation method. Then the horizontal and vertical prediction models are constructed...
Taking electrical signals in the Catharanthus roseus as the time series and using the Gaussian radial base function (RBF) and a delayed input window chosen at 50, an intelligent RBF forecast system is set up to forecast signals by the wavelet soft-threshold de-noised backward. It is obvious that the electrical signal in Catharanthus roseus is a sort of weak, unstable and low frequency signals. There...
In this paper, a novel approach to predict turning points for chaotic financial time series is proposed based on chaotic theory and machine learning. The nonlinear mapping between different data points in primitive time series is derived and proven. Our definition of turning points produces an event characterization function, which can transform the profile of time series to a measure. The RBF neural...
Taking electrical signals in the chrysanthemum (Dendranthema morifolium) as the time series and using the Gaussian radial base function (RBF) and a delayed input window chosen at 50, an intelligent RBF forecast system is set up to forecast signals by the wavelet soft-threshold de-noised backward. It is obvious that the electrical signal in chrysanthemum is a sort of weak, unstable and low frequency...
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.