Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
A novel Neural Network Based Fuzzy Inference System for financial default forecast will be introduced. A wide range of financial forecasts is known. This method is focusing on the economical default forecast, but the method can be used generally for other financial forecasts as well, for example for calculating the Value at Risk. This hybrid method is combined by two classical methods: the artificial...
In order to study the impact of drivers' distance cognition difference on traffic safety in dynamic environment of daytime and night-time, a real road tests was carried out by asking 19 drivers randomly selected to percept the distances of obstacles with different distances and velocities on daytime and nighttime. The values of cognition are obtained by statistical methods. The distance cognition...
Artificial neural network is an important research direction in data mining. It is used to solve classification and regression problems, and can find out the nonlinear relation between the input attribute and the output attribute, especially the smooth and continuous nonlinear relations. Use the Microsoft neural network to find out how the meteorological factors influence the precipitation, and to...
Water resources sustainable use evaluation plays an important role in water resources planning and management, and it is a typical multi-goals, multi-layers and multi-attributes decision-making process, it needs to consider comprehensively social, economic, resources and environmental factors. A new evaluation index system of water resources sustainable utilization has been set up based on Yunnan...
It has been 50 years since the idea popped up that calculating systems can be made on the replica of the biological neural networks. Still, the development of this science branch made the improvement of these systems possible only in the last 25-30 years. Nowadays, neural computing is a very extensive, separate science. Its solid theory basis made it possible to use them to solve many kind of problems...
This thesis introduces the forecasting methods of domestic and foreign road traffic flow, analyzes the advantages and shortcomings of all sorts of traffic flow forecasting methods and the actual forecasting effects. For the complexity of the urban traffic, the precision of some current traffic flow forecasting methods is not high. With respect to these questions, this thesis applies the chaotic neural...
In this paper the robustness of three different types of Fuzzy Flip-Flop based Neural Network (FNN) and the standard tansig based neural networks is compared from the various test function approximation goodness points of view. It is tested how well the fuzzy flip-flop based and the simulated neural networks handle the test data sets outlier points. The robust design of the FNN is presented, and the...
Evaluating road safety is essential in identifying the potential road safety hazard which could result in casualties and property losses. in this paper, a BP neural network was built by using neural network toolkit in "Matlab", Two similar roadways are used in calibrating and validating the network. The high level of predictability provided that the application of BP neural network model...
The drilling of hard-to-cut high manganese steel materials is a difficulty in the field of machining. Research method for drilling temperature which has been commonly used is experimental method. The method has long-time and the high-cost drawbacks. Adopting error back neural network technology and using Matlab and C language programming method, in this paper neural network prediction model of drilling...
At present, the determining method on feature weight have the problems of complexity and one-sidedness of determining in case-based reasoning system. In this paper, an integrated method based on BP Neural Network and sensitivity analysis is studied. An algorithm based on BP Neural Network and sensitivity analysis (BPNN-SA) is put forward, the network topology changes in accordance with input nodes...
Aiming at the shortages of the existing data-mining model for forecasting the industry security, a classification model based on rough sets and BP neural network (BPNN) is put forward in this paper. First, the theory of rough set is applied to pick up and reduce the index attributes. Then, the training samples are sent to the BPNN to train and learn. After that, the sorts of the coal industry security...
In this research, the combination of modal data is used to identify the damage of a FEM model using neural networks. The identification ability with different levels of noise and incomplete mode shapes are also investigated. It has been proved that the neural network using combination of modal parameters as input has a excellent identification ability with ideal error tolerance and robustness. Numberical...
A novel identification technique for lumped models of general distributed circuits (i.e. microwave transmission lines, monolithic integrated circuits and filters) is presented. The approach is based on a hybrid neural network having based on Multi-valued neurons network with a modified layer and learning process, whose convergence allows the validation of the circuit approximated lumped model. The...
In this paper we have proposed a new way to achieve the optimum learning rate that can reduce the learning time of the multi layer feed forward neural network. The effect of optimum numbers of inner iterations and numbers of hidden nodes on learning time and recognition rate has been shown. The Principal Component Analysis and Multilayer Feed Forward Neural Network are applied in face recognition...
In this work, design of low-voltage low-power analog artificial neural network (ANN) circuit blocks by using subthreshold floating-gate MOS (FGMOS) transistors and a neuron circuit is implemented. The circuit blocks, four-quadrant analog current multiplier and FGMOS based differential pair, have been designed and simulated in CADENCE environment with TSMC 0.35μm process parameters. Using the proposed...
Here we have presented an alternate ANN structure called functional link ANN (FLANN) for channel equalization. In contrast to a feed forward ANN structure i.e. a multilayer perceptron (MLP), the FLANN is basically a single layer structure in which non-linearity is introduced by enhancing the input pattern with nonlinear function expansion. A novel method of training the FLANNs using PSO Algorithm...
Neural networks are often selected as tool for software effort prediction because of their capability to approximate any continuous function with arbitrary accuracy. A major drawback of neural networks is the complex mapping between inputs and output, which is not easily understood by a user. This paper describes a rule extraction technique that derives a set of comprehensible IF-THEN rules from a...
We investigate how firing behavior of FitzHugh-Nagumo neuron depends on the intensity of Gaussian white noise. It is found that there exists an intermediate range intensity of noise where the firing behavior of neuron is induced and enhanced. To quantitatively study the firing degree of the neuron, the average number of firing spiking is introduced to measure the frequency of the firing patterns....
Objective Forecast and analysis of cerebral infraction incidence rate are the basis and key work of cerebral infraction prevention and control. At present, forecast of cerebral infraction incidence rate is mainly based on traditional research approach or single artificial neural network technology. Recent study results show that combined forecast model approach enjoys more precise forecast than monomial...
In this paper, two modeling approaches (artificial neural network and regression model) are established and used to predict the fiber diameter of melt blowing nonwovens. By analyzing the results of the models, the effects of process parameters on fiber diameter can be predicted. The results demonstrated that the ANN model yields more accurate and stable predictions than regression model, which is...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.