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.
Face is a complex multidimensional visual model and developing a computational model for face recognition is difficult. The paper presents a methodology for face recognition based on information theory approach of coding and decoding the face image. Proposed methodology is connection of two stages - Feature extraction using Principle Component Analysis and recognition using the feed forward back propagation...
Local minimum is incorporated problem in neural network (NN) training. To alleviate this problem, a modification of standard backpropagation (BP) algorithm, called BPCL for training NN is proposed. When local minimum arrives in the training, the weights of NN become idle. If the chaotic variation of learning rate (LR) is included during training, the weight update may be accelerated in the local minimum...
Aiming at the disadvantages of prediction model of single BP neural network, a prediction model was presented by combining AdaBoost algorithm and BP neural network for improving the forecasting accuracy of single BP neural network. A new updating method is proposed for the characters of ensemble BP neural network based on AdaBoost. The new method can update the model effectively and overcome the disadvantage...
Combining the intelligent algorithm such as BP neural network and support vector maching (SVM) with traditional chemical method, this paper models the relationship between plant surface color and its pigment. Using the neural network model constructed above, people can figure out the content of plant pigments by getting the corresponding plant surface color information. Compared with the traditional...
The goal of this project is thus to experiment with ANNs and to evaluate performance of ANN models in studying stock price patterns in time by attempting to predict future results of a time-series by simply studying patterns in the time-series of stock prices. In this project we have instantiated the proposed Neural Network using the stock prices of Iran Tractor Manufacturing Company during two years...
This paper focused on experimental data and study for the testing of the material mechanical properties using vibration technique. By applying vibration analysis and testing on the material, we could determine the natural frequencies, the damping ratio and mode shapes of the structure. However, in this study, we only considering the natural frequencies of the material as the input data needed for...
This paper presents a procedure for allocating reactive power using artificial neural network (ANN). Artificial neural network is trained based on data from Y-bus matrix. Training and testing of this ANN network have been done with five bus test system. Back propagation learning has been utilized to train the ANN. A numerical example on allocating reactive power using a feed forward back propagation...
Aiming at the difficulty of tank unit combat formation recognition in virtual simulation training, the recognition method based on BP neural network is put forward. After analyzing the definition and character of the tank unit combat formation, the recognition strategy for tank unit formation is put forward. Then the recognition model based on BP neural network is built. In order to get plentiful...
Established the computational model about the safe distance of vehicles. In order to simulate the dynamic model of rear-end, based on VB software to build a freeway rear-end simulation system. Simulation system provides an important means for in-depth study on rear-end probability. To investigate the non-linear relationship of probability and impact factors of rear-end, established probability of...
A forecasting model for gas emission based on wavelet neural network is proposed in this paper. In the model, wavelet neutral network (WNN) is applied to the forecasting with gradient descent and amended by validity of iteration training algorithm. Compared with back-propagation neural networks, forecasting of the model has advantages of faster convergence and more accurate. Simulation results have...
The generalization ability of neural network is an important aspect affecting its application. Meanwhile, the selection of training samples has a great impact on this ability. In order to improve the completeness of training samples, a method of samples self-learning of BP neural network based on clustering is put forward in this paper. By using the method of clustering, new samples can be collected...
Knowledge manufacturing system has the ability of modifying dynamically manufacturing mode rapidly when production environment factors change. It is essential to evaluate the matching degree of established manufacturing mode and changed production environment factors. In this paper, a matching decision model for self-adaptability of knowledge manufacturing system based on the fuzzy neural network...
Three indicators (R, I30, P), and all four indicators (R, I30, P, I) of erosive rainfall in Jia Zhaichuan small watershed of Song county are chosen respectively as the input vector to predict sedimentation volume with the two neural network of RBF and BP, and fit with the actual values. The results testify the fitting and predicted effects of RBF neural network are all better than BP network, as well...
In this paper we proposed a new algorithm for neural network training. This algorithm is developed from modification on Levenberg-Marquardt algorithm for MLP neural network learning. The proposed algorithm has good convergence. This method reduces the amount of oscillation in learning procedure. We named this algorithm as GK-LM Method. An example is given here to show usefulness of this method. Finally...
The feedforward neural networks trained with the online backpropagation (BP) learning algorithm have been widely studied in various areas of scientific research and engineering applications. In this paper we further study the convergence property of the online BP learning algorithm. Unlike the existing convergence analysis mainly focusing on the convergence of the gradient sequence of the error functions,...
This paper takes a kind of ceramic glaze as an example, and builds an improved BP neural network model for optimizing the formulation on ceramic glaze. The improved BP neural network adopts Levenberg-Marquardt algorithms. The paper reviews how to build the ceramic formulation optimization model based on BP artificial neural network, including the establishment of neural network, the training, and...
This paper aims to develop intelligent Predictive Monitoring Emission Systems (PEMS) for three distinct case studies involving traffic, gasoline fuel tanks and large combustion plants (LCP). The underlying theme of pollutant emissions exists in all three case studies whereby the gases that are monitored are NO2, unburned hydrocarbons, and SO2. These pollutants can cause grievous harm to health, environment...
This paper proposed the heart disease diagnosis system using nonlinear ARX (NARX) model. The system uses neural network for model estimation and classification of Normal and several heart diseases based on heart sounds. In classification, a spectrogram was applied to the modeled heart sounds for features extraction and selection. The features were fed to the FFNN and trained using Resilient Backpropagation...
This paper proposes that we can improve the accuracy of the distance between ZigBee with the algorithm of BP neural network. Firstly, we analyze the wireless signaling path loss model, the principle of measuring distance based on RSSI, and the algorithm of BP neural network fully. Secondly, we get the experimental data from the hardware platform of ZigBee. Finally, we use the algorithm of BP neural...
The traditional neural network is unavoidable to present local extreme value question, may result in failing training. On the basis of quantization of weapon system safe index, it has adopted neural network based on improved genetic algorithm to set up the systematic safety evaluation model of the weapon. It utilizes improved genetic algorithm to optimize the weight of neural network and get the final...
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.