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.
A new network for fuzzy-neural system was proposed based on the analysis and comparison of existing methods, which could be easy to distill the fuzzy rules. The network structure was adjusted by FBP(Fuzzy Back Propagation) learning algorithm to acquire network parameters and variable weights. By aiming at disadvantage of IP algorithm on rule-optimization, the Improved Iterative Pruning Neural Network...
Singular points detection, a crucial step for fingerprint identification system, is accurately robust, and reliable. In the processing of the fingerprint image matching and classification, many method use singular points to align two fingerprint images to surmount the problems about rotation and translation. The performances of the fingerprint recognition system rely on the effect of singular points...
It was found that many of factors would evidently affect the calibration results in Hybrid III 5th Female Dummy neck calibration tests. This paper developed a BP neural network model for analysis and prediction of the relationship between calibration parameters and neck deceleration characteristics. The input parameters of the BP model are calibration temperature, impact velocity of pendulum, cells...
A intelligent monitor and control system on multi-factor of aquaculture environment based on wireless sensor networks is designed adopting BP neural networks. The system uses wireless sensor nodes to detect a variety of water quality parameters transmitted to the on-site monitoring host computer through sink node wirelessly. The control module consists of fuzzy controller and decoupling neural network...
In order to design the products that meet consumer emotional demands, this paper proposes a systematic method which combines neural network with genetic algorithm. Firstly, a back propagation neural network is applied to map the relationships between product design elements and customer kansei image evaluation. Secondly, generic algorithm is employed to search for the optimal product form which satisfies...
Methods for the identification of temperature in intelligent building and building equipments is one of hot topics focused by lots of researchers in that research area. To implement the process of inspecting and forecasting of energy efficiency in building and its accessory, a feed forward neural network is used as the identification structure for temperature identification of internal space in building...
Network is more and more popular in the present society. Least squares support vector machine is a kind modified support vector machine for classification, which can solve a convex quadratic programming problem. Least squares support vector machine is presented to network intrusion detection. We apply KDDCUP99 experimental data of MIT Lincoln Laboratory to research the classification performance of...
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...
Prediction of regional logistics requirement provides a basis for the plan of regional logistics. In the study, support vector regression is presented to predict regional logistics requirement. The regional logistics data from 1996 to 2006 in Shanghai municipality are used as the application data of support vector regression. The comparison of prediction error between BP neural network and support...
There are many drawbacks in the current electric power emergency management system, which takes plans as the center. The urgent need is to replace for the electric power emergency management mechanism as the core of emergency response system, coping with several disasters in recent years. Because of the generally poor construction of response mechanism in China's electric power companies, the establishment...
In the paper, support vector machine is adopted to predict the time delay induced in the networked control system by using time delay historical data. We employ the reaction curve of sine to testify the feasibility of support vector machine. Finally, BP neural network delay predictor is used to compare with support vector machine delay predictor. The testing results demonstrate that the prediction...
Using genetic algorithm and BP neural network method of combining, this paper has established dynamic forward feedback correction model and has completed the automatic adjustment of the various parameters required for rolling steel pipe, and has made rolled steel pipe system work at the best value. After the actual data validation, the model can more accurately pre-adjusted parameters to achieve intelligent...
The accurate diagnosis of rice pest insects and diseases is very important for high yielding and high quality cultivation of rice. Because the characteristics of rice pest insects and diseases are miscellaneous, and its occurred environment is complex, it is difficult to diagnose accurately using artificial intelligence system. In this study, BP neural network technology is applied to a rice pest...
The problem of environmental quality assessment is a pattern recognition problem, and a well-trained ANN can exploit the underlying nonlinear relationships that determine the environmental rating of a region. In this study, we are trying with the neural network model to make an effective analysis for environmental quality assessment. A 4-9-1 three-layer feedforward neural network using the backpropagation...
It is widely believed that human resource competitiveness is becoming the core competitiveness of an enterprise. Nowadays, IT (Information Technology) is widely used in human resource management. This paper extracted four factors-cost factor, turnover factor, human resource planning factor and employee development factor from 30 indexes of the enterprise human resource competitiveness by using PCA...
As a substitute for conventional diesel, biodiesel has received considerable attention in many countries. To investigate the emissions of an engine by experiment is time-consuming and costly, so a lot of mathematical models are used to predict the emissions of engines. A back propagation (BP) neural network was used to establish an emission model of the diesel engine fueled with biodiesel The results...
Decision-making structures are important building blocks in most of the software; however, it may be difficult to verify them because there are various input conditions and several paths causing them to behave differently. Test oracles are reliable sources of how the software must operate. The aim of the present paper is to study the applications of Artificial Neural Networks as an automated oracle...
Ammonium dihydrogen phosphate(DAP) is widely used in the industry. Usually this product contains impurities and substances and may not satisfy the need of modern agricultural and industrial demand, so we must dip and recrystalize for high quality product. In the process of crystallization, the nucleation rate and the growth rate are the most important parameter, then we study these parameter in order...
In this paper, a new method of coal rock interface recognition(CRIR) based on independent component analysis and BP neural network is presented. ICA algorithm was used to separate the preprocessed acoustic signal and extract independent components of coal and rock. By analyzing power spectrum of the first two independent components, we found the difference of coal and rock in specific frequency interval...
Although simple genetic algorithm (SGA) can, to some extent, improve the back propagation neural network (BP), it is prone to prematurity and losing the optimal solutions. Niche technology and fuzzy control theory are introduced to improve SGA and the improved one is used to optimize BP. The improved genetic algorithm is used to optimize BP neural network. In addition, due to the increasingly voltage...
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.