A survey on RBF Neural Network for Intrusion Detection System
Henali Sheth
2014-12-01
Full Text Available Network security is a hot burning issue nowadays. With the help of technology advancement intruders or hackers are adopting new methods to create different attacks in order to harm network security. Intrusion detection system (IDS is a kind of security software which inspects all incoming and outgoing network traffic and it will generate alerts if any attack or unusual behavior is found in a network. Various approaches are used for IDS such as data mining, neural network, genetic and statistical approach. Among this Neural Network is more suitable approach for IDS. This paper describes RBF neural network approach for Intrusion detection system. RBF is a feed forward and supervise technique of neural network.RBF approach has good classification ability but its performance depends on its parameters. Based on survey we find that RBF approach has some short comings. In order to overcome this we need to do proper optimization of RBF parameters.
Evolving RBF neural networks for adaptive soft-sensor design.
Alexandridis, Alex
2013-12-01
This work presents an adaptive framework for building soft-sensors based on radial basis function (RBF) neural network models. The adaptive fuzzy means algorithm is utilized in order to evolve an RBF network, which approximates the unknown system based on input-output data from it. The methodology gradually builds the RBF network model, based on two separate levels of adaptation: On the first level, the structure of the hidden layer is modified by adding or deleting RBF centers, while on the second level, the synaptic weights are adjusted with the recursive least squares with exponential forgetting algorithm. The proposed approach is tested on two different systems, namely a simulated nonlinear DC Motor and a real industrial reactor. The results show that the produced soft-sensors can be successfully applied to model the two nonlinear systems. A comparison with two different adaptive modeling techniques, namely a dynamic evolving neural-fuzzy inference system (DENFIS) and neural networks trained with online backpropagation, highlights the advantages of the proposed methodology.
Classification data mining method based on dynamic RBF neural networks
Zhou, Lijuan; Xu, Min; Zhang, Zhang; Duan, Luping
2009-04-01
With the widely application of databases and sharp development of Internet, The capacity of utilizing information technology to manufacture and collect data has improved greatly. It is an urgent problem to mine useful information or knowledge from large databases or data warehouses. Therefore, data mining technology is developed rapidly to meet the need. But DM (data mining) often faces so much data which is noisy, disorder and nonlinear. Fortunately, ANN (Artificial Neural Network) is suitable to solve the before-mentioned problems of DM because ANN has such merits as good robustness, adaptability, parallel-disposal, distributing-memory and high tolerating-error. This paper gives a detailed discussion about the application of ANN method used in DM based on the analysis of all kinds of data mining technology, and especially lays stress on the classification Data Mining based on RBF neural networks. Pattern classification is an important part of the RBF neural network application. Under on-line environment, the training dataset is variable, so the batch learning algorithm (e.g. OLS) which will generate plenty of unnecessary retraining has a lower efficiency. This paper deduces an incremental learning algorithm (ILA) from the gradient descend algorithm to improve the bottleneck. ILA can adaptively adjust parameters of RBF networks driven by minimizing the error cost, without any redundant retraining. Using the method proposed in this paper, an on-line classification system was constructed to resolve the IRIS classification problem. Experiment results show the algorithm has fast convergence rate and excellent on-line classification performance.
Implementation of pattern recognition algorithm based on RBF neural network
Bouchoux, Sophie; Brost, Vincent; Yang, Fan; Grapin, Jean Claude; Paindavoine, Michel
2002-12-01
In this paper, we present implementations of a pattern recognition algorithm which uses a RBF (Radial Basis Function) neural network. Our aim is to elaborate a quite efficient system which realizes real time faces tracking and identity verification in natural video sequences. Hardware implementations have been realized on an embedded system developed by our laboratory. This system is based on a DSP (Digital Signal Processor) TMS320C6x. The optimization of implementations allow us to obtain a processing speed of 4.8 images (240x320 pixels) per second with a correct rate of 95% of faces tracking and identity verification.
Application of RBF Neural Network in OptimizingMachining Parameters
朱喜林; 吴博达; 武星星
2004-01-01
In machining processes, errors of rough in dimension, shape and location lead to changes in processing quantity, and the material of a workpiece may not be uniform. For these reasons, cutting force changes in machining, making the machining system deformable. Consequently errors in workpieces may occur. This is called the error reflection phenomenon. Generally, such errors can be reduced through repeated processing while using appropriate processing quantity in each processing based on operator's experience.According to the theory of error reflection, the error reflection coefficient indicates the extent to which errors of rough influence errors of workpieces. It is related to several factors such as machining condition, hardness of the workpiece, etc. This non-linear relation cannot be worked out using any formula. RBF neural network can approximate a non-linear function within any precision and be trained fast. In this paper, non-linear mapping ability of a fuzzy-neural network is utilized to approximate the non-linear relation. After training of the network with swatch collection obtained in experiments, an appropriate output can be obtained when an input is given. In this way, one can get the required number of processing and the processing quantity each time from the machining condition. Angular rigidity of a machining system,hardness of workpiece, etc., can be input in a form of fuzzy values. Feasibility in solving error reflection and optimizing machining parameters with a RBF neural network is verified by a simulation test with MATLAB.
A Sliding Mode Control-based on a RBF Neural Network for Deburring Industry Robotic Systems
Yong Tao; Jiaqi Zheng; Yuanchang Lin
2016-01-01
A sliding mode control method based on radial basis function (RBF) neural network is proposed for the deburring of industry robotic systems. First, a dynamic model for deburring the robot system is established. Then, a conventional SMC scheme is introduced for the joint position tracking of robot manipulators. The RBF neural network based sliding mode control (RBFNN-SMC) has the ability to learn uncertain control actions. In the RBFNN-SMC scheme, the adaptive tuning algorithms for network par...
Abghari, H.; van de Giesen, N.; Mahdavi, M.; Salajegheh, A.
2009-04-01
Artificial intelligence modeling of nonstationary rainfall-runoff has some restrictions in simulation accuracy due to the complexity and nonlinearity of training patterns. Preprocessing of trainings dataset could determine homogeneity of rainfall-runoff patterns before modeling. In this presentation, a new hybrid model of Artificial Intelligence in conjunction with clustering is introduced and applied to flow prediction. Simulation of Nazloochaei river flow in North-West Iran was the case used for development of a PNN-RBF model. PNN classify a training dataset in two groups based on Parezen theory using unsupervised classification. Subsequently each data group is used to train and test two RBF networks and the results are compared to the application of all data in a RBF network without classification. Results show that classification of rainfall-runoff patterns using PNN and prediction of runoff with RBF increase prediction precise of networks. Keywords: Probabilistic Neural Network, Radial Base Function Neural Network, Parezen theory, River Flow Prediction
Liu, Jinkun
2013-01-01
Radial Basis Function (RBF) Neural Network Control for Mechanical Systems is motivated by the need for systematic design approaches to stable adaptive control system design using neural network approximation-based techniques. The main objectives of the book are to introduce the concrete design methods and MATLAB simulation of stable adaptive RBF neural control strategies. In this book, a broad range of implementable neural network control design methods for mechanical systems are presented, such as robot manipulators, inverted pendulums, single link flexible joint robots, motors, etc. Advanced neural network controller design methods and their stability analysis are explored. The book provides readers with the fundamentals of neural network control system design. This book is intended for the researchers in the fields of neural adaptive control, mechanical systems, Matlab simulation, engineering design, robotics and automation. Jinkun Liu is a professor at Beijing University of Aeronautics and Astronauti...
An artificial Radial Basis Function (RBF) neural network model was developed for the prediction of mass transfer of the phospholipids from canola meal in supercritical CO2 fluid. The RBF kind of artificial neural networks (ANN) with orthogonal least squares (OLS) learning algorithm were used for mod...
On-line identification of hybrid systems using an adaptive growing and pruning RBF neural network
Alizadeh, Tohid
2008-01-01
This paper introduces an adaptive growing and pruning radial basis function (GAP-RBF) neural network for on-line identification of hybrid systems. The main idea is to identify a global nonlinear model that can predict the continuous outputs of hybrid systems. In the proposed approach, GAP......-RBF neural network uses a modified unscented kalman filter (UKF) with forgetting factor scheme as the required on-line learning algorithm. The effectiveness of the resulting identification approach is tested and evaluated on a simulated benchmark hybrid system....
A Model to Predict Rolling Force of Finishing Stands with RBF Neural Networks
无
2005-01-01
In view of intrinsic imperfection of traditional models of rolling force, in order to improve the prediction accuracy of rolling force, a new method combining radial basis function (RBF) neural networks with traditional models to predict rolling force was proposed. The off-line simulation indicates that the predicted results are much more accurate than that with traditional models.
RBF-Type Artificial Neural Network Model Applied in Alloy Design of Steels
YOU Wei; LIU Ya-xiu; BAI Bing-zhe; FANG Hong-sheng
2008-01-01
RBF model, a new type of artificial neural network model was developed to design the content of carbon in low-alloy engineering steels. The errors of the ANN model are. MSE 0. 052 1, MSRE 17. 85%, and VOF 1. 932 9. The results obtained are satisfactory. The method is a powerful aid for designing new steels.
Adaptive RBF Neural Network Control for Three-Phase Active Power Filter
Juntao Fei
2013-05-01
Full Text Available Abstract An adaptive radial basis function (RBF neural network control system for three-phase active power filter (APF is proposed to eliminate harmonics. Compensation current is generated to track command current so as to eliminate the harmonic current of non-linear load and improve the quality of the power system. The asymptotical stability of the APF system can be guaranteed with the proposed adaptive neural network strategy. The parameters of the neural network can be adaptively updated to achieve the desired tracking task. The simulation results demonstrate good performance, for example showing small current tracking error, reduced total harmonic distortion (THD, improved accuracy and strong robustness in the presence of parameters variation and nonlinear load. It is shown that the adaptive RBF neural network control system for three-phase APF gives better control than hysteresis control.
Erkan Beşdok
2009-08-01
Full Text Available This paper introduces a comparison of training algorithms of radial basis function (RBF neural networks for classification purposes. RBF networks provide effective solutions in many science and engineering fields. They are especially popular in the pattern classification and signal processing areas. Several algorithms have been proposed for training RBF networks. The Artificial Bee Colony (ABC algorithm is a new, very simple and robust population based optimization algorithm that is inspired by the intelligent behavior of honey bee swarms. The training performance of the ABC algorithm is compared with the Genetic algorithm, Kalman filtering algorithm and gradient descent algorithm. In the experiments, not only well known classification problems from the UCI repository such as the Iris, Wine and Glass datasets have been used, but also an experimental setup is designed and inertial sensor based terrain classification for autonomous ground vehicles was also achieved. Experimental results show that the use of the ABC algorithm results in better learning than those of others.
RBF neural network and active circles based algorithm for contours extraction
Zhou Zhiheng; Zeng Delu; Xie Shengli
2007-01-01
For the contours extraction from the images, active contour model and self-organizing map based approach are popular nowadays. But they are still confronted with the problems that the optimization of energy function will trap in local minimums and the contour evolutions greatly depend on the initial contour selection. Addressing to these problems, a contours extraction algorithm based on RBF neural network is proposed here. A series of circles with adaptive radius and center is firstly used to search image feature points that are scattered enough. After the feature points are clustered, a group of radial basis functions are constructed. Using the pixels' intensities and gradients as the input vector, the final object contour can be obtained by the predicting ability of the neural network. The RBF neural network based algorithm is tested on three kinds of images, such as changing topology, complicated background, and blurring or noisy boundary. Simulation results show that the proposed algorithm performs contours extraction greatly.
Research on Method of Character Recognition Based on Hough Transform and RBF Neural Network
Zhang Yin
2015-01-01
Full Text Available A method of character recognition based on Hough transform and RBF neural network is proposed through research on weight accumulation algorithm of Hough transform. According to the feature of characters’ structure by using the duality of point-line Hough transform was done. In this method, the number of the points on the same line in parameter space and the position coordinates of the elements in image mapping space were taken to RBF neural network recognition system as characteristic input vector. It reduced the dimension of character feature vector and reflected the overall distribution of character lattice and the essential feature of character shape. The simulation results indicated there were some merits in this improved method: capability of recognition is strong, the quantity of calculation is small, and the speed of calculation is quick.
An Adaptive-PSO-Based Self-Organizing RBF Neural Network.
Han, Hong-Gui; Lu, Wei; Hou, Ying; Qiao, Jun-Fei
2016-10-24
In this paper, a self-organizing radial basis function (SORBF) neural network is designed to improve both accuracy and parsimony with the aid of adaptive particle swarm optimization (APSO). In the proposed APSO algorithm, to avoid being trapped into local optimal values, a nonlinear regressive function is developed to adjust the inertia weight. Furthermore, the APSO algorithm can optimize both the network size and the parameters of an RBF neural network simultaneously. As a result, the proposed APSO-SORBF neural network can effectively generate a network model with a compact structure and high accuracy. Moreover, the analysis of convergence is given to guarantee the successful application of the APSO-SORBF neural network. Finally, multiple numerical examples are presented to illustrate the effectiveness of the proposed APSO-SORBF neural network. The results demonstrate that the proposed method is more competitive in solving nonlinear problems than some other existing SORBF neural networks.
Study of CNG/diesel dual fuel engine's emissions by means of RBF neural network
刘震涛; 费少梅
2004-01-01
Great efforts have been made to resolve the serious environmental pollution and inevitable declining of energy resources. A review of Chinese fuel reserves and engine technology showed that compressed natural gas (CNG)/diesel dual fuel engine (DFE) was one of the best solutions for the above problems at present. In order to study and improve the emission performance of CNG/diesel DFE, an emission model for DFE based on radial basis function (RBF) neural network was developed which was a black-box input-output training data model not require priori knowledge. The RBF centers and the connected weights could be selected automatically according to the distribution of the training data in input-output space and the given approximating error. Studies showed that the predicted results accorded well with the experimental data over a large range of operating conditions from low load to high load. The developed emissions model based on the RBF neural network could be used to successfully predict and optimize the emissions performance of DFE. And the effect of the DFE main performance parameters, such as rotation speed, load, pilot quantity and injection timing, were also predicted by means of this model. In resume, an emission prediction model for CNG/diesel DFE based on RBF neural network was built for analyzing the effect of the main performance parameters on the CO, NOx emissions of DFE. The predicted results agreed quite well with the traditional emissions model, which indicated that the model had certain application value, although it still has some limitations, because of its high dependence on the quantity of the experimental sample data.
Study of CNG/diesel dual fuel engine's emissions by means of RBF neural network.
Liu, Zhen-tao; Fei, Shao-mei
2004-08-01
Great efforts have been made to resolve the serious environmental pollution and inevitable declining of energy resources. A review of Chinese fuel reserves and engine technology showed that compressed natural gas (CNG)/diesel dual fuel engine (DFE) was one of the best solutions for the above problems at present. In order to study and improve the emission performance of CNG/diesel DFE, an emission model for DFE based on radial basis function (RBF) neural network was developed which was a black-box input-output training data model not require priori knowledge. The RBF centers and the connected weights could be selected automatically according to the distribution of the training data in input-output space and the given approximating error. Studies showed that the predicted results accorded well with the experimental data over a large range of operating conditions from low load to high load. The developed emissions model based on the RBF neural network could be used to successfully predict and optimize the emissions performance of DFE. And the effect of the DFEmain performance parameters, such as rotation speed, load, pilot quantity and injection timing, were also predicted by means of this model. In resumé, an emission prediction model for CNG/diesel DFE based on RBF neural network was built for analyzing the effect of the main performance parameters on the CO, NOx, emissions of DFE. The predicted results agreed quite well with the traditional emissions model, which indicated that the model had certain application value, although it still has some limitations, because of its high dependence on the quantity of the experimental sample data.
Adaptive Control for Robotic Manipulators Base on RBF Neural Network
MA Jing
2013-09-01
Full Text Available An adaptive neural network controller is brought forward by the paper to solve trajectory tracking problems of robotic manipulators with uncertainties. The first scheme consists of a PD feedback and a dynamic compensator which is composed by neural network controller and variable structure controller. Neutral network controller is designed to adaptive learn and compensate the unknown uncertainties, variable structure controller is designed to eliminate approach errors of neutral network. The adaptive weight learning algorithm of neural network is designed to ensure online real-time adjustment, offline learning phase is not need; Global asymptotic stability (GAS of system base on Lyapunov theory is analysised to ensure the convergence of the algorithm. The simulation result s show that the kind of the control scheme is effective and has good robustness.
A RBF neural network model with GARCH errors: Application to electricity price forecasting
Coelho, Leandro dos Santos [Industrial and Systems Engineering Graduate Program, PPGEPS, Pontifical Catholic University of Parana, Imaculada Conceicao, 1155, Zip code 80215-901, Curitiba, Parana (Brazil); Santos, Andre A.P. [Department of Statistics, Universidad Carlos III de Madrid, C/ Madrid, 126, 28903 Getafe, Madrid (Spain)
2011-01-15
In this article, we propose a nonlinear forecasting model based on radial basis function neural networks (RBF-NNs) with Gaussian activation functions and robust clustering algorithms to model the conditional mean and a parametric generalized autoregressive conditional heteroskedasticity (GARCH) specification to model the conditional volatility. Instead of calibrating the parameters of the RBF-NNs via numerical simulations, we propose an estimation procedure by which the number of basis functions, their corresponding widths and the parameters of the GARCH model are jointly estimated via maximum likelihood along with a genetic algorithm to maximize the likelihood function. We use this model to provide multi-step-ahead point and direction-of-change forecasts of the Spanish electricity pool prices. (author)
RBF neural network prediction on weak electrical signals in Aloe vera var. chinensis
Wang, Lanzhou; Zhao, Jiayin; Wang, Miao
2008-10-01
A Gaussian radial base function (RBF) neural network forecast on signals in the Aloe vera var. chinensis by the wavelet soft-threshold denoised as the time series and using the delayed input window chosen at 50, is set up to forecast backward. There was the maximum amplitude at 310.45μV, minimum -75.15μV, average value -2.69μV and Aloe vera var. chinensis respectively. The electrical signal in Aloe vera var. chinensis is a sort of weak, unstable and low frequency signals. A result showed that it is feasible to forecast plant electrical signals for the timing by the RBF. The forecast data can be used as the preferences for the intelligent autocontrol system based on the adaptive characteristic of plants to achieve the energy saving on the agricultural production in the plastic lookum or greenhouse.
Identification of TSS in the Human Genome Based on a RBF Neural Network
Zhi-Hong Peng; Jie Chen; Li-Jun Cao; Ting-Ting Gao
2006-01-01
The identification of functional motifs in a DNA sequence is fundamentally a statistical pattern recognition problem. This paper introduces a new algorithm for the recognition of functional transcription start sites (TSSs) in human genome sequences, in which a RBF neural network is adopted, and an improved heuristic method for a 5-tuple feature viable construction, is proposed and implemented in two RBFPromoter and ImpRBFPromoter packages developed in Visual C++6.0. The algorithm is evaluated on several different test sequence sets. Compared with several other promoter recognition programs, this algorithm is proved to be more flexible, with stronger learning ability and higher accuracy.
Adaptive Global Sliding Mode Control for MEMS Gyroscope Using RBF Neural Network
Yundi Chu
2015-01-01
Full Text Available An adaptive global sliding mode control (AGSMC using RBF neural network (RBFNN is proposed for the system identification and tracking control of micro-electro-mechanical system (MEMS gyroscope. Firstly, a new kind of adaptive identification method based on the global sliding mode controller is designed to update and estimate angular velocity and other system parameters of MEMS gyroscope online. Moreover, the output of adaptive neural network control is used to adjust the switch gain of sliding mode control dynamically to approach the upper bound of unknown disturbances. In this way, the switch item of sliding mode control can be converted to the output of continuous neural network which can weaken the chattering in the sliding mode control in contrast to the conventional fixed gain sliding mode control. Simulation results show that the designed control system can get satisfactory tracking performance and effective estimation of unknown parameters of MEMS gyroscope.
Nuclear power plant fault diagnosis based on genetic-RBF neural network
SHI Xiao-cheng; XIE Chun-ling; WANG Yuan-hui
2006-01-01
It is necessary to develop an automatic fault diagnosis system to avoid a possible nuclear disaster caused by an inaccurate fault diagnosis in the nuclear power plant by the operator. Because Radial Basis Function Neural Network (RBFNN) has the characteristics of optimal approximation and global approximation. The mixed coding of binary system and decimal system is introduced to the structure and parameters of RBFNN, which is trained in course of the genetic optimization. Finally, a fault diagnosis system according to the frequent faults in condensation and feed water system of nuclear power plant is set up. As a result, Genetic-RBF Neural Network (GRBFNN) makes the neural network smaller in size and higher in generalization ability. The diagnosis speed and accuracy are also improved.
Lukas Falat
2014-01-01
Full Text Available In this paper, authors apply feed-forward artificial neural network (ANN of RBF type into the process of modelling and forecasting the future value of USD/CAD time series. Authors test the customized version of the RBF and add the evolutionary approach into it. They also combine the standard algorithm for adapting weights in neural network with an unsupervised clustering algorithm called K-means. Finally, authors suggest the new hybrid model as a combination of a standard ANN and a moving average for error modeling that is used to enhance the outputs of the network using the error part of the original RBF. Using high-frequency data, they examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, authors perform the comparative out-of-sample analysis of the suggested hybrid model with statistical models and the standard neural network.
Lei Wang
2014-01-01
Full Text Available Offshore floating wind turbine (OFWT has been a challenging research spot because of the high-quality wind power and complex load environment. This paper focuses on the research of variable torque control of offshore wind turbine on Spar floating platform. The control objective in below-rated wind speed region is to optimize the output power by tracking the optimal tip-speed ratio and ideal power curve. Aiming at the external disturbances and nonlinear uncertain dynamic systems of OFWT because of the proximity to load centers and strong wave coupling, this paper proposes an advanced radial basis function (RBF neural network approach for torque control of OFWT system at speeds lower than rated wind speed. The robust RBF neural network weight adaptive rules are acquired based on the Lyapunov stability analysis. The proposed control approach is tested and compared with the NREL baseline controller using the “NREL offshore 5 MW wind turbine” model mounted on a Spar floating platform run on FAST and Matlab/Simulink, operating in the below-rated wind speed condition. The simulation results show a better performance in tracking the optimal output power curve, therefore, completing the maximum wind energy utilization.
Research on Space Vector PWM Based on RBF Neural Network%基于RBF神经网络的SVPWM研究
宣光银; 胡丹; 车畅
2011-01-01
论述了电压空间矢量脉宽调制( SVPWM)的基本原理,提出利用径向基(RBF)网络实现SVPWM的方法；并在Matlab下结合神经网络工具箱进了仿真研究.仿真结果表明,RBF-SVPWM收敛速度快、误差精度高,使用该方法建立的异步电动机控制系统具有更小的定子电流谐波和转矩脉动.%The basic principle of space voltage vector PWM was discussed,and a new algorithm for SVPWM based on radial basis function neural network( RBF-SVPWM) was proposed. The emulation of RBF-SVPWM was carried out in Mat-lab together with Nntoolbox. The results indicate that RBF-SVPWM has a fast convergence and high accurate error,and the induction motor control system using RBF-SVPWM also has less stator current harmonics and torque pulsation.
ZHANG Yongzhi
2016-10-01
Full Text Available A dynamic fuzzy RBF neural network model was built to predict the mechanical properties of welded joints, and the purpose of the model was to overcome the shortcomings of static neural networks including structural identification, dynamic sample training and learning algorithm. The structure and parameters of the model are no longer head of default, dynamic adaptive adjustment in the training, suitable for dynamic sample data for learning, learning algorithm introduces hierarchical learning and fuzzy rule pruning strategy, to accelerate the training speed of model and make the model more compact. Simulation of the model was carried out by using three kinds of thickness and different process TC4 titanium alloy TIG welding test data. The results show that the model has higher prediction accuracy, which is suitable for predicting the mechanical properties of welded joints, and has opened up a new way for the on-line control of the welding process.
Tatar Afshin
2016-03-01
Full Text Available Raw natural gases usually contain water. It is very important to remove the water from these gases through dehydration processes due to economic reasons and safety considerations. One of the most important methods for water removal from these gases is using dehydration units which use Triethylene glycol (TEG. The TEG concentration at which all water is removed and dew point characteristics of mixture are two important parameters, which should be taken into account in TEG dehydration system. Hence, developing a reliable and accurate model to predict the performance of such a system seems to be very important in gas engineering operations. This study highlights the use of intelligent modeling techniques such as Multilayer perceptron (MLP and Radial Basis Function Neural Network (RBF-ANN to predict the equilibrium water dew point in a stream of natural gas based on the TEG concentration of stream and contractor temperature. Literature data set used in this study covers temperatures from 10 °C to 80 °C and TEG concentrations from 90.000% to 99.999%. Results showed that both models are accurate in prediction of experimental data and the MLP model gives more accurate predictions compared to RBF model.
Lihua Yang
2015-04-01
Full Text Available In order to improve the accuracy of grain production forecasting, this study proposed a new combination forecasting model, the model combined stepwise regression method with RBF neural network by assigning proper weights using inverse variance method. By comparing different criteria, the result indicates that the combination forecasting model is superior to other models. The performance of the models is measured using three types of error measurement, which are Mean Absolute Percentage Error (MAPE, Theil Inequality Coefficient (Theil IC and Root Mean Squared Error (RMSE. The model with smallest value of MAPE, Theil IC and RMSE stands out to be the best model in predicting the grain production. Based on the MAPE, Theil IC and RMSE evaluation criteria, the combination model can reduce the forecasting error and has high prediction accuracy in grain production forecasting, making the decision more scientific and rational.
Radiation acquisition and RBF neural network analysis on BOF end-point control
Zhao, Qi; Wen, Hong-yuan; Zhou, Mu-chun; Chen, Yan-ru
2008-12-01
There are some problems in Basic Oxygen Furnace (BOF) steelmaking end-point control technology at present. A new BOF end-point control model was designed, which was based on the character of carbon oxygen reaction in Basic Oxygen Furnace steelmaking process. The image capture and transformation system was established by Video for Windows (VFW) library function, which is a video software development package promoted by Microsoft Corporation. In this paper, the Radial Basic Function (RBF) neural network model was established by using the real-time acquisition information. The input parameters can acquire easily online and the output parameter is the end-point time, which can compare with the actual value conveniently. The experience results show that the predication result is ideal and the experiment results show the model can work well in the steelmaking adverse environment.
MIMO Lyapunov Theory-Based RBF Neural Classifier for Traffic Sign Recognition
King Hann Lim
2012-01-01
Full Text Available Lyapunov theory-based radial basis function neural network (RBFNN is developed for traffic sign recognition in this paper to perform multiple inputs multiple outputs (MIMO classification. Multidimensional input is inserted into RBF nodes and these nodes are linked with multiple weights. An iterative weight adaptation scheme is hence designed with regards to the Lyapunov stability theory to obtain a set of optimum weights. In the design, the Lyapunov function has to be well selected to construct an energy space with a single global minimum. Weight gain is formed later to obey the Lyapunov stability theory. Detail analysis and discussion on the proposed classifier’s properties are included in the paper. The performance comparisons between the proposed classifier and some existing conventional techniques are evaluated using traffic sign patterns. Simulation results reveal that our proposed system achieved better performance with lower number of training iterations.
GONG Huanchun
2014-01-01
In order to diagnose the unit economic performance online,the radial basis function (RBF) process neural network with two hidden layers was introduced to online prediction of steam turbine exhaust enthalpy.Thus,the model reflecting complicated relationship between the steam turbine exhaust enthalpy and the relative operation parameters was established.Moreover,the enthalpy of final stage extraction steam and exhaust from a 300 MW unit turbine was taken as the example to perform the online calculation. The results show that,the average relative error of this method is less than 1%,so the accuracy of this al-gorithm is higher than that of the BP neutral network.Furthermore,this method has advantages of high convergence rate,simple structure and high accuracy.
An adaptive control for a variable speed wind turbine using RBF neural network
El Mjabber E.
2016-01-01
Full Text Available In this work, a controller based on Radial Basis Functions (RBF for network adaptation is considered. The adaptive Neural Network (NN control approximates the nonlinear dynamics of the wind turbine based on input/output measurement and ensures smooth tracking of optimal tip speed-ratio at different wind speeds. The wind turbine system and this controller were modeled and a program to integrate the obtained coupled equations was developed under Matlab/Simulink software package. Then, performance of the controller was studied numerically. The proposed controller was found to effectively improve the control performance against large uncertainty of the wind turbine system. comparison with nonlinear dynamic State feedback control with Kalman filter controller was performed, and the obtained results have demonstrated the relevance of this RBFNN based controller.
Poultangari, Iman; Shahnazi, Reza; Sheikhan, Mansour
2012-09-01
In order to control the pitch angle of blades in wind turbines, commonly the proportional and integral (PI) controller due to its simplicity and industrial usability is employed. The neural networks and evolutionary algorithms are tools that provide a suitable ground to determine the optimal PI gains. In this paper, a radial basis function (RBF) neural network based PI controller is proposed for collective pitch control (CPC) of a 5-MW wind turbine. In order to provide an optimal dataset to train the RBF neural network, particle swarm optimization (PSO) evolutionary algorithm is used. The proposed method does not need the complexities, nonlinearities and uncertainties of the system under control. The simulation results show that the proposed controller has satisfactory performance.
Wang, Zhongqi; Yang, Bo; Kang, Yonggang; Yang, Yuan
2016-01-01
Fixture plays an important part in constraining excessive sheet metal part deformation at machining, assembly, and measuring stages during the whole manufacturing process. However, it is still a difficult and nontrivial task to design and optimize sheet metal fixture locating layout at present because there is always no direct and explicit expression describing sheet metal fixture locating layout and responding deformation. To that end, an RBF neural network prediction model is proposed in this paper to assist design and optimization of sheet metal fixture locating layout. The RBF neural network model is constructed by training data set selected by uniform sampling and finite element simulation analysis. Finally, a case study is conducted to verify the proposed method.
姚应水; 叶明全
2011-01-01
目的 RBF神经网络是一种重要的数据挖掘分类模型,探讨RBF神经网络在解决判别分析问题中的应用.方法 通过实例比较RBF神经网络和logistic回归模型的性能优劣.结果 RBF神经网络的回代拟合效果和泛化能力明显优于logistic回归模型.结论RBF神经网络在医学统计学领域中具有较好的应用前景.%Objective RBF neural network is an important data mining classification model in data mining. To explore the application of RBF neural network on medical discriminant analysis through comparing with logistic regression. Methods Comparing the prediction results by some statistical indexes of the RBF neural network and the logistic regression by using an example. Results The comparison results of the prediction performance between RBF neural network and logistic regression show that RBF neural network is much better than logistic regression for the data. Conclusion RBF neural network will make a better facture of its appfi-cadon in medical researches.
Gao, Xiangdong; Chen, Yuquan; You, Deyong; Xiao, Zhenlin; Chen, Xiaohui
2017-02-01
An approach for seam tracking of micro gap weld whose width is less than 0.1 mm based on magneto optical (MO) imaging technique during butt-joint laser welding of steel plates is investigated. Kalman filtering(KF) technology with radial basis function(RBF) neural network for weld detection by an MO sensor was applied to track the weld center position. Because the laser welding system process noises and the MO sensor measurement noises were colored noises, the estimation accuracy of traditional KF for seam tracking was degraded by the system model with extreme nonlinearities and could not be solved by the linear state-space model. Also, the statistics characteristics of noises could not be accurately obtained in actual welding. Thus, a RBF neural network was applied to the KF technique to compensate for the weld tracking errors. The neural network can restrain divergence filter and improve the system robustness. In comparison of traditional KF algorithm, the RBF with KF was not only more effectively in improving the weld tracking accuracy but also reduced noise disturbance. Experimental results showed that magneto optical imaging technique could be applied to detect micro gap weld accurately, which provides a novel approach for micro gap seam tracking.
Wen-Yeau Chang
2013-01-01
Full Text Available This paper proposes an equivalent circuit parameters measurement and estimation method for proton exchange membrane fuel cell (PEMFC. The parameters measurement method is based on current loading technique; in current loading test a no load PEMFC is suddenly turned on to obtain the waveform of the transient terminal voltage. After the equivalent circuit parameters were measured, a hybrid method that combines a radial basis function (RBF neural network and enhanced particle swarm optimization (EPSO algorithm is further employed for the equivalent circuit parameters estimation. The RBF neural network is adopted such that the estimation problem can be effectively processed when the considered data have different features and ranges. In the hybrid method, EPSO algorithm is used to tune the connection weights, the centers, and the widths of RBF neural network. Together with the current loading technique, the proposed hybrid estimation method can effectively estimate the equivalent circuit parameters of PEMFC. To verify the proposed approach, experiments were conducted to demonstrate the equivalent circuit parameters estimation of PEMFC. A practical PEMFC stack was purposely created to produce the common current loading activities of PEMFC for the experiments. The practical results of the proposed method were studied in accordance with the conditions for different loading conditions.
Study of CNG／diesel dual fuel engine＇s emissions by means of RBF neural network
刘震涛; 费少梅
2004-01-01
Great efforts have been made to resolve the serious environmental pollution and inevitable declining of energy resources. A review of Chinese fuel reserves and engine technology showed that compressed natural gas (CNG)/diesel dual fuel engine (DFE) was one of the best solutions for the above problems at present. In order to study and improve the emission performance of CNG/diesel DFE, an emission model for DFE based on radial basis function (RBF) neural network was developed which was a black-box input-output training data model not require priori knowledge. The RBF centers and the connected weights could be selected automatically according to the distribution of the training data in input-output space and the given approximating error. Studies showed that the predicted results accorded well with the experimental data over a large range of operating conditions from low load to high load. The developed emissions model based on the RBF neural network could be used to successfully predict and optimize the emissions performance of DFE. And the effect of the DFE main performance parameters, such as rotation speed, load, pilot quantity and injection timing, were also predicted by means of this model. In resum6, an emission prediction model for CNG/diesel DFE based on RBF neural network was built for analyzing the effect of the main performance parameters on the CO, NOx emissions of DFE. The predicted results agreed quite well with the traditional emissions model, which indicated that the model had certain application value, although it still has some limitations, because of its high dependence on the quantity of the experimental sample data.
熊亮; 赵俊锴
2015-01-01
Assessment of compressive strength of substation concrete column is an important foundation of damage degree and bearing capacity of construction.An RBF neural network model (RBF-NN )is applied to assessing compressive strength of concrete by ultrasonic and rebound combined method.An experimental method is given for compressive strength of concrete test by ultrasonic and rebound combined method.It is proved that RBF-NN model has higher evaluation precision than that of regression calculation by experimental test and emulation analysis.%变电站混凝土立柱抗压强度的评定是判断变电站混凝土结构损伤程度、剩余承载力的重要依据。设计了一个 RBF 神经网络模型，将其应用于超声回弹综合法评定变电站混凝土立柱抗压强度，给出了用超声回弹法进行混凝土强度测试的方法。经试验测试和仿真分析表明，所提出的 RBF 神经网络比传统的回归计算方法具有更高的评估精度。
基于RBF神经网络的语音情感识别%Speech Emotion Recognition Based on RBF Neural Network
张海燕; 唐建芳
2011-01-01
The principle of radial base function neural network and its train algorithm are introduced in this paper.Meanwhile,the model of speech emotion recognition based on RBF neural network is established.In the recognition experiments,BP neural network and RBF neural network are compared in the same testing environment.The recognition rate of RBF neural network is 3% more than BP neural network.The results show that the method based on RBF neural network speech emotion recognition is effective.%介绍了径向基函数神经网络的原理、训练算法,并建立了RBF神经网络的语音情感识别的模型。在实验中比较了BP神经网络与RBF神经网络分别用于语音情感识别识别率,RBF神经网络的平均识别率高于BP神经网络3%。结果表明,基于RBF神经网络的语音情感识别方法的有效性。
LP(K)中RBF神经网络的系统识别问题%LP(K) Approximation Problems in System Identification with RBF Neural Networks
南东; 隆金玲
2009-01-01
Lp approximation problems in system identification with RBF neural networks are investigated.It is proved that by superpositions of some functions of one variable in Lploc(R),one can approximate continuous functionals defined on a compact subset of Lp(K) and continuous operators from a compact subset of Lp1 (K1) to a compact subset of Lp2 (K(2).These results show that if its activation function is in Lploc(R) and is not an even polynomial,then this RBF neural networks can approximate the above systems with any accuracy.
Ahmadi Majid
2003-01-01
Full Text Available This paper introduces a novel method for the recognition of human faces in digital images using a new feature extraction method that combines the global and local information in frontal view of facial images. Radial basis function (RBF neural network with a hybrid learning algorithm (HLA has been used as a classifier. The proposed feature extraction method includes human face localization derived from the shape information. An efficient distance measure as facial candidate threshold (FCT is defined to distinguish between face and nonface images. Pseudo-Zernike moment invariant (PZMI with an efficient method for selecting moment order has been used. A newly defined parameter named axis correction ratio (ACR of images for disregarding irrelevant information of face images is introduced. In this paper, the effect of these parameters in disregarding irrelevant information in recognition rate improvement is studied. Also we evaluate the effect of orders of PZMI in recognition rate of the proposed technique as well as RBF neural network learning speed. Simulation results on the face database of Olivetti Research Laboratory (ORL indicate that the proposed method for human face recognition yielded a recognition rate of 99.3%.
2D Sketch based recognition of 3D freeform shapes by using the RBF Neural Network
Qin, S F; Sun, Guangmin; Wright, D K; Lim, S.; Khan, U.; Mao, C.
2005-01-01
This paper presents a novel free-form surface recognition method from 2D freehand sketching. The approach is based on the Radial basis function (RBF), an artificial intelligence technique. A simple three-layered network has been designed and constructed. After training and testing with two types of surfaces (four sided boundary surfaces and four close section surfaces), it has been shown that the method is useful in freeform surface recognition. The testing results are very satisfactory.
2D sketch based recognition of 3D freeform shape by using the RBF neural network
Qin, SF; Sun, GM; Wright, DK; Lim, S.; Khan, U.; Mao, C.
2005-01-01
This paper presents a novel free-form surface recognition method from 2D freehand sketching. The approach is based on the Radial basis function (RBF), an artificial intelligence technique. A simple three-layered network has been designed and constructed. After training and testing with two types of surfaces (four sided boundary surfaces and four close section surfaces), it has been shown that the method is useful in freeform surface recognition. The testing results are very satisfactory.
Fatma Zohra Chelali
2015-01-01
Full Text Available Face recognition has received a great attention from a lot of researchers in computer vision, pattern recognition, and human machine computer interfaces in recent years. Designing a face recognition system is a complex task due to the wide variety of illumination, pose, and facial expression. A lot of approaches have been developed to find the optimal space in which face feature descriptors are well distinguished and separated. Face representation using Gabor features and discrete wavelet has attracted considerable attention in computer vision and image processing. We describe in this paper a face recognition system using artificial neural networks like multilayer perceptron (MLP and radial basis function (RBF where Gabor and discrete wavelet based feature extraction methods are proposed for the extraction of features from facial images using two facial databases: the ORL and computer vision. Good recognition rate was obtained using Gabor and DWT parameterization with MLP classifier applied for computer vision dataset.
Zhang, Ridong; Tao, Jili; Lu, Renquan; Jin, Qibing
2016-12-08
Modeling of distributed parameter systems is difficult because of their nonlinearity and infinite-dimensional characteristics. Based on principal component analysis (PCA), a hybrid modeling strategy that consists of a decoupled linear autoregressive exogenous (ARX) model and a nonlinear radial basis function (RBF) neural network model are proposed. The spatial-temporal output is first divided into a few dominant spatial basis functions and finite-dimensional temporal series by PCA. Then, a decoupled ARX model is designed to model the linear dynamics of the dominant modes of the time series. The nonlinear residual part is subsequently parameterized by RBFs, where genetic algorithm is utilized to optimize their hidden layer structure and the parameters. Finally, the nonlinear spatial-temporal dynamic system is obtained after the time/space reconstruction. Simulation results of a catalytic rod and a heat conduction equation demonstrate the effectiveness of the proposed strategy compared to several other methods.
WANG Hong-qi; WANG Xue-yuan; TANG Yu
2005-01-01
This paper designs an intelligent evaluation approach using a Radial Basis Function (RBF) Artificial Neural Network. We based our approach on establishing a comprehensive advantage evaluating index system that offers scientific substance for creating a development plan and the strategic management of high-tech industry and regional cluslers of high-tech enterprises. Furthermore, this paper selects some typical high-tech enterprises' data to make comprehensive training on the network system. Meanwhile, the paper chooses some enterprises as testing samples to test the method, the result of which proves that this method is truly effective. The research of this paper provides a comprehensive advantage evaluating and managing method for high-tech enterprise.
贾伟宽; 赵德安; 刘晓洋; 唐书萍; 阮承治; 姬伟
2015-01-01
In order to improve the recognition precision and speed for apple, and further improve the harvesting efficiency of apple harvesting robot, an apple recognition method based on combiningK-means clustering segmentation with genetic radial basis function (RBF) neural network is proposed. Firstly, the captured apple image is transformed into L*a*b* color space, and then under this color space, theK-means clustering algorithm is used to segment the apple image. The color feature components and shape components of segmented image are extracted respectively. The color features include R, G, B, H, S and I, a total of 6 feature components; and the shape features include circular variance, density, ratio of perimeter square to area, and 7 Hu invariant moments, a total of 10 shape components. These extracted 16 features are used as the inputs of neural network to train RBF neural network, and get the apple recognition model. Due to some inherent defects the RBF neural network has, such as low learning rate, easily causing over fitting phenomenon, genetic algorithm (GA) is introduced to optimize the connection weights and the number of hidden layer neurons. In this study, a new optimization way is adopted, that is, the hybrid encoding of the number of hidden layer neurons and connection weights is carried out simultaneously. This moment, the learning of weights is not completed, and the least mean square (LMS) is used to further learn the connection weights. Finally, an optimized neural network model (GA-RBF-LMS) is established, which is to improve the operating efficiency and recognition precision. In the experiments, there are 150 images captured, and they have 229 apples; among them 50 images are selected as training samples, and the rest as testing samples. Every image for training sample has only one apple, so the testing samples have 179 apples. In order to get the precise model, fruits of apple are together with branches and leaves for training during the training
Design of SVPWM Overmodulation Based on RBF Neural Networks%基于RBF神经网络的SVPWM过调制
易灵芝; 何素芬; 李举成; 彭寒梅; 李明; 陈彦如
2009-01-01
线性调制状态下的逆变器,存在不能充分利用直流母线电压的问题,为了获得尽可能大的输出电压,一般对逆变器进行过调制控制.由于过调制的非线性,计算复杂,提出新的基于神经网络的SVPWM逆变器,采用线性调制和过调制2种模式,通过限定轨迹双调制模式法,实现在整个调制范围内线性控制.采用资源分配法确定径向基函数的网络结构和参数,设计出较精简的网络实现SVPWM;并将这种逆变器应用于异步电动机控制系统中.最后在Matlab环境下建立基于神经网络的SVPWM逆变器供电的异步电机控制系统仿真模型, 仿真结果表明,该方法简单、高效、控制效果良好,能提高直流母线电压利用率,降低输出电流谐波含量和电机转矩脉动.%The problem of obtaining the higher output voltage value in linear modulation condition PWM inversion is discussed.A complete artificial-neural-network space vector pulse width modulation(ANN-SVM)controller for a voltage source inverter is presented.The operation is very well both in under-modulation and over-modulation regions.The linear control is realized in the entire modulation scope by limit trajectories.The resources method of distribution determination RBF network architecture and the parameter are used.The RBF neural network realize the voltage space vector modulate to control the inverter,which is applied to the control system of asynchronous machine.The simulation results show that the method features simplicity,high efficiency and excellent control effect.The use ratio of DC bus voltage is raised,and the output current harmonics content and the torque pulsation are reduced.
Rough RBF Neural Network Based on Extreme Learning%基于极速学习的粗糙RBF神经网络
马刚; 丁世飞; 史忠植
2012-01-01
提出了一种用于训练粗糙RBF神经网络（rough RBF neural networks,R-RBF）的极速学习机（extreme learning machine,ELM）方法,通过引入矩阵的Moore-Penrose逆,将传统的迭代学习方法转换为一种求线性方程的极小范数最小二乘解的方法.实验证明,在训练精度、训练时间上都能够达到非常优越的性能,其泛化精度能够提升50%以上.%The paper proposes a method of training rough RBF neural networks（R-RBF） using the extreme learning machine（ELM）, which eonverts the traditional iterative training method to solve norm least-squares solution of general linear system by introducing Moore-Penrose inverse. Experiments show that it can reach a very superior performance in both time and aeeuraey when ELM trains the Rough RBF Neural Networks, which can improve the generalization accuracy more than 50% compared with the traditional thinking of adjusting parameters iterative[y.
RBF neural network based $\\mathcal{H}_{\\infty}$ synchronization for unknown chaotic systems
Choon Ki Ahn
2010-08-01
In this paper, we propose a new $\\mathcal{H}_{\\infty}$ synchronization strategy, called a Radial Basis Function Neural Network $\\mathcal{H}_{\\infty}$ synchronization (RBFNNHS) strategy, for unknown chaotic systems in the presence of external disturbance. In the proposed framework, a radial basis function neural network (RBFNN) is constructed as an alternative to approximate the unknown nonlinear function of the chaotic system. Based on this neural network and linear matrix inequality (LMI) formulation, the RBFNNHS controller and the learning laws are presented to reduce the effect of disturbance to an $\\mathcal{H}_{\\infty}$ norm constraint. It is shown that ﬁnding the RBFNNHS controller and the learning laws can be transformed into the LMI problem and solved using the convex optimization method. A numerical example is presented to demonstrate the validity of the proposed RBFNNHS scheme.
权值与结构双确定法的RBF神经网络分类器%RBF Neural Network Classifier with Weights and Structure Determination Method
张雨浓; 王茹; 廖柏林; 刘锦荣; 林键煜
2014-01-01
In order to solve the difficulties in determining the weights and structure of the radial basis function (RBF) neural network.Based on the weights-direct-determination (WDD)method and the relationship among centers,variances, the number of hidden-layer neurons and the performance of the neural network,a pruning-while-growing-type weights-and-structure-determination (PWGT-WASD)algorithm is proposed.On the basis of the PWGT-WASD algorithm,a kind of RBF neural network classifier is constructed,and its classifying and antinoise ability is further discussed in this paper.Com-puter numerical experiment results substantiate that the proposed PWGT-WASD algorithm can determine the centers,the va-riances and the optimal weights and structure of RBF neural network quickly and effectively.The constructed RBF pattern classifier has the superiority in terms of classification and antinoise ability.%为了解决径向基函数(RBF)神经网络权值与结构难以确定的问题，基于权值直接确定法，及隐层神经元中心、方差、数目与神经网络性能的关系，提出一种边增边删型的网络权值与结构双确定法。在此方法基础之上，构建一种 RBF神经网络分类器并探讨其分类性能和抗噪能力。计算机数值实验结果验证所提出的边增边删型的权值与结构双确定法能够快速、有效地确定网络的中心、方差和网络最优的权值与结构，所构造的模式分类器具有优越的分类性能和抗噪能力。
A Deep Web Query Interfaces Classification Method Based on RBF Neural Network
YUAN Fang; ZHAO Yao; ZHOU Xu
2007-01-01
This paper proposes a new approach for classification for query interfaces of Deep Web, which extracts features from the form's text data on the query interfaces, assisted with the synonym library, and uses radial basic function neural network (RBFNN) algorithm to classify the query interfaces. The applied RBFNN is a kind of effective feed-forward artificial neural network, which has a simple networking structure but features with strength of excellent nonlinear approximation, fast convergence and global convergence. A TEL_8 query interfaces' data set from UIUC on-line database is used in our experiments, which consists of 477 query interfaces in 8 typical domains. Experimental results proved that the proposed approach can efficiently classify the query interfaces with an accuracy of 95.67%.
Research on Data Mining Based on RBF Neural Network%基于RBF神经网络的数据挖掘研究
徐晓
2014-01-01
This paper discusses the principle and related methods of data mining technology based on data warehouse, and introduces the principle and characteristics of RBF neural network. Aiming at the characteristics of RBF neural network such as strong nonlinear mapping ability and high-speed learning, this paper introduces the data cleaning, pretreatment and regularization steps of data mining method based on RBF neural network. With the distributed information storage feature, the neural network can use a large number of connections between neurons and the analysis of connection weights to limit specific information. The network system built by this idea will not lead to an overall paralysis, even if the local network is damaged..%探讨了基于数据仓库的数据挖掘技术的原理与相关方法，介绍了RBF神经网络的原理与特点。针对RBF神经网络非线性映射能力强和学习速度快等特点，介绍了基于RBF神经网络的数据挖掘方法的数据清洗、预处理和正则化等操作步骤。神经网络具有分布式存储信息的特点，能够利用大量神经元间的连接，以及连接权值的分析，来限定特定信息。使用这种思想构建的网络系统，即使在局部的网络损坏，也不会导致整体的瘫痪。
Automated Stellar Classification for Large Surveys with EKF and RBF Neural Networks
Ling Bai; Ping Guo; Zhan-Yi Hu
2005-01-01
An automated classification technique for large size stellar surveys is proposed. It uses the extended Kalman filter as a feature selector and pre-classifier of the data, and the radial basis function neural networks for the classification.Experiments with real data have shown that the correct classification rate can reach as high as 93%, which is quite satisfactory. When different system models are selected for the extended Kalman filter, the classification results are relatively stable. It is shown that for this particular case the result using extended Kalman filter is better than using principal component analysis.
Application of RBF neural network to fault diagnosis in heliostats filed%RBF神经网络在定日镜场故障诊断中的应用
王成昱; 万定生; 郭铁铮
2011-01-01
针对定日镜场故障与征兆之间的关系特点,介绍了RBF神经网络运用于定日镜场故障诊断的基本方法.利用MATLAB神经网络工具箱建立和训练RBF神经网络,并对网络进行了测试.结果说明RBF神经网络在定目镜场故障诊断中具有较高的准确性和可靠性.%For the characteristic of the relationship between faults and symptoms, the basic principle and method of application of RBF neural network technique for the fault diagnosis in heliostats filed were introduced. The RBF neural network was built by using the neural network toolbox of MATLAB. The test result showed the use of the RBF network neural model was accurate and reliable.
Mohammed Awad
2016-07-01
Full Text Available Email is one of the most popular communication media in the current century; it has become an effective and fast method to share and information exchangeall over the world. In recent years, emails users are facing problem which is spam emails. Spam emails are unsolicited, bulk emails are sent by spammers. It consumes storage of mail servers, waste of time and consumes network bandwidth.Many methods used for spam filtering to classify email messages into two groups spam and non-spam. In general, one of the most powerful tools used for data lassification is Artificial Neural Networks (ANNs; it has the capability of dealing a huge amount of data with high dimensionality in better accuracy. One important type of ANNs is the Radial Basis Function Neural Networks (RBFNN that will be used in this work to classify spam message. In this paper, we present a new approach of spam filtering technique which combinesRBFNN and Particles Swarm Optimization (PSO algorithm (HC-RBFPSO. The proposed approach uses PSO algorithm to optimize the RBFNN param eters, depending on the evolutionary heuristic search process of PSO. PSO use to optimize the best position of the RBFNN centers c. The Radii r optimize using K-Nearest Neighbors algorithmand the weights w optimize using Singular Value Decomposition algorithm within each iterative process of PSO depending the fitness (error function. The experiments are conducted on spam dataset namely SPAMBASE downloaded from UCI Machine Learning Repository. The experimental results show that our approach is performed in accuracy compared with other approaches that use the same dataset.
Approach to red tide prediction on RBF neural network%基于RBF神经网络的赤潮预测方法
李慧; 顾沈明
2012-01-01
Red tide is an anomalous phenomenon and is characterized by abruptness and nonlinearity, so the red tide prediction has been a hotspot in the oceanographic studies. The fundamentals of RBF neural network are briefly introduced, and the application of artificial neural network method to the red tide prediction is discussed. Based on the RBF neural network, the simulation experiments are also illustrated by using red tide monitoring data, and the experimental analysis is also proposed.%赤潮是一种由多因素综合作用引发的生态异常现象,具有突发性及非线性等特点.对其进行预测预报一直是海洋科学研究的热点.简要介绍了RBF神经网络的基本原理,探讨了应用该人工神经网络进行赤潮预测的方法.利用RBF神经网络模型对赤潮灾害监测数据进行仿真实验,并对结果进行了分析.
3D Vision by Using Calibration Pattern with Inertial Sensor and RBF Neural Networks.
Beṣdok, Erkan
2009-01-01
Camera calibration is a crucial prerequisite for the retrieval of metric information from images. The problem of camera calibration is the computation of camera intrinsic parameters (i.e., coefficients of geometric distortions, principle distance and principle point) and extrinsic parameters (i.e., 3D spatial orientations: ω, ϕ, κ, and 3D spatial translations: t(x), t(y), t(z)). The intrinsic camera calibration (i.e., interior orientation) models the imaging system of camera optics, while the extrinsic camera calibration (i.e., exterior orientation) indicates the translation and the orientation of the camera with respect to the global coordinate system. Traditional camera calibration techniques require a predefined mathematical-camera model and they use prior knowledge of many parameters. Definition of a realistic camera model is quite difficult and computation of camera calibration parameters are error-prone. In this paper, a novel implicit camera calibration method based on Radial Basis Functions Neural Networks is proposed. The proposed method requires neither an exactly defined camera model nor any prior knowledge about the imaging-setup or classical camera calibration parameters. The proposed method uses a calibration grid-pattern rotated around a static-fixed axis. The rotations of the calibration grid-pattern have been acquired by using an Xsens MTi-9 inertial sensor and in order to evaluate the success of the proposed method, 3D reconstruction performance of the proposed method has been compared with the performance of a traditional camera calibration method, Modified Direct Linear Transformation (MDLT). Extensive simulation results show that the proposed method achieves a better performance than MDLT aspect of 3D reconstruction.
3D Vision by Using Calibration Pattern with Inertial Sensor and RBF Neural Networks
Erkan Beşdok
2009-06-01
Full Text Available Camera calibration is a crucial prerequisite for the retrieval of metric information from images. The problem of camera calibration is the computation of camera intrinsic parameters (i.e., coefficients of geometric distortions, principle distance and principle point and extrinsic parameters (i.e., 3D spatial orientations: ω, φ, κ, and 3D spatial translations: tx, ty, tz. The intrinsic camera calibration (i.e., interior orientation models the imaging system of camera optics, while the extrinsic camera calibration (i.e., exterior orientation indicates the translation and the orientation of the camera with respect to the global coordinate system. Traditional camera calibration techniques require a predefined mathematical-camera model and they use prior knowledge of many parameters. Definition of a realistic camera model is quite difficult and computation of camera calibration parameters are error-prone. In this paper, a novel implicit camera calibration method based on Radial Basis Functions Neural Networks is proposed. The proposed method requires neither an exactly defined camera model nor any prior knowledge about the imaging-setup or classical camera calibration parameters. The proposed method uses a calibration grid-pattern rotated around a static-fixed axis. The rotations of the calibration grid-pattern have been acquired by using an Xsens MTi-9 inertial sensor and in order to evaluate the success of the proposed method, 3D reconstruction performance of the proposed method has been compared with the performance of a traditional camera calibration method, Modified Direct Linear Transformation (MDLT. Extensive simulation results show that the proposed method achieves a better performance than MDLT aspect of 3D reconstruction.
ATTACK-DEFENSE GAME MODEL BASED ON RBF NEURAL NETWORK%基于RBF神经网络的攻防博弈模型
娄燕强; 宋如顺; 马永彩
2011-01-01
In order to elucidate how to determine the types between game sides in the process of network attack and defense and then to choose the action strategy, the attack - defense game model based on RBF neural network is put forward. Firstly, the two - player stochastic game model is used to analyze the characteristics of offensive and defensive sides, to reveal the restrict factors of strategies selection. Then,the optimal strategies chosen by both sides can be got through perfect Bayesian Nash equilibrium. At last, the RBF neural network is adopted to reason out the types of the suspects according to their action strategies and system status.%为了阐明网络攻防过程中博弈双方如何确定对方的类型,从而选择行动策略,提出了基于RBF神经网络的攻防博弈模型.首先使用两人随机博弈模型来分析网络攻防双方的特点,揭示制约双方选择策略的因素;通过精炼贝叶斯纳什均衡求得博弈双方选择的最优策略;最后,根据可疑者的行动策略和系统的状况,使用RBF神经网络对其类型进行推理.
Research on Telephone Charge Estimate Based on RBF Neural Network%基于RBF神经网络的话费估计问题研究
孙立炜; 林峰
2013-01-01
Due to the expense of the lost data,it is important to estimate the lost data according to the existing data. In this paper,the lost telephone charging data are estimated by RBF neural network,which achieves better effect. When RBF neural network is applied to numerical value estimating,it is important to conclude principles of choosing the best estimate value form aspects of the spread constant,nerve cells number and mean squared error.%数据丢失常常会造成损失，需要根据已有数据估计所丢失的数据。本文利用RBF神经网络估计丢失的话费数据，取得了较好的效果。在利用RBF神经网络处理数值估计问题时，要从散布常数、神经元个数和均方误差三个方面归纳最优估计值选择原则。
Rishi, Rahul; Choudhary, Amit; Singh, Ravinder; Dhaka, Vijaypal Singh; Ahlawat, Savita; Rao, Mukta
2010-02-01
In this paper we propose a system for classification problem of handwritten text. The system is composed of preprocessing module, supervised learning module and recognition module on a very broad level. The preprocessing module digitizes the documents and extracts features (tangent values) for each character. The radial basis function network is used in the learning and recognition modules. The objective is to analyze and improve the performance of Multi Layer Perceptron (MLP) using RBF transfer functions over Logarithmic Sigmoid Function. The results of 35 experiments indicate that the Feed Forward MLP performs accurately and exhaustively with RBF. With the change in weight update mechanism and feature-drawn preprocessing module, the proposed system is competent with good recognition show.
一种改进的RBF神经网络参数优化方法%Improved method for RBF neural network parameters optimization
张辉; 柴毅
2012-01-01
An improved method for RBF neural network parameters optimization is proposed. The number of nodes in the hidden layer is determined by using RAN (Resource Allocating Network), meanwhile strategy of pruning is introduced to remove those hidden units which make insignificant contribution to overall network output. Central position, width and weight of the neural network are optimized by the improved PSO (Particle Swarm Optimization) algorithm, so as to obtain the appropriate structure and control parameters. The new algorithm is used to predict the model of CSTR, and the result indicates that RBF neural network optimized by this algorithm has a smaller structure and high generalization ability.%提出了一种改进的RBF神经网络参数优化算法.通过资源分配网络算法确定隐含层节点个数,引入剪枝策略删除对网络贡献不大的节点,用改进的粒子群算法对RBF网络的中心、宽度、权值进行优化,使RBF网络不仅可以得到合适的结构,同时也可以得到合适的控制参数.将此算法用于连续搅拌釜反应器模型的预测,结果表明,此算法优化后的RBF网络结构小,并且具有较高的泛化能力.
王瑞; 史天运; 王彤
2011-01-01
对实测风速数据进行Kalman滤波,去除实测风速数据的偏差；通过归一化处理,消除数据中的冗余成分;针对RBF神经网络的预测误差会随着时间的推移而增大的问题,采用滚动式训练方法在线训练RBF神经网络;用训练好的RBF神经网络进行风速预测,再对预测结果进行反归一化处理,得到最终的预测风速.仿真结果表明,运用基于RBF神经网络的铁路短时风速预测方法对短时风速进行预测,最大相对误差仅为5.92％,可满足铁路防灾安全监控系统中风速预测子系统的要求.%The measured wind speed was processed with Kalman filter algorithm to eliminate deviations. The redundancies in the measured data were removed through normalization processing. Then, RBF neural network was online trained by using the rolling training method to deal with the problem that the prediction error of RBF neural network would increase as time went on. Finally, the wind speed was predicted by using the well-trained RBF neural network. The final forecasted wind speed was then obtained by anti-normalizing the output of RBF neural network. The simulation results show that the maximum relative error is only 5. 92% using the proposed railway short-time wind speed prediction algorithm based on RBF neural network, which can satisfy the requirements of the wind forecasting subsystem in railway disaster prevention and safety monitoring system.
陈红杰; 李高锋
2015-01-01
针对建筑工程特点，提出了基于RBF神经网络的建筑工程投标报价方法，建立建筑工程投标报价标高率数学模型。应用MATLAB计算软件，以实例验证了该模型的正确性及实用性。%According to the peculiarity of construction engineering, based on the theory of RBF neural networks. Mark-up rate evaluation model of construction engineering is set up. A particular software MATLAB is employed to analyze the evaluation model. The accuracy and value of the approach are testified by the prototypical data.
ZHANG Hao
2017-08-01
Full Text Available With SiO2 as the carrier, decanoic acid-palmitic acid as a phase change material,the micron SiO2-based phase change and humidity controlling composite materials were prepared by sol-gel method. The scheme was optimized by uniform design in a combination with RBF neural network to optimizing preparation of micron SiO2-based phase change and humidity controlling composite materials. The performance of micron SiO2-based phase change and humidity controlling composite materials with optimal uniform particle size distribution were tested and characterized. The results show that RBF neural network has the best approximation effect, when spread is 0.5; optimization technology parameters are solution pH value 4.27, amount of deionized water (mole ratio between deionized water and tetraethyl orthosilicate is 8.58, amount of absolute alcohol (mole ratio between absolute alcohol and tetraethyl orthosilicate is 4.83 and ultrasonic wave power is 316W; micron SiO2-based phase change and humidity controlling composite materials with optimal uniform particle size distribution' d10 is 383.51nm, d50 is 511.63nm and d90 is 658.76nm, measured value of d90-d10 is 275.25nm, the measured value and the predicted value are in good agreement (relative error is -2.64%; micron SiO2-based phase change and humidity controlling composite materials with optimal uniform particle size distribution' equilibrium moisture content in the relative humidity of 40%-60% is 0.0925-0.1493g/g, phase transition temperature is 20.02-23.45℃ and phase change enthalpy is 54.06-60.78J/g.
薛晓岑; 向文国; 吕剑虹
2014-01-01
针对热工过程的非线性辨识问题，提出了一种基于差分进化算法（ DE ）的径向基函数神经网络（ RBFNN）模型设计方法。该方法将DE算法的种群分解为几组并行的子种群，每组子种群对应于一类隐节点数相同的RBF网络。在RBFNN的学习过程中进行多子种群并行优化，从而实现RBF网络结构与参数的同时调整。算法可以利用热工对象的输入输出数据，自动设计出满足误差精度要求且结构较小的RBFNN模型。然后将该算法应用于热工对象的辨识，对于单输入单输出系统，得到的RBFNN模型只需1个隐节点。对于多输入单输出系统，RBF网络也仅需较少的隐层节点。仿真结果表明，用该方法设计的RBFNN模型结构简单，且辨识误差小，具有较好的泛化能力。%For the nonlinear identification of thermal process, a new radial basis function neural net-work ( RBFNN) design method is proposed based on the differential evolution algorithm ( DE) .In the method, the population in the DE algorithm is divided into several parallel subpopulations, and each subpopulation corresponds to a class of RBF network solutions with the same hidden nodes.In the RBFNN learning process, the network structure and parameters are adjusted simultaneously through the parallel optimization of the subpopulations.Under the given error limit, the algorithm can design an RBF model automatically with fewer hidden nodes according to thermal input and out-put data.Then, the algorithm is used to identify nonlinear thermal processes.For single-input sin-gle-output system identification, only one node is required in the RBFNN hidden layer.For multi-in-put single-output system identification, the RBFNN model also requires less hidden nodes.The sim-ulation results show that the proposed approach can achieve the given identification accuracy with fe-wer hidden nodes, and has good generalization ability.
Human Reliability Prediction of Lifting Operation Based on RBF Neural Network%基于RBF的起重作业岗位人因可靠性预测
王洪德; 马成正
2012-01-01
In order to improve the reliability of lifting operation, and prevent accident caused by human errors, bearing randomness, fuzziness and uncertainty of human error in mind, an RBF neural network-based method for analyzing the human error's nonlinear dynamics process was put forwarded. Taking the lifting operation as example, firstly, an indexes system about the human reliability prediction was constructed , which included the factors of the operator, the communion interface, the operating circumstance, the operating characteristics and the operating organization. Then the indexes were quantified. Secondly, according to human reliability analysis (HRA) theory and the scene record, the human error data were calculated out, and the human error rates were given. Finally, basing on the analysis of the operator's tiredness and emotion, information channels, operation complexity and time margin, lighting and wind power conditions, working pressure and safety supervision, an RBF neural network-based model for lifting operation human reliability was built. The results indicate that the RBF prediction includes the operation reliability as well as the cognitive reliability, and that the predictions results conform with the actual observed values up to 92. 0%.%为提高起重作业可靠性,防止人因失误酿成事故,针对人因失误的随机性、模糊性和不确定性特点,提出运用具有非线性映射能力和容错能力的径向基函数( RBF)神经网络,分析人因失误非线性动力学过程.以起重机操作岗位作为人因可靠性分析(HRA)实例,首先,建立基于“作业人员、交流界面、作业环境、作业特性、作业组织”的人因可靠性预测指标体系,并对指标进行量化；其次,根据人因可靠性原理,统计出人因失误次数,给出人因失误率；最后,通过对“人的疲劳和情绪、交流通道、作业复杂程度和时间裕度、照明环境和风力影响、工作强度和安全监管”等
改进的双模型结构RBF神经网络及其应用%Improved RBF neural network with double model structure and its application
李全善; 张义山; 曹柳林; 林晓琳; 崔佳
2011-01-01
提出了离线结构学习和在线权值校正相结合的双模型结构RBF神经网络,以离线学习和在线校正相结合的方式实现网络的自学习和自校正,满足了软测量仪表现场应用的要求.针对应用过程中出现预测误差过大的现象,通过对网络算法进行分析,研究影响网络预测精度的因素,在此基础上,提出了以K均值聚类法和递推下降算法相结合的RBF神经网络建模改进算法,仿真结果和实际应用证明了改进算法的有效性.%A dual model RBF (radial basis function) neural network was proposed in this paper. One is used for self-learning, which learns one time a day. The other is used for on-line correcting, which is the running model currently. Both the self-learning model and the on-line correcting model are corrected six times every day and should track the current conditions of the system quickly. At the same time, the accuracy of the two models should be compared. If the accuracy of the on-line correcting model is less than the one of the self-learning model, the latter becomes the new currently running model instead of the old one. Otherwise, the currently model is maintained. To solve the problem of neural network large prediction errors, a network algorithm analysis is given and the influence factors of the network prediction accuracy are found. At last, an improved algorithm of RBF neural network modeling is proposed, which combines K-means clustering method with the recursive descent algorithm. Simulation and practical application proved the effectiveness of the improved method.
连黎明; 唐军
2014-01-01
通过对数控转台SKZT3500用恒流静压轴承进行特性分析，借助软件MATLAB7．1中神经网络工具箱，将RBF神经网络的理论和算法应用到恒流静压轴承静刚度预测中。经过对物理样机进行相关试验，把测量获得的样本数据用于对RBF神经网络进行训练和测试。结果表明，RBF神经网络能够较准确地预测恒流静压轴承的静刚度。%Through analysis of the characteristics of constant -current hydrostatic bearings for NC rotary table SKZT3500,the theory and arithmetic for the RBF neural network are applied to predict the static stiffness for the bear-ings by using neural network toolbox in MATLAB 7.1.The measured sample data is used to train and test the RBF neural network through experiment of physical prototype.The results show that the RBF neural network can accurately forecast the static stiffness of constant-current hydrostatic bearings.
Assareh, Ehsanolah; Poultangari, Iman [Dezful Branch, Islamic Azad University, Dezful (Iran, Islamic Republic of); Tandis, Emad [Mechanical Engineering Department, University of Jundi Shapor, Dezful (Iran, Islamic Republic of); Nedael, Mojtaba [Dept. of Energy Engineering, Graduate School of the Environment and Energy, Science and Research Branch, Islamic Azad University, Tehran (Iran, Islamic Republic of)
2016-10-15
Enhancing the energy production from wind power in low-wind areas has always been a fundamental subject of research in the field of wind energy industry. In the first phase of this research, an initial investigation was performed to evaluate the potential of wind in south west of Iran. The initial results indicate that the wind potential in the studied location is not sufficient enough and therefore the investigated region is identified as a low wind speed area. In the second part of this study, an advanced optimization model was presented to regulate the torque in the wind generators. For this primary purpose, the torque of wind turbine is adjusted using a Proportional and integral (PI) control system so that at lower speeds of the wind, the power generated by generator is enhanced significantly. The proposed model uses the RBF neural network to adjust the net obtained gains of the PI controller for the purpose of acquiring the utmost electricity which is produced through the generator. Furthermore, in order to edify and instruct the neural network, the optimal data set is obtained by a Hybrid genetic algorithm along with a gravitational search algorithm (HGA-GSA). The proposed method is evaluated by using a 5MW wind turbine manufactured by National Renewable Energy Laboratory (NREL). Final results of this study are indicative of the satisfactory and successful performance of the proposed investigated model.
基于RBF神经网络的老年痴呆症智能诊断研究%Study on Intelligent Diagnosis of Senile Dementia Based on RBF Neural Network
张会敏; 叶明全; 罗永钱; 孟婷玮; 陈玥珠
2015-01-01
In order to verify single RBF neural network is more suitable for the predictive diagnosis of senile dementia, through the simulation experiment, a single BP neural network, a single RBF neural network, a genetic algorithm to optimize BP neural network and a genetic algorithm to optimize RBF neural network are used to predict senile dementia, establishing of these four kinds of network model, then analyzing and comparing the forecasted results of these four kinds of network model. The simulation experiments were carried out on the platform of Matlab software, the results show that: in the predictive diagnosis of senile dementia, the single RBF neural network predictive results is higher than the single BP neural network,and the modeling time is shorter. Furthermore, the prediction results of the single RBF neural network is as the same as the genetic algorithm to optimize BP neural network, but the single RBF neural network model is relatively simple, and the prediction results are more stable. Therefore, diagnosis and prediction of the single RBF neural network is more suitable for senile dementia, and this conclusion can be used as a theoretical guide to the actual application.%为验证单RBF神经网络更适用于老年痴呆症的预测诊断，通过仿真实验将单BP神经网络、单RBF神经网络、遗传算法优化BP神经网络及遗传算法优化RBF神经网络分别应用于老年痴呆症的预测诊断，建立这四种网络模型，并对四种网络模型的预测结果进行分析比较。仿真实验在Matlab软件平台上进行。结果表明：在老年痴呆症的预测诊断中，单RBF神经网络比单BP神经网络预测结果更好，建模时间更短。此外，单RBF神经网络与遗传算法优化的BP神经网络预测结果相同，但单RBF神经网络建模较为简单，预测结果更为稳定。而遗传算法对RBF神经网络优化作用不明显。因此，单RBF神经网络更适用于老年痴呆症的预测诊
吕岚; 甘旭升; 屈虹; 赵海涛
2014-01-01
为提高RBF神经网络的建模性能，提出一种基于改进无迹Kalman滤波（UKF）的RBF神经网络训练算法。在该算法中，首先将比例最小偏度单形Sigma点采样策略引入UT，以有效改进UKF，提升其计算效率，然后利用改进的UKF优化估计RBF神经网络的最优参数。仿真结果表明，改进的UKF比EKF具有更高的RBF神经网络模型训练精度，与传统UKF的模型精度大体相当，但速度更快，计算效率更高。%To improve the modeling of RBF neural network,a training algorithm of RBF neural network based on modified Unscented Kalman Filter(UKF)is proposed. In the algorithm,first a scaled minimal skew simplex Sigma point sampling strategy is introduced in Unscented Transform (UT) to improve UKF for computation efficiency,and then the improved UKF is used to optimize the parameters of RBF neural network. Simulation show that,for the training problem of RBF neural network,the model precision of proposed UKF is higher than that of EKF,and is approximately close to traditional UKF with faster training and better computation.
袁红春; 潘金晶
2016-01-01
In order to improve accuracy of dissolved oxygen prediction,radial basis function( RBF)neural network based on improved recursive least square algorithm is applied to predict the dissolved oxygen. Using K means clustering algorithm to choose the center of hidden layer units and improved recursive least square algorithm is used to optimize the weights of hidden layer to output layer of RBF neural network. Simulation results show that the proposed method has good nonlinear fitting ability and its prediction precision is higher than RBF neural network and RBF neural network based on recusive least square algorithm.%为提高溶解氧预测的准确性，将基于改进型递归最小二乘算法优化的径向基函数（ RBF）神经网络方法应用于溶解氧预测。利用K均值聚类算法进行隐层单元中心选择；利用改进型递归最小二乘算法优化RBF神经网络隐含层到输出层的权值。仿真结果表明：该方法对溶解氧的预测具有较好的非线性拟合能力，预测精度优于RBF神经网络和递归最小二乘算法优化的RBF神经网络。
张军朝; 陈俊杰
2011-01-01
Photovoltaic Array is nonlinear, and the power generated by it is influenced by sun light, temperature and so on. We put forward PV array model by using neural networks identification technique in this paper. The temperature, radiation and voltage of the solar cells are taken as the input and the current as the output of the neural networks model. Using RBF neural network to model for photovoltaic battery and particle swarm optimization algorithm to optimize the RBF neural network, finally the photovoltaic model is established. Simulated experiments are carried out on the photovoltaic battery data, the results show that the improved RBF neural networks have better accuracy and adapt ability than traditional RBF method. The RBF neural networks modeling makes it possible to design on-line controller of photovoltaic system.%本文研究神经网络在光伏电池建模优化问题.由于光伏电池具有高度非线性特性,其输出功率受到外界自然因素的影响,使得传统方法不能满足光伏控制系统动态要求.针对上述问题,本文提出一种粒子群优化的神经网络光伏电池建模算法.改进的方法以日照、温度和负载电压作为提出的RBF神经网络模型的输入值,把光伏电池的输出功率作为神经网络的输出,采用RBF神经网络对光伏电池进行建模,同时利用粒子群算法对神经网络参数进行优化,最后建立光伏电池的动态响应模型.仿真实验结果证明,所提模型更好地克服传统方法的缺点,收敛速度快,具有较高的预测精度和适合能力.
龙亿; 杜志江; 王伟东
2015-01-01
为改善外骨骼机器人灵敏度放大控制( SAC)性能,结合遗传算法( GA)与径向基函数( RBF)神经网络建立在线计算外骨骼机器人的精确动力学模型.用GA优化RBF神经网络的中心矢量与基宽度,并对RBF网络的权值实时更新,在线学习外骨骼机器人动力学模型中的参数矩阵,进一步推导出SAC控制律.仿真结果表明:GA优化后的RBF网络,可以在线学习外骨骼的动力学模型,基于该模型的SAC能够实现精确的人体轨迹跟踪,相比于优化前,人体轨迹跟踪误差以及人机交互信息会快速减小并收敛到0的微小邻域内,可实现人机协调运动.%To improve performance of sensitivity amplification control ( SAC ) for exoskeleton robot, genetic algorithm( GA) and RBF neural network was combined to obtain accurate dynamic model of exoskeleton robot online. Parameters of center vector and base width of RBF neural network were obtained by GA optimization, and online RBF weights learning process was constructed to obtain estimation matrix parameters of dynamics system, finally, SAC control law was deduced. Simulation results showed that the RBF network optimized by GA could learn exoskeleton dynamics model parameters online. Based on the learned model, the SAC could achieve more precise human trajectory tracking where tracking error and human-robot interaction force converged to the small neighborhood of zero simultaneously compared with those without optimization. The proposed RBF neural network with GA optimization which learned dynamics model parameters online for exoskeleton robot dynamics model could achieve highly accurate trajectory following for SAC, ultimately realize cooperative movement between human and exoskeleton.
Equalizer Based on RBF Neural Network and RLS Algorithm%基于RBF神经网络与RLS算法的均衡器
吕志胜; 赖惠成
2009-01-01
将径向基函数神经网络与横向均衡器相结合,采用递推最小二乘算法更新权值.将最小二乘误差作为代价函数以及与误差相关的变步长,使输出误差较传统的神经网络均衡器进一步减小,收敛速度得到提高.仿真结果表明,该均衡器对线性信道和非线性信道都表现出较好的性能,在较严重的非线性情况下其优越性更明显.%This paper combines Radial Base Function(RBF) neural network and landscape filter, uses Recursive Least Square(RLS) algorithm to update the weight and uses variable steps associated with errors, the output error and the convergence speed are both improved. Simulations results show that the new equalizer has better performance, whether it is in linear or nonlinear. In more serious cases, its advantages are much more obvious.
苗青; 曹广益; 朱新坚
2006-01-01
The temperature models of anode and cathode of direct methanol fuel cell (DMFC) stack were established by using radial basis function (RBF) neural networks identification technique to deal with the modeling and control problem of DMFC stack. An adaptive fuzzy neural networks temperature controller was designed based on the identification models established, and parameters of the controller were regulated by novel back propagation (BP) algorithm. Simulation results show that the RBF neural networks identification modeling method is correct, effective and the models established have good accuracy. Moreover, performance of the adaptive fuzzy neural networks temperature controller designed is superior.
RBF networks with mixed radial basis functions
Ciftcioglu, O.; Sariyildiz, I.S.
2000-01-01
After the introduction to neural network technology as multivariable function approximation, radial basis function (RBF) networks have been studied in many different aspects in recent years. From the theoretical viewpoint, approximation and uniqueness of the interpolation is studied and it has been
Compensation for unmatched uncertainty with adaptive RBF network
user
radial basis function (RBF) neural networks have showed strong universal approximation ability for unknown ..... w is the ideal constant weight, the ... w with the weight estimation error )(~ twi ..... Gaussian networks for direct adaptive control.
卫晓娟; 丁旺才; 李宁洲; 郭文志
2016-01-01
为解决神经网络结构及参数的优化选择问题，以提高机车齿轮箱故障诊断的精度，提出一种基于引力搜索RB F神经网络的机车齿轮箱智能故障诊断方法。基于高斯RB F神经网络建立机车齿轮箱故障诊断模型，采用减聚类算法确定RB F神经网络结构，并结合混沌优化策略及人工蜂群搜索算子提出自适应混合引力搜索算法对故障诊断模型进行优化求解，避免了参数选择的盲目性。采用国际标准测试数据集对该方法进行分类性能测试，结果表明其分类精度明显优于经GA算法、SPSO算法、QPSO算法和GSA算法优化的RBF神经网络。将该方法应用于机车齿轮箱故障的诊断，应用实例验证了该方法的有效性。%In order to solve the issue of the determination of neural network structure and the optimization of neural network parameters to improve the accuracy of fault diagnosis of locomotive gearbox ,an intelligent fault diagnosis method based on the gravitational search algorithm and RBF neural network was proposed . When the locomotive gearbox fault diagnosis model was established based on Gaussian RBF neural network , subtractive clustering algorithm was used to determine the structure of RBF neural network .By reference to the artificial bee colony search operator and chaos optimization strategy , an adaptive hybrid gravitational search algorithm was proposed and applied to solve and optimize the fault diagnosis model , to avoid the blindness of parameter selection . Results of the classification performance test on the proposed method using UCI testing data sets showed that the classification accuracy of the proposed method was significantly better than the RBF neural net‐work optimized by GA algorithm ,SPSO algorithm ,QPSO algorithm and GSA algorithm . The application of the proposed method in fault diagnosis of locomotive gearbox demonstrated the effectiveness of this method .
Dong-Mei Qin; Ping Guo; Zhan-Yi Hu; Yong-Heng Zhao
2003-01-01
For LAMOST, the largest sky survey program in China, the solution ofthe problem of automatic discrimination of stars from galaxies by spectra has shownthat the results of the PSF test can be significantly refined. However, the problemis made worse when the redshifts of galaxies are not available. We present a newautomatic method of star/(normal) galaxy separation, which is based on StatisticalMixture Modeling with Radial Basis Function Neural Networks (SMM-RBFNN).This work is a continuation of our previous one, where active and non-active celestialobjects were successfully segregated. By combining the method in this paper andthe previous one, stars can now be effectively separated from galaxies and AGNs bytheir spectra-a major goal of LAMOST, and an indispensable step in any automaticspectrum classification system. In our work, the training set includes standardstellar spectra from Jacoby's spectrum library and simulated galaxy spectra of E0,SO, Sa, Sb types with redshift ranging from 0 to 1.2, and the test set of stellarspectra from Pickles' atlas and SDSS spectra of normal galaxies with SNR of 13.Experiments show that our SMM-RBFNN is more efficient in both the trainingand testing stages than the BPNN (back propagation neural networks), and moreimportantly, it can achieve a good classification accuracy of 99.22% and 96.52%,respectively for stars and normal galaxies.
张爱科; 符保龙; 李辉
2012-01-01
Web文本分类是数据挖掘研究的一个热点问题.针对文本向量维度过高的特点,提出一种改进的模糊聚类RBF网络集成的文本分类方法,该方法利用模糊C均值聚类算法对文本特征向量进行简化、抽取,引入自适应遗传算法优化RBF神经网络的权值,构建RBF网络集成模型对文本进行分类.实验结果表明,该方法具有更高的分类效率和正确率.%Web text classification is a hot issue in the research on data mining. In view of the characteristics of high dimension text vector, the paper proposes an improved text classification method of fuzzy cluster RBF network integration. The method uses fuzzy c-means clustering algorithm to simplify and extract the text eigenvector, introduces adaptive genetic algorithm for optimization of RBF Neural network weights, and builds a RBF network model for text classification. Experimental results show that the method possesses a higher classification efficiency and accuracy.
王莉; 王德明; 张广明; 周献中
2011-01-01
A radical basis function (RBF) neural network model combined with rough sets was used to predict short-term wind speed. Rough sets were used to reduce input feature space so that the significant factors for wind speed prediction could be found as the input variables of RBF neural network prediction model. Online rolling optimization was adopted in training RBF neural network. The latest sample was added into the training sets, thus the prediction model could catch recent changes of wind speed. The proposed method was used to predict wind speed in 1 h. Simulation results showed that the method had advantages of simplicity and high precision.%结合粗糙集提出了一种RBF神经网络短期风速预测模型.采用粗糙集对预测模型的输入特征空间进行约简,找出对未来预测的风速具有主要影响的因素,以此作为RBF神经网络预测模型的输入变量；在RBF神经网络训练的过程中,采用在线滚动优化策略,将最新的样本加入训练集,从而使预测模型能够跟踪风速的最新变化.将提出的方法用于某风电场的lh短期风速预测,仿真实验结果表明该方法具有结构简单、预测精度高的优点.
Application of RBF Neural Network in Optimizing Machining Parameters%径向基函数网络在优化机械加工参数中的应用
朱喜林; 吴博达; 武星星
2004-01-01
In machining processes, errors of rough in dimension, shape and location lead to changes in processing quantity, and the material of a workpiece may not be uniform. For these reasons, cutting force changes in machining, making the machining system deformable. Consequently errors in workpieces may occur. This is called the error reflection phenomenon. Generally, such errors can be reduced through repeated processing while using appropriate processing quantity in each processing based on operator's experience.According to the theory of error reflection, the error reflection coefficient indicates the extent to which errors of rough influence errors of workpieces. It is related to several factors such as machining condition, hardness of the workpiece, etc. This non-linear relation cannot be worked out using any formula. RBF neural network can approximate a non-linear function within any precision and be trained fast. In this paper, non-linear mapping ability of a fuzzy-neural network is utilized to approximate the non-linear relation. After training of the network with swatch collection obtained in experiments, an appropriate output can be obtained when an input is given. In this way, one can get the required number of processing and the processing quantity each time from the machining condition. Angular rigidity of a machining system,hardness of workpiece, etc., can be input in a form of fuzzy values. Feasibility in solving error reflection and optimizing machining parameters with a RBF neural network is verified by a simulation test with MATLAB.
Application of RBF neural network algorithm in dynamic weighing%RBF神经网络算法在动态称重中的应用∗
陈超波; 杨楠
2016-01-01
In this paper,focus on the complexity of weighing data in the dynamic detection system of the highway,the different weighing data processing methods to make a comparison,and proposed the use of RBF neural network to deal with the dynamic weighing data.Firstly review introduced the whole vehicle dynamic system,after the radial basis function network topology and the centers of the radial basis function selection are introduced.Finally the test-bed to build a testing platform,through experiments with a two axle vehicle with different speed through the test stand,the dynamic parameters acquisition.Finally,using the data collected,using MATLAB to simulate,verify the radial basis function network to the dynamic weighing data processing show good speed and accuracy.%针对高速公路动态检测系统中称重数据的复杂性，将不同的称重数据处理办法做出对比，并提出利用 RBF神经网络对动态称重数据进行处理。文章首先综述性的介绍了车辆动态系统整体构成，之后对径向基函数网络的拓扑结构以及径向基函数中心的选取进行了介绍，最后利以试验台搭建检测平台，通过实验用两轴小车进行以不同的速度通过试验台，采集其动态参数。最后利用采集到的数据，用 MATLAB 进行仿真，验证了径向基函数网络对动态称重数据的处理表现出良好的速度与精度。
张高扬; 翟成功; 刁永辉
2013-01-01
本文在纬编摇粒绒织物的保暖性能测试中，利用RBF人工神经网络的智能鉴别和预测功能，在实验测试中进行实验数据的预测、鉴别和修订，排除错误的数据；利用RBF人工神经网络强大的数据处理能力，来进行数据分析，保证数据处理的准确性，以便得到更加客观真实的结论。%This paper is designed to use the intelligent data forecasted and distinguished function of RBF artificial neural network in the thermal test of the weft polar fleece, in order to modify the test data and eliminate mistakes. The test data is analyzed by using RBF artificial neural network to ensure the data pro-cessing veracity and the impersonal conclusion.
张培; 陈光大; 张旭
2011-01-01
It is unnecessary to establish concrete function expression, the known discrete data can be fitted by using neural network to extend hydraulic turbine combined characteristic cure. And we can also add boundary conditions to predict unknown zones, so as to raise the work efficiency and data precision in data treatment concerning hydraulic turbine combined characteristics. This paper intro- duces the use of gP neural network and RBF neural network in extending hydraulic turbine combined characteristic curve. I.astly, the results of the two methods are compared and some conclusions are obtained.%利用神经网络对水轮机综合特性曲线进行数据处理和延伸，不必建立具体的函数关系表达式，就可对已知的离散数据进行拟合。并且还可以结合边界约束条件对未知区域内的数据进行预测，从而提高了水轮机综合特性曲线数据处理的工作效率和数据精度。分别介绍了用BP神经网络和RBF神经网络对水轮机综合特性曲线数据处理和延伸的方法。并采用一机组的样本数据进行训练，比较2种方法的训练结果得出结论。
谭昶; 肖南峰
2011-01-01
针对手势识别的手区域分割、手势特征提取和手势分类的三个过程,提出了一种新的静态手势识别方法.改进了传统的RCE神经网络用于手区域的分割,具有更高的运行速度和更强的抗噪能力.依Freeman链码方向提取手的边缘到掌心的距离作为手势的特征向量.将上一步得到的手势特征向量作为RBF神经网络的输入,进行网络的训练和分类.实验验证了该方法的有效性和可行性,并用其实现了人和仿人机器人的剪刀石头布的猜拳游戏.%Hand gesture recognition usually includes hand image segmentation,features extraction,and hand gestures classification. In this paper,a new method is proposed to deal with the three phases of static hand gesture recognition. The traditional RCE neural network is improved and it is applied to hand image segmentation.The improved RCE neural network is proved to has running fast and strong ability of anti-noise. Freeman chain code is used to extract the distance from hand edge to the centre of the palm as feature vectors. Those feature vectors are used as the input of RBF neural network. Experiment resuits show this method is efficient and feasible. A scissors-paper-stone game between human and humanoid robot is developed by using this method.
吴一晓; 杨然; 李占军; 何浩强; 胡红丽
2014-01-01
Objective:To design a knee Osteoarthritis classifier of magnetic resonance T2 map data, which used for OA disease classification. Methods:Collected 46 cases of knee image with a total of 1380 data by magnetic resonance imaging (MRI) T2 mapping technique, and extracted T2 value data of 10 Asian region based on articular cartilage whole organ magnetic resonance imaging score (WORMS) partition. Then took the T2 value data as the characteristic quantity by data mining, and structured radial basis function (RBF) neural network classifier, combined with the clinical diagnosis to classify and recognize the data of collected sample. Results:The study finally found that RBF classifier reflected 75% of recognition accuracy rate, and it showed good effect of OA data classification. Conclusion:The knee osteoarthritis RBF neural network classifier based on direct determination method can get the optimal weights, right center and variance by simple steps, without any iteration. We suggest that it is a classifier fit to OA disease.%目的：设计一种膝关节骨性关节炎(OA)磁共振T2 map数据分类器，用于OA疾病分类。方法：通过磁共振成像(MRI)T2 mapping技术，采集46例膝关节MRI图像共计1380个数据，按膝关节软骨全器官磁共振成像评分(WORMS)分区方法提取10个亚区的T2值数据，以T2值数据为特征量进行数据挖掘，建立径向基函数(RBF)神经网络分类器，结合临床诊断结果实行对采集样本数据分类识别。结果：RBF分类器对于膝关节T2 map数据最终识别准确率为75%，体现了良好的OA数据分类效果。结论：基于直接确定法的RBF神经网络构造的膝关节OA分类器无需任何迭代，通过简单步骤就得到最优权值、合适的中心以及方差，适合作为OA的疾病分类器。
高丙坤; 郑仁谦; 尹淑欣; 张莉; 岳武峰
2016-01-01
为了正确判断管道是否发生泄漏，本文采用混合学习方法对网络进行训练学习。通过将管道运行参数作为神经网络的输入，管道运行状态作为神经网络的输出，实现两者的非线性映射，以此来判断输入信号是否为泄漏信号，并选用K-means聚类方法和递推最小二乘法来确定网络参数。通过用天然气管道运行的实测数据对RBF神经网络进行了训练和测试，得到结果误差在可接受的范围内，从而证明RBF神经网络的方法可用于天然气管道泄漏检测的研究。%In order to correctly determine whether pipeline leakage occurs, this paper adopts a hybrid learning method for network training. We set the pipeline operation parameters as the input of neural network and running status of the pipe as the neural network output, realizing the two nonlinear mapping, in order to determine whether the input signal is leakage signal , and select K-means clustering method and the recursive least square method to determine the network parameters. With the measurements of the gas pipeline operation on training and testing the RBF neural network, we get the results in an acceptable error range, which prove that the method of RBF neural network can be used for natural gas pipeline leak detection.
RBF网络在有源降噪系统中的应用仿真%The Application Simulation of RBF Neural Network in Active Noise Control System
姜丽飞
2011-01-01
针对车辆舱室内的噪声特点,在分析噪声系统非线性特性的基础上,将高速实时信号处理器DSP应用于有源降噪系统的硬件设计中,提出一种基于变结构RBF神经网络的噪声自适应控制方案,给出滤波-x算法并进行仿真验证.同时将该滤波算法的降噪效果和基本的滤波-x算法的进行比较.结果表明,采用该控制算法取得了良好的降噪效果.%Aiming at the characteristics of noise in vehicle cabins, and analyzing nonlinear characteristics of the system, the high-speed real-time signal processor (DSP) was used in active noise control system and an adaptive noise control project based on RBF networks was proposed.An algorithm of FX-RBF was given and simulated.Its noise reduction effect was compared with that of the basic filter-X algorithm.Simulation results showed that the noise reduction effect of the FX-RBF algorithm is good.
Application of BP NN and RBF NN in Modeling Activated Sludge System
王维斌; 郑丕谔; 李金勇
2003-01-01
Based on the operation data from a certain wastewater treatment plant(WWTP) in northeast China, the models of back propagation neural network(BP NN) and radial basis function neural network(RBF NN) have been designed respectively and the ability of convergence and generalization has been analyzed separately. As for BP NN, the effects of numbers of layers and nodes have been studied; as for RBF NN, the influences of the number of nodes and the RBF′s width have been studied. It is concluded that BP NN has converged much slowly in comparison with RBF NN. The conclusion that the RBF NN is suitable for modeling activated sludge system has been drawn. An automatically optimum design program for RBF NN has been developed, through which the RBF NN model of traditional activated sludge system has been established.
张少迪; 王延杰; 孙宏海
2012-01-01
A network training method for star pattern recognition was designed by combining a classific Radial Basic Function(RBF) neural network and star pattern samples. Firstly, the star pattern abstraction method was discussed and a triangulation based on star magnitudes was induced to connect the stars which probably appear in the same field of view. By taking extrated angular distances as the characteristic of star pattern, a star pattern sample set with completion, translation and rotation in-variance was established. Then, RBF neural network was studied to recognize the star patterns. RBF network training method was classified as sequence learning and batch learning. Some typical algorithms that could represent the two methods were studied on their advantages and disadvantages,and a new training method was designed based on the specialty of above star pattern sample sets. Experiments indicate that the designed method is more appropriate than those typical algorithms. Several star images were simulated through software, which was regarded as the observatory data and entered into the trained RBF neural network to test. The experiment results show that the network can recognize all the star patterns successfully.%根据经典径向基函数(RBF)神经网络的优势,结合星图模式样本集的特点,设计了一种适合星图模式样本的网络训练算法.从提取星图模式入手,引入三角剖分理论,将可能出现在同一视场内的恒星以三角形的形式连接起来,提取连接的角距作为星图模式,建立了具有完备性、平移旋转不变性的星图模式样本集.然后,利用RBF神经网络做星图识别,研究顺序训练方法和批量训练方法,总结多种经典算法的优缺点,并设计了一种训练方法.通过实验证明了该种方法较其他经典算法更为适合学习星图模式样本.最后,给出RBF神经网络相关的训练数据,并通过模拟星图软件获得若干模拟星图作为观测样本,利用
Self-adaptive RBF Neural Network Control Theory of Switched Reluctance Motor%开关磁阻电机自适应RBF神经网络控制方法研究
蔡益春; 王立标
2012-01-01
Switched reluctance motor doubly salient structure and magnetic circuit of the motor flux is highly saturated highly nonlinear, leading to classical PID control can not get higher control precision. Designing of feed-forward and feedback controller based on self-adaptive RBF neural network for SRM, the simulation results show that, this method can improve the precision of motor speed, torque pulsation, thereby optimizing the motor operat-ing performance.%开关磁阻电机(switched reluctance motor,SRM)双凸极结构和磁路高度饱和使得电机磁链呈高度非线性,导致经典PID控制不能得到较高的控制精度.设计了基于自适应RBF(radial basis function)神经网络的SRM前馈+反馈控制器,对电机实行自适应控制.仿真结果表明,该方法能提高电机转速精度,降低转矩脉动,从而优化电机的运行性能.
王军号; 孟祥瑞; 吴宏伟
2011-01-01
针对瓦斯传感器常见的偏置型、冲击型、漂移型和周期型4种突发型故障,以小波分析和RBF神经网络为基础,提出了由小波包分解提取特征能量谱与扩展Kalman滤波算法(EKF)优化的RBF神经网络进行模式分类辨识的瓦斯传感器故障诊断方法.对瓦斯传感器的输出信号进行小波包分解,运用基于代价函数的局域判别基(LDB)算法进行裁剪,获取最优的特征能量谱,经处理后作为特征向量训练EKF-RBF神经网络,采用参数增广和统计动力学方法,通过带有整定因子的EKF参数估计,用来辨识瓦斯传感器的故障类型.实验结果表明:该方法的辨识正确率在95%以上,误报率和漏报率都明显优于其他算法,能够有效用于瓦斯传感器的故障在线诊断.%For four types of common abrupt faults of gas sensor, namely offset, impact, drift and periodic types, on the basis of wavelet analysis and RBF neural network, a method of the gas sensor fault diagnosis was proposed based on the pattern classification of characteristic energy spectrum extracted by the decomposition of wavelet packet and RBF neural network optimized by Extended Kalman Filter (EKF). The optimal characteristic energy spectrum was obtained through the decomposition of wavelet packet of output signal of gas sensor and optimally cut by Local Discriminant Base (LDB) based on the cost function. After processed, as the characteristic vector for training EKF-RBF neural network, adopted augnented parameters and method of statistical mechanics, and through the EKF parameter estimation with tuning factor, it was used to identify the fault type of sensor. The experimental results show that the identification accuracy is above 95 ％ ,its rate of false alarm and fail alarm is superior to other algorithms, and the method can be effectively applied to the online fault diagnosis of gas sensor.
基于RBF神经网络的池州市降水序列预测%Prediction of precipitation series based on RBF neural network in Chizhou city
沈艳; 杨春雷; 张庆国; 朱雅莉
2012-01-01
时间序列预测分析方法是进行预测预报的有效工具,有着广泛的应用.针对时间序列的非线性、动态变化等特征,基于RBF神经网络对时间序列预测方法进行改进,并以安徽省池州市1959 ～2009年来的月降水量为时间序列数据样本,用MATLAB软件编程,采用基于随机选取中心的RBF神经网络预测方法,对池州市的月降水量进行预测,并选择不同的扩展速度参数,用均方误差进行检验.通过与BP网络模型的预测结果比较分析,表明RBF模型的预测效果较好.建立的基于随机选取中心的RBF神经网络模型,不需要计算原始时间序列数据的复杂函数关系,具有操作简单、学习速度快、短期预测精度高等优点,用于时间序列预测方面能够获得十分满意的结果,具有很高的应用价值.%The time series analysis which used to forecast time series is an effective method and has been used widely. For the non-linear and dynamic characters, we improved time series forecast method based on RBF neural network with month precipitation of 1959-2009 in Chizhou, Anhui as data sample of time series. We used MATLAB software to program and forecast month precipitation of Chizhou based on RBF neural network forecast method of random selection center. At last, we chose different speed and test it with RMSE (root mean square error) . Compared with BPNN(backpropagation neural network), predictive validity of RBF model based on random selection center is preferable and does not need to calculate complexed functional relationship of the original time series data, with advantage of simple operation, study fast and high short-term forecast accuracy.
郭兰平; 俞建宁; 张建刚; 漆玉娟; 张旭东
2011-01-01
提出一种基于遗传算法和RBF神经网络相结合的时间序列预测模型,克服了单个神经网络在非线性时间序列预测中容易陷入局部极小值及网络训练速度缓慢的问题.以居民消费价格指数数据进行训练和测试,与传统的BP神经网络预测模型相比较,该模型的预测精度是令人满意的,数值模拟证明了该方法的有效性和可行性.%A time series forecasting model based on genetic algorithm and RBF neural network is proposed.The problem that single neural network in nonlinear time series forecasting easily gets into the local minimum and neural network has a very slow study rate is overcome. The model is then used to forecast the inhabitant consumer price index (CPI). Compared with the traditional BP neural network forecast model, this model forecast precision is satisfying. Numerical simulation illustrates the feasibility of the technique.
利用RBF神经网络实现高斯型函数积分%Implementation for Gauss- Type Function Integral Using RBF Neural Networks
杨军; 马晓岩; 万山虎; 江晶
2003-01-01
导出了在一定精度下高斯型函数积分近似表达式,利用径向基函数(RBF)网络具有良好的逼近任意非线性映射的特点,提出了一种改进的RBF网络方法以实现对高斯型函数积分.实验结果表明所提出方法具有较高的逼近计算精度.
雷金莉; 窦满峰
2014-01-01
Because of the environmental parameters transformation, the parameters perturbation and load torque disturbances of the brushless direct current motor ( BLDCM) in near space will appear, and the response speed and stability of control system will be bad. To solve this problem, we propose an adaptive fuzzy control algorithm based on RBF( radial basis function) neural network compensation. The adaptive fuzzy controller is deduced to ensure the BLDCM system has good dynamic performance, the RBF neural network is adopted to do online identification and compensate for the speed error when the parameters perturbation and load torque disturbance appear in order to a-chieve the purposes of fast response speed and good robustness. Comparing the simulation results of adaptive fuzzy control with those of RBF neural network compensation and adaptive fuzzy control, we show preliminarily that:(1) the adaptive fuzzy control Based on RBF neural network has a strong robustness against the uncertainties of the BLDCM;(2) its response time is shorten by adaptive fuzzy control over 10ms;(3) its peak electromagnetic torque is decreased about 20% during the response process.%近空间用无刷直流电机（ BLDCM）受环境参数影响出现不确定性参数摄动和负载扰动，系统的控制性能降低。为消除不确定性因素的影响，提出了一种基于RBF网络补偿的自适应模糊控制算法。该控制算法是在自适应模糊控制的基础上，引入RBF网络补偿控制器，对参数摄动和负载转矩突变引起的转速误差进行在线辨识和动态补偿，以达到快速鲁棒自适应控制目的。对比具有RBF网络补偿的自适应模糊控制和自适应模糊控制的模拟仿真实验结果表明：在转速变化、负载转矩突变和转动惯量改变条件下，有RBF网络补偿控制的响应时间缩短了10 ms以上，响应过程中，电磁转矩的瞬时峰值减少了20％左右，对近空间BLDCM系统的不确定性鲁棒性强。
基于PF-RBF神经网络的短期风电功率预测%Short-Term Wind Power Prediction Based on PF-RBF Neural Network
王永翔; 陈国初; 张鑫
2014-01-01
为了提高风电功率的预测精度，研究了一种基于粒子滤波(PF)与径向基函数(RBF)神经网络相结合的风电功率预测方法。使用PF算法对历史风速数据进行滤波处理，将处理后的风速数据结合风向、温度的历史数据，归一化后构成风电功率预测模型的新的输入数据；利用处理后的新的输入数据和输出数据，建立PF-RBF神经网络预测模型，预测风电场的输出功率。仿真结果表明，使用该预测模型进行风电功率预测，预测精度有一定的提高，连续120 h功率预测的平均绝对百分误差达到8.04%，均方根误差达到10.67%。%To improve accuracy of wind power prediction,this paper proposes a short-term wind power prediction method combining a particle filter (PF)and a radial basis function (RBF) neural network.Historical wind speed data are first processed with a particle filter.The processed wind speed data combined with the historical data of wind direction and temperature are used as in-put to the model.A PF-RBF neural network of wind power output prediction model is established using the new input data.Simulation results show that the proposed model is accurate in wind power prediction.The mean absolute percentage prediction error in a period of 120 hours has been reduced to 8.04%,and the root mean square error is 10.67%.
李建龙; 陈向东; 倪进权; 谢冰青
2014-01-01
RBF神经网络具有较强的拟合能力和稳定性，得到了广泛的应用。以FPGA芯片为核心器件，设计实现RBF神经网络。利用SOPC Builder设计硬件架构，通过添加指令，在NIOS环境下利用C语言进行设计，这样就解决了利用Verilog或VHDL设计消耗资源多和软件模拟耗时多的问题。最后以Altera公司的Cyclone IV系列芯片作为验证器件，结果表明该方法实现简单，可靠性强，消耗资源少。%RBF neural network with fitting ability and stability has been widely used. Based on the FPGA chip as a core de-vice,the RBF neural network is designed in this paper. The hardware architecture was designed by means of SOPC Builder,the added instructions and C language in NIOS environment. In this way,the problems existing in the design were solved,because they consume too many resources by using Verilog or VHDL to carry out the design and take much more time in software simula-tion. The Cyclone IV series chip of Altera Company was taken to perform the verification. The result shows that the method is simple,and has high reliability and less consumption of resources.
基于PSO优化RBF神经网络的反应釜故障诊断%Application of PSO —based RBF Neural Network in Fault Diagnosis of CSTR
陈波; 潘海鹏; 邓志辉
2012-01-01
A new PSO algorithm with dynamically changing inertia weight and study factors based on improved adaptive PSO was proposed, where the inertia weight of the particle was adjusted adap-tively based on fitness of the particle. The diversity of inertia weight made a compromise between the global convergence and local convergence speed, so it can alleviate the problem of premature convergence effectively. The algorithm was applied to train RBF neural network and a model of fault diagnosis for CSTR was established,compared with PSO algorithm,the proposed algorithm can improve the training efficiency of neural network effectively and obtain good diagnosis results.%针对单一径向基函数(RBF)神经网络在反应釜故障诊断中泛化能力不足的缺点,设计了基于粒子群(PSO)算法优化的RBF神经网络.利用PSO算法操作简单、容易实现等特点及其智能背景,对RBF神经网络的参数、连接权重进行优化,并用经PSO算法优化的RBF神经网络对反应釜故障进行仿真诊断.仿真诊断结果表明,PSO算法优化的RBF神经网络具有较好的分类效果,较RBF诊断模型精度高、收敛快,具有推广应用价值.
李楠; 赵均海; 王娟; 吴赛
2014-01-01
针对混杂纤维混凝土强度受多种因素影响，强度与各影响因素之间关系为复杂的非线性问题，通过人工神经网络的自适应、自学习和非线性映射，可以找到以影响因素为输入变量、以混杂纤维混凝土强度为输出变量之间的非线性关系，在文献试验实测值的基础上采用MATLAB神经网络工具箱建立了四个三层RBF和BP神经网络模型，采用所建立的RBF和BP神经网络对混杂纤维混凝土的抗拉强度和抗折强度分别进行预测，并将各自的预测值和实测值进行了对比分析。结果表明：RBF神经网络预测值与试验实测值吻合良好，较之BP神经网络有更高的强度预测能力，该方法可行且预测精度满足工程需要，为工程上研究混杂纤维混凝土强度提供了新方法。%The strength of hybrid fiber reinforced concrete is influenced by many factors,and the relationship between them are complex nonlinear problem,but the nonlinear relationship between input variables like some of the factors and output variables like the strength of hybrid fiber reinforced concrete can be obtained by self-adapting,self-studying and nonlinear mapping of artificial neural network.Based on experimental values,four RBF and BP neural network models were established in MATLAB neural network toolbox,compressive strength and flexural strength of hybrid fiber reinforced concrete were predicted respectively by using RBF and BP neural network model. The predicted values and measured values were analyzed in comparison.The results showed that the predicted values of RBF neural network was in good agreement with the experimental values,and compared with the BP neural network had a higher strength prediction ability,the method was feasible and the prediction accuracy can meet the needs of engineering,providing a new method for the research on strength of hybrid fiber reinforced concrete in engineering field.
Monitoring of Concrete Slab Dam Deformation Based on AFSA-RBF Neural Network%基于AFSA－RBF模型的混凝土平板坝变形监测
梁嘉琛; 赵鲲鹏; 杨景文
2016-01-01
针对混凝土平板坝水平位移监测序列呈非线性变化的特点，采用经验模态分解（ EMD）方法对混凝土平板坝水平位移监测序列进行分解，并采用计算最大信噪比的方法对信号进行去噪。面板坝的坝顶上下游方向水平位移主要受上下游水位和环境温度的影响，据此建立AFSA－RBF神经网络模型和RBF神经网络模型，对混凝土平板坝上下游方向水平位移进行预测，结果表明：AFSA－RBF模型能够很好地反映混凝土平板坝水平位移变化趋势和规律，预测结果有较高的精度，符合大坝安全监测的要求，可以在混凝土平板坝安全监测和评价中应用。%In view of the nonlinear and cyclical change characteristics of the horizontal displacement observation data of concrete slab dam, this paper used the method of empirical mode decomposition ( EMD) to decompose the horizontal displacement observation data of concrete slab dam and adopted the method of calculating the maximum SNR to denoise the signal. Concrete slab dam horizontal displacements of dam crest upstream and downstream direction mainly were affected by upstream and downstream water level and environment temperature. Based on this, it established AFSA⁃RBF and General RBF neural network model, and forecasted the horizontal displacement of concrete slab dam. The results show that AFSA⁃RBF model can reflect the tendency and rule of the concrete slab dam horizontal displacement change well. The predicted results have higher accuracy, which can meet the requirement of dam safety monitoring. The model can be applied in the safety monitoring and evaluation of concrete slab dam.
GPS/leveling quasi-geoid fitting based on RBF neural networks%基于RBF神经网络的GPS/水准高程异常拟合
束蝉方; 李斐; 李明峰
2011-01-01
To determine an orthometric height using GPS, it is necessary to know the geoid/ quasi-geoid undulation. Fitting of GPS/leveling scatting data is one of main methods to get the quasi-geoid unknown. This paper proposed a new method for the fitting of GPS/leveling data based on radial basis functions (RBF) neural networks. The new learning algorithm selected the centers among the vertices of the Vornoni diagram of the sample data points. The bandwidth parameters of RBF, which was supposed experientially to be linear related to the distance from the center to the nearest scattering data point, were chosen optimizedly using generalized cross validation (GCV). The numerical results tested in one zone indicate that the new method is efficient for the geoid/quasi-geoid undulation fitting.%通过对离散GPS/水准点观测数据进行拟合从而获得区域内任意一点的高程异常是工程实践中经常遇到的问题.本文将径向基函数(RBF)神经网络方法应用于GPS/水准高程异常拟合,提出了一种新型网络学习方法.该方法首先通过对GPS/水准数据点进行Delaunay三角剖分,以其对偶Voronoi图的节点来构造选择基函数中心,再通过广义交叉验证(GCV)来最优确定基函数的宽度参数,最后利用最小二乘来确定RBF的输出权值,从而优化网络学习效果.实验结果表明,该学习方法取得良好的网络性能,和其它常用拟合方法的比较结果也反映出RBF神经网络适合应用于GPS/水准高程异常拟合.
基于RBF神经网络的自适应均衡器研究%Study on New Adaptive Equalizers Based on RBF Neural Networks
王军锋; 褚晓勇; 宋国乡
2002-01-01
在研究基于径向基函数(RBF)神经网络的均衡器结构以及传统自适应均衡算法的基础上,提出了两种新的基于RBF神经网络的自适应均衡器,并给出了相应的自适应均衡算法.新的均衡器是将判决反馈引入到RBF神经网络中以及将Adaline网络与RBF网络有机的结合而分别构成的,仿真结果表明这两种新算法比基于RBF神经网络的自适应均衡算法都具有更好的收敛性能.
基于RB F神经网络的集成增量学习算法%RESEARCH ON RBF NEURAL NETWORK-BASED ENSEMBLE INCREMENTAL LEARNING ALGORITHM
彭玉青; 赵翠翠; 高晴晴
2016-01-01
针对增量学习的遗忘性问题和集成增量学习的网络增长过快问题，提出基于径向基神经网络（RBF）的集成增量学习方法。为了避免网络的遗忘性，每次学习新类别知识时都训练一个RBF神经网络，把新训练的RBF神经网络加入到集成系统中，从而组建成一个大的神经网络系统。分别采用最近中心法、最大概率法、最近中心与最大概率相结合的方法进行确定获胜子网络，最终结果由获胜子网络进行输出。在最大概率法中引入自组织映（SOM）的原型向量来解决类中心相近问题。为了验证网络的增量学习，用UCI机器学习库中Statlog（Landsat Satellite）数据集做实验，结果显示该网络在学习新类别知识后，既获得了新类别的知识也没有遗忘已学知识。%Aiming at the forgetfulness problem of incremental learning and the excessive network growth problem of the integrated incremental learning,this paper proposes an integrated incremental learning method which is based on the radial basis function (RBF)neural network.In order to avoid the forgetfulness of the network,for each knowledge learning of new category we all trained an RBF neural network,and added the newly trained RBF neural network to the integrated system so as to form a large system of neural networks.To determine the winning sub-network,we adopted the nearest centre method,the maximum probability method and the combination of these two methods,and the final result was outputted by the winning sub-network.Moreover,we introduced the prototype vectors of self-organising map to maximum probability method for solving the problem of class centre similarity.For verifying the proposed network incremental learning,we made the experiments using the Statlog (Landsat Satellite)dataset in UCI machine learning library.Experimental results showed that after learning the knowledge of new category,this network could accept the new without
RBF neural network prediction algorithm for zero speed parking of elevator%电梯零速停靠的RBF神经网络预测算法
丁宝; 唐海燕; 丁艳虹; 齐维贵
2009-01-01
针对电梯运行过程中存在爬行距离的问题,提出了基于RBF(Radial Basis Function)神经网络的爬行距离预测模型.将预测的爬行距离增加到电梯速度曲线的匀速段,实现减小或消除爬行距离的目的,从而实现电梯的零速停靠.从电梯运行现场采集大量的原始数据,建立RBF神经网络预测模型,与BP(BackPropagation)预测方法进行仿真比较,结果表明RBF神经网络具有更好的预测效果.给出了应用零速停靠RBF预测算法前后电梯运行的速度曲线,爬行距离减小或消除,电梯的运行时间变短,实现了节能.
王云静; 李燕; 曲正伟; 刘圣楠
2016-01-01
It is of great significance to accurately identify the type of disturbance signal to analyze and control the pow-er quality problem.In this paper, a new method of power quality disturbance identification based on matching pursuit optimized by particle swarm optimization ( PSO-MP) and RBF neural network is proposed.Firstly, in order to let the residue signal to better reflect the different disturbance signal difference, the fundamental atomic library is constructed to extract the fundamental frequency signals;Then, the MP algorithm is optimized by PSO to reduce the calculation a-mount, which combines with discrete Gabor atom libraries to accurately extract atomic parameters of residual disturb-ance signal by sparse decomposition, Finally, the RBF neural network is used to identify disturbance signals by fea-tures, which is the mean and standard deviation of the atomic parameter and projection of residual signal on the atom. Simulation examples show that the proposed method can effectively identify several common power quality disturbances with a small amount of computation and good anti-noise performance.%准确识别扰动信号类型对分析和治理电能质量问题具有重要意义。文中提出一种基于粒子群优化匹配追踪算法（ PSO－MP）和RBF神经网络的电能质量扰动识别方法。首先，构建工频原子库将工频信号提取出来，得到的残余信号能更好地体现扰动信号差异性；再利用PSO优化匹配追踪算法以减小计算量，并结合离散Gabor原子库对残余扰动信号进行稀疏分解，准确提取其原子参数；最后将原子参数以及残余信号在原子上的投影的均值和标准偏差作为特征量，利用RBF神经网络对扰动信号进行识别。仿真算例表明，该方法能够有效地识别几种常见的电能质量扰动，且具有抗噪性能强、计算量小等优点。
王冬生; 李世华; 周杏鹏
2011-01-01
针对自来水生产过程的原水水质评价问题,提出了一种基于PSO-RBF神经网络模型的原水水质评价方法.首先,根据水厂生产经验和历史数据分析,制定面向自来水生产过程的原水水质评价标准.然后,采用粒子群优化(PSO)算法训练的RBF神经网络模型,对苏州市相城水厂的进厂原水水质实施在线评价.最后,将进厂原水水质在线评价结果作为前馈量,增加相城水厂药剂(矾和臭氧)投加过程的前馈控制环节,使得药剂投加量能够根据原水水质的变化及时做出调整.实际应用效果表明,与改进前的反馈控制过程相比,过程出水水质更加平稳,提高了自来水生产过程应对原水水质变化的能力.%In consideration of the assessment problem of raw water quality oriented to drinking water treatment process, an assessment method of raw rater quality based on the PSO-RBF neural network model is proposed. First, on the basis of productive experiences and analysis of historical data in the waterworks, an assessment standard oriented to the process of drinking water treatment is established. Then, the radial basis function (RBF) neural network model trained by the particle swarm optimization ( PSO) algorithm is used for the on-line assessment of raw water quality in the Xiangcheng Waterworks of Suzhou city. Finally, feed-forward control elements are added to the pharmaceutical (alum and ozone) dosing control processes of Xiangcheng Waterworks, using the online assessment result as the feed-forward compensation. The results of the practical operation show that the produced water quality becomes more stable, and the adaptation ability of drinking water treatment to the variation of raw water quality is improved.
刘述文; 潘宏侠; 刘涛涛
2015-01-01
局域均值分解(Local Mean Decomposition,LMD)是近年来出现的一种新的时频分析方法,在机械设备故障诊断领域中的应用日益广泛.针对齿轮箱振动故障信号的非平稳性和非线性,提出了一种基于局域均值分解和径向基函数神经网络(Radial BasisFunction Neural Network,RBF)相结合的齿轮箱故障诊断方法.该方法利用小波包对原始信号进行消噪;利用LMD对处理后信号进行分解,得到一系列PF分量(Product Function,PF);选取包含主要故障信息的PF分量并从中提取偏度系数等特征参数对RBF神经网络进行训练,并对齿轮箱故障进行识别和分类.通过实例验证了该方法的有效性.
胡浩; 何子辉
2012-01-01
Based on the analysis of induction motor loss model, and aimed at the complicated nonlinear relation between the torque and rotational speed with optimal excitation, this paper puts forward a RBF neural network and establishes the model of induction motor efficiency optimization. It ues the MATLAB to simulate the system. The experimental results show the system＇s efficiency is improved and the loss of induction motor is reduced significantly.%在对磁链定向下感应电机损耗模型进行了详细的分析基础上，针对电机转矩和转速与最优励磁电流存在严重的非线性关系，文中提出一种径向基神经网络控制方法并建立电机效率优化控制模型，对电机进行最大效率优化控制。仿真结果表明该系统运行效率明显提高，降低了电机损耗。
基于RBF神经网络的军事物流设施规模预测%Prediction of Military Logistics Facilities Scale Based on RBF Neural Network
刘洪娟; 甘明; 肖育; 姜玉宏
2013-01-01
确定合理的军事物流设施规模对于成功实施军事后勤保障十分重要。提出了基于RBF神经网络的军事物流设施规模预测模型的建模方法，该方法旨在确定军事物流设施规模与其影响因素之间的非线性关系；采用算例说明了基于RBF神经网络的军事物流设施规模预测的具体做法，对军事物流设施规模的确定具有指导意义。%It is important for successfully implementing the military logistics support to determine the reasonable facilities scale of military logistics. This paper puts forward the modeling method for prediction of military logistics facilities scale based on RBF neural network. The purpose of this method is for determining the nonlinear relationship between military logistics facilities scale and its related influence factors. Detailed operations of ascertaining facilities scale of military logistics have been illustrated by usage of an example. This method is a guidance for determining the military logistics facilities scale.
王蕾
2014-01-01
Because of the construction of logistics park in our country is in operation of the site planning and management need to explore in practice ,therefore,this article in view of the logistics park location selection problem ,to build the site selection evaluation system model based on RBF neural network to applied research ,will be for our country's logistics park planning and development provides a new theoretical basis and the overall framework of reference .%由于我国物流园区的建设在选址规划和管理运作方面还需在实际中探索，因此，文中针对物流园区选址问题，构建基于RBF神经网络的选址评价体系模型进行应用研究，将为我国的物流园区规划发展提供了新的理论基础和整体框架参考。
郭小燕; 张明
2013-01-01
针对RBF神经网络确定核函数中心时没有考虑输入样本分类指标权重的问题,提出了一种动态加权聚类算法.在算法中利用样本之间的加权距离代替了欧氏距离作为选定核函数中心的量度.在此基础上,建立了信用评价模型,利用已知类别的样本对模型进行训练,再利用训练好的模型对未知类别的样本进行预测,实验结果验证了模型的有效性.%A dynamic weighting cluster algorithm is proposed in this article in view of the problem of input sample's classification weight being not considered by formerly RBF neural network. In this algorithm, the weighting distance replaces the Euclidean distance to act the role of measurement to the cluster. Based on this, the credit evaluation model is established, which is trained by known category sample. Then the trained model is used to forecast the unknown category sample, the experimental result confirms the model' s validity.
范立强; 吕国芳
2016-01-01
针对目前混凝土强度预测中存在的不确定性，难以自适应性的确定神经网络隐含层，建立了基于高维云的RBF神经网络的混凝土预测模型。运用MATLAB 8.10进行仿真实验。实验结果表明该模型综合考虑了影响混凝土强度的各种因素，能够实现预测结果的随机性和模糊性，具有更高的预测精度，更快的训练速度，可以广泛应用于生产现场实地的混凝土强度预测和质量检验。%According to the current situation that forecasting concrete strength is uncertainty, it is difficult to make sure the adaptability for the hidden layer of neural network. It has built the prediction model of concrete strength based on high dimensional cloud RBF neural network and has carried out the simulated experiment by MATLAB 8.10. The experimental results show that it considers various factors affecting the concrete strength, can realize randomness and fuzziness of the results, has higher precision of prediction and faster training speed. It can be widely used in the production of in-situ concrete prediction and quality inspection.
蔡坤; 刘兴高
2012-01-01
内部热耦合精馏(ITCDIC)是迄今为止所提出的四大精馏节能技术中节能效果最高,但唯一没有商业化的节能技术,比常规精馏要节能40％以上,没有商业化的主要种类基于减聚类、K-means原因之一在于该过程具有较强的非线性、复杂动态特性以及耦合性,给控制方案的设计带来了诸多困难.由于径向基(RBF)神经网络具有快速学习并能逼近任意非线性函数的优点,本文提出了一种基于RBF神经网络内模控制的混合优化算法,是一种粒子群优化的混合优化算法,以苯-甲苯物系作为研究实例,并与国际公开报道的结果进行了详细比较,研究结果表明基于混合优化算法的RBF神经网络内模控制相比于传统的PID、常规RBF算法和国际公开报道有着更好的控制效果.%Internal thermally coupled distillation is the most promising of four major distillation energy-saving technologies, which can save more than 40 % energy compared with traditional distillation process, but it has not been widely used. The bottleneck that prevents the process from being commercialized is the operational difficulties due to the nonlinearity, complex dynamics and interactive nature of the process. The radial basis(RBF) neural network has fast learning and can identify any nonlinear function. We presented a hybrid optimization algorithm for RBF neural network, which is based on particle swarm optimization, gradient descent method, K-means clustering and subtractive clustering algorithm. Take the benzene-toluene system as a research case and compared with the international public reporting results. The hybrid optimization algorithm for RBF neural network is more reliable than PID algorithm, conventional RBF and the international public reporting results.
曹留帅; 朱军
2014-01-01
为实现CFD技术在潜艇操纵性优化设计中的应用，文章结合粘性求解器和RBF神经网络预报了潜艇的水动力。通过引入首部和尾部肥瘦指数，确定了潜艇主艇体线型表达的五参数模型。采用均匀试验设计方法，给出了30条潜艇模型的五参数表达。针对每个模型，分别计算了9个漂角下的纵向力、横向力和摇首力矩，得到共计270组数据。为提高计算效率和精度，利用ANSYS ICEM CFD脚本文件和ANSYS FLUENT journal函数实现了从模型建立、网格划分到数值模拟的自动化操作。在多漂角计算过程中，采用“漂角扫掠”方法加快收敛速度。利用上述计算结果训练RBF神经网络，得到了潜艇水动力预报的神经网络模型。以SUBOFF为例，采用该网络预报了其水动力，并与文中数值方法计算结果、试验结果和文献值进行对比，符合较好，说明该方法可应用于工程实践。%To explore the usage of CFD techniques into the optimization design process of submarine maneuverability, CFD-based calculations and RBF neural network were combined to predict the sub-marine hydrodynamics. The fullness of the nose and stern index was introduced to the geometric de-scription of submarine axisymmetric hull, thus creating a five-parameter model for the hull geometry expression. A series of 30 similar hull bodies was adopted by the uniform design approach. For each of the models, 9 different drift angle cases were calculated, and 270 groups of data were achieved con-sisting of the longitudinal force, the lateral force and the yaw moment. To improve the efficiency and accuracy of the computation, automatic mesh and computation using the ANSYS ICEM CFD scripts and ANSYS FLUENT journal functions were used, as well as the drift sweep procedure. A RBF neu-ral network was adopted and trained by the computation results to predict the hydrodynamics of oth-er submarines. For the SUBOFF case, the
朱懿峰; 宋执环
2011-01-01
An algorithm of RBF neural network soft measurement based on SoC is proposed. The entire training and prediction algorithms are implemented successfully on the hardware platform of dual-core SoC processor. In order to apply algorithm effectively on the platform whose compute speed and memory are limited,specific solutions about the structure of the network, weight update pattern and step and data preprocessing mode is proposed. The data set test results prove that the algorithm transplantation method satisfies the requirements of industrial application,which has a variety of advantages such as portable,low-cost and extensible.%提出了一种面向片上系统(SoC)的RBF神经网络的软测量算法,在OMAP-L137双核处理器SoC 硬件平台上成功实现了整个训练与预测算法.针对SoC计算速度和存储空间等资源有限,对网络结构、权值更新模式和步长以及数据预处理方式等参数提出了具体的解决方案.经过相关数据集的测试结果表明:提出的算法移植方法完全满足工业应用的要求,且具有便携性、低成本、可扩展等多种优点.
何耀耀; 许启发; 杨善林; 余本功
2013-01-01
According to the problem of short-term load forecasting in the power system, this paper proposed a probability density forecasting method using radical basis function (RBF) neural network quantile regression based on the existed researches on combination forecasting and probability interval prediction. The probability density function of load at any period in a day was evaluated. The proposed method can obtain more useful information than point prediction and interval prediction, and can implement the whole probability distribution forecasting for future load. The practical data of a city in China show that the proposed probability density forecasting method can gain more accurate result of point prediction and obtain the forecasting results of integrated probability density function of short-term load.%针对电力系统短期负荷预测问题,在现有的组合预测和概率性区间预测的基础上,提出了基于RBF神经网络分位数回归的概率密度预测方法,得出未来一天中任意时期负荷的概率密度函数,可以得到比点预测和区间预测更多的有用信息,实现了对未来负荷完整概率分布的预测.中国某市实际数据的预测结果表明,提出的概率密度预测方法不仅能得出较为精确的点预测结果,而且能够获得短期负荷完整的概率密度函数预测结果.
李君波; 刘旺开
2014-01-01
针对高压热动力试验台测控系统需要控制的参数多，控制任务要求复杂，控制精度要求高，且各参数间存在耦合的情况，提出了基于 BP＋RBF神经网络 PID的智能控制的方法；应用智能控制的方法解决传统的 PID控制无法解决的问题；实际应用表明基于 BP神经网络整定的 PID控制器具有较好的自学习和自适应性，能保证控制精度等要求，控制效果比较令人满意。%As there are many parameters to be controlled in the Highpressure Thermodynamics Test Unit,the control task is demanding, and the requirement of the control precision is high.And there is a complicated coupling between parameters.In view of these difficulties,a method of intelligent control based on BP + RBF neural network and PID is Proposed.The intelligent control method is used to solve the problem that can not be solved by the traditional PID control method.In practical application the system has met the specifications require-ments perfectly,and achieved excellent controlling effect,though the mathematical model of the control object is complicated.
基于径向基函数网络的宣城市空气质量预测%Based on RBF Neural Network Prediction of Air Quality in the Xuancheng
吴有训; 彭慕平; 刘勇
2011-01-01
A method of prediction of air quality is proposed based on RBF artificial neural network (ANN), making a low-dimension ANN learing matrix through principal component analysis, it could distill the main information of many factorials and remarkably decrease the dimension. According to the characteristics of the prediction of air quality, this paper selects the data in Xuancheng from 2003 to 2005 that greatly influence the air quality. The experimental result shows that the performance of prediction of air quality is favorable, the learning speed is fast and the rate of accurate is high, so it have a practical value. It provides a precise and generalization and efficient way for the prediction of air quality.%提出了一种应用人工神经网络进行空气质量预测的方法,即采用径向基函数神经网络进行短期的空气质量预测；并采用了主成分分析方法降低神经网络学习矩阵维数,浓缩预测信息,降维去噪.选取宣城市气象局2003年到2005年地面气象观测资料作为预测因子,宣城市环境保护监测中心提供的PM10、So2浓度值作为预测对象,进行训练学习和预测验证.研究结果表明:将该方法应用于空气质量预测,效果良好,具有较强的实用性和推广能力.
王立峰; 肖子旺; 王子强
2011-01-01
By taking finite element analysis results as sample data, an invisible mapping relationship between basic variables and structural response is established and a risk quantitative analysis method of high-risk location identification during V-shaped pier construction, by using RBF (Radial Basis Function) artificial neuron network is presented. Through a numerical simulation based on the principle of Monte Carlo, structural failure probability of each checking section of Vshaped pier during construction is calculated. It is proved by engineering project and concluded that, the method of construction risk analyzing based on radial basis function neural network can be used as an efficient reliability analysis method. It is reasonable and applicable, which can provide a theoretical basis for risk-decision during V-shaped pier construction.%运用RBF神经网络(Radial Basis Function Neural Network)理论,分析了大夹角V撑施工期间最大风险因素可能发生的部位,并对V撑的结构失效风险性进行了定量分析.将有限元分析结果作为神经网络训练样本数据,利用径向基神经网络建立了基本变量和结构响应之间的隐性映射关系,根据蒙特卡洛原理进行模拟计算,最终得出V撑施工过程中各个危险截面出现结构失效的概率预估值.通过工程实例验证表明,基于径向基神经网络所建立的施工过程风险分析方法计算效率高,具有可行性和有效性,同时为V撑施工风险决策提供了理论依据.
Load Identification of Electric Locomotive Based on RBF Neural Network%基于RBF神经网络的电力机车负荷辨识
薛强; 蔡承才; 米海亭
2016-01-01
针对目前我国铁路机车型号较多，牵引网故障后机车类型辨识过程环节较多，实时性较差问题，本文研究了不同机车运行时电流有效值特点和谐波特性，提出了利用人工神经网络的方法来在线实现电力机车负荷辨识的方法，实验仿真结果表明，该方法可以准确快速的识别出运行于供电臂上的电力机车负荷类型，实时性好。%Aimed at the current problems of the railway locomotive in China, such as the models are too many, the links of locomotive type identification process after the failure of traction network are too much and the real-time problems are poor, this paper studies the characteristics of current effective value and harmonic of the operation of different locomotives. The method of using artificial neural network to realize load identification of electric locomotive is presented. Experimental results show that the proposed method can accurately and quickly identify the load type of electric locomotive running on the power supply arm, and the real-time performance is good.
Optimal design of structures for earthquake loads by a hybrid RBF-BPSO method
Eysa Salajegheh; Saeed Gholizadeh; Mohsen Khatibina
2008-01-01
The optimal seismic design of structures requires that time history analyses (THA) be carried out repeatedly. This makes the optimal design process inefficient, in particular, if an evolutionary algorithm is used. To reduce the overall time required for structural optimization, two artificial intelligence strategies are employed. In the first strategy, radial basis function (RBF) neural networks are used to predict the time history responses of structures in the optimization flow. In the second strategy, a binary particle swarm optimization (BPSO) is used to find the optimum design. Combining the RBF and BPSO, a hybrid RBF-BPSO optimization method is proposed in this paper, which achieves fast optimization with high computational performance. Two examples are presented and compared to determine the optimal weight of structures under earthquake loadings using both exact and approximate analyses. The numerical results demonstrate the computational advantages and effectiveness of the proposed hybrid RBF-BPSO optimization method for the seismic design of structures.
关海鸥; 杜松怀; 李春兰; 苏娟; 梁英; 武子超; 邵利敏
2013-01-01
针对农村低压电网剩余电流保护与动作技术中，如何检测总泄漏电流中人体触电支路电流的难题，该文利用严格线性相位与任意幅度特性的FIR(finite impulse response)数字滤波技术和具有自适应性与最佳逼近特性的RBF(radial basis function)神经网络有机结合，提出一种基于FIR数字滤波的RBF神经网络作为触电电流信号的检测方法.首先，采用FIR数字滤波器选定合适的窗函数和滤波阶数，对触电试验获得的总泄漏电流及触电电流进行滤波预处理；然后，将预处理后的信号波形作为样本集，选定适合的RBF函数，建立从总泄漏电流中提取触电电流波形的3层RBF神经网络模型.仿真试验结果表明：该方法速度快且稳定，检测值与实际值的平均相对误差为3.76%，具有良好的适应性和实用性，对于研制新一代剩余电流保护动作装置具有重要意义.%Residual current protection device (RCD) has been widely used in low-voltage, rural power grids because it plays a very important role in avoiding physical shock, equipment damage, and electrical fires, etc, caused by leakage. At present, a setting value of leakage current can often be used as a key action for RCD. However, the electric shock current signal of the human body cannot be detected, and when unexpected current values close to or more than the setting value emerge, this will lead to the malfunction of RCD. In order to overcome the shortcomings above, we present a new recognition method for electric shock signal using digital filter technology and radial basis neural network. The method has three main stages. First, total leakage current and electric short current has been pre-processed using the finite impulse response digital filtering, which was designed by choosing suitable window functions and filter order. Second, the pre-processed signals are trained to create a three-level radial basis neural network
Deterministic System Identification Using RBF Networks
Joilson Batista de Almeida Rego
2014-01-01
Full Text Available This paper presents an artificial intelligence application using a nonconventional mathematical tool: the radial basis function (RBF networks, aiming to identify the current plant of an induction motor or other nonlinear systems. Here, the objective is to present the RBF response to different nonlinear systems and analyze the obtained results. A RBF network is trained and simulated in order to obtain the dynamical solution with basin of attraction and equilibrium point for known and unknown system and establish a relationship between these dynamical systems and the RBF response. On the basis of several examples, the results indicating the effectiveness of this approach are demonstrated.
杨剑锋; 张翠; 张峰
2015-01-01
针对机械臂运动轨迹控制中存在的跟踪精度不高的问题，采用了一种基于EC-RBF神经网络的模型参考自适应控制方案对机械臂进行模型辨识与轨迹跟踪控制。该方案采用了两个RBF神经网络，运用EC-RBF学习算法，采用离线与在线相结合的方法来训练神经网络，一个用来实现对机械臂进行模型辨识，一个用来实现对机械臂轨迹跟踪控制。对二自由度机械臂进行仿真，结果表明，使用该控制方案对机械臂进行轨迹跟踪控制具有较高的控制精度，且因采用EC-RBF学习算法使网络具有更快的训练速度，从而使得控制过程较迅速。%According to the problem that the tracking accuracy is not high enough in trajectory tracking control of robot manipulators, a model reference adaptive control scheme based on EC-RBF neural networks is adopted to achieve robot manipulator model identification and trajectory tracking control. This control scheme contains two RBF neural networks which are trained offline and online, using EC-RBF learning algorithm. The one is used to identify the robot manipulator’s model, and the other one is used to achieve its trajectory tracking control. Simulation result of 2-degree-of-freedom robot manipulator demonstrates that using this method for robot manipulator trajectory tracking control has high control accuracy, and the networks which gain high training speed because of the EC-RBF learning algorithm make the control process faster.
黄榕波; 郭穗勋
2010-01-01
提出变量可分离函数的径向基函数网络拟合模型(Fitting Model based Radial Basis Function network to Variable Separable Function,VSRBF)及其学习算法并分析VSRBF的VC维.VSRBF是一个由多个子径向基函数网络组成的分工协作系统,由于把高维模型分解为低维模型,与传统径向基函数网络(Based Radial Basis Function Network,RBF)相比, VSRBF 不仅明显地降低了系统复杂性而且网络的收敛速度更快. 证明了VSRBF的VC维低于传统RBF的VC维,实验表明VSRBF在处理高维模型的行为明显优于RBF.
Performance prediction for Grid workflow activities based on features-ranked RBF network
Wang Jie; Duan Rubing; Farrukh Nadeem
2009-01-01
Accurate performance prediction of Grid workflow activities can help Grid schedulers map activities to appropriate Grid sites. This paper describes an approach based on features-ranked RBF neural network to predict the performance of Grid workflow activities. Experimental results for two kinds of real world Grid workflow activities are presented to show effectiveness of our approach.
基于RBF神经网络的水下机器人传感器状态监测方法研究%Research on condition monitor for AUV sensors based on RBF neural network
张铭钧; 孙瑞琛; 王玉甲
2005-01-01
为了实现水下机器人多传感器状态监测,根据其工作环境及所配置传感器的数量,提出了基于径向基函数(RBF)神经网络的传感器状态监测方法,建立了二级神经网络监测模型,解决了多传感器故障诊断和信号恢复的问题.基于某型水下机器人海中试验数据进行计算机仿真试验的结果,验证了该方法的有效性和可行性.
陈建松; 闵雁; 伍乃骐
2008-01-01
本文在CAE仿真的基础上,采用田口试验设计(Taguchi)和径向基神经网络(RBF)技术对引起翘曲的塑参数进行了优化.结果表明:Tagucbi技术可以在较少的试验次数的情况下,确定各因素对翘曲的影响程度,获取各因素最佳的水平组合;运用RBF建立翘曲产生的神经网络模型,可以预测各因素在不同水平组合下的翘曲变形程度,达到离线预测的目的.
姬晓飞; 申东日; 陈义俊
2003-01-01
针对径向基函数(RBF)神经网络用于非线性系统辨识时存在的问题,对径向基函数网络的拓扑结构作了改进,并给出了改进的径向基函数(MRBF)神经网络的中心选取方法和权值在线调整算法,最后用改进的径向基函数网络对一个典型工业对象(CSTR)进行了应用研究,结果表明方法有效.
Forecast of US dollar/RMB exchange rate based on RBF neural network%基于RBF神经网络美元兑人民币汇率的预测
肖强; 钱晓东
2009-01-01
提出一种基于RBF神经网络的美元兑人民币汇率预测模型,该模型通过对近两年美元兑人民币汇率的历史数据分析,采用了改进的K-均值聚类算法,动态地确定RBF神经网络中心,并采用最小二乘法进行RBF神经网络的权值调整,通过美元兑人民币汇率的预测,结果表明该模型有较好的预测和泛化能力,可以取得好的预测结果.
黎云汉; 朱善安
2007-01-01
本文提出了一种基于递归正交最小二乘的径向基函数(RBF)网络人脸识别算法,该算法首先使用主成分分析(PCA)提取输入图像特征,将提取的特征作为RBF网络的输入进行识别,在求取网络权值时采用递归正交最小二乘(ROLS)算法.实验表明,该算法能明显地缩短训练时间同时具有较高的识别率.
RBF递归神经网络在供热解耦控制中的应用%Application of RBF recursion neural network to heat supply decoupling control
陈烈; 朱学莉; 齐维贵; 方修睦
2010-01-01
针对供热过程耦合特性和节能控制的需要,提出了一种基于径向基函数(RBF)递归神经网络的供热解耦控制方法.通过典型信号响应与最小二乘结合的方法得到供热耦合系统模型,利用RBF递归神经网络进行解耦控制,消除了质调节、量调节通道间的非线性强耦合作用.仿真结果证明该方法具有良好的解耦控制特性,满足供热系统多回路控制的要求.
Prediction of the yield of biomass semi-coke based on RBF neural network%基于RBF神经网络生物质半焦产量的预测
胡爱娟; 刘杨; 袁清泉; 王桂荣; 石硕
2012-01-01
Biomass, as a renewable clean energy, has broad development prospects. Pyrolysis is the key step in thermochemical process of the biomass. This paper analyzes the factors which influence the semi-coke yield in the process of furfural residue and rice husk co-pyrolysis and sets up a RBF network model according to the three main factors to predict the yield of biomass semi-coke. The deviation of simulation results derive partly from the network and the learning samples and the selection of impact factors and more derive from experimental data. Through the error analysis, this model has better precision. The prediction results prove the feasibility of the application of RBF to thermo gravimetric pyrolysis of biomass.%生物质能作为一种可再生的清洁能源,开发利用前景广阔,热解反应是生物质热化学转化中的关键环节.本文分析了糠醛渣和稻壳共热解过程中影响半焦产量的各因素,根据三个主要因素,建立RBF神经网络模型,并应用此模型对半焦产量进行预测.其中,模拟结果的偏差一部分来源于网络和学习样本及影响因子的选取,更多的来源于实验数据.通过误差分析,本文建立的模型具有较好的精度,证明了RBF网络应用于热重分析仪中生物质热解领域的可行性.
张雷; 胡彦红; 陈巍巍; 刘秋鞍; 林建中; 张丽芳
2010-01-01
在径向基函数(Radial Basis Function,RBF)神经网络成熟的基础上,对旋转机械的转子系统进行故障诊断,针对梯度下降法容易产生梯度消失的问题,提出用扩展卡尔曼滤波器(Extended Kalman Filter,EKF)对权重进行调节训练,并将结果与反向传播(Back Propagation,BP)算法和梯度下降调节进行比较,用EKF训练的RBF神经网络不仅在性能上有优势,在精度和迭代速度上亦优于其他方法.相信在今后的实际应用中尤其在旋转机械故障诊断中可以更大地发挥其优势.
Performance Investigation of the RBF Localization Algorithm
Juraj Machaj
2013-01-01
Full Text Available In the present paper the impact of network properties on localization accuracy of Rank Based Fingerprinting algorithm will be investigated. Rank Based Fingerprinting (RBF will be described in detail together with Nearest Neighbour fingerprinting algorithms. RBF algorithm is a new algorithm and was designed as improvement of standard fingerprinting algorithms. Therefore exhaustive testing needs to be performed. This testing is mainly focused on optimal distribution of APs and its impact on positioning accuracy. Simulations were performed in Matlab environment in three different scenarios. In the first scenario different numbers of APs were implemented in the area to estimate the impact of APs number on the localization accuracy of the Rank Based Fingerprinting algorithm. The second scenario was introduced to evaluate the impact of APs placement in the localization area on the accuracy of the positioning using fingerprinting algorithms. The last scenario was proposed to investigate an impact of the number of heard APs and distribution of the RSS values on the accuracy of the RBF algorithm. Results achieved by the RBF algorithm in the first and second scenarios were compared to commonly used NN and WKNN algorithms.
Logarithmic Spiral-based Construction of RBF Classifiers
Mohamed Wajih Guerfala
2017-02-01
Full Text Available Clustering process is defined as grouping similar objects together into homogeneous groups or clusters. Objects that belong to one cluster should be very similar to each other, but objects in different clusters will be dissimilar. It aims to simplify the representation of the initial data. The automatic classification recovers all the methods allowing the automatic construction of such groups. This paper describes the design of radial basis function (RBF neural classifiers using a new algorithm for characterizing the hidden layer structure. This algorithm, called k-means Mahalanobis distance, groups the training data class by class in order to calculate the optimal number of clusters of the hidden layer, using two validity indexes. To initialize the initial clusters of k-means algorithm, the method of logarithmic spiral golden angle has been used. Two real data sets (Iris and Wine are considered to improve the efficiency of the proposed approach and the obtained results are compared with basic literature classifier
Upset Prediction in Friction Welding Using Radial Basis Function Neural Network
Wei Liu
2013-01-01
Full Text Available This paper addresses the upset prediction problem of friction welded joints. Based on finite element simulations of inertia friction welding (IFW, a radial basis function (RBF neural network was developed initially to predict the final upset for a number of welding parameters. The predicted joint upset by the RBF neural network was compared to validated finite element simulations, producing an error of less than 8.16% which is reasonable. Furthermore, the effects of initial rotational speed and axial pressure on the upset were investigated in relation to energy conversion with the RBF neural network. The developed RBF neural network was also applied to linear friction welding (LFW and continuous drive friction welding (CDFW. The correlation coefficients of RBF prediction for LFW and CDFW were 0.963 and 0.998, respectively, which further suggest that an RBF neural network is an effective method for upset prediction of friction welded joints.
李敏; 王家序; 肖科; 黄超; 徐超
2012-01-01
Combining with nonlinear,strong coupling dynamics model of a robot manipulator,this paper presented a digital robust sliding mode robot control algorithm,which compensated for the uncertainties of robot manipulator-LuGre dynamic friction with three fuzzy RBF neural network, and trained parameters of nonlinear dynamic friction on-line and adaptively. Then this paper analyzed the Lyapunov stability of the algorithm. The simulation of a two degrees of freedom robot manipulator proves that the algorithm is of high accuracy, high reliability, high quality, stable and strong robustness. Meanwhile, nonlinear kinetic phenomena, such as rhombus attractor, lie in the kinetic properties of the friction model of the robot manipulator.%结合非线性、强耦合的机器人动力学模型,提出了采用3个模糊RBF神经网络对机器人中的不确定项——LuGre动态摩擦进行分块补偿的机器人数字鲁棒滑模控制算法,在线自适应训练非线性动态摩擦项的参数,并分析了该算法的Lyapunov稳定性.通过在二自由度机器人上的仿真,证明了该算法具有高精度、高可靠性、高品质、稳定、强鲁棒性等特点.同时发现了该机器人的摩擦模型中存在类菱形吸引子等非线性动力学现象.
陈红构; 赵晔
2011-01-01
A Multi-objective decision-making model is put forward to solve the issue of the supply chain cooperation partner selection in logistics enterprises. The paper excogitates a system of evaluation which is coincident with the characteristics of the logistics supply chain based on the essential feature and performance of logistics enterprises. Three aspects of logistics enterprise supply chain partners' partnership, partner characteristics and flexible cooperation are analyzed. The partners are classified as the core partners, important partners, potential partners, foundation partners. It is effectiveness and availability of this arithmetic that structuring the cooperation partner selection model in logistics enterprises based on the RBF neural networks.%提出了物流供应链企业合作伙伴选择问题的多目标决策模型,结合物流企业的行业特点,设计了符合物流企业供应链特点的合作伙伴选择指标体系,从伙伴关系、伙伴特性和合作柔性三个方面对物流企业供应链合作伙伴进行分析,将伙伴分类为核心伙伴、重要伙伴、潜力伙伴、基础伙伴,通过构造基于径向基函数神经网络的选择模型对合作伙伴进行归类选择.通过实证研究,结果表明该方法有效、实用.
Meshless RBF based pseudospectral solution of acoustic wave equation
Mishra, Pankaj K
2015-01-01
Chebyshev pseudospectral (PS) methods are reported to provide highly accurate solution using polynomial approximation. Use of polynomial basis functions in PS algorithms limits the formulation to univariate systems constraining it to tensor product grids for multi-dimensions. Recent studies have shown that replacing the polynomial by radial basis functions in pseudospectral method (RBF-PS) has the advantage of using irregular grids for multivariate systems. A RBF-PS algorithm has been presented here for the numerical solution of inhomogeneous Helmholtz's equation using Gaussian RBF for derivative approximation. Efficacy of RBF approximated derivatives has been checked through error analysis comparison with PS method. Comparative study of PS, RBF-PS and finite difference approach for the solution of a linear boundary value problem has been performed. Finally, a typical frequency domain acoustic wave propagation problem has been solved using Dirichlet boundary condition and a point source. The algorithm present...
Liu, Lin; Shen, Songhua; Liu, Qiang
2006-11-01
A novel method to detect power quality disturbance of distribution power system combing complex wavelet transform (WT) with radial basis function (RBF) neural network is presented. The paper tries to explain to design complex supported orthogonal wavelets by Morlet compactly supported orthogonal real wavelets, and then explore the extraction of disturbance signal to obtain the feature information, and finally propose several novel wavelet combined information (CI) to analyze the disturbance signal, superior to real wavelet analysis result. The feature obtained from WT coefficients are inputted into RBF network for power quality disturbance pattern recognition. The power quality disturbance recognition model is established and the synthesized method of recursive orthogonal least squares algorithm (ROLSA) with improved Givens transform is used to fulfill the network structure and parameter identification. By means of choosing enough samples to train the recognition model, the type of disturbance can be obtained when signal representing fault is inputted to the trained network. The results of simulation analysis show that the complex WT combined with RBF network are more sensitive to signal singularity, and found to be significant improvement over current methods in real-time detection and better noise proof ability.
The overlapped radial basis function-finite difference (RBF-FD) method: A generalization of RBF-FD
Shankar, Varun
2017-08-01
We present a generalization of the RBF-FD method that computes RBF-FD weights in finite-sized neighborhoods around the centers of RBF-FD stencils by introducing an overlap parameter δ ∈ (0 , 1 ] such that δ = 1 recovers the standard RBF-FD method and δ = 0 results in a full decoupling of stencils. We provide experimental evidence to support this generalization, and develop an automatic stabilization procedure based on local Lebesgue functions for the stable selection of stencil weights over a wide range of δ values. We provide an a priori estimate for the speedup of our method over RBF-FD that serves as a good predictor for the true speedup. We apply our method to parabolic partial differential equations with time-dependent inhomogeneous boundary conditions - Neumann in 2D, and Dirichlet in 3D. Our results show that our method can achieve as high as a 60× speedup in 3D over existing RBF-FD methods in the task of forming differentiation matrices.
Ou, Yu-Yen; Gromiha, M Michael; Chen, Shu-An; Suwa, Makiko
2008-06-01
Discriminating outer membrane proteins (OMPs) from other folding types of globular and membrane proteins is an important task both for identifying OMPs from genomic sequences and for the successful prediction of their secondary and tertiary structures. We have developed a method based on radial basis function networks and position specific scoring matrix (PSSM) profiles generated by PSI-BLAST and non-redundant protein database. Our approach with PSSM profiles has correctly predicted the OMPs with a cross-validated accuracy of 96.4% in a set of 1251 proteins, which contain 206 OMPs, 667 globular proteins and 378 alpha-helical inner membrane proteins. Furthermore, we applied our method on a dataset containing 114 OMPs, 187 TMH proteins and 195 globular proteins obtained with less than 20% sequence identity and obtained the cross-validated accuracy of 95%. This accuracy of discriminating OMPs is higher than other methods in the literature and our method could be used as an effective tool for dissecting OMPs from genomic sequences. We have developed a prediction server, TMBETADISC-RBF, which is available at http://rbf.bioinfo.tw/~sachen/OMP.html.
崔维; 丁玲
2016-01-01
为了提高采摘机器人自主导航和路径规划能力，提出了基于计算机视觉路径规划和 RBF 神经网络自适应逼近算法的导航方法。使用图像分割、平滑处理和边缘检测技术，根据图像像素灰度值确定了导航线的位置，利用逐行扫描的方法得到了导航离散点。路径规划和跟踪使用RBF神经网络逼近算法，通过逼近误差和权值控制路径跟踪的精度，系统响应的执行端使用液压伺服系统，提高了机器人自主导航的精度。以黄瓜采摘作为研究对象，在日光温室对机器人采摘作业进行了测试，通过测试得到了 RBF 神经网络的路径跟踪误差曲线。测试结果表明：机器人可以很好地逼近跟踪规划路径，其计算精度较高，跟踪效果较好。%In order to improve the ability of autonomous navigation and path planning of picking robot , a navigation meth-od is proposed based on computer vision path planning and RBF neural network adaptive approximation algorithm .The use of image segmentation , smoothing and edge detection technology ,the navigation line positions are determined accord-ing to the image pixel gray value using progressive scan method of navigation discrete points .The path planning and tracking using RBF neural network approximation algorithm , the accuracy of the system response is controlled by the ac-curacy of the error and weight control .Taking cucumber as the research object , it tested the robot picking operation in greenhouse , and obtained the path tracking error curve of RBF neural network .The test results show that the robot can get a good approximation of the path .
Burken, John J.
2005-01-01
This viewgraph presentation reviews the use of a Robust Servo Linear Quadratic Regulator (LQR) and a Radial Basis Function (RBF) Neural Network in reconfigurable flight control designs in adaptation to a aircraft part failure. The method uses a robust LQR servomechanism design with model Reference adaptive control, and RBF neural networks. During the failure the LQR servomechanism behaved well, and using the neural networks improved the tracking.
Adaptive Neural Control for a Class of Outputs Time-Delay Nonlinear Systems
Ruliang Wang
2012-01-01
Full Text Available This paper considers an adaptive neural control for a class of outputs time-delay nonlinear systems with perturbed or no. Based on RBF neural networks, the radius basis function (RBF neural networks is employed to estimate the unknown continuous functions. The proposed control guarantees that all closed-loop signals remain bounded. The simulation results demonstrate the effectiveness of the proposed control scheme.
Tao Hu
2013-01-01
Full Text Available Horizontal attenuation total reflection Fourier transformation infrared spectroscopy (HATR-FT-IR studies on cuscutae semen and its confusable varieties Japanese dodder and sinapis semen combined with discrete wavelet transformation (DWT and radial basis function (RBF neural networks have been conducted in order to classify them. DWT is used to decompose the FT-IRs of cuscutae semen, Japanese dodder, and sinapis semen. Two main scales are selected as the feature extracting space in the DWT domain. According to the distribution of cuscutae semen, Japanese dodder, and sinapis semen’s FT-IRs, three feature regions are determined at detail 3, and two feature regions are determined at detail 4 by selecting two scales in the DWT domain. Thus five feature parameters form the feature vector. The feature vector is input to the RBF neural networks to train so as to accurately classify the cuscutae semen, Japanese dodder, and sinapis semen. 120 sets of FT-IR data are used to train and test the proposed method, where 60 sets of data are used to train samples, and another 60 sets of FT-IR data are used to test samples. Experimental results show that the accurate recognition rate of cuscutae semen, Japanese dodder, and sinapis semen is average of 100.00%, 98.33%, and 100.00%, respectively, following the proposed method.
A RBF Network Learning Scheme Using Immune Algorithm Based on Information Entropy
GONG Xin-bao; ZANG Xiao-gang; ZHOU Xi-lang
2005-01-01
A hybrid learning method combining immune algorithm and least square method is proposed to design the radial basis function(RBF) networks. The immune algorithm based on information entropy is used to determine the structure and parameters of RBF nonlinear hidden layer, and weights of RBF linear output layer are computed with least square method. By introducing the diversity control and immune memory mechanism, the algorithm improves the efficiency and overcomes the immature problem in genetic algorithm. Computer simulations demonstrate that the RBF networks designed in this method have fast convergence speed with good performances.
NO mediates downregulation of RBF after a prolonged reduction of renal perfusion pressure in SHR
Sørensen, Charlotte Mehlin; Leyssac, Paul Peter; Skott, Ole
2003-01-01
The aim of the study was to investigate mechanisms underlying the downregulation of renal blood flow (RBF) after a prolonged reduction in renal perfusion pressure (RPP) in adult spontaneously hypertensive rats (SHR). We tested the effect on the RBF response of clamping plasma ANG II in sevoflurane...... of plasma ANG II concentrations, general COX inhibition, and specific inhibition of COX-2. In contrast, clamping the NO system diminished the ability of SHR to downregulate RBF to a lower level. The downregulation of RBF was not associated with a resetting of the lower limit of autoregulation in the control...... of vasoconstrictory prostaglandins....
Ebtehaj, Isa; Bonakdari, Hossein; Zaji, Amir Hossein
2016-01-01
In this study, an expert system with a radial basis function neural network (RBF-NN) based on decision trees (DT) is designed to predict sediment transport in sewer pipes at the limit of deposition. First, sensitivity analysis is carried out to investigate the effect of each parameter on predicting the densimetric Froude number (Fr). The results indicate that utilizing the ratio of the median particle diameter to pipe diameter (d/D), ratio of median particle diameter to hydraulic radius (d/R) and volumetric sediment concentration (C(V)) as the input combination leads to the best Fr prediction. Subsequently, the new hybrid DT-RBF method is presented. The results of DT-RBF are compared with RBF and RBF-particle swarm optimization (PSO), which uses PSO for RBF training. It appears that DT-RBF is more accurate (R(2) = 0.934, MARE = 0.103, RMSE = 0.527, SI = 0.13, BIAS = -0.071) than the two other RBF methods. Moreover, the proposed DT-RBF model offers explicit expressions for use by practicing engineers.
Normalized RBF networks: application to a system of integral equations
Golbabai, A; Seifollahi, S; Javidi, M [Department of Mathematics, Iran University of Science and Technology, Narmak, Tehran 16844 (Iran, Islamic Republic of)], E-mail: golbabai@iust.ac.ir, E-mail: seif@iust.ac.ir, E-mail: mojavidi@yahoo.com
2008-07-15
Linear integral and integro-differential equations of Fredholm and Volterra types have been successfully treated using radial basis function (RBF) networks in previous works. This paper deals with the case of a system of integral equations of Fredholm and Volterra types with a normalized radial basis function (NRBF) network. A novel learning algorithm is developed for the training of NRBF networks in which the BFGS backpropagation (BFGS-BP) least-squares optimization method as a recursive model is used. In the approach presented here, a trial solution is given by an NRBF network of incremental architecture with a set of unknown parameters. Detailed learning algorithms and concrete examples are also included.
Neural network modeling and control of proton exchange membrane fuel cell
CHEN Yue-hua; CAO Guang-yi; ZHU Xin-jian
2007-01-01
A neural network model and fuzzy neural network controller was designed to control the inner impedance of a proton exchange membrane fuel cell(PEMFC)stack. A radial basis function(RBF)neural network model was trained by the input-output data of impedance. A fuzzy neural network controller Was designed to control the impedance response.The RBF neural network model was used to test the fuzzy neural network controller.The results show that the RBF model output Can imitate actual output well, themaximal errorisnotbeyond 20 mΩ, thetrainingtime is about 1 s by using 20 neurons, and the mean squared errors is 141.9 mΩ2.The impedance of the PEMFC stack is controlled within the optimum range when the load changes, and the adjustive time is ahnllt 3 rain.
Using the Correlation Criterion to Position and Shape RBF Units for Incremental Modelling
Xun-Xian Wang; Sheng Chen; Chris J. Harris
2006-01-01
A novel technique is proposed for the incremental construction of sparse radial basis function (RBF) networks.The correlation between an RBF regressor and the training data is used as the criterion to position and shape the RBF node, and it is shown that this is equivalent to incrementally minimise the modelling mean square error. A guided random search optimisation method, called the repeated weighted boosting search, is adopted to append RBF nodes one by one in an incremental regression modelling procedure. The experimental results obtained using the proposed method demonstrate that it provides a viable alternative to the existing state-of-the-art modelling techniques for constructing parsimonious RBF models that generalise well.
Nonlinear Model Predictive Control Based on a Self-Organizing Recurrent Neural Network.
Han, Hong-Gui; Zhang, Lu; Hou, Ying; Qiao, Jun-Fei
2016-02-01
A nonlinear model predictive control (NMPC) scheme is developed in this paper based on a self-organizing recurrent radial basis function (SR-RBF) neural network, whose structure and parameters are adjusted concurrently in the training process. The proposed SR-RBF neural network is represented in a general nonlinear form for predicting the future dynamic behaviors of nonlinear systems. To improve the modeling accuracy, a spiking-based growing and pruning algorithm and an adaptive learning algorithm are developed to tune the structure and parameters of the SR-RBF neural network, respectively. Meanwhile, for the control problem, an improved gradient method is utilized for the solution of the optimization problem in NMPC. The stability of the resulting control system is proved based on the Lyapunov stability theory. Finally, the proposed SR-RBF neural network-based NMPC (SR-RBF-NMPC) is used to control the dissolved oxygen (DO) concentration in a wastewater treatment process (WWTP). Comparisons with other existing methods demonstrate that the SR-RBF-NMPC can achieve a considerably better model fitting for WWTP and a better control performance for DO concentration.
基于PSO-RBF的建筑能耗预测模型研究%Prediction Model of Building Energy Consumption Based on PSO-RBF
季文娟; 顾永松
2015-01-01
Themodelofenergyconsumptionpredictionisbuiltafteranalyzingcharacteristicson energy consumption changes of public building in hot summer and cold winter area. Particle swarm optimization algorithm is used to optimize the model, and the PSO-RBF neural network prediction model is established. Using the energy consumption data of subject research, the samples of building energy consumption is built. Then the RBF neural network and PSO-RBF neural network are trained on MATLAB. Experiments are conducted to predict energy consumption values of typical public buildings. The results show that accuracy of the prediction model is improved obviously after being optimized, and it has strong learning and predicting ability. The model can predict energy consumption value of public buildings accurately.%通过研究分析夏热冬冷地区公共建筑能耗变化特点, 建立了RBF神经网络建筑能耗预测模型. 在此基础上运用微粒群算法对模型优化,建立了基于PSO-RBF的建筑能耗预测模型. 利用大量数据构造样本集,运用软件分别对优化前后的预测模型进行训练,并运用到典型公共建筑能耗值的预测实例中. 结果表明基于PSO-RBF的建筑能耗预测模型的学习能力和预测能力强,能较准确地实现公共建筑能耗预测.
张永志; 董俊慧
2014-01-01
针对焊接过程的高度非线性,多种因素的复杂交互作用,难以预测焊接接头力学性能的问题和常用反馈(Backpropagation,BP)神经网络的不足,利用模糊C均值(Fuzzy C-means,FCM)聚类算法和伪逆法相结合,建立焊接接头力学性能模糊径向基(Radial basis function,RBF)神经网络预测模型.以TC4钛合金惰性气体钨极保护焊(Tungsten inert gas arcwelding,TIG焊)焊接工艺参数(焊接电流、焊接速度和氩气流量)作为模型的输入参数,以焊后力学性能(抗拉强度、抗弯强度、伸长率、焊缝硬度和热影响区硬度)作为模型的输出参数.利用27组试验数据对所建模型进行学习训练,用另外9组试验数据进行仿真.结果表明,利用该方法所建模型具有结构稳定、训练速度快、适应性强、鲁棒性好、预测精度高的特点,能够预测焊接接头力学性能.通过数学解析,用函数形式表达焊接工艺参数与接头力学性能之间的规律,可以优化焊接工艺参数,为调控焊接接头的质量提供依据.
Radial basis function neural network for power system load-flow
Karami, A.; Mohammadi, M.S. [Faculty of Engineering, The University of Guilan, P.O. Box 41635-3756, Rasht (Iran)
2008-01-15
This paper presents a method for solving the load-flow problem of the electric power systems using radial basis function (RBF) neural network with a fast hybrid training method. The main idea is that some operating conditions (values) are needed to solve the set of non-linear algebraic equations of load-flow by employing an iterative numerical technique. Therefore, we may view the outputs of a load-flow program as functions of the operating conditions. Indeed, we are faced with a function approximation problem and this can be done by an RBF neural network. The proposed approach has been successfully applied to the 10-machine and 39-bus New England test system. In addition, this method has been compared with that of a multi-layer perceptron (MLP) neural network model. The simulation results show that the RBF neural network is a simpler method to implement and requires less training time to converge than the MLP neural network. (author)
Acute appendicitis diagnosis using artificial neural networks.
Park, Sung Yun; Kim, Sung Min
2015-01-01
Artificial neural networks is one of pattern analyzer method which are rapidly applied on a bio-medical field. The aim of this research was to propose an appendicitis diagnosis system using artificial neural networks (ANNs). Data from 801 patients of the university hospital in Dongguk were used to construct artificial neural networks for diagnosing appendicitis and acute appendicitis. A radial basis function neural network structure (RBF), a multilayer neural network structure (MLNN), and a probabilistic neural network structure (PNN) were used for artificial neural network models. The Alvarado clinical scoring system was used for comparison with the ANNs. The accuracy of the RBF, PNN, MLNN, and Alvarado was 99.80%, 99.41%, 97.84%, and 72.19%, respectively. The area under ROC (receiver operating characteristic) curve of RBF, PNN, MLNN, and Alvarado was 0.998, 0.993, 0.985, and 0.633, respectively. The proposed models using ANNs for diagnosing appendicitis showed good performances, and were significantly better than the Alvarado clinical scoring system (p < 0.001). With cooperation among facilities, the accuracy for diagnosing this serious health condition can be improved.
Noise Reduction Technique for Images using Radial Basis Function Neural Networks
Sander Ali Khowaja
2014-07-01
Full Text Available This paper presents a NN (Neural Network based model for reducing the noise from images. This is a RBF (Radial Basis Function network which is used to reduce the effect of noise and blurring from the captured images. The proposed network calculates the mean MSE (Mean Square Error and PSNR (Peak Signal to Noise Ratio of the noisy images. The proposed network has also been successfully applied to medical images. The performance of the trained RBF network has been compared with the MLP (Multilayer Perceptron Network and it has been demonstrated that the performance of the RBF network is better than the MLP network.
Wang, Z O; Zhu, T
2000-01-01
This paper presents an efficient recursive learning algorithm for improving generalization performance of radial basis function (RBF) neural networks. The approach combines the rival penalized competitive learning (PRCL) [Xu, L., Kizyzak, A. & Oja, E. (1993). Rival penalized competitive learning for clustering analysis, RBF net and curve detection, IEEE Transactions on Neural Networks, 4, 636-649] and the regularized least squares (RLS) to provide an efficient and powerful procedure for constructing a minimal RBF network that generalizes very well. The RPCL selects the number of hidden units of network and adjusts centers, while the RLS constructs the parsimonious network and estimates the connection weights. In the RLS we derived a simple recursive algorithm, which needs no matrix calculation, and so largely reduces the computational cost. This combined algorithm significantly enhances the generalization performance and the real-time capability of the RBF networks. Simulation results of three different problems demonstrate much better generalization performance of the present algorithm over other existing similar algorithms.
Efficient and exact mesh deformation using multiscale RBF interpolation
Kedward, L.; Allen, C. B.; Rendall, T. C. S.
2017-09-01
Radial basis function (RBF) interpolation is popular for mesh deformation due to robustness and generality, but the cost scales with the number of surface points sourcing the deformation as O (Ns3). Hence, there have been numerous works investigating efficient methods using reduced datasets. However, although reduced-data methods are efficient, they require a secondary method to treat an error vector field to ensure surface points not included in the primary deformation are moved to the correct location, and the volume mesh moved accordingly. A new method is presented which captures global and local motions at multiple scales using all the surface points, and so no correction stage is required; all surface points are used and a single interpolation built, but the cost and conditioning issues associated with RBF methods are eliminated. Moreover, the sparsity introduced is exploited using a wall distance function, to further reduce the cost. The method is compared to an efficient greedy method, and it is shown mesh quality is always comparable with or better than with the greedy method, and cost is comparable or cheaper at all stages. Surface mesh preprocessing is the dominant cost for reduced-data methods and this cost is reduced significantly here: greedy methods select points to minimise interpolation error, requiring repeated system solution and cost O (Nred4) to select Nred points; the multiscale method has no error, and the problem is transferred to a geometric search, with cost O (Ns log (Ns)), resulting in an eight orders of magnitude cost reduction for three-dimensional meshes. Furthermore, since the method is dependent on geometry, not deformation, it only needs to be applied once, prior to simulation, as the mesh deformation is decoupled from the point selection process.
OPTIMASI LEARNING RADIAL BASIS FUNCTION NEURAL NETWORK DENGAN EXTENDED KALMAN FILTER
Oni Soesanto
2015-09-01
Full Text Available Dalam paper ini dibahas mengenai optimasi Radial Basis Function Neural Network (RBFNN dengan Extended Kalman Filter. Proses learning RBF dengan Extended Kalman Filter menggunakan parameter bobot pada hidden center RBF yaitu noise proses pada perhitungan bobot hidden center dan noise pengukuran pada data output. Extended Kalman Filter pada jaringan syaraf RBF berfungsi mengoptimalkan bobot pada hidden center dengan meminimalkan error pada output RBF dengan parameter proses pada unit center RBF dan parameter bobot output pada output layer. Bobot output optimal diperoleh pada saat error output pada training RBF telah konvergen, selanjutnya digunakan untuk proses testing. Algoritma Extended Kalman Filter dan Radial Basis Fuction (EKF-RBF memungkinkan proses learning memungkinkan center dan variansi pada hidden layer tidak perlu dihitung sebelum bobot output optimum ditemukan. Hasil simulasi menunjukkan bahwa pada training, performansi klasifikasi algoritma EKF-RBF mampu mengenali rata-rata 92.42% dan untuk prediksi didapatkan MAE sebesar 5,3846 dan RMSE sebesar 16,2398 dengan CPU time 24,4146 detik dengan iterasi rata-rata 68,8 iterasi, testing in sample rata-rata MAE sebesar 4,3388, rata-rata RMSE sebesar 13,2230 dan rata-rata CPU time sebesar 0,1123 detik sedangkan pada testing out sample didapatkan rata-rata MAE sebesar 4,1065, RMSE sebesar 11,0126 dan CPU time sebesar 0,0265 detik. Kata kunci : Extended Kalman Filter, Extended Kalman Filter â€“ Radial Basis Function (EKF-RBF, Optimasi Jaringan Syaraf RBF
Performance Comparison of Neural Networks for HRTFs Approximation
无
2000-01-01
In order to approach to head-related transfer functions (HRTFs), this paper employs and compares three kinds of one-input neural network models, namely, multi-layer perceptron (MLP) networks, radial basis function (RBF) networks and wavelet neural networks (WNN) so as to select the best network model for further HRTFs approximation. Experimental results demonstrate that wavelet neural networks are more efficient and useful.
IMMUNE RBF NETWORK AND ITS APPLICATION IN THE MODULATION-STYLE RECOGNITION OF RADAR SIGNALS
Gong Xinbao; Zang Xiaogang; Zhou Xilang; Hu Guangrui
2003-01-01
Based on Immune Programming(IP), a novel Radial Basis Function (RBF) networkdesigning method is proposed. Through extracting the preliminary knowledge about the widthof the basis function as the vaccine to form the immune operator, the algorithm reduces thesearching space of canonical algorithm and improves the convergence speed. The application ofthe RBF network trained with the algorithm in the modulation-style recognition of radar signalsdemonstrates that the network has a fast convergence speed with good performances.
铁路扣件图像检测中的RBF-SVM模型优化%Optimization of RBF-SVM model in railway fastener detection system
刘甲甲; 王凯; 袁建英; 江晓亮; 李柏林
2014-01-01
在开发的铁路扣件检测系统中，RBF-SVM被作为扣件图像分类识别的分类器。核参数的选择是RBF-SVM模型优化研究中的重要问题，将量子粒子群算法应用于参数的优化选择，在(c，γ)参数可调范围内产生初始种群，将种群中的个体作为RBF-SVM的参数进行学习；经过多次迭代获得最佳参数对(c，γ)，并将该参数对作为RBF-SVM的核参数训练支持向量机。实验表明，QPSO的性能优于传统的 PSO算法，该方法在解决支持向量机优化方面表现出了高效的收敛性和稳定性，并且在该方法的基础上形成的铁路扣件检测算法是切实可行的。%In the railway fastener detection system, RBF-SVM is used as image classifier for railway fasteners. The selection of kernel parameters is an important problem in RBF-SVM research. A parameter selection method based on quantum genet-ic algorithm(QPSO)is presented. Initial population is produced in the adjustable range of parameters c and γ, and individuals in it are used as the parameters of RBF-SVM to calculation; then by multi-iterations, the parameters (c,γ) are obtained which are corresponding to fitness of population, and used as kernel parameters of Radial Basis kernel Function of Support Vector Machine(RBF-SVM)to training model. The experimental results indicate that the QPSO algorithm outperforms PSO algorithm. It has a high convergence and stability, and the detection algorithm of rail fastener based on it is practicable.
Variable Neural Adaptive Robust Control: A Switched System Approach
Lian, Jianming; Hu, Jianghai; Zak, Stanislaw H.
2015-05-01
Variable neural adaptive robust control strategies are proposed for the output tracking control of a class of multi-input multi-output uncertain systems. The controllers incorporate a variable-structure radial basis function (RBF) network as the self-organizing approximator for unknown system dynamics. The variable-structure RBF network solves the problem of structure determination associated with fixed-structure RBF networks. It can determine the network structure on-line dynamically by adding or removing radial basis functions according to the tracking performance. The structure variation is taken into account in the stability analysis of the closed-loop system using a switched system approach with the aid of the piecewise quadratic Lyapunov function. The performance of the proposed variable neural adaptive robust controllers is illustrated with simulations.
Sensor Fault Diagnosis for a Class of Time Delay Uncertain Nonlinear Systems Using Neural Network
Mou Chen; Chang-Sheng Jiang; Qing-Xian Wu
2008-01-01
In this paper, a sliding mode observer scheme of sensor fault diagnosis is proposed for a class of time delay nonlinear systems with input uncertainty based on neural network. The sensor fault and the system input uncertainty are assumed to be unknown but bounded. The radial basis function (RBF) neural network is used to approximate the sensor fault. Based on the output of the RBF neural network, the sliding mode observer is presented. Using the Lyapunov method, a criterion for stability is given in terms of matrix inequality. Finally, an example is given for illustrating the availability of the fault diagnosis based on the proposed sliding mode observer.
Nonlinear modelling of a SOFC stack by improved neural networks identification
无
2007-01-01
The solid oxide fuel cell (SOFC) is a nonlinear system that is hard to model by conventional methods. So far, most existing models are based on conversion laws, which are too complicated to be applied to design a control system. To facilitate a valid control strategy design, this paper tries to avoid the internal complexities and presents a modelling study of SOFC performance by using a radial basis function (RBF) neural network based on a genetic algorithm (GA). During the process of modelling, the GA aims to optimize the parameters of RBF neural networks and the optimum values are regarded as the initial values of the RBF neural network parameters. The validity and accuracy of modelling are tested by simulations, whose results reveal that it is feasible to establish the model of SOFC stack by using RBF neural networks identification based on the GA. Furthermore, it is possible to design an online controller of a SOFC stack based on this GA-RBF neural network identification model.
Liu, Long; Sun, Jun; Xu, Wenbo; Du, Guocheng; Chen, Jian
2009-01-01
Hyaluronic acid (HA) is a natural biopolymer with unique physiochemical and biological properties and finds a wide range of applications in biomedical and cosmetic fields. It is important to increase HA production to meet the increasing HA market demand. This work is aimed to model and optimize the amino acids addition to enhance HA production of Streptococcus zooepidemicus with radial basis function (RBF) neural network coupling quantum-behaved particle swarm optimization (QPSO) algorithm. In the RBF-QPSO approach, RBF neural network is used as a bioprocess modeling tool and QPSO algorithm is applied to conduct the optimization with the established RBF neural network black model as the objective function. The predicted maximum HA yield was 6.92 g/L under the following conditions: arginine 0.062 g/L, cysteine 0.036 g/L, and lysine 0.043 g/L. The optimal amino acids addition allowed HA yield increased from 5.0 g/L of the control to 6.7 g/L in the validation experiments. Moreover, the modeling and optimization capacity of the RBF-QPSO approach was compared with that of response surface methodology (RSM). It was indicated that the RBF-QPSO approach gave a slightly better modeling and optimization result compared with RSM. The developed RBF-QPSO approach in this work may be helpful for the modeling and optimization of the other multivariable, nonlinear, time-variant bioprocesses.
YANG Xiao-hua; HUANG Jing-feng; WANG Jian-wen; WANG Xiu-zhen; LIU Zhan-yu
2007-01-01
Hyperspectral reflectance (350-2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices (VIs) were used to predict the rice agronomic parameters including Leaf Area Index (LAI, m2 green leaf/m2 soil) and Green Leaf Chlorophyll Density (GLCD,mg chlorophyll/m2 soil) by the traditional regression models and Radial Basis Function Neural Network (RBF). RBF emerged as a variant of Artificial Neural Networks (ANNs) in the late 1980's. A large variety of training algorithms has been tested for training RBF networks. In this study, Original RBF (ORBF), Gradient Descent RBF (GDRBF), and Generalized Regression Neural Network (GRNN) were employed. Results showed that green waveband Normalized Difference Vegetation Index (NDVIgreen) and TCARI/OSAVI have the best prediction power for LAI by exponent model and ORBF respectively, and that TCARI/OSAVI has the best prediction power for GLCD by exponent model and GDRBF. The best performances of RBF are compared with the traditional models, showing that the relationship between VIs and agronomic variables are further improved when RBF is used.Compared with the best traditional models, ORBF using TCARI/OSAVI improves the prediction power for LAI by lowering the Root Mean Square Error (RMSE) for 0.1119, and GDRBF using TCARI/OSAVI improves the prediction power for GLCD by lowering the RMSE for 26.7853. It is concluded that RBF provides a useful exploratory and predictive tool when applied to the sensitive VIs.
Bahita Mohamed
2011-01-01
Full Text Available In this work, we introduce an adaptive neural network controller for a class of nonlinear systems. The approach uses two Radial Basis Functions, RBF networks. The first RBF network is used to approximate the ideal control law which cannot be implemented since the dynamics of the system are unknown. The second RBF network is used for on-line estimating the control gain which is a nonlinear and unknown function of the states. The updating laws for the combined estimator and controller are derived through Lyapunov analysis. Asymptotic stability is established with the tracking errors converging to a neighborhood of the origin. Finally, the proposed method is applied to control and stabilize the inverted pendulum system.
师洪; 宋绍云
2013-01-01
Structure of incremental neural network (IncNet) is controlled by growing and pruning to match the complexity of training data. Extended Kalman Filter algorithm used as learning algorithm. Bi-radial transfer functions, more flexible than other functions commonly used in artificial neural networks. The latest improvement added is the ability to rotate the contours of constant values of transfer functions in multidimensional spaces with only N-l adaptive parameters. Results on approximation benchmarks and on the real world psychometric classification problem clearly show superior generalization performance of presented network comparing with other classification models.%增量神经网络(IneNet)的结构是由增长和剪枝控制,并且与训练数据的复杂性相匹配.用扩展卡尔曼滤波算法作为其学习算法.双径向转移函数比其它常用于人工神经网络的转移函数更具有灵活性.最新的改进是在多维空间中(具有N-1个参数)增加转移函数的旋转常数值.通过对逼近基准和心理分类问题的结果分析,清楚地表明比其他分类网络模型具有更强的泛化性.
A Hybrid Framework using RBF and SVM for Direct Marketing
M. Govidarajan
2013-05-01
Full Text Available one of the major developments in machine learning in the past decade is the ensemble method, which finds highly accurate classifier by combining many moderately accurate component classifiers. This paper addresses using an ensemble of classification methods for direct marketing. Direct marketing has become an important application field for data mining. In direct marketing, companies or organizations try to establish and maintain a direct relationship with their customers in order to target them individually for specific product offers or for fund raising. A variety of techniques have been employed for analysis ranging from traditional statistical methods to data mining approaches. In this research work, new hybrid classification method is proposed by combining classifiers in a heterogeneous environment using arcing classifier and their performances are analyzed in terms of accuracy. A Classifier ensemble is designed using Radial Basis Function (RBF and Support Vector Machine (SVM as base classifiers. Here, modified training sets are formed by resampling from original training set; classifiers constructed using these training sets and then combined by voting. Empirical results illustrate that the proposed hybrid systems provide more accurate direct marketing system.
Clavier, Amandine; Ruby, Vincent; Rincheval-Arnold, Aurore; Mignotte, Bernard; Guénal, Isabelle
2015-09-01
In accordance with its tumor suppressor role, the retinoblastoma protein pRb can ensure pro-apoptotic functions. Rbf1, the Drosophila homolog of Rb, also displays a pro-apoptotic activity in proliferative cells. We have previously shown that the Rbf1 pro-apoptotic activity depends on its ability to decrease the level of anti-apoptotic proteins such as the Bcl-2 family protein Buffy. Buffy often acts in an opposite manner to Debcl, the other Drosophila Bcl-2-family protein. Both proteins can localize at the mitochondrion, but the way they control apoptosis still remains unclear. Here, we demonstrate that Debcl and the pro-fission gene Drp1 are necessary downstream of Buffy to trigger a mitochondrial fragmentation during Rbf1-induced apoptosis. Interestingly, Rbf1-induced apoptosis leads to a Debcl- and Drp1-dependent reactive oxygen species production, which in turn activates the Jun Kinase pathway to trigger cell death. Moreover, we show that Debcl and Drp1 can interact and that Buffy inhibits this interaction. Notably, Debcl modulates Drp1 mitochondrial localization during apoptosis. These results provide a mechanism by which Drosophila Bcl-2 family proteins can control apoptosis, and shed light on a link between Rbf1 and mitochondrial dynamics in vivo. © 2015. Published by The Company of Biologists Ltd.
Filtered-X Radial Basis Function Neural Networks for Active Noise Control
Bambang Riyanto
2004-05-01
Full Text Available This paper presents active control of acoustic noise using radial basis function (RBF networks and its digital signal processor (DSP real-time implementation. The neural control system consists of two stages: first, identification (modeling of secondary path of the active noise control using RBF networks and its learning algorithm, and secondly neural control of primary path based on neural model obtained in the first stage. A tapped delay line is introduced in front of controller neural, and another tapped delay line is inserted between controller neural networks and model neural networks. A new algorithm referred to as Filtered X-RBF is proposed to account for secondary path effects of the control system arising in active noise control. The resulting algorithm turns out to be the filtered-X version of the standard RBF learning algorithm. We address centralized and decentralized controller configurations and their DSP implementation is carried out. Effectiveness of the neural controller is demonstrated by applying the algorithm to active noise control within a 3 dimension enclosure to generate quiet zones around error microphones. Results of the real-time experiments show that 10-23 dB noise attenuation is produced with moderate transient response.
Wear Debris Identification Using Feature Extraction and Neural Network
王伟华; 马艳艳; 殷勇辉; 王成焘
2004-01-01
A method and results of identification of wear debris using their morphological features are presented. The color images of wear debris were used as initial data. Each particle was characterized by a set of numerical parameters combined by its shape, color and surface texture features through a computer vision system. Those features were used as input vector of artificial neural network for wear debris identification. A radius basis function (RBF) network based model suitable for wear debris recognition was established,and its algorithm was presented in detail. Compared with traditional recognition methods, the RBF network model is faster in convergence, and higher in accuracy.
On the role of polynomials in RBF-FD approximations: I. Interpolation and accuracy
Flyer, Natasha; Fornberg, Bengt; Bayona, Victor; Barnett, Gregory A.
2016-09-01
Radial basis function-generated finite difference (RBF-FD) approximations generalize classical grid-based finite differences (FD) from lattice-based to scattered node layouts. This greatly increases the geometric flexibility of the discretizations and makes it easier to carry out local refinement in critical areas. Many different types of radial functions have been considered in this RBF-FD context. In this study, we find that (i) polyharmonic splines (PHS) in conjunction with supplementary polynomials provide a very simple way to defeat stagnation (also known as saturation) error and (ii) give particularly good accuracy for the tasks of interpolation and derivative approximations without the hassle of determining a shape parameter. In follow-up studies, we will focus on how to best use these hybrid RBF polynomial bases for FD approximations in the contexts of solving elliptic and hyperbolic type PDEs.
CLASSIFICATIONS OF EEG SIGNALS FOR MENTAL TASKS USING ADAPTIVE RBF NETWORK
薛建中; 郑崇勋; 闫相国
2004-01-01
Objective This paper presents classifications of mental tasks based on EEG signals using an adaptive Radial Basis Function (RBF) network with optimal centers and widths for the Brain-Computer Interface (BCI) schemes. Methods Initial centers and widths of the network are selected by a cluster estimation method based on the distribution of the training set. Using a conjugate gradient descent method, they are optimized during training phase according to a regularized error function considering the influence of their changes to output values. Results The optimizing process improves the performance of RBF network, and its best cognition rate of three task pairs over four subjects achieves 87.0%. Moreover, this network runs fast due to the fewer hidden layer neurons. Conclusion The adaptive RBF network with optimal centers and widths has high recognition rate and runs fast. It may be a promising classifier for on-line BCI scheme.
On the role of polynomials in RBF-FD approximations: II. Numerical solution of elliptic PDEs
Bayona, Victor; Flyer, Natasha; Fornberg, Bengt; Barnett, Gregory A.
2017-03-01
RBF-generated finite differences (RBF-FD) have in the last decade emerged as a very powerful and flexible numerical approach for solving a wide range of PDEs. We find in the present study that combining polyharmonic splines (PHS) with multivariate polynomials offers an outstanding combination of simplicity, accuracy, and geometric flexibility when solving elliptic equations in irregular (or regular) regions. In particular, the drawbacks on accuracy and stability due to Runge's phenomenon are overcome once the RBF stencils exceed a certain size due to an underlying minimization property. Test problems include the classical 2-D driven cavity, and also a 3-D global electric circuit problem with the earth's irregular topography as its bottom boundary. The results we find are fully consistent with previous results for data interpolation.
Prediction of Double Layer Grids' Maximum Deflection Using Neural Networks
Reza K. Moghadas
2008-01-01
Full Text Available Efficient neural networks models are trained to predict the maximum deflection of two-way on two-way grids with variable geometrical parameters (span and height as well as cross-sectional areas of the element groups. Backpropagation (BP and Radial Basis Function (RBF neural networks are employed for the mentioned purpose. The inputs of the neural networks are the length of the spans, L, the height, h and cross-sectional areas of the all groups, A and the outputs are maximum deflections of the corresponding double layer grids, respectively. The numerical results indicate that the RBF neural network is better than BP in terms of training time and performance generality.
RBF multiuser detector with channel estimation capability in a synchronous MC-CDMA system.
Ko, K; Choi, S; Kang, C; Hong, D
2001-01-01
The authors propose a multiuser detector with channel estimation capability using a radial basis function (RBF) network in a synchronous multicarrier-code division multiple access (MC-CDMA) system. The authors propose to connect an RBF network to the frequency domain to effectively utilize the frequency diversity. Simulations were performed over frequency-selective and multi-path fading channels. These simulations confirmed that the proposed receiver can be used both for the channel estimation and as a multi-user receiver, thus permitting an increase in the number of active users.
DENSENESS OF RADIAL-BASIS FUNCTIONS IN L2（Rn） AND ITS APPLICATIONS IN NEURAL NETWORKS
CHENTIANPING; CHENHONG
1996-01-01
The authors discuss problems of approximation to functions in L2 (Rn)and operators from L2(Rn1)to L2(Rn2)by Radial-Basis Functions. The results obtained solve the parblem of capability of RBF neural networks,a basic problem in neural networks.
Reduced-Order Modeling for Flutter/LCO Using Recurrent Artificial Neural Network
Yao, Weigang; Liou, Meng-Sing
2012-01-01
The present study demonstrates the efficacy of a recurrent artificial neural network to provide a high fidelity time-dependent nonlinear reduced-order model (ROM) for flutter/limit-cycle oscillation (LCO) modeling. An artificial neural network is a relatively straightforward nonlinear method for modeling an input-output relationship from a set of known data, for which we use the radial basis function (RBF) with its parameters determined through a training process. The resulting RBF neural network, however, is only static and is not yet adequate for an application to problems of dynamic nature. The recurrent neural network method [1] is applied to construct a reduced order model resulting from a series of high-fidelity time-dependent data of aero-elastic simulations. Once the RBF neural network ROM is constructed properly, an accurate approximate solution can be obtained at a fraction of the cost of a full-order computation. The method derived during the study has been validated for predicting nonlinear aerodynamic forces in transonic flow and is capable of accurate flutter/LCO simulations. The obtained results indicate that the present recurrent RBF neural network is accurate and efficient for nonlinear aero-elastic system analysis
Reduced-Order Modeling for Flutter/LCO Using Recurrent Artificial Neural Network
Yao, Weigang; Liou, Meng-Sing
2012-01-01
The present study demonstrates the efficacy of a recurrent artificial neural network to provide a high fidelity time-dependent nonlinear reduced-order model (ROM) for flutter/limit-cycle oscillation (LCO) modeling. An artificial neural network is a relatively straightforward nonlinear method for modeling an input-output relationship from a set of known data, for which we use the radial basis function (RBF) with its parameters determined through a training process. The resulting RBF neural network, however, is only static and is not yet adequate for an application to problems of dynamic nature. The recurrent neural network method [1] is applied to construct a reduced order model resulting from a series of high-fidelity time-dependent data of aero-elastic simulations. Once the RBF neural network ROM is constructed properly, an accurate approximate solution can be obtained at a fraction of the cost of a full-order computation. The method derived during the study has been validated for predicting nonlinear aerodynamic forces in transonic flow and is capable of accurate flutter/LCO simulations. The obtained results indicate that the present recurrent RBF neural network is accurate and efficient for nonlinear aero-elastic system analysis
Applications of Neural Networks in Spinning Prediction
程文红; 陆凯
2003-01-01
The neural network spinning prediction model (BP and RBF Networks) trained by data from the mill can predict yarn qualities and spinning performance. The input parameters of the model are as follows: yarn count, diameter, hauteur, bundle strength, spinning draft, spinning speed, traveler number and twist.And the output parameters are: yarn evenness, thin places, tenacity and elongation, ends-down.Predicting results match the testing data well.
APPROACH TO FAULT ON-LINE DETECTION AND DIAGNOSIS BASED ON NEURAL NETWORKS FOR ROBOT IN FMS
1998-01-01
Based on radial basis function (RBF) neural networks, the healthy working model of each sub-system of robot in FMS is established. A new approach to fault on-line detection and diagnosis according to neural networks model is presented. Fault double detection based on neural network model and threshold judgement and quick fault identification based on multi-layer feedforward neural networks are applied, which can meet quickness and reliability of fault detection and diagnosis for robot in FMS.
李慧; 徐文尚; 李迪; 刘杰; 孙运营
2012-01-01
The RBF neural network was chosen to build pH value and concentration models and to adjust reac tor solution so that slow convergence speed and relative minimum and other weakness of negative gradient de scent method can be controlled. Actual application shows that both speed and precision can meet the require ment of pH value and concentration control.%选用径向基函数神经网络建立pH值和浓度的模型,克服了在白炭黑生产过程中采用负梯度下降法调节反应釜溶液pH值和浓度时存在收敛速度慢和局部极小等缺点.实际应用表明:其速度和精度完全达到了工艺上对pH值和浓度的控制要求.
A Regularized SNPOM for Stable Parameter Estimation of RBF-AR(X) Model.
Zeng, Xiaoyong; Peng, Hui; Zhou, Feng
2017-01-20
Recently, the radial basis function (RBF) network-style coefficients AutoRegressive (with exogenous inputs) [RBF-AR(X)] model identified by the structured nonlinear parameter optimization method (SNPOM) has attracted considerable interest because of its significant performance in nonlinear system modeling. However, this promising technique may occasionally confront the problem that the parameters are divergent in the optimization process, which may be a potential issue ignored by most researchers. In this paper, a regularized SNPOM, together with the regularization parameter detection technique, is presented to estimate the parameters of RBF-AR(X) models. This approach first separates the parameters of an RBF-AR(X) model into a linear parameters set and a nonlinear parameters set, and then combines a gradient-based nonlinear optimization algorithm for estimating the nonlinear parameters and the regularized least squares method for estimating the linear parameters. Several examples demonstrate that the proposed approach is effective to cope with the potential unstable problem in the parameters search process, and may also yield better or similar multistep forecasting accuracy and better robustness than the previous method.
Lukas Falat; Dusan Marcek; Maria Durisova
2016-01-01
This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the sug...
Term Structure of Interest Rates Based on Artificial Neural Network
无
2007-01-01
In light of the nonlinear approaching capability of artificial neural networks ( ANN), the term structure of interest rates is predicted using The generalized regression neural network (GRNN) and back propagation (BP) neural networks models. The prediction performance is measured with US interest rate data. Then, RBF and BP models are compared with Vasicek's model and Cox-Ingersoll-Ross (CIR) model. The comparison reveals that neural network models outperform Vasicek's model and CIR model,which are more precise and closer to the real market situation.
Neutron spectrum unfolding using radial basis function neural networks.
Alvar, Amin Asgharzadeh; Deevband, Mohammad Reza; Ashtiyani, Meghdad
2017-07-26
Neutron energy spectrum unfolding has been the subject of research for several years. The Bayesian theory, Monte Carlo simulation, and iterative methods are some of the methods that have been used for neutron spectrum unfolding. In this study, the radial basis function (RBF), multilayer perceptron, and artificial neural networks (ANNs) were used for the unfolding of neutron spectrum, and a comparison was made between the networks' results. Both neural network architectures were trained and tested using the same data set for neutron spectrum unfolding from the response of LiI detectors with Eu impurity. Advantages of each ANN method in the unfolding of neutron energy spectrum were investigated, and the performance of the networks was compared. The results obtained showed that RBF neural network can be applied as an effective method for unfolding neutron spectrum, especially when the main target is the neutron dosimetry. Copyright © 2017 Elsevier Ltd. All rights reserved.
Yao, Wei; Fang, Jiakun; Zhao, Ping
2013-01-01
the characteristics of the conventional PID, but adjust the parameters of PID controller online using identified Jacobian information from RBFNN. Hence, it has strong adaptability to the variation of the system operating condition. The effectiveness of the proposed controller is tested on a two-machine five-bus power...... system and a four-machine two-area power system under different operating conditions in comparison with the lead-lag damping controller tuned by evolutionary algorithm (EA). Simulation results show that the proposed damping controller achieves good robust performance for damping the low frequency...... oscillations under different operating conditions and is superior to the lead-lag damping controller tuned by EA....
Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm
Samanta B
2004-01-01
Full Text Available A study is presented to compare the performance of bearing fault detection using three types of artificial neural networks (ANNs, namely, multilayer perceptron (MLP, radial basis function (RBF network, and probabilistic neural network (PNN. The time domain vibration signals of a rotating machine with normal and defective bearings are processed for feature extraction. The extracted features from original and preprocessed signals are used as inputs to all three ANN classifiers: MLP, RBF, and PNN for two-class (normal or fault recognition. The characteristic parameters like number of nodes in the hidden layer of MLP and the width of RBF, in case of RBF and PNN along with the selection of input features, are optimized using genetic algorithms (GA. For each trial, the ANNs are trained with a subset of the experimental data for known machine conditions. The ANNs are tested using the remaining set of data. The procedure is illustrated using the experimental vibration data of a rotating machine with and without bearing faults. The results show the relative effectiveness of three classifiers in detection of the bearing condition.
Video Traffic Prediction Using Neural Networks
Miloš Oravec
2008-10-01
Full Text Available In this paper, we consider video stream prediction for application in services likevideo-on-demand, videoconferencing, video broadcasting, etc. The aim is to predict thevideo stream for an efficient bandwidth allocation of the video signal. Efficient predictionof traffic generated by multimedia sources is an important part of traffic and congestioncontrol procedures at the network edges. As a tool for the prediction, we use neuralnetworks – multilayer perceptron (MLP, radial basis function networks (RBF networksand backpropagation through time (BPTT neural networks. At first, we briefly introducetheoretical background of neural networks, the prediction methods and the differencebetween them. We propose also video time-series processing using moving averages.Simulation results for each type of neural network together with final comparisons arepresented. For comparison purposes, also conventional (non-neural prediction isincluded. The purpose of our work is to construct suitable neural networks for variable bitrate video prediction and evaluate them. We use video traces from [1].
Efficient algorithm for training interpolation RBF networks with equally spaced nodes.
Huan, Hoang Xuan; Hien, Dang Thi Thu; Tue, Huynh Huu
2011-06-01
This brief paper proposes a new algorithm to train interpolation Gaussian radial basis function (RBF) networks in order to solve the problem of interpolating multivariate functions with equally spaced nodes. Based on an efficient two-phase algorithm recently proposed by the authors, Euclidean norm associated to Gaussian RBF is now replaced by a conveniently chosen Mahalanobis norm, that allows for directly computing the width parameters of Gaussian radial basis functions. The weighting parameters are then determined by a simple iterative method. The original two-phase algorithm becomes a one-phase one. Simulation results show that the generality of networks trained by this new algorithm is sensibly improved and the running time significantly reduced, especially when the number of nodes is large.
A RBF Based Local Gridfree Scheme for Unsteady Convection-Diffusion Problems
Sanyasiraju VSS Yedida
2009-12-01
Full Text Available In this work a Radial Basis Function (RBF based local gridfree scheme has been presented for unsteady convection diffusion equations. Numerical studies have been made using multiquadric (MQ radial function. Euler and a three stage Runge-Kutta schemes have been used for temporal discretization. The developed scheme is compared with the corresponding finite difference (FD counterpart and found that the solutions obtained using the former are more superior. As expected, for a fixed time step and for large nodal densities, thought the Runge-Kutta scheme is able to maintain higher order of accuracy over the Euler method, the temporal discretization is independent of the improvement in the solution which in the developed scheme has been achived by optimizing the shape parameter of the RBF.
Solving time-dependent problems by an RBF-PS method with an optimal shape parameter
Neves, A M A; Roque, C M C; Ferreira, A J M; Jorge, R M N [Departamento de Engenharia Mecanica e Gestao Industrial, Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465 Porto (Portugal); Soares, C M M, E-mail: ana.m.neves@fe.up.p, E-mail: croque@fe.up.p, E-mail: ferreira@fe.up.p, E-mail: cristovao.mota.soares@dem.ist.utl.p, E-mail: rnatal@fe.up.p [IDMEC - Instituto de Engenharia Mecanica - Instituto Superior Tecnico, Av. Rovisco Pais, 1096 Lisboa Codex (Portugal)
2009-08-01
An hybrid technique is used for the solutions of static and time-dependent problems. The idea is to combine the radial basis function (RBF) collocation method and the pseudospectal (PS) method getting to the RBF-PS method. The approach presented in this paper includes a shape parameter optimization and produces highly accurate results. Different examples of the procedure are presented and different radial basis functions are used. One and two-dimensional problems are considered with various boundary and initial conditions. We consider generic problems, but also results on beams and plates. The displacement and the stress analysis are conducted for static and transient dynamic situations. Results obtained are in good agreement with exact solutions or references considered.
A Hybrid RBF-SVM Ensemble Approach for Data Mining Applications
M.Govindarajan
2014-02-01
Full Text Available One of the major developments in machine learning in the past decade is the ensemble method, which finds highly accurate classifier by combining many moderately accurate component classifiers. This paper addresses using an ensemble of classification methods for data mining applications like intrusion detection, direct marketing, and signature verification. In this research work, new hybrid classification method is proposed for heterogeneous ensemble classifiers using arcing and their performances are analyzed in terms of accuracy. A Classifier ensemble is designed using a Radial Basis Function (RBF and Support Vector Machine (SVM as base classifiers. Here, modified training sets are formed by resampling from original training set; classifiers constructed using these training sets and then combined by voting. The proposed RBF-SVM hybrid system is superior to individual approach for intrusion detection, direct marketing, and signature verification in terms of classification accuracy.
Nonlinear Adaptive PID Control for Greenhouse Environment Based on RBF Network
Guanghui Li
2012-04-01
Full Text Available This paper presents a hybrid control strategy, combining Radial Basis Function (RBF network with conventional proportional, integral, and derivative (PID controllers, for the greenhouse climate control. A model of nonlinear conservation laws of enthalpy and matter between numerous system variables affecting the greenhouse climate is formulated. RBF network is used to tune and identify all PID gain parameters online and adaptively. The presented Neuro-PID control scheme is validated through simulations of set-point tracking and disturbance rejection. We compare the proposed adaptive online tuning method with the offline tuning scheme that employs Genetic Algorithm (GA to search the optimal gain parameters. The results show that the proposed strategy has good adaptability, strong robustness and real-time performance while achieving satisfactory control performance for the complex and nonlinear greenhouse climate control system, and it may provide a valuable reference to formulate environmental control strategies for actual application in greenhouse production.
Nonlinear adaptive PID control for greenhouse environment based on RBF network.
Zeng, Songwei; Hu, Haigen; Xu, Lihong; Li, Guanghui
2012-01-01
This paper presents a hybrid control strategy, combining Radial Basis Function (RBF) network with conventional proportional, integral, and derivative (PID) controllers, for the greenhouse climate control. A model of nonlinear conservation laws of enthalpy and matter between numerous system variables affecting the greenhouse climate is formulated. RBF network is used to tune and identify all PID gain parameters online and adaptively. The presented Neuro-PID control scheme is validated through simulations of set-point tracking and disturbance rejection. We compare the proposed adaptive online tuning method with the offline tuning scheme that employs Genetic Algorithm (GA) to search the optimal gain parameters. The results show that the proposed strategy has good adaptability, strong robustness and real-time performance while achieving satisfactory control performance for the complex and nonlinear greenhouse climate control system, and it may provide a valuable reference to formulate environmental control strategies for actual application in greenhouse production.
Weather forecasting based on hybrid neural model
Saba, Tanzila; Rehman, Amjad; AlGhamdi, Jarallah S.
2017-02-01
Making deductions and expectations about climate has been a challenge all through mankind's history. Challenges with exact meteorological directions assist to foresee and handle problems well in time. Different strategies have been investigated using various machine learning techniques in reported forecasting systems. Current research investigates climate as a major challenge for machine information mining and deduction. Accordingly, this paper presents a hybrid neural model (MLP and RBF) to enhance the accuracy of weather forecasting. Proposed hybrid model ensure precise forecasting due to the specialty of climate anticipating frameworks. The study concentrates on the data representing Saudi Arabia weather forecasting. The main input features employed to train individual and hybrid neural networks that include average dew point, minimum temperature, maximum temperature, mean temperature, average relative moistness, precipitation, normal wind speed, high wind speed and average cloudiness. The output layer composed of two neurons to represent rainy and dry weathers. Moreover, trial and error approach is adopted to select an appropriate number of inputs to the hybrid neural network. Correlation coefficient, RMSE and scatter index are the standard yard sticks adopted for forecast accuracy measurement. On individual standing MLP forecasting results are better than RBF, however, the proposed simplified hybrid neural model comes out with better forecasting accuracy as compared to both individual networks. Additionally, results are better than reported in the state of art, using a simple neural structure that reduces training time and complexity.
Vuković, Najdan; Miljković, Zoran
2013-10-01
Radial basis function (RBF) neural network is constructed of certain number of RBF neurons, and these networks are among the most used neural networks for modeling of various nonlinear problems in engineering. Conventional RBF neuron is usually based on Gaussian type of activation function with single width for each activation function. This feature restricts neuron performance for modeling the complex nonlinear problems. To accommodate limitation of a single scale, this paper presents neural network with similar but yet different activation function-hyper basis function (HBF). The HBF allows different scaling of input dimensions to provide better generalization property when dealing with complex nonlinear problems in engineering practice. The HBF is based on generalization of Gaussian type of neuron that applies Mahalanobis-like distance as a distance metrics between input training sample and prototype vector. Compared to the RBF, the HBF neuron has more parameters to optimize, but HBF neural network needs less number of HBF neurons to memorize relationship between input and output sets in order to achieve good generalization property. However, recent research results of HBF neural network performance have shown that optimal way of constructing this type of neural network is needed; this paper addresses this issue and modifies sequential learning algorithm for HBF neural network that exploits the concept of neuron's significance and allows growing and pruning of HBF neuron during learning process. Extensive experimental study shows that HBF neural network, trained with developed learning algorithm, achieves lower prediction error and more compact neural network. Copyright © 2013 Elsevier Ltd. All rights reserved.
Radial Basis Function Neural Network Modeling Using Fuzzy Subspace Clustering%模糊子空间聚类的径向基函数神经网络建模
张江滨; 邓赵红; 王士同
2015-01-01
传统径向基函数(radial basis function,RBF)神经网络模型在处理噪声环境下的数据时,会因缺乏去除噪音特征的机制而使得受训模型的泛化性能下降.针对此缺陷,根据模糊子空间聚类(fuzzy subspace clus-tering,FSC)算法的子空间特性,为RBF神经网络添加特征抽取机制,提出了一种模糊子空间聚类RBF神经网络建模新方法(RBF neural network modeling using fuzzy subspace clustering,FSC-RBF-NN).与传统RBF神经网络建模方法相比,FSC-RBF-NN方法可根据FSC的子空间特性和特征抽取机制,为不同的隐含层节点选取不同的特征子空间.当训练数据中含有大量噪音特征时,FSC-RBF-NN方法可通过特征抽取机制去除噪音特征,只保留对建模有积极作用的特征,使模型能保持良好的泛化性能.模拟和真实数据集上的实验结果亦验证了FSC-RBF-NN方法在噪声环境下具有更好的鲁棒性.%When training data in the noisy environment, the generalization performance of traditional RBF (radial basis function) neural network is degraded because of the deficiency of feature extraction mechanism. This paper pro-poses a novel modeling method, i.e., RBF neural network modeling using fuzzy subspace clustering (FSC-RBF-NN) which adds feature extraction mechanism to overcome this challenge. Compared with traditional RBF neural network modeling, the proposed method can extract different subspace features for different nodes in hidden layer according to the subspace features of FSC (fuzzy subspace clustering) method and the feature extraction mechanism. When the training data contain lots of noise features, the proposed method can still keep good generalization performance by using the feature extraction mechanism to remove noise features. The experimental results on the synthetic and real-world datasets prove that the FSC-RBF-NN method has strong robustness in the noisy environment.
Cheng, Longlong; Zhang, Guangju; Wan, Baikun; Hao, Linlin; Qi, Hongzhi; Ming, Dong
2009-01-01
Functional electrical stimulation (FES) has been widely used in the area of neural engineering. It utilizes electrical current to activate nerves innervating extremities affected by paralysis. An effective combination of a traditional PID controller and a neural network, being capable of nonlinear expression and adaptive learning property, supply a more reliable approach to construct FES controller that help the paraplegia complete the action they want. A FES system tuned by Radial Basis Function (RBF) Neural Network-based Proportional-Integral-Derivative (PID) model was designed to control the knee joint according to the desired trajectory through stimulation of lower limbs muscles in this paper. Experiment result shows that the FES system with RBF Neural Network-based PID model get a better performance when tracking the preset trajectory of knee angle comparing with the system adjusted by Ziegler- Nichols tuning PID model.
Neural Network Predictive Control for Vanadium Redox Flow Battery
Hai-Feng Shen
2013-01-01
Full Text Available The vanadium redox flow battery (VRB is a nonlinear system with unknown dynamics and disturbances. The flowrate of the electrolyte is an important control mechanism in the operation of a VRB system. Too low or too high flowrate is unfavorable for the safety and performance of VRB. This paper presents a neural network predictive control scheme to enhance the overall performance of the battery. A radial basis function (RBF network is employed to approximate the dynamics of the VRB system. The genetic algorithm (GA is used to obtain the optimum initial values of the RBF network parameters. The gradient descent algorithm is used to optimize the objective function of the predictive controller. Compared with the constant flowrate, the simulation results show that the flowrate optimized by neural network predictive controller can increase the power delivered by the battery during the discharge and decrease the power consumed during the charge.
YANG Xiao-Hua; WANG Fu-Min; HUANG Jing-Feng; WANG Jian-Wen; WANG Ren-Chao; SHEN Zhang-Quan; WANG Xiu-Zhen
2009-01-01
The radial basis function (RBF) emerged as a variant of artificial neural network.Generalized regression neural network (GRNN) is one type of RBF,and its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets.Hyperspectral reflectance (350 to 2 500 nm) data were recorded at two different rice sites in two experiment fields with two cultivars,three nitrogen treatments and one plant density (45 plants m-2).Stepwise multivariable regression model (SMR) and RBF were used to compare their predictability for the leaf area index (LAI) and green leaf chlorophyll density (GLCD) of rice based on reflectance (R) and its three different transformations,the first derivative reflectance (D1),the second derivative reflectance (D2) and the log-transformed reflectance (LOG).GRNN based on D1 was the best model for the prediction of rice LAI and GLCD.The relationships between different transformations of reflectance and rice parameters could be further improved when RBF was employed.Owing to its strong capacity for nonlinear mapping and good robustness,GRNN could maximize the sensitivity to chlorophyll content using D1.It is concluded that RBF may provide a useful exploratory and predictive tool for the estimation of rice biophysical parameters.
Neural-networks-based Modelling and a Fuzzy Neural Networks Controller of MCFC
无
2002-01-01
Molten Carbonate Fuel Cells (MCFC) are produced with a highly efficient and clean power generation technology which will soon be widely utilized. The temperature characters of MCFC stack are briefly analyzed. A radial basis function (RBF) neural networks identification technology is applied to set up the temperature nonlinear model of MCFC stack, and the identification structure, algorithm and modeling training process are given in detail. A fuzzy controller of MCFC stack is designed. In order to improve its online control ability, a neural network trained by the I/O data of a fuzzy controller is designed. The neural networks can memorize and expand the inference rules of the fuzzy controller and substitute for the fuzzy controller to control MCFC stack online. A detailed design of the controller is given. The validity of MCFC stack modelling based on neural networks and the superior performance of the fuzzy neural networks controller are proved by Simulations.
J. Pavlovicova
2007-04-01
Full Text Available In this contribution, human face as biometric is considered. Original method of feature extraction from image data is introduced using MLP (multilayer perceptron and PCA (principal component analysis. This method is used in human face recognition system and results are compared to face recognition system using PCA directly, to a system with direct classification of input images by MLP and RBF (radial basis function networks, and to a system using MLP as a feature extractor and MLP and RBF networks in the role of classifier. Also a two-stage method for face recognition is presented, in which Kohonen self-organizing map is used as a feature extractor. MLP and RBF network are used as classifiers. In order to obtain deeper insight into presented methods, also visualizations of internal representation of input data obtained by neural networks are presented.
Forecasting ozone concentrations in the east of Croatia using nonparametric Neural Network Models
Kovač-Andrić, Elvira; Sheta, Alaa; Faris, Hossam; Gajdošik, Martina Šrajer
2016-07-01
Ozone is one of the most significant secondary pollutants with numerous negative effects on human health and environment including plants and vegetation. Therefore, more effort is made recently by governments and associations to predict ozone concentrations which could help in establishing better plans and regulation for environment protection. In this study, we use two Artificial Neural Network based approaches (MPL and RBF) to develop, for the first time, accurate ozone prediction models, one for urban and another one for rural area in the eastern part of Croatia. The evaluation of actual against the predicted ozone concentrations revealed that MLP and RBF models are very competitive for the training and testing data in the case of Kopački Rit area whereas in the case of Osijek city, MLP shows better evaluation results with 9% improvement in the correlation coefficient. Furthermore, subsequent feature selection process has improved the prediction power of RBF network.
Forecasting ozone concentrations in the east of Croatia using nonparametric Neural Network Models
Elvira Kovac-Andric; Alaa Sheta; Hossam Faris; Martina Srajer Gajdosik
2016-07-01
Ozone is one of the most significant secondary pollutants with numerous negative effects on humanhealth and environment including plants and vegetation. Therefore, more effort is made recently bygovernments and associations to predict ozone concentrations which could help in establishing betterplans and regulation for environment protection. In this study, we use two Artificial Neural Networkbased approaches (MPL and RBF) to develop, for the first time, accurate ozone prediction models, onefor urban and another one for rural area in the eastern part of Croatia. The evaluation of actual againstthe predicted ozone concentrations revealed that MLP and RBF models are very competitive for thetraining and testing data in the case of Kopaˇcki Rit area whereas in the case of Osijek city, MLP showsbetter evaluation results with 9% improvement in the correlation coefficient. Furthermore, subsequentfeature selection process has improved the prediction power of RBF network.
Hybrid model decomposition of speech and noise in a radial basis function neural model framework
Sørensen, Helge Bjarup Dissing; Hartmann, Uwe
1994-01-01
applied is based on a combination of the hidden Markov model (HMM) decomposition method, for speech recognition in noise, developed by Varga and Moore (1990) from DRA and the hybrid (HMM/RBF) recognizer containing hidden Markov models and radial basis function (RBF) neural networks, developed by Singer...... and Lippmann (1992) from MIT Lincoln Lab. The present authors modified the hybrid recognizer to fit into the decomposition method to achieve high performance speech recognition in noisy environments. The approach has been denoted the hybrid model decomposition method and it provides an optimal method...... for decomposition of speech and noise by using a set of speech pattern models and a noise model(s), each realized as an HMM/RBF pattern model...
蔡珣; 陈智; Kanishka T yagi; 于宽3; 李子强; 朱波
2015-01-01
提出了一种混合加权距离测量（weighted distance measure ，weighted DM ）参数的构建和训练RBF（radial basis function）神经网络的两步批处理算法。该算法在引进了 DM 系数参数的基础上，采用Newton 法分别对径向基函数的覆盖参数、均值向量参数、加权距离测度系数以及输出权值进行了优化，并在优化过程中利用 OLS（orthogonal least squares）法来求解 New ton 法的方程组。通过实验数据，不仅分析了 New ton 法优化的各个参数向量对 RBF 网络训练的影响，而且比较了混合优化加权 DM 与RLS‐RBF（recursive least square RBF neural network）网络训练算法的收敛性和计算成本。所得到的结论表明整合了优化参数的加权 DM‐RBF 网络训练算法收敛速度比 RLS‐RBF 网络训练算法更快，而且具有比 LM‐RBF （Levenberg‐Marquardt RBF ）训练算法更小的计算成本，从而说明 OLS 求解的Newton 法对优化 RBF 网络参数具有重要应用价值。%A hybrid two‐step second‐order batch approach is presented for constructing and training radial basis function (RBF) neural networks .Unlike other RBF neural network learning algorithms , the proposed paradigm uses New ton’s method to train each set of network parameters ,i .e .spread parameters ,mean vector parameters and weighted distance measure (DM ) coefficients and output weights parameters .For efficiently calculating the second‐order equations of New ton’s method ,all the optimal parameters are found out using orthogonal least squares (OLS ) with the multiply optimal learning factors(MOLFs) for training mean vector parameters .The simulation results of the proposed hybrid training algorithm on a real dataset are compared with those of the recursive least square based RBF(RLS‐RBF) and Levenberg‐Marquardt method based RBF(LM‐RBF) training algorithms .Also , the analysis of the training performance for optimization of each
Kayri, Murat
2015-01-01
The objective of this study is twofold: (1) to investigate the factors that affect the success of university students by employing two artificial neural network methods (i.e., multilayer perceptron [MLP] and radial basis function [RBF]); and (2) to compare the effects of these methods on educational data in terms of predictive ability. The…
Application of Nonlinear Predictive Control Based on RBF Network Predictive Model in MCFC Plant
CHEN Yue-hua; CAO Guang-yi; ZHU Xin-jian
2007-01-01
This paper described a nonlinear model predictive controller for regulating a molten carbonate fuel cell (MCFC). A detailed mechanism model of output voltage of a MCFC was presented at first. However, this model was too complicated to be used in a control system. Consequently, an off line radial basis function (RBF) network was introduced to build a nonlinear predictive model. And then, the optimal control sequences were obtained by applying golden mean method. The models and controller have been realized in the MATLAB environment. Simulation results indicate the proposed algorithm exhibits satisfying control effect even when the current densities vary largely.
Study on the Robot Robust Adaptive Control Based on Neural Networks
温淑焕; 王洪瑞; 吴丽艳
2003-01-01
Force control based on neural networks is presented. Under the framework of hybrid control, an RBF neural network is used to compensate for all the uncertainties from robot dynamics and unknown environment first. The technique will improve the adaptability to environment stiffness when the end-effector is in contact with the environment, and does not require any a priori knowledge on the upper bound of syste uncertainties. Moreover, it need not compute the inverse of inertia matrix. Learning algorithms for neural networks to minimize the force error directly are designed. Simulation results have shown a better force/position tracking when neural network is used.
武玉英; 李豪; 蒋国瑞
2015-01-01
In order to improve the self-learning ability of traditional negotiation,this paper integrated multi-agent intelligent technology ,designed the negotiation framework based on the blackboard model,constructed the five-elements negotiation model,adopted the negotiation strategy based on Q-reinforcement learning,proposed a negotiation strategy;then it optimized the negotiation strategy by the RBF neural network,predicted the information of opponent for adjusting the concession extent. At last,it verifies the feasibility and validity of the algorithm through a sample application.When comparing to the un-opti-mized Q-reinforcement learning,it can enhance the learning ability of the negotiation agents,reduce the negotiation time,and improve the efficiency of resolving conflicts.%为提高传统协商自学习能力，利用多 agent 智能技术，建立基于黑板模型的协商框架，构建五元组协商模型，采取 Q-强化学习算法，给出一种协商策略；使用 RBF 神经网络进一步优化协商策略，预测对手信息并调整让步幅度。通过算例验证该方法的可行性和有效性，通过与未改进的 Q-强化学习算法对比，该方法可增强协商agent 的自学习能力，缩短协商时间，提高冲突消解效率。
Numerical Solution of Stokes Flow in a Circular Cavity Using Mesh-free Local RBF-DQ
Kutanaai, S Soleimani; Roshan, Naeem; Vosoughi, A;
2012-01-01
This work reports the results of a numerical investigation of Stokes flow problem in a circular cavity as an irregular geometry using mesh-free local radial basis function-based differential quadrature (RBF-DQ) method. This method is the combination of differential quadrature approximation...... is applied on a two-dimensional geometry. The obtained results from the numerical simulations are compared with those gained by previous works. Outcomes prove that the current technique is in very good agreement with previous investigations and this fact that RBF-DQ method is an accurate and flexible method...... in solution of partial differential equations (PDEs)....
Tian, H; Liu, C; Gao, X D; Yao, W B
2013-03-01
Granulocyte colony-stimulating factor (G-CSF) is a cytokine widely used in cancer patients receiving high doses of chemotherapeutic drugs to prevent the chemotherapy-induced suppression of white blood cells. The production of recombinant G-CSF should be increased to meet the increasing market demand. This study aims to model and optimize the carbon source of auto-induction medium to enhance G-CSF production using artificial neural networks coupled with genetic algorithm. In this approach, artificial neural networks served as bioprocess modeling tools, and genetic algorithm (GA) was applied to optimize the established artificial neural network models. Two artificial neural network models were constructed: the back-propagation (BP) network and the radial basis function (RBF) network. The root mean square error, coefficient of determination, and standard error of prediction of the BP model were 0.0375, 0.959, and 8.49 %, respectively, whereas those of the RBF model were 0.0257, 0.980, and 5.82 %, respectively. These values indicated that the RBF model possessed higher fitness and prediction accuracy than the BP model. Under the optimized auto-induction medium, the predicted maximum G-CSF yield by the BP-GA approach was 71.66 %, whereas that by the RBF-GA approach was 75.17 %. These predicted values are in agreement with the experimental results, with 72.4 and 76.014 % for the BP-GA and RBF-GA models, respectively. These results suggest that RBF-GA is superior to BP-GA. The developed approach in this study may be helpful in modeling and optimizing other multivariable, non-linear, and time-variant bioprocesses.
薛亮; 樊卫国; 汪小志
2016-01-01
In order to improve the accuracy of robot manipulator movement and improve the efficiency of robot movement, a methodis proposed based on genetic algorithm and RBF neural network .The robot manipulator's movement and the whole trajectory are optimized.In order to verify the design of the picking robot reliability, in the experimental green-house on the robot's picking performance were tested, test items include robot path planning of mobile and manipulator path planning.Through the test, we found that using the RBF neural network algorithm can effectively control of manipu-lator motion in the three-dimensional space, in under the control of the genetic algorithm, the robot can with less amount of calculation using neural network algorithm search to get the optimal path, and the calculation precision is above 99%, for its high accuracy, which provides a valuable reference for the fast computational efficiency and effect of high vegetable production picking robot design.%为了提高果蔬采摘机器人机械手运动的精确性，提高机器人移动的效率，提出了一种基于遗传算法和RBF网络的机器人运动轨迹控制方法，并对果蔬机器人机械手的活动和整体的移动轨迹进行优化，有效地提高了果蔬采摘机器人的工作精度和作业效率。为了验证设计的采摘机器人的可靠性，在大棚内对机器人的采摘性能进行了测试，包括机器人移动路径规划和机械手路径规划。通过测试发现：使用 RBF 神经网络算法可以有效地控制机械手在三维空间内的运动；在遗传算法控制下，机器人可以通过较少的计算次数利用神经网络算法搜索得到最优路径，计算精度达到了99％以上。其计算精度及效率高，为高效果蔬采摘机器人的设计提供了较有价值的参考。
李鑫; 杨开明; 朱煜
2012-01-01
According to the modeling error in the dynamical model of robotic manipulators, a new self-adaptive control strategy based on modeling error compensated by RBF neural network was proposed. By means of Computed Torque control method based on inverse dynamics, and through input torque and desired trajectory corrected, two self-adaptive control schemes based on error compensated were developed. The correction terms were learned on-line by RBF neural network, and the adaptive learning law of network weights was developed based on Lyapunov stability theory, therefore the convergence and stability were guaranteed. Simulations are presented for a planner manipulator with two joints, the trajectory tracking results show that the modeling error can be effectively approximated and compensated, the RBF neural network improves the performance and makes the controller have robustness to the parameter perturbations, and it can be applied to the control for robotic manipulators.%针对机械手动力学建模误差,提出了基于RBF神经网络误差补偿的自适应控制策略。在基于逆动力学的计算力矩控制方法的基础上,对系统输入与目标轨迹进行修正,设计了两种误差补偿自适应控制器。利用RBF神经网络对修正项在线自学习,并根据Lyapunov稳定性理论建立了网络权重自适应学习律,保证了跟踪误差的收敛及系统的稳定。以平面转动双臂机械手轨迹跟踪为例进行仿真,结果表明该方法能够有效地补偿建模误差,提高了系统的控制性能并使控制系统具有对参数摄动的鲁棒性,对于机械手自适应控制具有一定的可行性。
基于混沌径向基函数的风电功率短期预测%Prediction of short-term wind power based on chaotic RBF
李玲玲; 李宗礼; 李俊豪; 李志刚
2014-01-01
风电功率预测方法分为两类，即直接预测法与功率曲线转换法。因风电功率具有混沌特性，故将混沌时间序列的相关理论引入到风速和风电功率预测中。鉴于预测精度在很大程度上取决于模型参数的选择，为此先用C-C法联合优化了重构相空间的参数，再用径向基RBF神经网络模型直接预测风电功率，或者由该模型得到风速预测值后，根据对应的风电机组功率特性曲线而推算出风电功率预测值。实例分析结果表明：所提出的两种方法均有较高的预测精度，其中基于混沌径向基RBF神经网络的风电功率直接预测法效果更优。%There were two kinds of method to predict the wind power, which were the direct forecasting method and the power curve conversion forecasting method. The wind speed and the wind power were predicted with the theories related to the chaotic time series because the wind power was chaotic. First the parameters of the phase-space reconstruction were optimized by C-C method because the accuracy of the prediction largely depended on the parameters used; then the wind power was predicted by the RBF neural network. The predicted wind power could also be achieved based on the curve of wind turbines after the wind speed was predicted by the RBF neural network. The analysis of the example shows that both of the methods have good performances in accuracy and the direct way based on the chaotic RBF neural network is better than the other one.
王学全; 刘君梅; 杨恒华; 赵学彬; 陈琦
2012-01-01
Evaporation is an important factor affecting thermal balance and water budget over the earth surface. A long-term observation of soil evaporation over semi-fixed dune was carried out with micro-lysimeters （MLS） in the high-frigid regions in the Qinghai-Tibetan Plateau of China during the period of 2006 -2009, the dataset was consisted of the collected daily soil evaporation as the output and the corresponding meteorological observation data including relative air humidity, air temperature, wind speed and soil moisture content as the input. A desert soil evaporation model was developed to research soil evaporation over semi-fixed dune based on the radial basis function （RBF） neural network, and the multiple linear regression （MLR） was used to validate the model. The results show that the values calculated with RBF network output were consistent with the observed values, and the root mean squared error was 0.14 mm. Both the average absolute percent error and the root mean squared error for the RBF neural network were lower than those for the MLR model. The RBF neural network model is good for calculating desert soil evaporation other than the traditional mathematical evaporation model, and it is characterized by the simple development, high accuracy and strong adaptability.%蒸发是地表能量平衡和水分平衡的重要组成部分。2006-2009年在青海东南部沙区半固定沙丘，利用微型蒸发器（MLS）对土壤蒸发进行了测定，结合气象观测数据，利用RBF神经网络技术，建立了沙区半固定沙丘土壤蒸发模型，并应用多元回归技术进行了验证。结果表明：已经构建的RBF神经网络计算土壤蒸发与实测值吻合较好，均方差是0．4mm，其绝对误差和均方差均小于多元线性回归计算值。模型在确定沙区土壤蒸发中具有实用可靠的优势。
Differentiation of digital tb images using texture analysis and rbf classifier.
Priya, E; Srinivasan, S; Ramakrishnan, S
2012-01-01
In this work, differentiation of positive and negative images of Tuberculosis (TB) sputum smear has been attempted using statistical method based on Gray Level Co-occurrence Matrix (GLCM). The sputum smear images (N=100) recorded under standard image acquisition protocol are considered for this work. Second order statistical texture analysis is performed on the acquired images using GLCM method and a set of nineteen features are derived. Principal Component Analysis (PCA) is then employed to reduce feature sets, to enhance the efficiency of differentiation and to reduce the redundancy. These feature sets are further classified using Radial Basis Function (RBF) classifier. Results show that GLCM is able to differentiate positive and negative TB images. Correlation is found to be high for many of the parameters. Application of PCA reduced the number of features to four which had maximum magnitude in the first principal component. Higher classification accuracy is achieved using RBF classifier. It appears that this method of texture analysis could be useful to develop automated system for characterization and classification of digital TB sputum smear images.
Ishii-Minami, Naoko; Kawahara, Yoshihiro; Yoshida, Yuri; Okada, Kazunori; Ando, Sugihiro; Matsumura, Hideo; Terauchi, Ryohei; Minami, Eiichi; Nishizawa, Yoko
2016-01-01
Magnaporthe oryzae, the fungus causing rice blast disease, should contend with host innate immunity to develop invasive hyphae (IH) within living host cells. However, molecular strategies to establish the biotrophic interactions are largely unknown. Here, we report the biological function of a M. oryzae-specific gene, Required-for-Focal-BIC-Formation 1 (RBF1). RBF1 expression was induced in appressoria and IH only when the fungus was inoculated to living plant tissues. Long-term successive imaging of live cell fluorescence revealed that the expression of RBF1 was upregulated each time the fungus crossed a host cell wall. Like other symplastic effector proteins of the rice blast fungus, Rbf1 accumulated in the biotrophic interfacial complex (BIC) and was translocated into the rice cytoplasm. RBF1-knockout mutants (Δrbf1) were severely deficient in their virulence to rice leaves, but were capable of proliferating in abscisic acid-treated or salicylic acid-deficient rice plants. In rice leaves, Δrbf1 inoculation caused necrosis and induced defense-related gene expression, which led to a higher level of diterpenoid phytoalexin accumulation than the wild-type fungus did. Δrbf1 showed unusual differentiation of IH and dispersal of the normally BIC-focused effectors around the short primary hypha and the first bulbous cell. In the Δrbf1-invaded cells, symplastic effectors were still translocated into rice cells but with a lower efficiency. These data indicate that RBF1 is a virulence gene essential for the focal BIC formation, which is critical for the rice blast fungus to suppress host immune responses. PMID:27711180
曹龙汉; 刘小丽; 郭晓东; 王申涛; 代睿
2011-01-01
针对气门故障,以缸盖振动信号的小波包能量谱作为故障特征参数,提出一种粗糙集(RS)与改进的量了微粒群径向基函数神经网络(QPSO-RBF NN)相结合的故障诊断方法.首先应用粗糙集对试验所得的特征参数进行属性约简,去掉冗余信息,简化RBF网络的结构；然后将带变异算子的QPSO算法引入到RBF网络的学习过程中,改进其现有的学习算法,进一步提高故障预测能力.通过对6135D型柴油机气门故障进行诊断,结果表明该方法提高了诊断的精度和效率.%A fault diagnosis method of combining RS (rough set) and improved QPSO-RBF NN (quantum-behaved particle swarm optimization-radial basis function neural network) is proposed for valve fault, in which wavelet packet energy spectrum from vibration signals of bonnet is taken as fault characteristic parameters. Firstly, attributes of characteristic parameters are reduced by RS theory in order to delete redundant attributes and simplify the inputs of RBF NN, then QPSO algorithm with mutation operator is introduced into the learning process of RBF NN to improve its existing learning algorithms and enhance its predictive ability. The simulation results of valve fault on 6135D type diesel engine show that the method enhancs accuracy and efficiency of fault diagnosis.
V. Bayona
2015-04-01
Full Text Available A numerical model based on Radial Basis Function-generated Finite Differences (RBF-FD is developed for simulating the Global Electric Circuit (GEC within the Earth's atmosphere, represented by a 3-D variable coefficient linear elliptic PDE in a spherically-shaped volume with the lower boundary being the Earth's topography and the upper boundary a sphere at 60 km. To our knowledge, this is (1 the first numerical model of the GEC to combine the Earth's topography with directly approximating the differential operators in 3-D space, and related to this (2 the first RBF-FD method to use irregular 3-D stencils for discretization to handle the topography. It benefits from the mesh-free nature of RBF-FD, which is especially suitable for modeling high-dimensional problems with irregular boundaries. The RBF-FD elliptic solver proposed here makes no limiting assumptions on the spatial variability of the coefficients in the PDE (i.e. the conductivity profile, the right hand side forcing term of the PDE (i.e. distribution of current sources or the geometry of the lower boundary.
Using neural networks to speed up optimization algorithms
Bazan, M
2000-01-01
The paper presents the application of radial-basis-function (RBF) neural networks to speed up deterministic search algorithms used for the design and optimization of superconducting LHC magnets. The optimization of the iron yoke of the main dipoles requires a number of numerical field computations per trial solution as the field quality depends on the excitation of the magnets. This results in computation times of about 30 minutes for each objective function evaluation (on a DEC-Alpha 600/333) and only the most robust (deterministic) optimization algorithms can be applied. Using a RBF function approximator, the achieved speed-up of the search algorithm is in the order of 25% for problems with two parameters and about 18% for problems with three and five design variables. (13 refs).
Babita Majhi
2014-09-01
Full Text Available This paper develops and assesses the performance of a hybrid prediction model using a radial basis function neural network and non-dominated sorting multiobjective genetic algorithm-II (NSGA-II for various stock market forecasts. The proposed technique simultaneously optimizes two mutually conflicting objectives: the structure (the number of centers in the hidden layer and the output mean square error (MSE of the model. The best compromised non-dominated solution-based model was determined from the optimal Pareto front using fuzzy set theory. The performances of this model were evaluated in terms of four different measures using Standard and Poor 500 (S&P500 and Dow Jones Industrial Average (DJIA stock data. The results of the simulation of the new model demonstrate a prediction performance superior to that of the conventional radial basis function (RBF-based forecasting model in terms of the mean average percentage error (MAPE, directional accuracy (DA, Thelis’ U and average relative variance (ARV values.
朱群雄; 李澄非
2006-01-01
Many applications of principal component analysis (PCA) can be found in dimensionality reduction.But linear PCA method is not well suitable for nonlinear chemical processes. A new PCA method based on improved input training neural network (IT-NN) is proposed for the nonlinear system modelling in this paper. Momentum factor and adaptive learning rate are introduced into learning algorithm to improve the training speed of IT-NN. Contrasting to the auto-associative neural network (ANN), IT-NN has less hidden layers and higher training speed. The effectiveness is illustrated through a comparison of IT-NN with linear PCA and ANN with experiments.Moreover, the IT-NN is combined with RBF neural network (RBF-NN) to model the yields of ethylene and propylene in the naphtha pyrolysis system. From the illustrative example and practical application, IT-NN combined with RBF-NN is an effective method of nonlinear chemical process modelling.
DU Lin-na; WU Li-hang; LU Jia-hui; GUO Wei-liang; MENG Qing-fan; JIANG Chao-jun; SHEN Si-le; TENG Li-rong
2007-01-01
Partial least squares(PLS), back-propagation neural network (BPNN) and radial basis function neural network(RBFNN) were respectively used for estalishing quantative analysis models with near infrared(NIR) diffuse reflectance spectra for determining the contents of rifampincin(RMP), isoniazid(INH) and pyrazinamide(PZA) in rifampicin isoniazid and pyrazinamide tablets. Savitzky-Golay smoothing, first derivative, second derivative, fast Fourier transform(FFT) and standard normal variate(SNV) transformation methods were applied to pretreating raw NIR diffuse reflectance spectra. The raw and pretreated spectra were divided into several regions, depending on the average spectrum and RSD spectrum. Principal component analysis(PCA) method was used for analyzing the raw and pretreated spectra in different regions in order to reduce the dimensions of input data. The optimum spectral regions and the models' parameters were chosen by comparing the root mean square error of cross-validation(RMSECV) values which were obtained by leave-one-out cross-validation method. The RMSECV values of the RBFNN models for determining the contents of RMP, INH and PZA were 0.00288, 0.00226 and 0.00341, respectively. Using these models for predicting the contents of INH, RMP and PZA in prediction set, the RMSEP values were 0.00266, 0.00227 and 0.00411, respectively. These results are better than those obtained from PLS models and BPNN models. With additional advantages of fast calculation speed and less dependence on the initial conditions, RBFNN is a suitable tool to model complex systems.
Joseph Ahlander
Full Text Available BACKGROUND: The retinoblastoma (Rb tumor suppressor protein can function as a DNA replication inhibitor as well as a transcription factor. Regulation of DNA replication may occur through interaction of Rb with the origin recognition complex (ORC. PRINCIPAL FINDINGS: We characterized the interaction of Drosophila Rb, Rbf1, with ORC. Using expression of proteins in Drosophila S2 cells, we found that an N-terminal Rbf1 fragment (amino acids 1-345 is sufficient for Rbf1 association with ORC but does not bind to dE2F1. We also found that the C-terminal half of Rbf1 (amino acids 345-845 interacts with ORC. We observed that the amino-terminal domain of Rbf1 localizes to chromatin in vivo and associates with chromosomal regions implicated in replication initiation, including colocalization with Orc2 and acetylated histone H4. CONCLUSIONS/SIGNIFICANCE: Our results suggest that Rbf1 can associate with ORC and chromatin through domains independent of the E2F binding site. We infer that Rbf1 may play a role in regulating replication directly through its association with ORC and/or chromatin factors other than E2F. Our data suggest an important role for retinoblastoma family proteins in cell proliferation and tumor suppression through interaction with the replication initiation machinery.
Artificial neural networks applied to forecasting time series.
Montaño Moreno, Juan J; Palmer Pol, Alfonso; Muñoz Gracia, Pilar
2011-04-01
This study offers a description and comparison of the main models of Artificial Neural Networks (ANN) which have proved to be useful in time series forecasting, and also a standard procedure for the practical application of ANN in this type of task. The Multilayer Perceptron (MLP), Radial Base Function (RBF), Generalized Regression Neural Network (GRNN), and Recurrent Neural Network (RNN) models are analyzed. With this aim in mind, we use a time series made up of 244 time points. A comparative study establishes that the error made by the four neural network models analyzed is less than 10%. In accordance with the interpretation criteria of this performance, it can be concluded that the neural network models show a close fit regarding their forecasting capacity. The model with the best performance is the RBF, followed by the RNN and MLP. The GRNN model is the one with the worst performance. Finally, we analyze the advantages and limitations of ANN, the possible solutions to these limitations, and provide an orientation towards future research.
MALLESWARAN M,
2010-12-01
Full Text Available Global positioning System (GPS and Inertial Navigation System (INS data can be integrated together to provide a reliable navigation. GPS/INS data integration provides reliable navigation solutions by overcoming each of their shortcomings, including signal blockage for GPS and increase in position errors with time for INS. This paper aims to provide GPS/INS data integration utilizing Artificial Neural Network (ANN architecture. This architecture is based on Feed Forward Neural Networks, which generally includes Radial Basis Function (RBF neural network and Back Propagation neural network (BPN. These are systematic methods for training multi-layer artificial networks. The BPN-ANN and RBF-ANN modules are trained to predict the INS position error and provide accurate positioning of the moving vehicle. This paper also compares performance of theGPS/INS data integration system by using different activation function like Bipolar Sigmoidal Function (BPSF, Binary Sigmoidal Function (BISF, Hyperbolic Tangential Function (HTF and Gaussian Function (GF in BPN-ANN and using Gaussian function in RBF-ANN.
庄述燕
2013-01-01
To install the reactive power compensation in grid connection point is an effective method to improve the voltage stability of wind power and ensure reliable operation. This paper designs a kind of STATCOM with superconducting magnetic energy storage. It achieves system decoupling of the feedback linearization using the inverse system method, and then controls the decoupled inverse system based on the RBF neural network sliding mode control. Simulation results show that the inverse system method and RBF neural network sliding mode control show a good effect in improving the system dynamic response speed and the system robustness. The results accord with the dynamic response characteristics of STATCOM with SMES.% 在并网点接入无功补偿器是提高电压稳定保证风电可靠运行的有效方法。设计一种带超导储能的静态无功补偿器，应用逆系统方法实现系统反馈线性化解耦，再采用RBF神经网络滑模控制对解耦逆系统进行控制。仿真结果表明：采用逆系统方法和RBF神经网络滑模控制对提高系统的动态响应速度和改善系统鲁棒性具有良好的效果，所得结果符合带超导储能的静态无功补偿器的动态响应特性。
Study of RBF Nerve Network Tuning PD Control Algoritm of Bilateral Servo System
Guang Wen
2013-01-01
Full Text Available In construction tele-robot system. When p-f architecture force feedback was used, the impact of large feedback force result in the strike-like feeling on the operators hand. If the amplitude is high, it will cause the control unstable. So a improved force feedback control method with the feature of a T-S fuzzy feedback coefficient, which could be modified online nonlinearly and continuously, is developed. A RBF-PID force controller is also designed, and formed a bilateral hydraulic servo control system. The experimental results indicate that the new improved control method reduced the impact of the feedback force, enhanced the compliance and transparency of the tele-operation of construction tele-robot system.
RBF Nerve Network Tuning PD Control Scheme for Tele-operation Robot Servo System
Guang Wen
2013-11-01
Full Text Available In the bilateral hydraulic servo control system of a construction tele-robot with in-situ force sensing, the p-f type force feedback architecture is liable to result in an impact on the operator hand, and its high amplitude will cause the control unstable. In order to solve this problem an improved force feedback control method with the feature of a T-S fuzzy feedback coefficient, which could be modified online nonlinearly and continuously, is proposed. And a RBF-PID force controller is also designed, and formed a bilateral hydraulic servo control system. The experimental results indicate that the new improved control method reduced the impact of the feedback force, the compliance and transparency of the tele-operation of construction tele-robot system are enhanced.
Wojcieszak, D.; Przybył, J.; Lewicki, A.; Ludwiczak, A.; Przybylak, A.; Boniecki, P.; Koszela, K.; Zaborowicz, M.; Przybył, K.; Witaszek, K.
2015-07-01
The aim of this research was investigate the possibility of using methods of computer image analysis and artificial neural networks for to assess the amount of dry matter in the tested compost samples. The research lead to the conclusion that the neural image analysis may be a useful tool in determining the quantity of dry matter in the compost. Generated neural model may be the beginning of research into the use of neural image analysis assess the content of dry matter and other constituents of compost. The presented model RBF 19:19-2-1:1 characterized by test error 0.092189 may be more efficient.
Leandro dos Santos Coelho
2007-04-01
Full Text Available As ferramentas de identificação de sistemas e previsão de séries temporais permitem a concepção de modelos matemáticos baseados em dados numéricos. O problema essencial, nestes casos, é determinar o modelo matemático apropriado. Esse artigo apresenta o projeto de uma rede neural função de base radial (RN-RBF para a previsão de séries temporais. Na utilização da RN-RBF para previsão de sistemas não-lineares é difícil determinar um conjunto apropriado de centros e aberturas para as funções de ativação Gaussianas para obter uma boa estrutura. Neste trabalho, a configuração da RN-RBF é baseada em uma abordagem híbrida baseada em método de agrupamento de dados de Gustafson-Kessel e procedimento de otimização usando evolução diferencial. O projeto de RN-RBF é validado para previsão de um passo à frente dos preços de troncos de eucalipto para celulose e serraria para ilustrar a eficiência da abordagem híbrida proposta. Além disso, o desempenho do projeto de RN-RBF baseado nos resultados de previsão é apresentado e discutido neste artigo.Computational tools of system identification and prediction of time series allows for the conception of mathematical models based on numerical data. The key problem in these cases is to find a suitable mathematical model. This paper presents a radial basis function neural network (RBF-NN design for forecasting time series. Using the RBF-NN for nonlinear system forecasting is quite difficult as one has to choose an appropriate set of centers and spreads for the Gaussian activation functions to achieve a good network structure. In this work, the setup of RBF-NN is based on a hybrid method based on the Gustafson-Kessel clustering method and optimization procedure by differential evolution. The RBF-NN design is validated for the one-step ahead forecasting of eucalyptus wood prices for cellulose and sawmill to illustrate the effectiveness of this hybrid approach. The performance of
On-line Cutting Quality Recognition in Milling Using a Radical Basis Function Neural Network
无
2000-01-01
Tool wear, chatter vibration, chip breaking and built-up edge are main phenomena to be monitored in modern manufacturing processes, which are considered as important factors to the quality of products.They are closely related to the cutting parameters, which are to be selected in manufacturing process.However, it is very difficult to measure directly the cutting quality based on on-line monitoring.In this study, the relationship between the cutting parameters and cutting quality is analyzed.A Radical Basis Function (RBF) neural network based on-line quality recognition scheme is also presented, which monitors the level of surface roughness.The experimental results reveal that the RBF neural network has a high prediction success rate.
Eftekhari Zadeh, E.; Feghhi, S. A. H.; Roshani, G. H.; Rezaei, A.
2016-05-01
Due to variation of neutron energy spectrum in the target sample during the activation process and to peak overlapping caused by the Compton effect with gamma radiations emitted from activated elements, which results in background changes and consequently complex gamma spectrum during the measurement process, quantitative analysis will ultimately be problematic. Since there is no simple analytical correlation between peaks' counts with elements' concentrations, an artificial neural network for analyzing spectra can be a helpful tool. This work describes a study on the application of a neural network to determine the percentages of cement elements (mainly Ca, Si, Al, and Fe) using the neutron capture delayed gamma-ray spectra of the substance emitted by the activated nuclei as patterns which were simulated via the Monte Carlo N-particle transport code, version 2.7. The Radial Basis Function (RBF) network is developed with four specific peaks related to Ca, Si, Al and Fe, which were extracted as inputs. The proposed RBF model is developed and trained with MATLAB 7.8 software. To obtain the optimal RBF model, several structures have been constructed and tested. The comparison between simulated and predicted values using the proposed RBF model shows that there is a good agreement between them.
Xiaodong Mao
2014-06-01
Full Text Available In this study, near-infrared reflectance spectroscopy and radial basis function (RBF neural network algorithm were used to measure the protein content of wheat owing to their nondestructiveness and quick speed as well as better performance compared to the traditional measuring method (semimicro-Kjeldahl in actual practice. To simplify the complex structure of the RBF network caused by the excessive wave points of samples obtained by near-infrared reflectance spectroscopy, we proposed the particle swarm optimization (PSO algorithm to optimize the cluster center in the hidden layers of the RBF neural network. In addition, a series of improvements for the PSO algorithm was also made to deal with its drawbacks in premature convergence and mechanical inertia weight setting. The experimental analysis demonstrated that the improved PSO algorithm greatly reduced the complexity of the network structure and improved the training speed of the RBF network. Meanwhile, the research result also proved the high performance of the model with its root-mean-square error of prediction (RMSEP and prediction correlation coefficient (R at 0.26576 and 0.975, respectively, thereby fulfilling the modern agricultural testing requirements featuring nondestructiveness, real-timing, and abundance in the number of samples.
Application of CMAC Neural Network to Solar Energy Heliostat Field Fault Diagnosis
Neng-Sheng Pai; Her-Terng Yau; Tzu-Hsiang Hung; Chin-Pao Hung
2013-01-01
Solar energy heliostat fields comprise numerous sun tracking platforms. As a result, fault detection is a highly challenging problem. Accordingly, the present study proposes a cerebellar model arithmetic computer (CMAC) neutral network for automatically diagnosing faults within the heliostat field in accordance with the rotational speed, vibration, and temperature characteristics of the individual heliostat transmission systems. As compared with radial basis function (RBF) neural network and ...
Zhu Guoqiang; Liu Jinkun
2015-01-01
An adaptive neural control scheme is proposed for a class of generic hypersonic flight vehicles. The main advantages of the proposed scheme include the following: (1) a new constraint variable is defined to generate the virtual control that forces the tracking error to fall within prescribed boundaries; (2) RBF NNs are employed to compensate for complex and uncertain terms to solve the problem of controller complexity; (3) only one parameter needs to be updated online at each design step, whi...
Michelle S Longworth
Full Text Available Previously, we discovered a conserved interaction between RB proteins and the Condensin II protein CAP-D3 that is important for ensuring uniform chromatin condensation during mitotic prophase. The Drosophila melanogaster homologs RBF1 and dCAP-D3 co-localize on non-dividing polytene chromatin, suggesting the existence of a shared, non-mitotic role for these two proteins. Here, we show that the absence of RBF1 and dCAP-D3 alters the expression of many of the same genes in larvae and adult flies. Strikingly, most of the genes affected by the loss of RBF1 and dCAP-D3 are not classic cell cycle genes but are developmentally regulated genes with tissue-specific functions and these genes tend to be located in gene clusters. Our data reveal that RBF1 and dCAP-D3 are needed in fat body cells to activate transcription of clusters of antimicrobial peptide (AMP genes. AMPs are important for innate immunity, and loss of either dCAP-D3 or RBF1 regulation results in a decrease in the ability to clear bacteria. Interestingly, in the adult fat body, RBF1 and dCAP-D3 bind to regions flanking an AMP gene cluster both prior to and following bacterial infection. These results describe a novel, non-mitotic role for the RBF1 and dCAP-D3 proteins in activation of the Drosophila immune system and suggest dCAP-D3 has an important role at specific subsets of RBF1-dependent genes.
Kai Heimel
Full Text Available In the phytopathogenic basidiomycete Ustilago maydis, sexual and pathogenic development are tightly connected and controlled by the heterodimeric bE/bW transcription factor complex encoded by the b-mating type locus. The formation of the active bE/bW heterodimer leads to the formation of filaments, induces a G2 cell cycle arrest, and triggers pathogenicity. Here, we identify a set of 345 bE/bW responsive genes which show altered expression during these developmental changes; several of these genes are associated with cell cycle coordination, morphogenesis and pathogenicity. 90% of the genes that show altered expression upon bE/bW-activation require the zinc finger transcription factor Rbf1, one of the few factors directly regulated by the bE/bW heterodimer. Rbf1 is a novel master regulator in a multilayered network of transcription factors that facilitates the complex regulatory traits of sexual and pathogenic development.
Heimel, Kai; Scherer, Mario; Vranes, Miroslav; Wahl, Ramon; Pothiratana, Chetsada; Schuler, David; Vincon, Volker; Finkernagel, Florian; Flor-Parra, Ignacio; Kämper, Jörg
2010-08-05
In the phytopathogenic basidiomycete Ustilago maydis, sexual and pathogenic development are tightly connected and controlled by the heterodimeric bE/bW transcription factor complex encoded by the b-mating type locus. The formation of the active bE/bW heterodimer leads to the formation of filaments, induces a G2 cell cycle arrest, and triggers pathogenicity. Here, we identify a set of 345 bE/bW responsive genes which show altered expression during these developmental changes; several of these genes are associated with cell cycle coordination, morphogenesis and pathogenicity. 90% of the genes that show altered expression upon bE/bW-activation require the zinc finger transcription factor Rbf1, one of the few factors directly regulated by the bE/bW heterodimer. Rbf1 is a novel master regulator in a multilayered network of transcription factors that facilitates the complex regulatory traits of sexual and pathogenic development.
Diagnosis of mechanical pumping system using neural networks and system parameters analysis
Tsai, Tai Ming; Wang, Wei Hui [National Taiwan Ocean University, Keelung (China)
2009-01-15
Normally, a mechanical pumping system is equipped to monitor some of the important input and output signals which are set to the prescribed values. This paper addressed dealing with these signals to establish the database of input- output relation by using a number of neural network models through learning algorithms. These signals encompass normal and abnormal running conditions. The abnormal running conditions were artificially generated. Meanwhile, for the purpose of setting up an on-line diagnosis network, the learning speed and accuracy of three kinds of networks, viz., the backpropagation (BPN), radial basis function (RBF) and adaptive linear (ADALINE) neural networks have been compared and assessed. The assessment criteria of the networks are compared with the correlation result matrix in terms of the neuron vectors. Both BPN and RBF are judged by the maximum vector based on the post-regression analysis, and the ADALINE is judged by the minimum vector based on the least mean square error analysis. By ignoring the neural network training time, it has been shown that if the mechanical diagnosis system is tackled off-line, the RBF method is suggested. However, for on-line diagnosis, the BPN method is recommended
Aoki, Y; Ishii, N; Watanabe, M; Yoshihara, F; Arisawa, M
1998-01-01
The major fungal pathogen for fungal diseases which have become a major medical problem in the last few years is Candida albicans, which can grow both in yeast and hyphae forms. This ability of C. albicans is thought to contribute to its colonization and dissemination within host tissues. In a recent few years, accompanying the introduction of molecular biological tools into C. albicans organism, several factors involved in the signal transduction pathway for yeast-hyphal transition have been identified. One MAP kinase pathway in C. albicans, similar to that leading to STE12 activation in Saccharomyces cerevisiae, has been reported. C. albicans strains mutant in these genes show retarded filamentous growth on a solid media but no impairment of filamentous growth in mice. These results suggest two scenarios that a kinase signaling cascade plays a part in stimulating the morphological transition in C. albicans, and that there would be another signaling pathway effective in animals. In this latter true hyphal pathway, although some candidate proteins, such as Efg1 (transcription factor), Int1 (integrin-like membrane protein), or Phr1 (pH-regulated membrane protein), have been identified, it is still too early to say that we understand the whole picture of that cascade. We have cloned a C. albicans gene encoding a novel DNA binding protein, Rbf1, that predominantly localizes in the nucleus, and shows transcriptional activation capability. Disruption of the functional RBF1 genes of C. albicans induced the filamentous growth on all solid and liquid media tested, suggesting that Rbf1 might be another candidate for the true hyphal pathway. Relationships with other factors described above, and the target (regulated) genes of Rbf1 is under investigation.
肖金凤; 肖杞铭; 曾铁军
2016-01-01
The available torque ripple suppression method of brushless DC motor has unsatisfactory suppression effect,or good ripple suppression effect while owning complicated learning algorithm,and is bad for promotion. To solve these problems, the field⁃oriented control system of the brushless DC motor was designed,which combines the RBF neural network and field⁃oriented control,and uses Luminary 615 microcontroller and brushless motor dedicated chip MC33035. The Visualbasic⁃based upper computer monitoring system matching with the motor was developed,which can realize the graphical display of parameters such as rotate speed and setting of motor parameters with low cost. The experimental results show that the designed RBF field⁃oriented control system of brushless DC motor has small torque ripple and high control accuracy.%针对现有无刷直流电机转矩脉动抑制方法存在抑制效果不理想，或脉动抑制效果好但学习算法复杂，不利于推广的问题，将RBF神经网络与磁场定向控制相结合，选用Luminary 615微控制器和无刷电机专用芯片MC33035，设计了无刷直流电机磁场定向控制系统。并开发基于Visual Basic的配套电机上位机监控系统，能在低成本下实现转速等参数的图形化显示及电机参数等的设置。实验结果表明，所设计的无刷直流电机RBF磁场定向控制系统转矩脉动小、控制精度高。
Numerical simulations of 1D inverse heat conduction problems using overdetermined RBF-MLPG method
Ahmad Shirzadi
2013-07-01
Full Text Available This paper proposes a numerical method to deal with the one-dimensional inverse heat conduction problem (IHCP. The initial temperature, a condition on an accessible part of the boundary and an additional temperature measurements in time at an arbitrary location in the domain are known, and it is required to determine the temperature and the heat flux on the remaining part of the boundary. Due to the missing boundary condition, the solution of this problem does not depend continuously on the data and therefore its numerical solution requires special care especially when noise is present in the measured data. In the proposed method, the time variable is eliminated by using finite differences approximation. The method uses a weak formulation of the problem to enjoy the stability condition. To avoid the numerical integration on the whole domain, the weak form equations are constructed on local subdomains. The approximate solution is assumed to be a linear combination of Multi Quadric (MQ radial basis function (RBF constructed on nodal points in the domain and on the boundary. Since the problem is known to be ill-posed, Thikhonov regularization strategy is employed to solve effectively the discrete ill-posed resultant linear system.
RBF-Based Monocular Vision Navigation for Small Vehicles in Narrow Space below Maize Canopy
Lu Liu
2016-06-01
Full Text Available Maize is one of the major food crops in China. Traditionally, field operations are done by manual labor, where the farmers are threatened by the harsh environment and pesticides. On the other hand, it is difficult for large machinery to maneuver in the field due to limited space, particularly in the middle and late growth stage of maize. Unmanned, compact agricultural machines, therefore, are ideal for such field work. This paper describes a method of monocular visual recognition to navigate small vehicles between narrow crop rows. Edge detection and noise elimination were used for image segmentation to extract the stalks in the image. The stalk coordinates define passable boundaries, and a simplified radial basis function (RBF-based algorithm was adapted for path planning to improve the fault tolerance of stalk coordinate extraction. The average image processing time, including network latency, is 220 ms. The average time consumption for path planning is 30 ms. The fast processing ensures a top speed of 2 m/s for our prototype vehicle. When operating at the normal speed (0.7 m/s, the rate of collision with stalks is under 6.4%. Additional simulations and field tests further proved the feasibility and fault tolerance of our method.
Karimi, H R; Babazadeh, A
2005-10-01
This paper deals with modeling and adaptive output tracking of a transverse flux permanent magnet machine as a nonlinear system with unknown nonlinearities by utilizing high gain observer and radial basis function networks. The proposed model is developed based on computing the permeance between rotor and stator using quasiflux tubes. Based on this model, the techniques of feedback linearization and Hinfinity control are used to design an adaptive control law for compensating the unknown nonlinear parts, such as the effect of cogging torque, as a disturbance is decreased onto the rotor angle and angular velocity tracking performances. Finally, the capability of the proposed method in tracking both the angle and the angular velocity is shown in the simulation results.
Luo, Shaohua [School of Automation, Chongqing University, Chongqing 400044 (China); Department of Mechanical Engineering, Chongqing Aerospace Polytechnic, Chongqing, 400021 (China); Wu, Songli [Department of Mechanical Engineering, Chongqing Aerospace Polytechnic, Chongqing, 400021 (China); Gao, Ruizhen [School of Automation, Chongqing University, Chongqing 400044 (China)
2015-07-15
This paper investigates chaos control for the brushless DC motor (BLDCM) system by adaptive dynamic surface approach based on neural network with the minimum weights. The BLDCM system contains parameter perturbation, chaotic behavior, and uncertainty. With the help of radial basis function (RBF) neural network to approximate the unknown nonlinear functions, the adaptive law is established to overcome uncertainty of the control gain. By introducing the RBF neural network and adaptive technology into the dynamic surface control design, a robust chaos control scheme is developed. It is proved that the proposed control approach can guarantee that all signals in the closed-loop system are globally uniformly bounded, and the tracking error converges to a small neighborhood of the origin. Simulation results are provided to show that the proposed approach works well in suppressing chaos and parameter perturbation.
Luo, Shaohua; Wu, Songli; Gao, Ruizhen
2015-07-01
This paper investigates chaos control for the brushless DC motor (BLDCM) system by adaptive dynamic surface approach based on neural network with the minimum weights. The BLDCM system contains parameter perturbation, chaotic behavior, and uncertainty. With the help of radial basis function (RBF) neural network to approximate the unknown nonlinear functions, the adaptive law is established to overcome uncertainty of the control gain. By introducing the RBF neural network and adaptive technology into the dynamic surface control design, a robust chaos control scheme is developed. It is proved that the proposed control approach can guarantee that all signals in the closed-loop system are globally uniformly bounded, and the tracking error converges to a small neighborhood of the origin. Simulation results are provided to show that the proposed approach works well in suppressing chaos and parameter perturbation.
Nord, Stefan; Bhatt, Monika J; Tükenmez, Hasan; Farabaugh, Philip J; Wikström, P Mikael
2015-08-01
The in vivo assembly of ribosomal subunits requires assistance by maturation proteins that are not part of mature ribosomes. One such protein, RbfA, associates with the 30S ribosomal subunits. Loss of RbfA causes cold sensitivity and defects of the 30S subunit biogenesis and its overexpression partially suppresses the dominant cold sensitivity caused by a C23U mutation in the central pseudoknot of 16S rRNA, a structure essential for ribosome function. We have isolated suppressor mutations that restore partially the growth of an RbfA-lacking strain. Most of the strongest suppressor mutations alter one out of three distinct positions in the carboxy-terminal domain of ribosomal protein S5 (S5) in direct contact with helix 1 and helix 2 of the central pseudoknot. Their effect is to increase the translational capacity of the RbfA-lacking strain as evidenced by an increase in polysomes in the suppressed strains. Overexpression of RimP, a protein factor that along with RbfA regulates formation of the ribosome's central pseudoknot, was lethal to the RbfA-lacking strain but not to a wild-type strain and this lethality was suppressed by the alterations in S5. The S5 mutants alter translational fidelity but these changes do not explain consistently their effect on the RbfA-lacking strain. Our genetic results support a role for the region of S5 modified in the suppressors in the formation of the central pseudoknot in 16S rRNA.
Nonlinear Time Series Forecast Using Radial Basis Function Neural Networks
ZHENGXin; CHENTian-Lun
2003-01-01
In the research of using Radial Basis Function Neural Network (RBF NN) forecasting nonlinear time series, we investigate how the different clusterings affect the process of learning and forecasting. We find that k-means clustering is very suitable. In order to increase the precision we introduce a nonlinear feedback term to escape from the local minima of energy, then we use the model to forecast the nonlinear time series which are produced by Mackey-Glass equation and stocks. By selecting the k-means clustering and the suitable feedback term, much better forecasting results are obtained.
Nonlinear Time Series Forecast Using Radial Basis Function Neural Networks
ZHENG Xin; CHEN Tian-Lun
2003-01-01
In the research of using Radial Basis Function Neural Network (RBF NN) forecasting nonlinear timeseries, we investigate how the different clusterings affect the process of learning and forecasting. We find that k-meansclustering is very suitable. In order to increase the precision we introduce a nonlinear feedback term to escape from thelocal minima of energy, then we use the model to forecast the nonlinear time series which are produced by Mackey-Glassequation and stocks. By selecting the k-means clustering and the suitable feedback term, much better forecasting resultsare obtained.
Software Aging Analysis of Web Server Using Neural Networks
G.Sumathi
2012-05-01
Full Text Available Software aging is a phenomenon that refers to progressive performance degradation or transient failures or even crashes in long running software systems such as web servers. It mainly occurs due to the deterioration of operating system resource, fragmentation and numerical error accumulation. A primitive method to fight against software aging is software rejuvenation. Software rejuvenation is a proactive fault management technique aimed at cleaning up the system internal state to prevent the occurrence of more severe crash failures in the future. It involves occasionally stopping the running software, cleaning its internal state and restarting it. An optimized schedule for performing the software rejuvenation has to be derived in advance because a long running application could not be put down now and then as it may lead to waste of cost. This paper proposes a method to derive an accurate and optimized schedule for rejuvenation of a web server (Apache by using Radial Basis Function (RBF based Feed Forward Neural Network, a variant of Artificial Neural Networks (ANN. Aging indicators are obtained through experimental setup involving Apache web server and clients, which acts as input to the neural network model. This method is better than existing ones because usage of RBF leads to better accuracy and speed in convergence.
An empirical RBF model of the magnetosphere parameterized by interplanetary and ground-based drivers
Tsyganenko, N. A.; Andreeva, V. A.
2016-11-01
In our recent paper (Andreeva and Tsyganenko, 2016), a novel method was proposed to model the magnetosphere directly from spacecraft data, with no a priori knowledge nor ad hoc assumptions about the geometry of the magnetic field sources. The idea was to split the field into the toroidal and poloidal parts and then expand each part into a weighted sum of radial basis functions (RBF). In the present work we take the next step forward by having developed a full-fledged model of the near magnetosphere, based on a multiyear set of space magnetometer data (1995-2015) and driven by ground-based and interplanetary input parameters. The model consolidates the largest ever amount of data and has been found to provide the best ever merit parameters, in terms of both the overall RMS residual field and record-high correlation coefficients between the observed and model field components. By experimenting with different combinations of input parameters and their time-averaging intervals, we found the best so far results to be given by the ram pressure Pd, SYM-H, and N-index by Newell et al. (2007). In addition, the IMF By has also been included as a model driver, with a goal to more accurately represent the IMF penetration effects. The model faithfully reproduces both externally and internally induced variations in the global distribution of the geomagnetic field and electric currents. Stronger solar wind driving results in a deepening of the equatorial field depression and a dramatic increase of its dawn-dusk asymmetry. The Earth's dipole tilt causes a consistent deformation of the magnetotail current sheet and a significant north-south asymmetry of the polar cusp depressions on the dayside. Next steps to further develop the new approach are also discussed.
The Prediction of Global Electron Content with Radial Basis Function Neural Network
Xue, J.
2016-12-01
The global electron content (GEC) is a sensitive indicator representing the dynamics of solar activities, which can faithfully reflect the global ionospheric variation.For understanding the global ionospheric variation in real time, it is important to predict the GEC through the observations of recent past. Since the change of GEC is complex, non-linear and time-varing, it is difficult to obtain a desirable prediction using the ordinary linear model. In this study, the Radial Basis Function (RBF) neural network method was used to predict the GEC through training the time series of significant length. The statistics were obtained by comparing the predictions with the measurements. It was found that the mean squared error(MSE) for the single-step prediction was within 0.24 TECu ^ 2 , while that for the multi-step prediction was less than 2 TECu ^ 2 . In addition, the Auto-Regressive and Moving Average Model (ARMA) method was also used for the GEC prediction. Comparison of the statistics of the two methods revealed that the performance of RBF nerual network is better than that of ARMA. Our study shows that the RBF neural network approach is capable of predicting the GEC with a superior performance.Furthermore, this provides a more accurate approach to understand the trend of the GEC.
RBF network designing based on artificial immune%基于人工免疫系统的RBF网络设计
朱亚男
2015-01-01
由于传统的RBF网络学习方法存在诸多的不足，本文提出基于免疫机制的三级RBF网络学习方法：在第一级得到网络隐层节点数作为疫苗，不仅可自行构建网络，还降低了第二级搜索空间的复杂度；第二级利用人工免疫算法对解空间进行多点搜索，得到全局最优的隐层非线性参数；第三级采用最小二乘法确定网络输出层线性参数，极大地降低了第二级结构的维数，提高了算法效率。经典型Hermit多项式逼近实验验证了该方法训练得到的RBF网络性能优越。%In order to improve the traditional RBF learning strategy, a three-level RBF network learning algorithm based on immune system is proposed, which can calculates the number of the hidden-layer neurons in the first level as immune vaccine, the network can be established and adjusted by itself, and the complexity of search space in the second level can be reduced. The global optimum hidden-layer nonlinear parameters are searched for in the second level by parallel searching with artificial immune algorithm. The output-layer linear parameters are estimated in the third level with least square method, which makes the design dimension of the second level decreased and the algorithm efficiency improved. The experiment of Hermit polynomial approximation shows that the performance of the RBF network trained by the algorithm is superior.
Radial Basis Function Neural Network Based Super-Resolution Restoration for an Underspled Image
苏秉华; 金伟其; 牛丽红
2004-01-01
To achieve restoration of high frequency information for an underspled and degraded low-resolution image, a nonlinear and real-time processing method-the radial basis function (RBF) neural network based super-resolution method of restoration is proposed. The RBF network configuration and processing method is suitable for a high resolution restoration from an underspled low-resolution image. The soft-competition learning scheme based on the k-means algorithm is used, and can achieve higher mapping approximation accuracy without increase in the network size. Experiments showed that the proposed algorithm can achieve a super-resolution restored image from an underspled and degraded low-resolution image, and requires a shorter training time when compared with the multiplayer perception (MLP) network.
Neural network approach for modification and fitting of digitized data in reverse engineering
JU Hua(鞠华); WANG Wen(王文); XIE Jin (谢金); CHEN Zi-chen(陈子辰)
2004-01-01
Reverse engineering in the manufacturing field is a process in which the digitized data are obtained from an existing object model or a part of it, and then the CAD model is reconstructed. This paper presents an RBF neural network approach to modify and fit the digitized data. The centers for the RBF are selected by using the orthogonal least squares learning algorithm. A mathematically known surface is used for generating a number of samples for training the networks. The trained networks then generated a number of new points which were compared with the calculating points from the equations. Moreover, a series of practice digitizing curves are used to test the approach. The results showed that this approach is effective in modifying and fitting digitized data and generating data points to reconstruct the surface model.
Neural network approach for modification and fitting of digitized data in reverse engineering~
鞠华; 王文; 谢金; 陈子辰
2004-01-01
Reverse engineering in the manufacturing field is a process in which the digitized data are obtained from an existing object model or a part of it, and then the CAD model is reconstructed. This paper presents an RBF neural network approach to modify and fit the digitized data. The centers for the RBF are selected by using the orthogonal least squares learning algorithm. A mathematically known surface is used for generating a number of samples for training the networks. The trained networks then generated a number of new points which were compared with the calculating points from the equations. Moreover, a series of practice digitizing curves are used to test the approach. The results showed that this approach is effective in modifying and fitting digitized data and generating data points to reconstruct the surface model.
Entropy Generation Due to Natural Convection in a Partially Heated Cavity by Local RBF-DQ Method
Soleimani, S.; Qajarjazi, A.; Bararnia, H.
2011-01-01
The Local Radial Basis Function-Differential Quadrature (RBF-DQ) method is applied to twodimensional incompressible Navier-Stokes equations in primitive form. Numerical results of heatlines and entropy generation due to heat transfer and fluid friction have been obtained for laminar natural...... convection. The variations of the entropy generation for different Rayleigh numbers are also investigated. Comparison between the present results and previous works demonstrated excellent agreements which verify the accuracy and flexibility of the method in simulating the fluid mechanics and heat transfer...
A Radial Basis Function (RBF) Method for the Fully Nonlinear 1D Serre Green-Naghdi Equations
Fabien, Maurice S
2014-01-01
In this paper, we present a spectral method based on Radial Basis Functions (RBFs) for numerically solving the fully nonlinear 1D Serre Green-Naghdi equations. The approximation uses an RBF discretization in space and finite differences in time; the full discretization is obtained by the method of lines technique. For select test cases (see Bonnenton et al. [2] and Kim [11]) the approximation achieves spectral (exponential) accuracy. Complete \\textsc{matlab} code of the numerical implementation is included in this paper (the logic is easy to follow, and the code is under 100 lines).
Barnett, Gregory A; Wicker, Louis J
2015-01-01
Polyharmonic spline (PHS) radial basis functions (RBFs) are used together with polynomials to create local RBF-finite-difference (RBF-FD) weights on different node layouts for spatial discretization of the compressible Navier-Stokes equations at low Mach number, relevant to atmospheric flows. Test cases are taken from the numerical weather prediction community and solved on bounded domains. Thus, attention is given on how to handle boundaries with the RBF-FD method, as well as a novel implementation for the presented approach. Comparisons are done on Cartesian, hexagonal, and quasi-uniformly scattered node layouts. Since RBFs are independent of a coordinate system (and only depend on the distance between nodes), changing the node layout amounts to changing one line of code. In addition, consideration and guidelines are given on PHS order, polynomial degree and stencil size. The main advantages of the present method are: 1) capturing the basic physics of the problem surprisingly well, even at very coarse resol...
Soft sensor for ratio of soda to aluminate based on PCA-RBF multiple network
GUI Wei-hua; LI Yong-gang; WANG Ya-lin
2005-01-01
Based on principal component analysis, a multiple neural network was proposed. The principal component analysis was firstly used to reorganize the input variables and eliminate the correlativity. Then the reorganized variables were divided into 2 groups according to the original information and 2 corresponding neural networks were established. A radial basis function network was used to depict the relationship between the output variables and the first group input variables which contain main original information. An other single-layer neural network model was used to compensate the error between the output of radial basis function network and the actual output variables. At last, The multiple network was used as soft sensor for the ratio of soda to aluminate in the process of high-pressure digestion of alumina. Simulation of industry application data shows that the prediction error of the model is less than 3%, and the model has good generalization ability.
Chaos control of ferroresonance system based on RBF-maximum entropy clustering algorithm
Liu Fan [Key Lab of High Voltage and Electrical New Technology of Ministry of Education, Chongqing University, Chongqing 400044 (China)]. E-mail: liufan2003@yahoo.com.cn; Sun Caixin [Key Lab of High Voltage and Electrical New Technology of Ministry of Education, Chongqing University, Chongqing 400044 (China); Sima Wenxia [Key Lab of High Voltage and Electrical New Technology of Ministry of Education, Chongqing University, Chongqing 400044 (China); Liao Ruijin [Key Lab of High Voltage and Electrical New Technology of Ministry of Education, Chongqing University, Chongqing 400044 (China); Guo Fei [Key Lab of High Voltage and Electrical New Technology of Ministry of Education, Chongqing University, Chongqing 400044 (China)
2006-09-11
With regards to the ferroresonance overvoltage of neutral grounded power system, a maximum-entropy learning algorithm based on radial basis function neural networks is used to control the chaotic system. The algorithm optimizes the object function to derive learning rule of central vectors, and uses the clustering function of network hidden layers. It improves the regression and learning ability of neural networks. The numerical experiment of ferroresonance system testifies the effectiveness and feasibility of using the algorithm to control chaos in neutral grounded system.
Bi Jun; Shao Sai; Guan Wei; Wang Lu
2012-01-01
The on-line estimation of the state of charge (SOC) of the batteries is important for the reliable running of the pure electric vehicle in practice.Because a nonlinear feature exists in the batteries and the radial-basis-function neural network (RBF NN) has good characteristics to solve the nonlinear problem,a practical method for the SOC estimation of batteries based on the RBF NN with a small number of input variables and a simplified structure is proposed.Firstly,in this paper,the model of on-line SOC estimation with the RBF NN is set.Secondly,four important factors for estimating the SOC are confirmed based on the contribution analysis method,which simplifies the input variables of the RBF NN and enhances the real-time performance of estimation.Finally,the pure electric buses with LiFePO4Li-ion batteries running during the period of the 2010 Shanghai World Expo are considered as the experimental object.The performance of the SOC estimation is validated and evaluated by the battery data from the electric vehicle.
Computationally efficient locally-recurrent neural networks for online signal processing
Hussain, A; Shim, I
1999-01-01
A general class of computationally efficient locally recurrent networks (CERN) is described for real-time adaptive signal processing. The structure of the CERN is based on linear-in-the- parameters single-hidden-layered feedforward neural networks such as the radial basis function (RBF) network, the Volterra neural network (VNN) and the functionally expanded neural network (FENN), adapted to employ local output feedback. The corresponding learning algorithms are derived and key structural and computational complexity comparisons are made between the CERN and conventional recurrent neural networks. Two case studies are performed involving the real- time adaptive nonlinear prediction of real-world chaotic, highly non- stationary laser time series and an actual speech signal, which show that a recurrent FENN based adaptive CERN predictor can significantly outperform the corresponding feedforward FENN and conventionally employed linear adaptive filtering models. (13 refs).
Chaos Synchronization Using Adaptive Dynamic Neural Network Controller with Variable Learning Rates
Chih-Hong Kao
2011-01-01
Full Text Available This paper addresses the synchronization of chaotic gyros with unknown parameters and external disturbance via an adaptive dynamic neural network control (ADNNC system. The proposed ADNNC system is composed of a neural controller and a smooth compensator. The neural controller uses a dynamic RBF (DRBF network to online approximate an ideal controller. The DRBF network can create new hidden neurons online if the input data falls outside the hidden layer and prune the insignificant hidden neurons online if the hidden neuron is inappropriate. The smooth compensator is designed to compensate for the approximation error between the neural controller and the ideal controller. Moreover, the variable learning rates of the parameter adaptation laws are derived based on a discrete-type Lyapunov function to speed up the convergence rate of the tracking error. Finally, the simulation results which verified the chaotic behavior of two nonlinear identical chaotic gyros can be synchronized using the proposed ADNNC scheme.
蔡时连; 许亮
2012-01-01
Book circulation is an important index for estimating of library.To resolve the forecast problem of book circulation,BP and RBF neural network predictive models are introduced in this paper.Based on the book circulation data of architectural book in the library from 2002 to 2010,Matlab simulation is implemented.The results show that the book circulation can be predicted by the two models effectively.%图书流通量是评价图书馆工作的重要指标.为解决图书流通量预测问题,引入BP和RBF神经网络预测模型.结合北京建筑工程学院图书馆2002年至2010年建筑类图书的流通数据进行了matlab仿真,结果表明,两种模型都能有效预测图书的流通量.
Study on Rear Axle Gear Residual Life Predication based on RBF Network%基于RBF网络的后桥齿轮残余寿命预测研究
曾宇露; 祝志芳
2012-01-01
为有效预测汽车后桥齿轮的残余寿命,针对后桥的非线性特性,提出了一种递归预处理与RBF网络相结合的齿轮残余寿命预测方法,并验证了该方法的可行性.利用该方法进行了汽车后桥齿轮残余寿命预测,结果表明,该方法对齿轮残余寿命的预测结果与齿轮疲劳试验结果吻合,预测精度高.%For the non-linearity property of rear axle, a new method, which consists of a recursive pretreatment and RBF neural networks, is presented in this paper to accurately predict residual life of rear axle gear. Simulation and experiment results have proved feasibility of this method. This method can be used to predict the residual life of rear axle gear, the results show that predication of gear residual life with this method is very accurate, and consistent with gear fatigue test results.
孙伟; 刘正江; 李新民; 黄建萍; 陈焕
2013-01-01
提出了局部均值分解(Local mean decomposition,简称LMD)方法和径向基函数神经网络(Radial Basis Function Neural Network,简称RBF)相结合的滚动轴承故障诊断方法.LMD方法是一种新的自适应时频分析方法,能够有效地提取故障特征.该方法首先采用LMD对滚动轴承振动信号进行分解,计算分解得到的PF分量能量比,作为特征向量输入到RBF神经网络中,进行故障分类和识别.通过真实滚动轴承数据的故障诊断实验,验证了该方法的有效性.
Mellit, A. [University Center of Medea, Institute of Engineering Sciences, Ain Dahab (Algeria); Benghanem, M. [University of Sciences Technology Houari Boumediene (USTHB), Faculty of ElectricalEngineering, El-Alia, Algiers (Algeria); Hadj Arab, A. [Development Center of Renewable Energy (CDER), Bouzareah, Algiers (Algeria); Guessoum, A. [Ministry for the Higher Education and Scientific Research, Algiers (Algeria)
2004-07-01
The main of this work is to train the RBF-IIR model to learn the prediction and modeling of the signals from stand-alone PV system. Once trained, the RBF-IIR estimates these signals faster. The validation of the model was performed with unknown signals data, which the network has not seen before. The ability of the network to make acceptable predictions even in an unusual day is an advantage of the present method. The estimation with correlation coefficient varied between 82 to 99 % was obtained. This accuracy is well within the acceptable level used by design engineers. The advantage of this model is to predict of different signal coming from the stand-alone prediction signals allow to analyzing and studying the performance of the PV systems and the sizing of PV system. Also this model have been compared between different neural networks structures, and given good results. (orig.)
Neuronal spike sorting based on radial basis function neural networks
Taghavi Kani M
2011-02-01
Full Text Available "nBackground: Studying the behavior of a society of neurons, extracting the communication mechanisms of brain with other tissues, finding treatment for some nervous system diseases and designing neuroprosthetic devices, require an algorithm to sort neuralspikes automatically. However, sorting neural spikes is a challenging task because of the low signal to noise ratio (SNR of the spikes. The main purpose of this study was to design an automatic algorithm for classifying neuronal spikes that are emitted from a specific region of the nervous system."n "nMethods: The spike sorting process usually consists of three stages: detection, feature extraction and sorting. We initially used signal statistics to detect neural spikes. Then, we chose a limited number of typical spikes as features and finally used them to train a radial basis function (RBF neural network to sort the spikes. In most spike sorting devices, these signals are not linearly discriminative. In order to solve this problem, the aforesaid RBF neural network was used."n "nResults: After the learning process, our proposed algorithm classified any arbitrary spike. The obtained results showed that even though the proposed Radial Basis Spike Sorter (RBSS reached to the same error as the previous methods, however, the computational costs were much lower compared to other algorithms. Moreover, the competitive points of the proposed algorithm were its good speed and low computational complexity."n "nConclusion: Regarding the results of this study, the proposed algorithm seems to serve the purpose of procedures that require real-time processing and spike sorting.
File access prediction using neural networks.
Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar
2010-06-01
One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors.
Automatic Identification of Axis Orbit Based on Both Wavelet Moment Invariants and Neural Network
FuXiang-qian; LiuGuang-lin; JiangJing; LiYou-ping
2003-01-01
Axis orbit is an important characteristic to be used in the condition monitoring and diagnosis system of rotating machine. The wavelet moment has the invariant to the translation, scaling and rotation. A method, which uses a neural network based on Radial Basis Function (RBF) and wavelet moment invariants to identify the orbit of shaft centerline of rotating machine is discussed in this paper. The principle and its application procedure of the method are introduced in detail. It gives simulation results of automatic identification for three typical axis orbits. It is proved that the method is effective and practicable.
Automatic Identification of Axis Orbit Based on Both Wavelet Moment Invariants and Neural Network
Fu Xiang-qian; Liu Guang-lin; Jiang Jing; Li You-ping
2003-01-01
Axis orbit is an important characteristic to be used in the condition monitoring and diagnosis system of rota-ting machine. The wavelet moment has the invariant to the translation, scaling and rotation. A method, which uses a neural network based on Radial Basis Function (RBF) and wavelet moment invariants to identify the orbit of shaft centerline of rotating machine is discussed in this paper. The principle and its application procedure of the method are intro-duced in detail. It gives simulation results of automatic identi-fication for three typical axis orbits. It is proved that the method is effective and practicable.
Yan Qing Chen; Yong Nian Ni
2009-01-01
Benzoic acid (BA),methylparaben (MP),propylparaben (PP) and sorbic acid (SA) are food preservatives,and they have well defined UV spectra.However,their spectra overlap seriously,and it is difficult to determine them individually from their mixtures without preseparation.In this paper,seven different chemometric approaches were applied to resolve the overlapping spectra and to determine these compounds simultaneously.With respect to the criteria of % relative prediction error (RPE) and % recovery,principal component regression (PCR) and radial basis function-artificial neural network (RBF-ANN) were the preferred methods.These two methods were successfully applied to the analysis of some commercial samples.
Adaptive Neural Control of Pure-Feedback Nonlinear Time-Delay Systems via Dynamic Surface Technique.
Min Wang; Xiaoping Liu; Peng Shi
2011-12-01
This paper is concerned with robust stabilization problem for a class of nonaffine pure-feedback systems with unknown time-delay functions and perturbed uncertainties. Novel continuous packaged functions are introduced in advance to remove unknown nonlinear terms deduced from perturbed uncertainties and unknown time-delay functions, which avoids the functions with control law to be approximated by radial basis function (RBF) neural networks. This technique combining implicit function and mean value theorems overcomes the difficulty in controlling the nonaffine pure-feedback systems. Dynamic surface control (DSC) is used to avoid "the explosion of complexity" in the backstepping design. Design difficulties from unknown time-delay functions are overcome using the function separation technique, the Lyapunov-Krasovskii functionals, and the desirable property of hyperbolic tangent functions. RBF neural networks are employed to approximate desired virtual controls and desired practical control. Under the proposed adaptive neural DSC, the number of adaptive parameters required is reduced significantly, and semiglobal uniform ultimate boundedness of all of the signals in the closed-loop system is guaranteed. Simulation studies are given to demonstrate the effectiveness of the proposed design scheme.
Dongliang Guo
2014-01-01
Full Text Available Indoor localization technique has received much attention in recent years. Many techniques have been developed to solve the problem. Among the recent proposed methods, radio frequency identification (RFID indoor localization technology has the advantages of low-cost, noncontact, non-line-of-sight, and high precision. This paper proposed two radial basis function (RBF neural network based indoor localization methods. The RBF neural networks are trained to learn the mapping relationship between received signal strength indication values and position of objects. Traditional method used the received signal strength directly as the input of neural network; we added another input channel by taking the difference of the received signal strength, thus improving the reliability and precision of positioning. Fuzzy clustering is used to determine the center of radial basis function. In order to reduce the impact of signal fading due to non-line-of-sight and multipath transmission in indoor environment, we improved the Gaussian filter to process received signal strength values. The experimental results show that the proposed method outperforms the existing methods as well as improves the reliability and precision of the RFID indoor positioning system.
Zhao, Ningbo; Li, Zhiming
2017-05-19
To effectively predict the thermal conductivity and viscosity of alumina (Al₂O₃)-water nanofluids, an artificial neural network (ANN) approach was investigated in the present study. Firstly, using a two-step method, four Al₂O₃-water nanofluids were prepared respectively by dispersing different volume fractions (1.31%, 2.72%, 4.25%, and 5.92%) of nanoparticles with the average diameter of 30 nm. On this basis, the thermal conductivity and viscosity of the above nanofluids were analyzed experimentally under various temperatures ranging from 296 to 313 K. Then a radial basis function (RBF) neural network was constructed to predict the thermal conductivity and viscosity of Al₂O₃-water nanofluids as a function of nanoparticle volume fraction and temperature. The experimental results showed that both nanoparticle volume fraction and temperature could enhance the thermal conductivity of Al₂O₃-water nanofluids. However, the viscosity only depended strongly on Al₂O₃ nanoparticle volume fraction and was increased slightly by changing temperature. In addition, the comparative analysis revealed that the RBF neural network had an excellent ability to predict the thermal conductivity and viscosity of Al₂O₃-water nanofluids with the mean absolute percent errors of 0.5177% and 0.5618%, respectively. This demonstrated that the ANN provided an effective way to predict the thermophysical properties of nanofluids with limited experimental data.
Investigating rainfall estimation from radar measurements using neural networks
A. Alqudah
2013-03-01
Full Text Available Rainfall observed on the ground is dependent on the four dimensional structure of precipitation aloft. Scanning radars can observe the four dimensional structure of precipitation. Neural network is a nonparametric method to represent the nonlinear relationship between radar measurements and rainfall rate. The relationship is derived directly from a dataset consisting of radar measurements and rain gauge measurements. The performance of neural network based rainfall estimation is subject to many factors, such as the representativeness and sufficiency of the training dataset, the generalization capability of the network to new data, seasonal changes, and regional changes. Improving the performance of the neural network for real time applications is of great interest. The goal of this paper is to investigate the performance of rainfall estimation based on Radial Basis Function (RBF neural networks using radar reflectivity as input and rain gauge as the target. Data from Melbourne, Florida NEXRAD (Next Generation Weather Radar ground radar (KMLB over different years along with rain gauge measurements are used to conduct various investigations related to this problem. A direct gauge comparison study is done to demonstrate the improvement brought in by the neural networks and to show the feasibility of this system. The principal components analysis (PCA technique is also used to reduce the dimensionality of the training dataset. Reducing the dimensionality of the input training data will reduce the training time as well as reduce the network complexity which will also avoid over fitting.
Biomimetic Hybrid Feedback Feedforward Neural-Network Learning Control.
Pan, Yongping; Yu, Haoyong
2017-06-01
This brief presents a biomimetic hybrid feedback feedforward neural-network learning control (NNLC) strategy inspired by the human motor learning control mechanism for a class of uncertain nonlinear systems. The control structure includes a proportional-derivative controller acting as a feedback servo machine and a radial-basis-function (RBF) NN acting as a feedforward predictive machine. Under the sufficient constraints on control parameters, the closed-loop system achieves semiglobal practical exponential stability, such that an accurate NN approximation is guaranteed in a local region along recurrent reference trajectories. Compared with the existing NNLC methods, the novelties of the proposed method include: 1) the implementation of an adaptive NN control to guarantee plant states being recurrent is not needed, since recurrent reference signals rather than plant states are utilized as NN inputs, which greatly simplifies the analysis and synthesis of the NNLC and 2) the domain of NN approximation can be determined a priori by the given reference signals, which leads to an easy construction of the RBF-NNs. Simulation results have verified the effectiveness of this approach.
Estimation of spatiotemporal neural activity using radial basis function networks.
Anderson, R W; Das, S; Keller, E L
1998-12-01
We report a method using radial basis function (RBF) networks to estimate the time evolution of population activity in topologically organized neural structures from single-neuron recordings. This is an important problem in neuroscience research, as such estimates may provide insights into systems-level function of these structures. Since single-unit neural data tends to be unevenly sampled and highly variable under similar behavioral conditions, obtaining such estimates is a difficult task. In particular, a class of cells in the superior colliculus called buildup neurons can have very narrow regions of saccade vectors for which they discharge at high rates but very large surround regions over which they discharge at low, but not zero, levels. Estimating the dynamic movement fields for these cells for two spatial dimensions at closely spaced timed intervals is a difficult problem, and no general method has been described that can be applied to all buildup cells. Estimation of individual collicular cells' spatiotemporal movement fields is a prerequisite for obtaining reliable two-dimensional estimates of the population activity on the collicular motor map during saccades. Therefore, we have developed several computational-geometry-based algorithms that regularize the data before computing a surface estimation using RBF networks. The method is then expanded to the problem of estimating simultaneous spatiotemporal activity occurring across the superior colliculus during a single movement (the inverse problem). In principle, this methodology could be applied to any neural structure with a regular, two-dimensional organization, provided a sufficient spatial distribution of sampled neurons is available.
Application of CMAC Neural Network to Solar Energy Heliostat Field Fault Diagnosis
Neng-Sheng Pai
2013-01-01
Full Text Available Solar energy heliostat fields comprise numerous sun tracking platforms. As a result, fault detection is a highly challenging problem. Accordingly, the present study proposes a cerebellar model arithmetic computer (CMAC neutral network for automatically diagnosing faults within the heliostat field in accordance with the rotational speed, vibration, and temperature characteristics of the individual heliostat transmission systems. As compared with radial basis function (RBF neural network and back propagation (BP neural network in the heliostat field fault diagnosis, the experimental results show that the proposed neural network has a low training time, good robustness, and a reliable diagnostic performance. As a result, it provides an ideal solution for fault diagnosis in modern, large-scale heliostat fields.
Adaptive Sliding Mode Control of MEMS Gyroscope Based on Neural Network Approximation
Yuzheng Yang
2014-01-01
Full Text Available An adaptive sliding controller using radial basis function (RBF network to approximate the unknown system dynamics microelectromechanical systems (MEMS gyroscope sensor is proposed. Neural controller is proposed to approximate the unknown system model and sliding controller is employed to eliminate the approximation error and attenuate the model uncertainties and external disturbances. Online neural network (NN weight tuning algorithms, including correction terms, are designed based on Lyapunov stability theory, which can guarantee bounded tracking errors as well as bounded NN weights. The tracking error bound can be made arbitrarily small by increasing a certain feedback gain. Numerical simulation for a MEMS angular velocity sensor is investigated to verify the effectiveness of the proposed adaptive neural control scheme and demonstrate the satisfactory tracking performance and robustness.
Research on Power Control of Wind Power Generation Based on Neural Network Adaptive Control
Hai-ying DONG; Chuan-hua SUN
2010-01-01
-For the characteristics of wind power generation system is multivariable,nonlinear and random,in this paper the neural network PID adaptive control is adopted.The size of pitch angle is adjusted in time to improve the performance of power control.The PID parameters are corrected by the gradient descent method,and Radial Basis Functinn(RBF)neural network is used as the system identifier in this method.Simulation results shaw that by using neural adaptive PID controller the generator power control can inhibit effectively the speed and affect the output power of generator.The dynamic performance and robustness of the controlled system is good,and the performance of wind power system is improved.
GUO Jin-song; LI Zhe
2009-01-01
An effective approach for describing complicated water quality processes is very important for fiver water quality management. We built two artificial neural network (ANN) models, a feed-forward back-propagation (BP) model and a radial basis function (RBF) model, to simulate the water quality of the Yangtze and Jialing Rivers in reaches crossing the city of Chongqing, P. R. China. Our models used the historical monitoring data of biological oxygen demand, dissolved oxygen, ammonia, oil and volatile phenolic compounds. Comparison with the one-dimensional traditional water quality model suggest that both BP and RBF models are superior; their higher accuracy and better goodness-of-fit indicate that the ANN calculation of water quality agrees better with measurement. It is demonstrated that ANN modeling can be a tool for estimating the water quality of the Yangtze River. Of the two ANN models, the RBF model calculates with a smaller mean error, but a larger root mean square error. More effort to identify out the causes of these differences would help optimize the su'uctures of neural network water-quality models.
Shankar, Varun; Wright, Grady B.; Fogelson, Aaron L.; Kirby, Robert M.
2014-05-01
We present a computational method for solving the coupled problem of chemical transport in a fluid (blood) with binding/unbinding of the chemical to/from cellular (platelet) surfaces in contact with the fluid, and with transport of the chemical on the cellular surfaces. The overall framework is the Augmented Forcing Point Method (AFM) (\\emph{L. Yao and A.L. Fogelson, Simulations of chemical transport and reaction in a suspension of cells I: An augmented forcing point method for the stationary case, IJNMF (2012) 69, 1736-52.}) for solving fluid-phase transport in a region outside of a collection of cells suspended in the fluid. We introduce a novel Radial Basis Function-Finite Difference (RBF-FD) method to solve reaction-diffusion equations on the surface of each of a collection of 2D stationary platelets suspended in blood. Parametric RBFs are used to represent the geometry of the platelets and give accurate geometric information needed for the RBF-FD method. Symmetric Hermite-RBF interpolants are used for enforcing the boundary conditions on the fluid-phase chemical concentration, and their use removes a significant limitation of the original AFM. The efficacy of the new methods are shown through a series of numerical experiments; in particular, second order convergence for the coupled problem is demonstrated.
Goudarzi, Nasser
2016-04-05
In this work, two new and powerful chemometrics methods are applied for the modeling and prediction of the (19)F chemical shift values of some fluorinated organic compounds. The radial basis function-partial least square (RBF-PLS) and random forest (RF) are employed to construct the models to predict the (19)F chemical shifts. In this study, we didn't used from any variable selection method and RF method can be used as variable selection and modeling technique. Effects of the important parameters affecting the ability of the RF prediction power such as the number of trees (nt) and the number of randomly selected variables to split each node (m) were investigated. The root-mean-square errors of prediction (RMSEP) for the training set and the prediction set for the RBF-PLS and RF models were 44.70, 23.86, 29.77, and 23.69, respectively. Also, the correlation coefficients of the prediction set for the RBF-PLS and RF models were 0.8684 and 0.9313, respectively. The results obtained reveal that the RF model can be used as a powerful chemometrics tool for the quantitative structure-property relationship (QSPR) studies.
Nondestructive diagnosis of flip chips based on vibration analysis using PCA-RBF
Su, Lei; Shi, Tielin; Liu, Zhiping; Zhou, Hongdi; Du, Li; Liao, Guanglan
2017-02-01
Flip chip technology combined with solder bump interconnection has been widely applied in IC package. The solder bumps are sandwiched between dies and substrates, leading to conventional techniques being difficult to diagnose the flip chips. Meanwhile, these conventional diagnosis methods are usually performed by human visual judgment. The human eye-fatigue can easily cause fault detection. Thus, it is difficult and crucial to detect the defects of flip chips automatically. In this paper, a nondestructive diagnosis system based on vibration analysis is proposed. The flip chip is excited by air-coupled ultrasounds and raw vibration signals are measured by a laser scanning vibrometer. Forty-two features are extracted for analysis, including ten time domain features, sixteen frequency domain features and sixteen wavelet packet energy features. Principal component analysis is used for feature reduction. Radial basis function neural network is adopted for classification and recognition. Flip chips in three states (good flip chips, flip chips with missing solder bumps and flip chips with open solder bumps) are utilized to validate the proposed method. The results demonstrate that this method is effective for defect inspection in flip chip package.
A hybrid method for image Denoising based on Wavelet Thresholding and RBF network
Sandeep Dubey
2012-06-01
Full Text Available Digital image denoising is crucial part of image pre-processing. The application of denoising process in satellite image data and also in television broadcasting. Image data sets collected by image sensors are generally contaminated by noise. Imperfect instruments, problems with the data acquisition process, and interfering natural phenomena can all degrade the data of interest. Furthermore, noise can be introduced by transmission errors and compression. Thus, denoising is often a necessary and the first step to be taken before the images data is analyzed. In this paper we proposed a novel methodology for image denoising. Image denoising method based on wavelet transform and radial basis neural network and also used concept of soft thresholding. Wavelet transform decomposed image in to different layers, the decomposed layer differentiate by horizontal, vertical and diagonal. For the test of our hybrid method, we used noise image dataset. This data provided by UCI machine learning website. Our proposed method compare with traditional method and our base paper method and getting better comparative result.
Goudarzi, Shidrokh; Haslina Hassan, Wan; Abdalla Hashim, Aisha-Hassan; Soleymani, Seyed Ahmad; Anisi, Mohammad Hossein; Zakaria, Omar M.
2016-01-01
This study aims to design a vertical handover prediction method to minimize unnecessary handovers for a mobile node (MN) during the vertical handover process. This relies on a novel method for the prediction of a received signal strength indicator (RSSI) referred to as IRBF-FFA, which is designed by utilizing the imperialist competition algorithm (ICA) to train the radial basis function (RBF), and by hybridizing with the firefly algorithm (FFA) to predict the optimal solution. The prediction accuracy of the proposed IRBF–FFA model was validated by comparing it to support vector machines (SVMs) and multilayer perceptron (MLP) models. In order to assess the model’s performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results indicate that the IRBF–FFA model provides more precise predictions compared to different ANNs, namely, support vector machines (SVMs) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real-time RSSI measurements. The results also suggest that the IRBF–FFA model can be applied as an efficient technique for the accurate prediction of vertical handover. PMID:27438600
PENG Lei; LIU Li; LONG Teng; GUO Xiaosong
2014-01-01
As a promising technique, surrogate-based design and optimization(SBDO) has been widely used in modern engineering design optimizations. Currently, static surrogate-based optimization methods have been successfully applied to expensive optimization problems. However, due to the low efficiency and poor flexibility, static surrogate-based optimization methods are difficult to efficiently solve practical engineering cases. At the aim of enhancing efficiency, a novel surrogate-based efficient optimization method is developed by using sequential radial basis function(SEO-SRBF). Moreover, augmented Lagrangian multiplier method is adopted to solve the problems involving expensive constraints. In order to study the performance of SEO-SRBF, several numerical benchmark functions and engineering problems are solved by SEO-SRBF and other well-known surrogate-based optimization methods including EGO, MPS, and IARSM. The optimal solutions, number of function evaluations, and algorithm execution time are recorded for comparison. The comparison results demonstrate that SEO-SRBF shows satisfactory performance in both optimization efficiency and global convergence capability. The CPU time required for running SEO-SRBF is dramatically less than that of other algorithms. In the torque arm optimization case using FEA simulation, SEO-SRBF further reduces 21% of thematerial volume compared with the solution from static-RBF subject to the stress constraint. This study provides the efficient strategy to solve expensive constrained optimization problems.
付立思; 何荣卜; 刘朋维
2012-01-01
According to the invariant moment theory, the binary and normalized maize disease images are obtained. A new and better RBF-BP neural network recognition system with the approximation and the fault tolerance is proposed. The Hu invariant moment' s advantages that contain translation, proportion, rotation invariant and good anti-jamming are all used to deal with the complex and changeful maize disease images. According to the invariant moment's reliability, independence, and little number of those characteristics, it can get a better convergence of recognition system to extract the maize image' s features and the training and recognition of RBF-BP neural network. The results of simulation show that the maize disease recognition of RBF-BP neural network has high accuracy and efficiency.%基于不变矩理论,对玉米病害图像进行二值化,图像归一化处理,提出一种新的、具有较好逼近能力和较强容错能力的RBF-BP神经网络识别系统.利用Hu不变矩特征的平移不变性、比例不变性、旋转不变生和对目标良好的抗干扰性等特性,处理复杂、多变的玉米病害图像,形成不变矩特征矢量样本库.根据Hu不变矩在提取图像特征过程中的可靠性、独立性及数目小的特点和RBF-BP神经网络在识别过程中较好收敛性特点,对玉米病害图像进行特征提取、网络训练和病害特征的识别.仿真实验结果表明RBF-BP神经网络系统的有效性.
Committee neural network model for rock permeability prediction
Bagheripour, Parisa
2014-05-01
Quantitative formulation between conventional well log data and rock permeability, undoubtedly the most critical parameter of hydrocarbon reservoir, could be a potent tool for solving problems associated with almost all tasks involved in petroleum engineering. The present study proposes a novel approach in charge of the quest for high-accuracy method of permeability prediction. At the first stage, overlapping of conventional well log data (inputs) was eliminated by means of principal component analysis (PCA). Subsequently, rock permeability was predicted from extracted PCs using multi-layer perceptron (MLP), radial basis function (RBF), and generalized regression neural network (GRNN). Eventually, a committee neural network (CNN) was constructed by virtue of genetic algorithm (GA) to enhance the precision of ultimate permeability prediction. The values of rock permeability, derived from the MPL, RBF, and GRNN models, were used as inputs of CNN. The proposed CNN combines results of different ANNs to reap beneficial advantages of all models and consequently producing more accurate estimations. The GA, embedded in the structure of the CNN assigns a weight factor to each ANN which shows relative involvement of each ANN in overall prediction of rock permeability from PCs of conventional well logs. The proposed methodology was applied in Kangan and Dalan Formations, which are the major carbonate reservoir rocks of South Pars Gas Field-Iran. A group of 350 data points was used to establish the CNN model, and a group of 245 data points was employed to assess the reliability of constructed CNN model. Results showed that the CNN method performed better than individual intelligent systems performing alone.
An electronic system for simulation of neural networks with a micro- second real time constraint
Chorti, A; Denby, B; Garda, P
2001-01-01
Neural networks implemented in hardware can perform pattern recognition very quickly, and as such have been used to advantage in the triggering systems of certain high energy physics experiments. Typically, time constants of the order of a few microseconds are required. We present a new system, MAHARADJA, for evaluating MLP and RBF neural network paradigms in real time. The system is tested on a possible ATLAS muon triggering application suggested by the Tel Aviv ATLAS group, consisting of a 4-8-8-4 MLP which must be evaluated in 10 microseconds. The inputs to the net are dx/dz, x(z=0), dy/dz, and y(z=0), whereas the outputs give pt, tan(phi), sin(theta), and q, the charge. With a 10 MHz clock, MAHARADJA calculates the result in 6.8 microseconds; at 20 MHz, which is readily attainable, this would be reduced to only 3.4 microseconds. The system can also handle RBF networks with 3 different distance metrics (Euclidean, Manhattan and Mahalanobis), and can simulate any MLP of 10 hidden layers or less. The electro...
An improved method using radial basis function neural networks to speed up optimization algorithms
Bazan, M; Russenschuck, Stephan
2002-01-01
The paper presents a method using radial basis function (RBF) neural networks to speed up deterministic search algorithms used for the optimization of superconducting magnets for the LHC accelerator project at CERN. The optimization of the iron yoke of the main LHC dipoles requires a number of numerical field computations per trial solution as the field quality depends on the excitation and local iron saturation in the yoke. This results in computation times of about 30 min for each objective function evaluation (on DEC-Alpha 600 /333). In this paper, we present a method for constructing an RBF neural network for a local approximation of the objective function. The computational time required for such a construction is negligible compared to the deterministic function evaluation, and, thus, yields a speed-up of the overall search process. The effectiveness of this method is demonstrated by means of two- and three-parametric optimization examples. The achieved speed-up of the search routine is up to 30%. (12 r...
Peak Ground Acceleration Prediction by Artificial Neural Networks for Northwestern Turkey
Kemal Günaydın
2008-01-01
Full Text Available Three different artificial neural network (ANN methods, namely, feed-forward back-propagation (FFBP, radial basis function (RBF, and generalized regression neural networks (GRNNs were applied to predict peak ground acceleration (PGA. Ninety five three-component records from 15 ground motions that occurred in Northwestern Turkey between 1999 and 2001 were used during the applications. The earthquake moment magnitude, hypocentral distance, focal depth, and site conditions were used as inputs to estimate PGA for vertical (U-D, east-west (E-W, and north-south (N-S directions. The direction of the maximum PGA of the three components was also added to the input layer to obtain the maximum PGA. Testing stage results of three ANN methods indicated that the FFBPs were superior to the GRNN and the RBF for all directions. The PGA values obtained from the FFBP were modified by linear regression analysis. The results showed that these modifications increased the prediction performances.
An indirect adaptive neural control of a visual-based quadrotor robot for pursuing a moving target.
Shirzadeh, Masoud; Amirkhani, Abdollah; Jalali, Aliakbar; Mosavi, Mohammad R
2015-11-01
This paper aims to use a visual-based control mechanism to control a quadrotor type aerial robot which is in pursuit of a moving target. The nonlinear nature of a quadrotor, on the one hand, and the difficulty of obtaining an exact model for it, on the other hand, constitute two serious challenges in designing a controller for this UAV. A potential solution for such problems is the use of intelligent control methods such as those that rely on artificial neural networks and other similar approaches. In addition to the two mentioned problems, another problem that emerges due to the moving nature of a target is the uncertainty that exists in the target image. By employing an artificial neural network with a Radial Basis Function (RBF) an indirect adaptive neural controller has been designed for a quadrotor robot in search of a moving target. The results of the simulation for different paths show that the quadrotor has efficiently tracked the moving target.
Sang, Hongqiang; Yang, Chenghao; Liu, Fen; Yun, Jintian; Jin, Guoguang
2016-12-01
It is very important for robotically assisted minimally invasive surgery to achieve a high-precision and smooth motion control. However, the surgical instrument tip will exhibit vibration caused by nonlinear friction and unmodeled dynamics, especially when the surgical robot system is attempting low-speed, fine motion. A fuzzy neural network sliding mode controller (FNNSMC) is proposed to suppress vibration of the surgical robotic system. Nonlinear friction and modeling uncertainties are compensated by a Stribeck model, a radial basis function (RBF) neural network and a fuzzy system, respectively. Simulations and experiments were performed on a 3 degree-of-freedom (DOF) minimally invasive surgical robot. The results demonstrate that the FNNSMC is effective and can suppress vibrations at the surgical instrument tip. The proposed FNNSMC can provide a robust performance and suppress the vibrations at the surgical instrument tip, which can enhance the quality and security of surgical procedures. Copyright © 2016 John Wiley & Sons, Ltd.
Estimation of equivalent internal-resistance of PEM fuel cell using artificial neural networks
无
2007-01-01
A practical method of estimation for the internal-resistance of polymer electrolyte membrane fuel cell (PEMFC) stack was adopted based on radial basis function (RBF) neural networks. In the training process, k-means clustering algorithm was applied to select the network centers of the input training data. Furthermore, an equivalent electrical-circuit model with this internal-resistance was developed for investigation on the stack. Finally using the neural networks model of the equivalent resistance in the PEMFC stack, the simulation results of the estimation of equivalent internal-resistance of PEMFC were presented. The results show that this electrical PEMFC model is effective and is suitable for the study of control scheme, fault detection and the engineering analysis of electrical circuits.
Cao, Hui; Li, Yao-Jiang; Zhou, Yan; Wang, Yan-Xia
2014-11-01
To deal with nonlinear characteristics of spectra data for the thermal power plant flue, a nonlinear partial least square (PLS) analysis method with internal model based on neural network is adopted in the paper. The latent variables of the independent variables and the dependent variables are extracted by PLS regression firstly, and then they are used as the inputs and outputs of neural network respectively to build the nonlinear internal model by train process. For spectra data of flue gases of the thermal power plant, PLS, the nonlinear PLS with the internal model of back propagation neural network (BP-NPLS), the non-linear PLS with the internal model of radial basis function neural network (RBF-NPLS) and the nonlinear PLS with the internal model of adaptive fuzzy inference system (ANFIS-NPLS) are compared. The root mean square error of prediction (RMSEP) of sulfur dioxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 16.96%, 16.60% and 19.55% than that of PLS, respectively. The RMSEP of nitric oxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 8.60%, 8.47% and 10.09% than that of PLS, respectively. The RMSEP of nitrogen dioxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 2.11%, 3.91% and 3.97% than that of PLS, respectively. Experimental results show that the nonlinear PLS is more suitable for the quantitative analysis of glue gas than PLS. Moreover, by using neural network function which can realize high approximation of nonlinear characteristics, the nonlinear partial least squares method with internal model mentioned in this paper have well predictive capabilities and robustness, and could deal with the limitations of nonlinear partial least squares method with other internal model such as polynomial and spline functions themselves under a certain extent. ANFIS-NPLS has the best performance with the internal model of adaptive fuzzy inference system having ability to learn more and reduce the residuals effectively. Hence, ANFIS-NPLS is an
Artificial Neural Networks for Diagnosis of Kidney Stones Disease
Koushal Kumar
2012-07-01
Full Text Available Artificial Neural networks are often used as a powerful discriminating classifier for tasks in medical diagnosis for early detection of diseases. They have several advantages over parametric classifiers such as discriminate analysis. The objective of this paper is to diagnose kidney stone disease by using three different neural network algorithms which have different architecture and characteristics. The aim of this work is to compare the performance of all three neural networks on the basis of its accuracy, time taken to build model, and training data set size. We will use Learning vector quantization (LVQ, two layers feed forward perceptron trained with back propagation training algorithm and Radial basis function (RBF networks for diagnosis of kidney stone disease. In this work we used Waikato Environment for Knowledge Analysis (WEKA version 3.7.5 as simulation tool which is an open source tool. The data set we used for diagnosis is real world data with 1000 instances and 8 attributes. In the end part we check the performance comparison of different algorithms to propose the best algorithm for kidney stone diagnosis. So this will helps in early identification of kidney stone in patients and reduces the diagnosis time.
应用RBF网络预测粉煤灰混凝土强度%Application of RBF neural network in strength forecast of fly ash concrete
周瑞林; 刘永建
2001-01-01
介绍了神经网络应用中使用广泛的RBF神经网络的模型及其学习算法,将其用于粉煤灰混凝土强度预测,结果表明,RBF网络方法是一种可以定量分析、简便易行、具有较高精度的预测方法,在混凝土性能预测中具有广阔的应用前景.
基于RBF网络的混凝土抗压强度的预测%Prediction of Concrete Compression Strength Based on RBF Neural Network
王晓伟
2006-01-01
为了预测混凝土的抗压强度,在分析RBF神经网络原理的基础上提出了用RBF神经网络模拟抗压强度与各影响因素间关系的方法.根据搅拌机的实际工作状况,建立了4个输入节点、1个输出节点的RBF神经网络模型,通过19组试验,验证了模型的可靠性.结果表明,实测结果与预测结果相接近,RBF神经网络模型是一种较准确的快速预测混凝土抗压强度的方法.
RBF网络在混凝土强度研究中的应用%Study of Strength of Concrete Using RBF Neural Networks
席剑辉; 韩敏; 王立久
2001-01-01
本文以混凝土抗压强度建模为例,介绍一种自组织学习的RBF算法,并与广受欢迎的BP算法比较.仿真结果表明,RBF网络的学习速度显著加快,并具有较好的泛化能力,能有效地应用于混凝土领域.
基于RBF神经网络的钢筋锈蚀程度预测%Forecast for corrosion of reinforcing steel based on RBF neural network
刘燕; 赵胜利; 易成
2009-01-01
通过分析钢筋锈蚀机理及其影响因素,建立了钢筋锈蚀程度预测的RBF网络模型.通过实例数据进行了分析预测,并与BP网络预测模型进行比较.测试结果表明:应用RBF网络模型对钢筋锈蚀程度进行预测,预测效果好,识别精度高.可见,径向基函数神经网络方法是一种可综合考虑各种影响因素、行之有效的钢筋锈蚀度预测分析方法.
基于正则化RBF神经网络的混凝土强度预测%Prediction of concrete strength based on regular RBF neural network
李钢; 吕国芳
2014-01-01
针对目前混凝土28天强度值的预测需时长、精度低的现状,建立了基于正则化RBF神经网络的混凝土强度预测模型,并运用MATLAB 7.13进行仿真实验.实验结果表明该模型综合考虑了影响混凝土强度的各种因素,能够实现非线性关系,具有较高的预测精度,并且训练速度快,可以节约大量的时间、人力、物力和财力,在混凝土强度预测领域具有广泛的应用前景.
基于RBF网络的商品混凝土强度预测分析%Performance Prediction of Commercial Concrete Based on RBF Neural Network
赵胜利; 刘燕
2005-01-01
提出具有9个输入节点, 1个输出节点的 RBF神经网络模型来模拟抗压强度及其影响因素之间复杂非线性关系.作为对比,作者同时比较了3种不同输入模型的RBF网络的预测效果并与传统的BP网络模型进行比较,结果表明,文章提出的RBF网络模型具有很高的预测精度和较强的泛化能力,可作为商品混凝土性能分析的一种新型有效的方法.
用RBF网络控制非线性系统的混沌运动%Using RBF neural networks for controlling nonlinear chaos
谭文; 周少武; 王耀南; 刘祖润
2002-01-01
设计RBF前向神经网络,以Ott、Grebogi和Yorke混沌控制策略作为训练网络控制算法的基础,通过参数扰动模型输出数据训练网络来产生控制非线性系统的混沌运动必须的小扰动时间序列信号,使其成为混沌控制器,将嵌入在混沌吸引子中不稳定周期轨道镇定到稳定不动点.Hénon映射的数值仿真结果证明该方法十分有效.图6,参7.
基于径向基神经网络的人民币汇率预测%Forecasting RMB Exchange Rate based on RBF Neural Network
周振
2009-01-01
准确预测汇率对经济发展的各方面都有着重要影响.首先说明了径向基神经网络运作的基本原理,探讨了径向基神经网络汇率预测的重要步骤.接着利用径向基神经网络的数值逼近与记忆功能,根据汇率历史观测数值,对人民币的汇率的行为进行预测.实验结果表明,将径向基神经网络用于人民币的预测是可行的和有效的.
Hybrid feedback feedforward: An efficient design of adaptive neural network control.
Pan, Yongping; Liu, Yiqi; Xu, Bin; Yu, Haoyong
2016-04-01
This paper presents an efficient hybrid feedback feedforward (HFF) adaptive approximation-based control (AAC) strategy for a class of uncertain Euler-Lagrange systems. The control structure includes a proportional-derivative (PD) control term in the feedback loop and a radial-basis-function (RBF) neural network (NN) in the feedforward loop, which mimics the human motor learning control mechanism. At the presence of discontinuous friction, a sigmoid-jump-function NN is incorporated to improve control performance. The major difference of the proposed HFF-AAC design from the traditional feedback AAC (FB-AAC) design is that only desired outputs, rather than both tracking errors and desired outputs, are applied as RBF-NN inputs. Yet, such a slight modification leads to several attractive properties of HFF-AAC, including the convenient choice of an approximation domain, the decrease of the number of RBF-NN inputs, and semiglobal practical asymptotic stability dominated by control gains. Compared with previous HFF-AAC approaches, the proposed approach possesses the following two distinctive features: (i) all above attractive properties are achieved by a much simpler control scheme; (ii) the bounds of plant uncertainties are not required to be known. Consequently, the proposed approach guarantees a minimum configuration of the control structure and a minimum requirement of plant knowledge for the AAC design, which leads to a sharp decrease of implementation cost in terms of hardware selection, algorithm realization and system debugging. Simulation results have demonstrated that the proposed HFF-AAC can perform as good as or even better than the traditional FB-AAC under much simpler control synthesis and much lower computational cost.
Robust nonlinear system identification using neural-network models.
Lu, S; Basar, T
1998-01-01
We study the problem of identification for nonlinear systems in the presence of unknown driving noise, using both feedforward multilayer neural network and radial basis function network models. Our objective is to resolve the difficulty associated with the persistency of excitation condition inherent to the standard schemes in the neural identification literature. This difficulty is circumvented here by a novel formulation and by using a new class of identification algorithms recently obtained by Didinsky et al. We show how these algorithms can be exploited to successfully identify the nonlinearity in the system using neural-network models. By embedding the original problem in one with noise-perturbed state measurements, we present a class of identifiers (under L1 and L2 cost criteria) which secure a good approximant for the system nonlinearity provided that some global optimization technique is used. In this respect, many available learning algorithms in the current neural-network literature, e.g., the backpropagation scheme and the genetic algorithms-based scheme, with slight modifications, can ensure the identification of the system nonlinearity. Subsequently, we address the same problem under a third, worst case L(infinity) criterion for an RBF modeling. We present a neural-network version of an H(infinity)-based identification algorithm from Didinsky et al and show how, along with an appropriate choice of control input to enhance excitation, under both full-state-derivative information (FSDI) and noise-perturbed full-state-information (NPFSI), it leads to satisfaction of a relevant persistency of excitation condition, and thereby to robust identification of the nonlinearity. Results from several simulation studies have been included to demonstrate the effectiveness of these algorithms.
de Castro, Ana-Isabel; Jurado-Expósito, Montserrat; Gómez-Casero, María-Teresa; López-Granados, Francisca
2012-01-01
In the context of detection of weeds in crops for site-specific weed control, on-ground spectral reflectance measurements are the first step to determine the potential of remote spectral data to classify weeds and crops. Field studies were conducted for four years at different locations in Spain. We aimed to distinguish cruciferous weeds in wheat and broad bean crops, using hyperspectral and multispectral readings in the visible and near-infrared spectrum. To identify differences in reflectance between cruciferous weeds, we applied three classification methods: stepwise discriminant (STEPDISC) analysis and two neural networks, specifically, multilayer perceptron (MLP) and radial basis function (RBF). Hyperspectral and multispectral signatures of cruciferous weeds, and wheat and broad bean crops can be classified using STEPDISC analysis, and MLP and RBF neural networks with different success, being the MLP model the most accurate with 100%, or higher than 98.1%, of classification performance for all the years. Classification accuracy from hyperspectral signatures was similar to that from multispectral and spectral indices, suggesting that little advantage would be obtained by using more expensive airborne hyperspectral imagery. Therefore, for next investigations, we recommend using multispectral remote imagery to explore whether they can potentially discriminate these weeds and crops. PMID:22629171
Ana-Isabel de Castro
2012-01-01
Full Text Available In the context of detection of weeds in crops for site-specific weed control, on-ground spectral reflectance measurements are the first step to determine the potential of remote spectral data to classify weeds and crops. Field studies were conducted for four years at different locations in Spain. We aimed to distinguish cruciferous weeds in wheat and broad bean crops, using hyperspectral and multispectral readings in the visible and near-infrared spectrum. To identify differences in reflectance between cruciferous weeds, we applied three classification methods: stepwise discriminant (STEPDISC analysis and two neural networks, specifically, multilayer perceptron (MLP and radial basis function (RBF. Hyperspectral and multispectral signatures of cruciferous weeds, and wheat and broad bean crops can be classified using STEPDISC analysis, and MLP and RBF neural networks with different success, being the MLP model the most accurate with 100%, or higher than 98.1%, of classification performance for all the years. Classification accuracy from hyperspectral signatures was similar to that from multispectral and spectral indices, suggesting that little advantage would be obtained by using more expensive airborne hyperspectral imagery. Therefore, for next investigations, we recommend using multispectral remote imagery to explore whether they can potentially discriminate these weeds and crops.
de Castro, Ana-Isabel; Jurado-Expósito, Montserrat; Gómez-Casero, María-Teresa; López-Granados, Francisca
2012-01-01
In the context of detection of weeds in crops for site-specific weed control, on-ground spectral reflectance measurements are the first step to determine the potential of remote spectral data to classify weeds and crops. Field studies were conducted for four years at different locations in Spain. We aimed to distinguish cruciferous weeds in wheat and broad bean crops, using hyperspectral and multispectral readings in the visible and near-infrared spectrum. To identify differences in reflectance between cruciferous weeds, we applied three classification methods: stepwise discriminant (STEPDISC) analysis and two neural networks, specifically, multilayer perceptron (MLP) and radial basis function (RBF). Hyperspectral and multispectral signatures of cruciferous weeds, and wheat and broad bean crops can be classified using STEPDISC analysis, and MLP and RBF neural networks with different success, being the MLP model the most accurate with 100%, or higher than 98.1%, of classification performance for all the years. Classification accuracy from hyperspectral signatures was similar to that from multispectral and spectral indices, suggesting that little advantage would be obtained by using more expensive airborne hyperspectral imagery. Therefore, for next investigations, we recommend using multispectral remote imagery to explore whether they can potentially discriminate these weeds and crops.
Adaptive neural sliding mode control for TCP networks%TCP网络的自适应神经滑模控制
叶成荫; 井元伟
2012-01-01
针对TCP网络的拥塞控制问题,考虑了TCP负载和往返时延具有较大的突发性和时变性的情况,结合滑模控制与RBF神经网络提出了一种主动队列管理算法.考虑到网络系统参数是未知时变的,采用RBF神经网络逼近网络系统参数,从而使得主动队列管理算法易于实现.依据李雅普诺夫稳定性理论设计了RBF神经网络权值的自适应律,使得网络系统参数得到了较好的估计.采用RBF神经网络的输出作为滑模控制器的参数设计了一种主动队列管理算法,使得网络系统是渐近稳定的.仿真结果表明所提出的算法与比例积分控制器和传统的滑模控制器相比具有较快的响应和稳定的队列长度,在网络参数变化时仍能获得较好的鲁棒性.%To save the problem of congestion control in transmission control protocol (TCP) networks, by incorporating sliding mode control with radial basis function ( RBF) neural networks, an active queue management algorithm is presented in presence of TCP load and round trip time which are more abrupt and time-varying. Since network system parameters are unknown and time-varying, the RBF neural networks were used to approximate the network system parameters so that the active queue management algorithm was easily implemented. The network system parameters are well estimated by updating the RBF neural network weights according to Lyapunov theory. By using the output of the RBF neural network as the sliding mode controller parameters, an active queue management algorithm was designed to guarantee the network system was asymptotically stable. Compared with proportional-integral controller and conventional sliding mode controller, simulation results show that the proposed algorithm has fast system response and steady queue length as well as better robustness under various network conditions.
Lukas Falat
2016-01-01
Full Text Available This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.
Falat, Lukas; Marcek, Dusan; Durisova, Maria
2016-01-01
This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.
徐桂云; 蒋恒深; 李辉; 阮殿旭
2012-01-01
为了减少基于无线传感器网络（WSN）的轴承故障诊断系统数据传输总量和网络负载同时提高故障诊断准确性,提出一种采用主元分析（PCA）与径向基（RBF）神经网络结合轴承数据的融合与故障诊断算法.首先建立基于LEACH协议的3层融合模型,然后簇首节点采用PCA对大量多传感器数据降维,最后Sink节点采用RBF对数据进行决策级融合.仿真结果表明：该算法3个成员节点各上传10个数据包,簇头节点融合后剩余4个,融合率为86.7%,每组故障识别准确率大于85%.该算法具有很好的识别率和高压缩率,能够很好应用于煤矿设备故障监测.%In order to reduce data quantity and wireless sensor network(WSN) load of bearing fault diagnosis system used by wireless sensor and increase accuracy of fault diagnosis, this research proposes a WSN devices based on monitor system, the principal component analysis (PCA) and radial basis (RBF) artificial neural networks as a data fusion diagnosis algorithm. Firstly a 3-layer data fusion model based on LEACH is established, and then dimension reduc- tion of sensor data is operated by cluster header node, and lastly sink node accomplish decision- level fusion of data. Simulation results show that 3 member transmits 10 data packets respec- tively, while only 4 packets are remained after data fusion by sink node, so data fusion ratio is 86.7%, and accuracy of fault diagnosis is 85 %. The algorithm with a good recognition rate and high compression ratio can be well applied in fault monitoring of the equipment for coal mine.
Chen, Jiajia; Zhao, Pan; Liang, Huawei; Mei, Tao
2014-09-18
The autonomous vehicle is an automated system equipped with features like environment perception, decision-making, motion planning, and control and execution technology. Navigating in an unstructured and complex environment is a huge challenge for autonomous vehicles, due to the irregular shape of road, the requirement of real-time planning, and the nonholonomic constraints of vehicle. This paper presents a motion planning method, based on the Radial Basis Function (RBF) neural network, to guide the autonomous vehicle in unstructured environments. The proposed algorithm extracts the drivable region from the perception grid map based on the global path, which is available in the road network. The sample points are randomly selected in the drivable region, and a gradient descent method is used to train the RBF network. The parameters of the motion-planning algorithm are verified through the simulation and experiment. It is observed that the proposed approach produces a flexible, smooth, and safe path that can fit any road shape. The method is implemented on autonomous vehicle and verified against many outdoor scenes; furthermore, a comparison of proposed method with the existing well-known Rapidly-exploring Random Tree (RRT) method is presented. The experimental results show that the proposed method is highly effective in planning the vehicle path and offers better motion quality.
Mustakim Mustakim
2016-02-01
Full Text Available The largest region that produces oil palm in Indonesia has an important role in improving the welfare of society and economy. Oil palm has increased significantly in Riau Province in every period, to determine the production development for the next few years with the functions and benefits of oil palm carried prediction production results that were seen from time series data last 8 years (2005-2013. In its prediction implementation, it was done by comparing the performance of Support Vector Regression (SVR method and Artificial Neural Network (ANN. From the experiment, SVR produced the best model compared with ANN. It is indicated by the correlation coefficient of 95% and 6% for MSE in the kernel Radial Basis Function (RBF, whereas ANN produced only 74% for R2 and 9% for MSE on the 8th experiment with hiden neuron 20 and learning rate 0,1. SVR model generates predictions for next 3 years which increased between 3% - 6% from actual data and RBF model predictions.
M. Safish Mary
2012-04-01
Full Text Available Classification of large amount of data is a time consuming process but crucial for analysis and decision making. Radial Basis Function networks are widely used for classification and regression analysis. In this paper, we have studied the performance of RBF neural networks to classify the sales of cars based on the demand, using kernel density estimation algorithm which produces classification accuracy comparable to data classification accuracy provided by support vector machines. In this paper, we have proposed a new instance based data selection method where redundant instances are removed with help of a threshold thus improving the time complexity with improved classification accuracy. The instance based selection of the data set will help reduce the number of clusters formed thereby reduces the number of centers considered for building the RBF network. Further the efficiency of the training is improved by applying a hierarchical clustering technique to reduce the number of clusters formed at every step. The paper explains the algorithm used for classification and for conditioning the data. It also explains the complexities involved in classification of sales data for analysis and decision-making.
Application of artificial neural networks to a study of nursing burnout.
Ladstätter, F; Garrosa, E; Badea, C; Moreno, B
2010-09-01
Nursing is generally considered to be a profession with high levels of emotional and physical stress that tend to increase. These high stress levels lead to a high risk of burnout. The objective was to assess whether artificial neural network (ANN) paradigms offer greater predictive accuracy than statistical methodologies, which are commonly used in the field of burnout. A radial basis function (RBF) network and hierarchical stepwise regression was used to assess burnout. The comparison of the two methodologies was carried out by analysing a sample of 462 nurses and student nurses. The subjects were from three hospitals in Madrid (Spain), who completed the 'Nursing Burnout Scale' survey. A RBF network was better suited for the analysis of burnout than hierarchical stepwise regression. The outcomes indicate furthermore that the relationship with the burnout process of the predictive variables age, job status, workload, experience with pain and death, conflictive interaction, role ambiguity and hardy personality is not entirely linear. The usage of ANNs in the field of burnout has been justified due to their superior ability to capture non-linear relationships, which is relevant for theory development. STATEMENT OF RELEVANCE: Due to the superior ability to capture non-linear relationships, ANNs are better suited to explain and predict burnout and its subdimensions than common statistical methods. From this perspective, more specific programmes to prevent burnout and its consequences in the workplace can be designed.
Amozegar, M; Khorasani, K
2016-04-01
In this paper, a new approach for Fault Detection and Isolation (FDI) of gas turbine engines is proposed by developing an ensemble of dynamic neural network identifiers. For health monitoring of the gas turbine engine, its dynamics is first identified by constructing three separate or individual dynamic neural network architectures. Specifically, a dynamic multi-layer perceptron (MLP), a dynamic radial-basis function (RBF) neural network, and a dynamic support vector machine (SVM) are trained to individually identify and represent the gas turbine engine dynamics. Next, three ensemble-based techniques are developed to represent the gas turbine engine dynamics, namely, two heterogeneous ensemble models and one homogeneous ensemble model. It is first shown that all ensemble approaches do significantly improve the overall performance and accuracy of the developed system identification scheme when compared to each of the stand-alone solutions. The best selected stand-alone model (i.e., the dynamic RBF network) and the best selected ensemble architecture (i.e., the heterogeneous ensemble) in terms of their performances in achieving an accurate system identification are then selected for solving the FDI task. The required residual signals are generated by using both a single model-based solution and an ensemble-based solution under various gas turbine engine health conditions. Our extensive simulation studies demonstrate that the fault detection and isolation task achieved by using the residuals that are obtained from the dynamic ensemble scheme results in a significantly more accurate and reliable performance as illustrated through detailed quantitative confusion matrix analysis and comparative studies.
Schwindling Jerome
2010-04-01
Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.
FGF Signaling Transforms Non-neural Ectoderm into Neural Crest
Yardley, Nathan; García-Castro, Martín I.
2012-01-01
The neural crest arises at the border between the neural plate and the adjacent non-neural ectoderm. It has been suggested that both neural and non-neural ectoderm can contribute to the neural crest. Several studies have examined the molecular mechanisms that regulate neural crest induction in neuralized tissues or the neural plate border. Here, using the chick as a model system, we address the molecular mechanisms by which non-neural ectoderm generates neural crest. We report that in respons...
周洪煜; 杜学森; 张振华; 黄耀珍
2015-01-01
In the circulating water waste heat recovery system, when heat pump heating net water outlet temperature trace heating load demand, that’s not only adjusted by driven steam capacity, and is easily influenced by operating conditions variation of the heating net backwater and circulating water, the traditional PID control method has a large overshoot volume and a poor load tracking ability. So a chaotic particle clone selection (CPCS)-radial basis function (RBF) direct multi-step predictive control strategy was proposed, with difference between heat pump heat supply network water outlet temperature predicted value and the set values as the objective function, using CPCS optimization algorithm to calculate the optimal values of driven steam when the objective function is the minimum. The prediction model was constructed by two RBF neural networks according to the field operation data in order to improve the model variable condition adaptability. The experimental results show that the control strategy can comprehensively learn the change of the parameters such as the heating net backwater temperature and circulating water temperature, and make driven steam tone act in advance, trace heating load demand change in time, and adapt fluctuation of exhaust gas residual heat under power generation load change, so has better energy saving effect and variable condition adaptability.%循环水余热回收系统中，热泵热网水出口温度在跟踪供热负荷需求时，在受驱动蒸汽量的调节的同时，往往易受热网回水、循环水等工况变化的影响，传统 PID 控制方式超调量大、负荷跟踪能力差。提出一种混沌变异克隆选择−径向基函数(CPCS-RBF)直接多步预测控制策略，以热泵热网水出口温度预测值与设定值差值为目标函数，利用CPCS优化算法求取目标函数最小时的驱动蒸汽最佳值。预测模型由2个RBF神经网络结合热泵现场运行数据构建，以提高热泵系统
Vonk, E.; Jain, L.C.; Veelenturf, L.P.J.
1995-01-01
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas
Mellit, A. [Univ. Center of Medea, Inst. of Engineering Sciences, Ain Dahab (Algeria); Benghanem, M. [Univ. of Sciences and Technology Houari Boumediene (USTHB), Faculty of Electrical Engineering, Algiers (Algeria); Arab, A. Hadj [Development Center of Renewable Energy (CDER), Algiers (Algeria); CIEMAT, Dept. de Energias Renerables, Madrid (Spain); Guessoum, A. [Ministry for the Higher Education and Scientific Research, Algiers (Algeria)
2005-08-01
In this paper we investigate, the possibility of using an adaptive Artificial Neural Network (ANN), in order to find a suitable model for sizing Stand-Alone Photovoltaic (SAPV) systems, based on a minimum of input data. The model combines Radial Basis Function (RBF) network and Infinite Impulse Response (IIR) filter in order to accelerate the convergence of the network. For the sizing of a photovoltaic (PV) systems, we need to determine the optimal sizing coefficients (K{sub PV}, K{sub B}). These coefficients allow us to determine the number of solar panels and storage batteries necessary to satisfy a given consumption, especially in isolated sites where the global solar radiation data is not always available. These coefficients are considered the most important parameters for sizing a PV system. Results obtained by classical models (analytical, numerical, analytical-numerical, B-spline function) and new models like feed-forward (MLP), radial basis function (RBF), MLP-IIR and RBF-IIR are compared with experimental sizing coefficients in order to illustrate the accuracy of the new developed model. This model has been trained by using 200 known optimal sizing coefficients corresponding to 200 locations in Algeria. In this way, the adaptive model was trained to accept and handle a number of unusual cases. The unknown validation sizing coefficients set produced very accurate estimation with a correlation coefficient of 98%. This result indicates that the proposed method can be successfully used for the estimation of optimal sizing coefficients of SAPV systems for any locations in Algeria. The methodology proposed in this paper however, can be generalized using different locations of the world. (Author)
Prediction of fMRI time series of a single voxel using radial basis function neural network
Song, Sutao; Zhang, Jiacai; Yao, Li
2011-03-01
A great deal of current literature regarding functional neuroimaging has elucidated the relationships of neurons distributed all over the brain. Modern neuroimaging techniques, such as the functional MRI (fMRI), provide a convenient tool for people to study the correlation among different voxels as well as the spatio-temporal patterns of brain activity. In this study, we present a computational model using radial basis function neural network (RBF-NN) to predict the fMRI voxel activation with the activation of other voxels acquired at the same time. The fMRI data from a visual images stimuli presentation experiment was separated into two sets; one was used to train the model, and the other to validate the accuracy or generalizability of the model. In the visual stimuli presentation experiment, the subject did simple one-back-repetition tasks when four categories of stimuli (houses, faces, cars, and cats) were presented. Voxel sets A and B were selected from fMRI data by two different voxel selection criterion: (1) Voxel set A are those activated for any kind of object stronger than the other three objects in regions of interest (ROIs) without correction (P=0.001); (2) Voxel set B are those activated for at least one of the categories of stimuli within the ROIs (FWE correction, P=0.05). RBF-NN regression models construct the nonlinear relationship between the activation of voxels in A and B. Our test results showed that RBF-NN can capture the nonlinear relationship existing in neurons and reveal the relationship between voxel's activation from different brain regions.
Application of Artificial Neural Networks for Efficient High-Resolution 2D DOA Estimation
M. Agatonović
2012-12-01
Full Text Available A novel method to provide high-resolution Two-Dimensional Direction of Arrival (2D DOA estimation employing Artificial Neural Networks (ANNs is presented in this paper. The observed space is divided into azimuth and elevation sectors. Multilayer Perceptron (MLP neural networks are employed to detect the presence of a source in a sector while Radial Basis Function (RBF neural networks are utilized for DOA estimation. It is shown that a number of appropriately trained neural networks can be successfully used for the high-resolution DOA estimation of narrowband sources in both azimuth and elevation. The training time of each smaller network is significantly re¬duced as different training sets are used for networks in detection and estimation stage. By avoiding the spectral search, the proposed method is suitable for real-time ap¬plications as it provides DOA estimates in a matter of seconds. At the same time, it demonstrates the accuracy comparable to that of the super-resolution 2D MUSIC algorithm.
Zhu Guoqiang
2015-01-01
Full Text Available An adaptive neural control scheme is proposed for a class of generic hypersonic flight vehicles. The main advantages of the proposed scheme include the following: (1 a new constraint variable is defined to generate the virtual control that forces the tracking error to fall within prescribed boundaries; (2 RBF NNs are employed to compensate for complex and uncertain terms to solve the problem of controller complexity; (3 only one parameter needs to be updated online at each design step, which significantly reduces the computational burden. It is proved that all signals of the closed-loop system are uniformly ultimately bounded. Simulation results are presented to illustrate the effectiveness of the proposed scheme.
Implementation of neural network hardware based on a floating point operation in an FPGA
Kim, Jeong-Seob; Jung, Seul
2007-12-01
This paper presents a hardware design and implementation of the radial basis function (RBF) neural network (NN) by the hardware description language. Due to its nonlinear characteristics, it is very difficult to implement for a system with integer-based operation. To develop nonlinear functions such sigmoid functions or exponential functions, floating point operations are required. The exponential function is designed based on the 32bit single-precision floating-point format. In addition, to update weights in the network, the back-propagation algorithm is also implemented in the hardware. Most operations are performed in the floating-point based arithmetic unit and accomplished sequentially by the instruction order stored in ROM. The NN is implemented and tested on the Altera FPGA "Cyclone2 EP2C70F672C8" for nonlinear classifications.
Lihua Yang
2015-04-01
Full Text Available Export volume forecasting of fresh fruits is a complex task due to the large number of factors affecting the demand. In order to guide the fruit growers’ sales, decreasing the cultivating cost and increasing their incomes, a hybrid fresh apple export volume forecasting model is proposed. Using the actual data of fresh apple export volume, the Seasonal Decomposition (SD model of time series and Radial Basis Function (RBF model of artificial neural network are built. The predictive results are compared among the three forecasting model based on the criterion of Mean Absolute Percentage Error (MAPE. The result indicates that the proposed combined forecasting model is effective because it can improve the prediction accuracy of fresh apple export volumes.
Evaluation of Starting Current of Induction Motors Using Artificial Neural Network
Iman Sadeghkhani
2014-07-01
Full Text Available Induction motors (IMs are widely used in industry including it be an electrical or not. However during starting period, their starting currents are so large that can damage equipment. Therefore, this current should be estimated accurately to prevent hazards caused by it. In this paper, the artificial neural network (ANN as an intelligent tool is used to evaluate starting current peak of IMs. Both Multilayer Perceptron (MLP and Radial Basis Function (RBF structures have been analyzed. Six learning algorithms, backpropagation (BP, delta-bar-delta (DBD, extended delta-bar-delta (EDBD, directed random search (DRS, quick propagation (QP, and levenberg marquardt (LM were used to train the MLP. The simulation results using MATLAB show that most developed ANNs can estimate the starting current peak of IMs with good accuracy. However, it is proven that LM and EDBD algorithms present better performance for starting current evaluation based on average of relative and absolute errors.
Nandkumar Wagh
2014-01-01
Full Text Available Continuity of power supply is of utmost importance to the consumers and is only possible by coordination and reliable operation of power system components. Power transformer is such a prime equipment of the transmission and distribution system and needs to be continuously monitored for its well-being. Since ratio methods cannot provide correct diagnosis due to the borderline problems and the probability of existence of multiple faults, artificial intelligence could be the best approach. Dissolved gas analysis (DGA interpretation may provide an insight into the developing incipient faults and is adopted as the preliminary diagnosis tool. In the proposed work, a comparison of the diagnosis ability of backpropagation (BP, radial basis function (RBF neural network, and adaptive neurofuzzy inference system (ANFIS has been investigated and the diagnosis results in terms of error measure, accuracy, network training time, and number of iterations are presented.
苏义鑫; 夏慧雯
2016-01-01
为了提高风电功率预测的准确度,提出了一种基于对手竞争惩罚学习算法( rival penalized competitive learning,RPCL)优化径向基函数( radial basis function,RBF)神经网络的风电功率预测模型。首先通过RPCL确定网络隐含层神经元数目以及中心点初始值,然后由K均值聚类法确定隐含层神经元的中心点和宽度,最后通过最小均值算法确定隐含层神经元与输出层神经元之间的权值。仿真结果表明：此优化模型相较于传统RBF网络具有更高的准确性。%For increasing the accuracy of wind power forecasting, a rival penalized competitive learning-based radial basis function ( RBF) neural network model was presented. Firstly the number of neural network hidden-layer-nodes and its initial center values were determined by rival penalized competitive learning. And then the width of RBF and the center values of network were identified accurately through K-means clustering. At last, appropriate weights of network were estimated by least mean square. The forecasting result shows that the presented model can lead to more accurate forecasting compared with the traditional neural network.
P. N. Kumar
2010-11-01
Full Text Available This paper outlines a methodology for aiding the decision making process for investment between two financial market assets (eg a risky asset versus a risk-free asset, using neural network architecture. A Feed Forward Neural Network (FFNN and a Radial Basis Function (RBF Network have been evaluated. The model is employed for arriving at a decision as to where to invest in the next time step, given data from the current time step. The time step could be chosen on daily/weekly/monthly basis, based on the investment requirement. In this study, the FFNN has yielded good results over RBF. Consequently the FFNN developed enable us make a decision on investment in the next time step between a risky asset (eg the BSE Sensex itself or a single share versus a risk-free asset (eg Securities like Govt Bonds, Public Provident Funds etc.The FFNN is trained with a set of data which helps in understanding the market behaviour. The input parameters or the information set consisting of six items is arrived at by considering important empirical features acting on real markets. These are designed to allow both passive and active, fundamental and technical trading strategies, and combinations of these. Using just six items simplifies the decision making process by extracting potentially useful information from the large quantity of historic data. The prediction made by the FFNN model has been validated from the actual market data. This model can be further extended to choose between any two categories of assets whose historical data is available.
Nath, Sankar; Kotal, S. D.; Kundu, P. K.
2016-12-01
Three artificial neural network (ANN) methods, namely, multilayer perceptron (MLP), radial basis function (RBF) and generalized regression neural network (GRNN) are utilized to predict the seasonal tropical cyclone (TC) activity over the north Indian Ocean (NIO) during the post-monsoon season (October, November, December). The frequency of TC and large-scale climate variables derived from NCEP/NCAR reanalysis dataset of resolution 2.5° × 2.5° were analyzed for the period 1971-2013. Data for the years 1971-2002 were used for the development of the models, which were tested with independent sample data for the year 2003-2013. Using the correlation analysis, the five large-scale climate variables, namely, geopotential height at 500 hPa, relative humidity at 500 hPa, sea-level pressure, zonal wind at 700 hPa and 200 hPa for the preceding month September, are selected as potential predictors of the post-monsoon season TC activity. The result reveals that all the three different ANN methods are able to provide satisfactory forecast in terms of the various metrics, such as root mean-square error (RMSE), standard deviation (SD), correlation coefficient ( r), and bias and index of agreement ( d). Additionally, leave-one-out cross validation (LOOCV) method is also performed and the forecast skill is evaluated. The results show that the MLP model is found to be superior to the other two models (RBF, GRNN). The (MLP) is expected to be very useful to operational forecasters for prediction of TC activity.
ZHANG Song-tao; REN Guang
2006-01-01
This study presents an adaptive fuzzy neural network (FNN) control system for the ship steering autopilot. For the Norrbin ship steering mathematical model with the nonlinear and uncertain dynamic characteristics, an adaptive FNN control system is designed to achieve high-precision track control via the backstepping approach. In the adaptive FNN control system, a FNN backstepping controller is a principal controller which includes a FNN estimator used to estimate the uncertainties, and a robust controller is designed to compensate the shortcoming of the FNN backstepping controller. All adaptive learning algorithms in the adaptive FNN control system are derived from the sense of Lyapunov stability analysis, so that system-tracking stability can be guaranteed in the closed-loop system. The effectiveness of the proposed adaptive FNN control system is verified by simulation results.
运用DE-RBFNN的直线伺服系统定位精度研究%Positioning accuracy study of linear servo system based on DE-RBFNN
林健; 黄家才; 陈桂
2012-01-01
提出一种基于差分进化算法(DE)的径向基函数神经网络(RBFNN)模型,用于预测直线伺服系统的定位误差.该模型用差分进化算法训练径向基函数(RBF)网络隐层中心位置、宽度和输出层连接权重.为了评价优化后RBF网络预测的精度,运用部分误差样本进行训练和仿真.构建了以数字信号处理器(DSP)为核心的直线电动机定位误差实验平台,根据误差校正值进行误差实时补偿实验.仿真和实验结果表明:经过DE算法训练的神经网络模型对工作台的误差具有良好的学习能力和泛化能力,与单纯RBF网络、基于遗传优化的RBF神经网络相比,该建模方法具有更高的定位精度.%A novel Radial Basis Function Neural Network(RBFNN) model based on learning algorithm Differential Evolution ( DE) is proposed to predict the positioning error of linear Bervo system. The DE algorithm automatically adjusts the width and positions of hidden layer RBF centers as well as the weights of output layer. In order to evaluate the accuracy of optimized RBF network prediction method,part of the error samples are used to train and simulate. A DSP-core linear motor positioning error experimental platform was built, the error compensation experiments are conducted. Hie simulation and experimental results indicate that RBFNN error model trained by the DE algorithm has a good learning ability and a generalization ability,the DE-RBFNN possesses superior positioning accuracy than RBFNN,GA-RBFNN.
Structure of RBF with long and short term memory based on field knowledge%基于先验知识的长短记忆RBF网络结构
韩丽; 史丽萍; 徐治皋
2008-01-01
提出了一种基于先验知识的RBF-LSFM(RBF with Long and Short Term Memory)网络结构.该网络将专业背景知识引入到神经网络的结构构造中,提出了具有长短期记忆功能的网络结构.同时引入了剪枝理论,使网络具有更精简的结构.将这种网络结构应用于热工过程中过热气温动态特性建模,仿真结果表明该神经网络模型具有较高的建模精度以及泛化能力.
Wei Zhang
2016-06-01
Full Text Available In the aerospace and aviation sectors, the damage tolerance concept has been applied widely so that the modeling analysis of fatigue crack growth has become more and more significant. Since the process of crack propagation is highly nonlinear and determined by many factors, such as applied stress, plastic zone in the crack tip, length of the crack, etc., it is difficult to build up a general and flexible explicit function to accurately quantify this complicated relationship. Fortunately, the artificial neural network (ANN is considered a powerful tool for establishing the nonlinear multivariate projection which shows potential in handling the fatigue crack problem. In this paper, a novel fatigue crack calculation algorithm based on a radial basis function (RBF-ANN is proposed to study this relationship from the experimental data. In addition, a parameter called the equivalent stress intensity factor is also employed as training data to account for loading interaction effects. The testing data is then placed under constant amplitude loading with different stress ratios or overloads used for model validation. Moreover, the Forman and Wheeler equations are also adopted to compare with our proposed algorithm. The current investigation shows that the ANN-based approach can deliver a better agreement with the experimental data than the other two models, which supports that the RBF-ANN has nontrivial advantages in handling the fatigue crack growth problem. Furthermore, it implies that the proposed algorithm is possibly a sophisticated and promising method to compute fatigue crack growth in terms of loading interaction effects.
Neural Induction, Neural Fate Stabilization, and Neural Stem Cells
Sally A. Moody
2002-01-01
Full Text Available The promise of stem cell therapy is expected to greatly benefit the treatment of neurodegenerative diseases. An underlying biological reason for the progressive functional losses associated with these diseases is the extremely low natural rate of self-repair in the nervous system. Although the mature CNS harbors a limited number of self-renewing stem cells, these make a significant contribution to only a few areas of brain. Therefore, it is particularly important to understand how to manipulate embryonic stem cells and adult neural stem cells so their descendants can repopulate and functionally repair damaged brain regions. A large knowledge base has been gathered about the normal processes of neural development. The time has come for this information to be applied to the problems of obtaining sufficient, neurally committed stem cells for clinical use. In this article we review the process of neural induction, by which the embryonic ectodermal cells are directed to form the neural plate, and the process of neural�fate stabilization, by which neural plate cells expand in number and consolidate their neural fate. We will present the current knowledge of the transcription factors and signaling molecules that are known to be involved in these processes. We will discuss how these factors may be relevant to manipulating embryonic stem cells to express a neural fate and to produce large numbers of neurally committed, yet undifferentiated, stem cells for transplantation therapies.
Curvature estimation of Point-Sampled model based on RBF%基于RBF的点模型曲率估算
张利军; 张若男
2016-01-01
Curvature estimation of point model is the basic work of the point geometry processing , which plays an important role in the follow-up works, such as point clouds simplification and feature extraction, etc. Based on radial basis functions (RBF), an algorithm is presented for effectively estimating curvatures on point-sampled model in this paper. Firstly, the nearest neighbors of each sampled point are quickly found by using kD-tree. Then, the local implicit surface of sampled point that approximates its nearest neighbors is reconstructed based on RBF. Finally, the curvatures of sampled point are estimated by applying the classical differential geometry theory to each implicit surface and their application is given in the point clouds simplification. Some experimental results demonstrated that the method could accurately estimate the curvatures on point sampled model and be effectively applied.%点模型的曲率等微分属性的估算是点模型数字几何处理的基础工作，在点模型数字几何处理的后续工作，如点云简化、特征提取等方面发挥着非常重要的作用。为了较准确地估算点模型的曲率，文章提出一种基于径向基函数（RBF）的点模型曲率估算方法。首先利用kD树，对点模型采样点的最近邻域进行快速搜索；然后基于RBF，对采样点的最近邻域进行局部隐式曲面重构；最后根据经典微分几何理论，在RBF重构曲面上进行曲率估算，同时文章给出了该方法在点云简化中的应用。实验结果表明，该方法对点模型采样点曲率的估算比较精确，并且成功在点云简化中得以应用。
陈龙宪
2012-01-01
As the RBF network can approach any model with any precision,we put forward an adaptive Controller of Robot Based on RBF Network with uncertainty of model approximation.The RBF network can greatly accelerate the learning speed and avoid local minima problems,suitable for real-time control requirements.The simulation results show that the control algorithm has strong robustness and superior tracking capability.%利用RBF网络能以任意精度逼近任意的连续函数的特点,设计一种基于模型不确定逼近RBF网络机器人的自适应控制器。采用RBF网络可以大大加快学习速度,并避免局部极小问题,适合于实时控制要求。仿真结果表明,该控制算法具有较强的鲁棒性和较好的跟踪性。
Wenshuang Chang
2013-09-01
Full Text Available Stress corrosion cracks (SCC in low-pressure steam turbine discs are serious hidden dangers to production safety in the power plants, and knowing the orientation and depth of the initial cracks is essential for the evaluation of the crack growth rate, propagation direction and working life of the turbine disc. In this paper, a method based on phased array ultrasonic transducer and artificial neural network (ANN, is proposed to estimate both the depth and orientation of initial cracks in the turbine discs. Echo signals from cracks with different depths and orientations were collected by a phased array ultrasonic transducer, and the feature vectors were extracted by wavelet packet, fractal technology and peak amplitude methods. The radial basis function (RBF neural network was investigated and used in this application. The final results demonstrated that the method presented was efficient in crack estimation tasks.
Yang, Xiaoxia; Chen, Shili; Jin, Shijiu; Chang, Wenshuang
2013-09-13
Stress corrosion cracks (SCC) in low-pressure steam turbine discs are serious hidden dangers to production safety in the power plants, and knowing the orientation and depth of the initial cracks is essential for the evaluation of the crack growth rate, propagation direction and working life of the turbine disc. In this paper, a method based on phased array ultrasonic transducer and artificial neural network (ANN), is proposed to estimate both the depth and orientation of initial cracks in the turbine discs. Echo signals from cracks with different depths and orientations were collected by a phased array ultrasonic transducer, and the feature vectors were extracted by wavelet packet, fractal technology and peak amplitude methods. The radial basis function (RBF) neural network was investigated and used in this application. The final results demonstrated that the method presented was efficient in crack estimation tasks.
Izzet Y Önel; K Burak Dalci; İbrahim Senol
2006-06-01
This paper investigates the application of induction motor stator current signature analysis (MCSA) using Park’s transform for the detection of rolling element bearing damages in three-phase induction motor. The paper ﬁrst discusses bearing faults and Park’s transform, and then gives a brief overview of the radial basis function (RBF) neural networks algorithm. Finally, system information and the experimental results are presented. Data acquisition and Park’s transform algorithm are achieved by using LabVIEW and the neural network algorithm is achieved by using MATLAB programming language. Experimental results show that it is possible to detect bearing damage in induction motors using an ANN algorithm.
Short-term Wind Power Forecast Based on Ridgelet Neural Network%基于脊波神经网络的短期风电功率预测
茆美琴; 周松林; 苏建徽
2011-01-01
对风电功率进行较为准确的预测是提高电力系统运行安全性与经济性的有效手段.在分析脊波神经网络原理的基础上,将其应用于风速、风向及风电功率预测.首先建立预测模型分别预测风速及风向,再采用非线性神经网络实现对实际功率曲线的逼近,最后根据风速预测值和实际功率拟合曲线计算功率预测值.仿真结果表明,采用脊波神经网络预测方法相对于小波神经网络、反向传播(BP)神经网络和径向基函数(RBF)神经网络方法,其风电功率预测结果准确性能得到提高.%Fairly accurate forecast of wind power is an effective means for improving power system security and economy. Based on an analysis of the principle of the ridgelet neural network, the network is applied to the forecast of wind speed, wind direction and wind power. Two forecast models are developed to predict wind speed and wind direction, respectively, and the nonlinear neural network is applied to the approximation of an actual power curve. Finally, the wind power is calculated according to the forecasted wind speed, wind direction and the power fitting curve. Simulation results show that, compared with the wavelet neural network, BP neural network and RBF neural network, the ridgelet neural network is found to yield a higher accuracy of wind power forecast than all the other three.
周峰; 葛锁良; 项琼; 张军
2006-01-01
针对大时滞及过程不确定的工业过程对象,提出一种PID神经网络控制方法,利用BP网络自整定学习,使PID参数实现最佳的非线性组合,克服了常规PID算法不适应大时滞及过程不确定系统的缺陷,大大提高了控制系统的鲁棒性.仿真研究和工程应用表明,本文控制方法容易实现,并且具有很强的鲁棒性和良好的控制品质.
Using RBF to Enable Circuit Emulation Service over Internet%采用RBF来支撑互联网络上的电路模拟服务
金涬; 张斌; 赵阳; 王庆波; 陈滢
2009-01-01
Circuit Emulation Service(CES)aims to enable packet switched networks to provide guaranteed services with comparable qualities of circuit switched networks.Our paper addresses the key issue of QoS of CES flows over Internet.Enlightened by the time division idea popularly used in circuit switched networks,we propose a time division based control mechanism to provide guaranteed QoS for the constant-rate CES flows.The control mechanism is able to estimate the arrival times of the coming packets in CES flows,and reserve the time slots for them.ACCOrdingly.it enables the packets to consume the reserved time slots of their own,so the CES flows are guaranteed to be processed.Refreshing Bloom Filter(RBF),an efficient data representation structure,is proposed to support the time division control mechanism.It consists of multiple bloom filters,and can efficiently record the arrival time slots of millions of packets.The proposed control system model could be a practical tool to support Circuit Emulation Services over Intemet.
林健; 汪木兰; 李宏胜
2011-01-01
针对数控直线伺服系统的定位误差补偿,采用激光干涉仪测量工作台的定位误差,建立基于RBF算法的神经网络误差模型.提出遗传算法的训练方案优化RBF的网络参数,为了评价优化后RBF网络预测的精度,运用部分误差样本进行训练和仿真.构建了以DSP为核心的直线电机定位误差实验平台,根据误差校正值进行误差实时补偿实验.仿真和实验结果表明:经过遗传算法训练的神经网络模型对工作台的误差具有良好的学习能力和泛化能力,工作台定位精度显著提高.%In view of the positioning error compensation of NC linear servo system, the positioning errors were measured by the laser interferometer, the neural network error model is set up by Radial Basis Function (RBF) algorithm.The training method of the genetic algorithm is also proposed to optimize the network parameters, in order to evaluate the accuracy of RBF network prediction method,part of the error samples are used to train and simulate.A DSP-core linear motor positioning error experimental platform was built, the error compensation experiments are conducted.The simulation and experimental results indicate that the RBF neural network error model trained by the genetic algorithm has a good learning ability and a generalization ability, the positioning accuracy is improved significantly.
Ritter, G.X.; Sussner, P. [Univ. of Florida, Gainesville, FL (United States)
1996-12-31
The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.
Neural tube defects are birth defects of the brain, spine, or spinal cord. They happen in the ... that she is pregnant. The two most common neural tube defects are spina bifida and anencephaly. In ...
Chung-Ming Kuan
2006-01-01
Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods.
Lei Wang; Cheng Shao; Hai Wang; Hong Wu
2006-01-01
Membrane technology has found wide applications in the petrochemical industry, mainly in the purification and recovery of the hydrogen resources. Accurate prediction of the membrane separation performance plays an important role in carrying out advanced process control (APC). For the first time, a soft-sensor model for the membrane separation process has been established based on the radial basis function (RBF) neural networks. The main performance parameters, i.e, permeate hydrogen concentration, permeate gas flux, and residue hydrogen concentration, are estimated quantitatively by measuring the operating temperature, feed-side pressure, permeate-side pressure, residue-side pressure, feed-gas flux, and feed-hydrogen concentration excluding flow structure, membrane parameters, and other compositions. The predicted results can gain the desired effects. The effectiveness of this novel approach lays a foundation for integrating control technology and optimizing the operation of the gas membrane separation process.
Rong Cheng
2015-06-01
Full Text Available In this paper, a novel self-creating disk-cell-splitting (SCDCS algorithm is proposed for training the radial wavelet neural network (RWNN model. Combining with the least square (LS method which determines the linear weight coefficients, SCDCS can create neurons adaptively on a disk according to the distribution of input data and learning goals. As a result, a disk map is made for input data as well as a RWNN model with proper architecture and parameters can be decided for the recognition task. The proposed SCDCS-LS based RWNN model is employed for the recognition of license plate characters. Compared to the classical radial-basis-function (RBF network with K-means clustering and LS, the proposed model can make a better recognition performance even with fewer neurons.
Constructive neural network learning
Lin, Shaobo; Zeng, Jinshan; Zhang, Xiaoqin
2016-01-01
In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of "constructive neural networks" in approximation theory, we focus on "constructing" rather than "training" feed-forward neural networks (FNNs) for learning, and propose a novel FNNs learning system called the constructive feed-forward neural network (CFN). Theoretically, we prove that the proposed method not only overcomes the classical saturation problem for FNN approximation, but also ...
BIALEK, W; RIEKE, F; VANSTEVENINCK, RRD; WARLAND, D
1991-01-01
Traditional approaches to neural coding characterize the encoding of known stimuli in average neural responses. Organisms face nearly the opposite task - extracting information about an unknown time-dependent stimulus from short segments of a spike train. Here the neural code was characterized from
Generalized classifier neural network.
Ozyildirim, Buse Melis; Avci, Mutlu
2013-03-01
In this work a new radial basis function based classification neural network named as generalized classifier neural network, is proposed. The proposed generalized classifier neural network has five layers, unlike other radial basis function based neural networks such as generalized regression neural network and probabilistic neural network. They are input, pattern, summation, normalization and output layers. In addition to topological difference, the proposed neural network has gradient descent based optimization of smoothing parameter approach and diverge effect term added calculation improvements. Diverge effect term is an improvement on summation layer calculation to supply additional separation ability and flexibility. Performance of generalized classifier neural network is compared with that of the probabilistic neural network, multilayer perceptron algorithm and radial basis function neural network on 9 different data sets and with that of generalized regression neural network on 3 different data sets include only two classes in MATLAB environment. Better classification performance up to %89 is observed. Improved classification performances proved the effectivity of the proposed neural network.
孔慧芳; 段锐; 鲍伟
2015-01-01
为了提高双离合器自动变速器（dual‐clutch transmission ，DCT ）电控系统故障诊断精度，文章提出了一种基于神经网络和证据理论的DCT电控系统故障诊断方法。该方法首先分别用BP神经网络和RBF神经网络对DC T电控系统进行故障诊断，然后利用D‐S证据理论将两者的诊断结果进行决策融合，得出最终的诊断结果。仿真结果表明，该方法能够有效提高DC T电控系统故障诊断的精度。%In order to improve the fault diagnosis accuracy of dual‐clutch transmission(DCT ) electronic control system ,a fault diagnosis scheme based on neural network and D‐S evidence theory is devel‐oped .Both the fault diagnosis based on BP neural network and based on RBF neural network of DCT electronic control system are studied .Then the D‐S evidence theory is applied to fusing the diagnosis results of BP neural network and RBF neural network .The simulation results are presented to demon‐strate the validity and effectiveness of the fault diagnosis scheme .
宋江腾; 曾攀; 赵加清; 李聪聪
2011-01-01
司太立(Stellite)合金是一种能耐各种类型磨损、腐蚀以及高温氧化的硬质合金.为研究其磨损性能,以Stellite6为例,在自行设计的摩擦磨损机上进行室温干摩擦和润滑条件下的磨损实验.以实验数据为基础,建立该合金磨损量的RBF神经网络预测模型.结果表明:RBF神经网络预测模型具有较好的收敛效果和预测精度,具有良好的应用前景.%The stellite alloys are hard alloys which can resist various wear,corrosion and oxidation at high temperature.In order to study the wearing behaviors of the stellite alloys, wear tests were carried out in the condition of dry friction and lubrication under room temperature by using a serf-designed tribometer. According to the experimental results, a RBF neural network model was proposed to predict the wear loss of stellite alloys. The results show that the RBF neural network has good application prospects for good convergence effect and prediction accuracy.
尤文坚; 梁兵; 李荫军
2013-01-01
In view of problem that eddy-current sensor cannot reflect measured physical quantity accurately caused by higher nonlinear of output characteristic parameter, the paper proposed a scheme of using RBF neural network to fit output characteristic parameter of eddy-current sensor. The scheme uses newrb function to create RBF neural network, and takes measured physical quantity as input matrix and output of eddy-current sensor as output matrix to train the RBF neural network, so as to obtain low root-mean-square error and smooth output characteristic fitting curve of eddy-current sensor. The simulation result showed that RBF neural network can effectively realize fitting of output characteristic of eddy-current sensor by selecting proper creating function and expanding coefficient.%针对电涡流传感器的输出特性参数非线性较大,不能精确地反映被测物理量的问题,提出了一种采用径向基神经网络对电涡流传感器的输出特性参数进行拟合的方案.该方案采用newrb函数创建一个径向基神经网络,以被测物理量作为输入矩阵、电涡流传感器输出电压作为输出矩阵,对该径向基神经网络进行训练,从而可得到均方根误差小且光滑的电涡流传感器输出特性拟合曲线.实验结果表明,只要选择合适的创建函数和扩展系数,径向基神经网络能有效地实现电涡流传感器输出特性的拟合.
Neural induction and factors that stabilize a neural fate
Rogers, Crystal; Moody, Sally A.; Casey, Elena
2009-01-01
The neural ectoderm of vertebrates forms when the BMP signaling pathway is suppressed. Herein we review the molecules that directly antagonize extracellular BMP and the signaling pathways that further contribute to reduce BMP activity in the neural ectoderm. Downstream of neural induction, a large number of “neural fate stabilizing” (NFS) transcription factors are expressed in the presumptive neural ectoderm, developing neural tube, and ultimately in neural stem cells. Herein we review what i...
Consciousness and neural plasticity
In contemporary consciousness studies the phenomenon of neural plasticity has received little attention despite the fact that neural plasticity is of still increased interest in neuroscience. We will, however, argue that neural plasticity could be of great importance to consciousness studies....... If consciousness is related to neural processes it seems, at least prima facie, that the ability of the neural structures to change should be reflected in a theory of this relationship "Neural plasticity" refers to the fact that the brain can change due to its own activity. The brain is not static but rather...... the relation between consciousness and brain functions. If consciousness is connected to specific brain structures (as a function or in identity) what happens to consciousness when those specific underlying structures change? It is therefore possible that the understanding and theories of neural plasticity can...
O Uso de Famílias de Circuitos e Rede Neural Artificial para Previsão de Demanda de Energia Elétrica
José Leomar Todesco
2004-08-01
denominado método indireto de previsão da carga, e dele decorrem todos os cálculos elétricos do circuito para aferir seu desempenho quanto à qualidade dos níveis de tensão, do carregamento dos equipamentos e condutores, do balanceamento da carga, bem como das perdas elétricas. Este artigo apresenta uma proposta de estudo das famílias de circuitos (residencial, comercial, industrial, rural, público e outros utilizando informações sobre o consumo de energia através da aplicação de algoritmos de clustering e, posteriormente, da aplicação de uma Rede Neural Artificial (RNA para a aproximação das curvas de demanda para as famílias identificadas. A RNA utilizada foi a Radial Basis Function (RBF, por ser um aproximador universal. São também apresentados no artigo testes comparativos realizados com o modelo de regressão linear simples e a RBF.
Chaotic diagonal recurrent neural network
Wang Xing-Yuan; Zhang Yi
2012-01-01
We propose a novel neural network based on a diagonal recurrent neural network and chaos,and its structure andlearning algorithm are designed.The multilayer feedforward neural network,diagonal recurrent neural network,and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map.The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.
Evolvable Neural Software System
Curtis, Steven A.
2009-01-01
The Evolvable Neural Software System (ENSS) is composed of sets of Neural Basis Functions (NBFs), which can be totally autonomously created and removed according to the changing needs and requirements of the software system. The resulting structure is both hierarchical and self-similar in that a given set of NBFs may have a ruler NBF, which in turn communicates with other sets of NBFs. These sets of NBFs may function as nodes to a ruler node, which are also NBF constructs. In this manner, the synthetic neural system can exhibit the complexity, three-dimensional connectivity, and adaptability of biological neural systems. An added advantage of ENSS over a natural neural system is its ability to modify its core genetic code in response to environmental changes as reflected in needs and requirements. The neural system is fully adaptive and evolvable and is trainable before release. It continues to rewire itself while on the job. The NBF is a unique, bilevel intelligence neural system composed of a higher-level heuristic neural system (HNS) and a lower-level, autonomic neural system (ANS). Taken together, the HNS and the ANS give each NBF the complete capabilities of a biological neural system to match sensory inputs to actions. Another feature of the NBF is the Evolvable Neural Interface (ENI), which links the HNS and ANS. The ENI solves the interface problem between these two systems by actively adapting and evolving from a primitive initial state (a Neural Thread) to a complicated, operational ENI and successfully adapting to a training sequence of sensory input. This simulates the adaptation of a biological neural system in a developmental phase. Within the greater multi-NBF and multi-node ENSS, self-similar ENI s provide the basis for inter-NBF and inter-node connectivity.
Application of radial basis neural network for state estimation of ...
user
conventional Weighted Least Squares (WLS) State Estimator on basis of time, ... The conventional state estimation is based on algorithmic method of solving a large ... The RBF unit or transfer function is similar to Gaussian density function, ...
Bayesian adaptive combination of short-term wind speed forecasts from neural network models
Li, Gong; Shi, Jing; Zhou, Junyi [Department of Industrial and Manufacturing Engineering, North Dakota State University, Dept. 2485, PO Box 6050, Fargo, ND 58108 (United States)
2011-01-15
Short-term wind speed forecasting is of great importance for wind farm operations and the integration of wind energy into the power grid system. Adaptive and reliable methods and techniques of wind speed forecasts are urgently needed in view of the stochastic nature of wind resource varying from time to time and from site to site. This paper presents a robust two-step methodology for accurate wind speed forecasting based on Bayesian combination algorithm, and three neural network models, namely, adaptive linear element network (ADALINE), backpropagation (BP) network, and radial basis function (RBF) network. The hourly average wind speed data from two North Dakota sites are used to demonstrate the effectiveness of the proposed approach. The results indicate that, while the performances of the neural networks are not consistent in forecasting 1-h-ahead wind speed for the two sites or under different evaluation metrics, the Bayesian combination method can always provide adaptive, reliable and comparatively accurate forecast results. The proposed methodology provides a unified approach to tackle the challenging model selection issue in wind speed forecasting. (author)
Garg, A. [Department of Mechanical Engineering, Indian Institute of Technology Guwahati, Guwahati 781039, Assam (India); Sastry, P.S. [Department of Mechanical Engineering, Indian Institute of Technology Guwahati, Guwahati 781039, Assam (India); Pandey, M. [Department of Mechanical Engineering, Indian Institute of Technology Guwahati, Guwahati 781039, Assam (India)]. E-mail: manmohan@iitg.ac.in; Dixit, U.S. [Department of Mechanical Engineering, Indian Institute of Technology Guwahati, Guwahati 781039, Assam (India); Gupta, S.K. [Atomic Energy Regulatory Board, Mumbai 400085 (India)
2007-02-15
Numerical simulation of natural circulation boiling water reactor is important in order to study its performance for different designs and under various off-design conditions. Numerical simulations can be performed by using thermal-hydraulic codes. Very fast numerical simulations, useful for extensive parametric studies and for solving design optimization problems, can be achieved by using an artificial neural network (ANN) model of the system. In the present work, numerical simulations of natural circulation boiling water reactor have been performed with RELAP5 code for different values of design parameters and operational conditions. Parametric trends observed have been discussed. The data obtained from these simulations have been used to train artificial neural networks, which in turn have been used for further parametric studies and design optimization. The ANN models showed error within {+-}5% for all the simulated data. Two most popular methods, multilayer perceptron (MLP) and radial basis function (RBF) networks, have been used for the training of ANN model. Sequential quadratic programming (SQP) has been used for optimization.
Jørgensen, Ivan Harald Holger; Bogason, Gudmundur; Bruun, Erik
1995-01-01
This paper proposes a new way to estimate the flow in a micromechanical flow channel. A neural network is used to estimate the delay of random temperature fluctuations induced in a fluid. The design and implementation of a hardware efficient neural flow estimator is described. The system...... is implemented using switched-current technique and is capable of estimating flow in the μl/s range. The neural estimator is built around a multiplierless neural network, containing 96 synaptic weights which are updated using the LMS1-algorithm. An experimental chip has been designed that operates at 5 V...
Federal Laboratory Consortium — As part of the Electrical and Computer Engineering Department and The Institute for System Research, the Neural Systems Laboratory studies the functionality of the...
Signal processing and neural network toolbox and its application to failure diagnosis and prognosis
Tu, Fang; Wen, Fang; Willett, Peter K.; Pattipati, Krishna R.; Jordan, Eric H.
2001-07-01
Many systems are comprised of components equipped with self-testing capability; however, if the system is complex involving feedback and the self-testing itself may occasionally be faulty, tracing faults to a single or multiple causes is difficult. Moreover, many sensors are incapable of reliable decision-making on their own. In such cases, a signal processing front-end that can match inference needs will be very helpful. The work is concerned with providing an object-oriented simulation environment for signal processing and neural network-based fault diagnosis and prognosis. In the toolbox, we implemented a wide range of spectral and statistical manipulation methods such as filters, harmonic analyzers, transient detectors, and multi-resolution decomposition to extract features for failure events from data collected by data sensors. Then we evaluated multiple learning paradigms for general classification, diagnosis and prognosis. The network models evaluated include Restricted Coulomb Energy (RCE) Neural Network, Learning Vector Quantization (LVQ), Decision Trees (C4.5), Fuzzy Adaptive Resonance Theory (FuzzyArtmap), Linear Discriminant Rule (LDR), Quadratic Discriminant Rule (QDR), Radial Basis Functions (RBF), Multiple Layer Perceptrons (MLP) and Single Layer Perceptrons (SLP). Validation techniques, such as N-fold cross-validation and bootstrap techniques, are employed for evaluating the robustness of network models. The trained networks are evaluated for their performance using test data on the basis of percent error rates obtained via cross-validation, time efficiency, generalization ability to unseen faults. Finally, the usage of neural networks for the prediction of residual life of turbine blades with thermal barrier coatings is described and the results are shown. The neural network toolbox has also been applied to fault diagnosis in mixed-signal circuits.
Dehghan, Mehdi; Mohammadi, Vahid
2017-08-01
In this research, we investigate the numerical solution of nonlinear Schrödinger equations in two and three dimensions. The numerical meshless method which will be used here is RBF-FD technique. The main advantage of this method is the approximation of the required derivatives based on finite difference technique at each local-support domain as Ωi. At each Ωi, we require to solve a small linear system of algebraic equations with a conditionally positive definite matrix of order 1 (interpolation matrix). This scheme is efficient and its computational cost is same as the moving least squares (MLS) approximation. A challengeable issue is choosing suitable shape parameter for interpolation matrix in this way. In order to overcome this matter, an algorithm which was established by Sarra (2012), will be applied. This algorithm computes the condition number of the local interpolation matrix using the singular value decomposition (SVD) for obtaining the smallest and largest singular values of that matrix. Moreover, an explicit method based on Runge-Kutta formula of fourth-order accuracy will be applied for approximating the time variable. It also decreases the computational costs at each time step since we will not solve a nonlinear system. On the other hand, to compare RBF-FD method with another meshless technique, the moving kriging least squares (MKLS) approximation is considered for the studied model. Our results demonstrate the ability of the present approach for solving the applicable model which is investigated in the current research work.
Neural Networks: Implementations and Applications
Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.
1996-01-01
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas
Neural Networks: Implementations and Applications
Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.
1996-01-01
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas
... NICHD Research Information Clinical Trials Resources and Publications Neural Tube Defects (NTDs): Condition Information Skip sharing on social media links Share this: Page Content What are neural tube defects? Neural (pronounced NOOR-uhl ) tube defects are ...
Ahmadi Azqhandi, M H; Ghaedi, M; Yousefi, F; Jamshidi, M
2017-11-01
Two machine learning approach (i.e. Radial Basis Function Neural Network (RBF-NN) and Random Forest (RF) was developed and evaluated against a quadratic response surface model to predict the maximum removal efficiency of brilliant green (BG) from aqueous media in relation to BG concentration (4-20mgL(-1)), sonication time (2-6min) and ZnS-NP-AC mass (0.010-0.030g) by ultrasound-assisted. All three (i.e. RBF network, RF and polynomial) model were compared against the experimental data using four statistical indices namely, coefficient of determination (R(2)), root mean square error (RMSE), mean absolute error (MAE) and absolute average deviation (AAD). Graphical plots were also used for model comparison. The obtained results using RBF network and RF exhibit a better performance in comparison to classical statistical model for both dyes. The significant factors were optimized using desirability function approach (DFA) combined central composite design (CCD) and genetic algorithm (GA) approach. The obtained optimal point was located in the valid region and the experimental confirmation tests were conducted showing a good accordance between the predicted optimal points and the experimental data. The properties of ZnS-NPs-AC were identified by X-ray diffraction; field emission scanning electron microscopy, energy dispersive X-ray spectroscopy (EDS) and Fourier transformation infrared spectroscopy. Various isotherm models for fitting the experimental equilibrium data were studied and Langmuir model was chosen as an efficient model. Various kinetic models for analysis of experimental adsorption data were studied and pseudo second order model was chosen as an efficient model. Moreover, ZnS nanoparticles loaded on activated carbon efficiently were regenerated using methanol and after five cycles the removal percentage do not change significantly. Copyright © 2017 Elsevier Inc. All rights reserved.
张殷钦; 刘俊民; 郝健
2011-01-01
【目的】建立地下水位预测的正则化RBF网络模型,为区域地下水资源的利用、规划和管理提供决策依据。【方法】以MATLAB7.0为平台,用函数newrb创建正则化RBF网络模型,基于宝鸡峡灌区B210号观测井1983-2009年的地下水位埋深资料,对网络模型进行训练后再用测试集检验,分别绘制训练集与测试集的拟合曲线,同时计算实测值与预测值间的相对误差（RE）、平均绝对偏差（MAD）和均方误差（MSE）,并将其与BP网络模型的相应值进行对比。【结果】正则化RBF网络模型和BP网络模型的相对误差均小于5%,平均绝对偏差分别为0.53和0.85,均方误差分别为0.54和1.15,相比之下,正则化RBF网络模型的预测精度更高。【结论】训练样本和测试样本的合理选取为时间序列的拟合扩展了思路,良好的泛化能力使正则化RBF网络模型在区域地下水位预测中具有一定的可行性。%【Objective】 Establishing regularized RBF network model for groundwater level prediction can provide strategic decision for groundwater use,planning and management.【Method】 Regularized RBF network model was built employing newrb function in MATLAB7.0 for well B210 in Baojixia irrigation area based on the groundwater level depth data from 1983 to 2009.The training sets and testing sets were used to train and test the network respectively.Corresponding fitting curve was plotted as well.Meanwhile,relative error（RE）,mean absolute deviation（MAD） and mean-square error（MSE） between predicted and measured values were all calculated and the comparison was addressed with BP network model.【Result】 RE of both regularized RBF and BP network model is less than 5%,MAD is 0.53 and 0.85,MSE is 0.54 and 1.15 respectively.By contrast,the precision of regularized RBF network model about predicted values is much higher.【Conclusion】 Selecting training sample and testing sample reasonably has provided a new
Neural network-based adaptive optimal control of a robot hydraulic actuator%机器人液压驱动器神经网络自适应最优控制
孙广彬; 王宏
2015-01-01
In order to effectively control the hydraulic nonlinear systems, a radial basis function (RBF) neural network‐based optimal control applied to the robot hydraulic actuator was presented. First, the hydraulic servo system was modeled based on the physics of the plant. Second, the Kalman filter was applied to estimate the internal state of the system with continuously changing magnitude and frequency of input signal. The model parameters were calculated and grouped for RBF neural net‐work training. Third, with the average of each group of parameters as nominal point, the RBF neural network was used to learn the rules how feedback gains changes with system parameters. Finally, the trained neural network was used to predict the feedback gains on line based on the parameter estimate of Kalman Filter and the trained adaptive controller. The proposed controller was validated by experi‐ment with setting time and tracking error to be 1/2 and 1/3 of the conventional linear quadratic requla‐tor controller, respectively.%为了有效地控制液压非线性系统，提出基于RB F神经网络的自适应最优控制系统，应用于机器人液压驱动器。首先，建立了液压系统的动力学模型；然后，输入幅值和频率连续变化的信号，应用卡尔曼滤波器估计液压系统状态，进而计算出模型参数，对模型参数进行分组用于训练RB F神经网络；接着，对不同组参数求平均作为参考点，用RB F神经网络学习最优控制器反馈增益随系统参数的变化规律；最后，训练完成的神经网络根据卡尔曼滤波器参数估计值在线预测并调节控制器增益。经实验验证，该控制系统调节时间和跟踪误差仅为普通线性二次型最优控制器的1／2和1／3左右。
Hørning, Annette
1994-01-01
Artiklen beskæftiger sig med muligheden for at anvende kunstige neurale net i forbindelse med datamatisk procession af naturligt sprog, specielt automatisk talegenkendelse.......Artiklen beskæftiger sig med muligheden for at anvende kunstige neurale net i forbindelse med datamatisk procession af naturligt sprog, specielt automatisk talegenkendelse....
Critical Branching Neural Networks
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
Consciousness and neural plasticity
changes or to abandon the strong identity thesis altogether. Were one to pursue a theory according to which consciousness is not an epiphenomenon to brain processes, consciousness may in fact affect its own neural basis. The neural correlate of consciousness is often seen as a stable structure, that is...
Critical Branching Neural Networks
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
Pani, Ajaya Kumar; Mohanta, Hare Krishna
2015-05-01
Particle size soft sensing in cement mills will be largely helpful in maintaining desired cement fineness or Blaine. Despite the growing use of vertical roller mills (VRM) for clinker grinding, very few research work is available on VRM modeling. This article reports the design of three types of feed forward neural network models and least square support vector regression (LS-SVR) model of a VRM for online monitoring of cement fineness based on mill data collected from a cement plant. In the data pre-processing step, a comparative study of the various outlier detection algorithms has been performed. Subsequently, for model development, the advantage of algorithm based data splitting over random selection is presented. The training data set obtained by use of Kennard-Stone maximal intra distance criterion (CADEX algorithm) was used for development of LS-SVR, back propagation neural network, radial basis function neural network and generalized regression neural network models. Simulation results show that resilient back propagation model performs better than RBF network, regression network and LS-SVR model. Model implementation has been done in SIMULINK platform showing the online detection of abnormal data and real time estimation of cement Blaine from the knowledge of the input variables. Finally, closed loop study shows how the model can be effectively utilized for maintaining cement fineness at desired value.
Hamid Heydari Gholanlo
2016-06-01
In this study, a radial basis function neural network (RBFNN improved by genetic algorithm has been employed to estimate formation water saturation by using conventional well-logging data. The used logging and core data have been gathered from a carbonated formation from one of oilfield located in south-west Iran, and finally their results of the proposed model were compared with the core analysis results. By checking the testing data from another well, it showed this method had a 0.027 for mean square errors and its correlation coefficient is equal to 0.870. These results implied on high accuracy of this model for oil saturation degree estimation. While the common methods like Archie, had a 0.041 mean square error and 0.720 of the correlation coefficient, which indicate a high ability of RBF model than the other usual empirical methods.
Modeling and Optimization of Microwave Circuits Based on Neural Networks%基于神经网络的微波电路建模与优化
刘荧; 林嘉宇; 毛钧杰
2000-01-01
本文讨论用神经网络对微波电路进行建模、优化。借助电磁场理论计算或基于实际测量，可得到微波电路的输入、输出样本数据，从而可训练神经网络，在兼顾它的推广性能的基础上，对微波电路建模。进一步，通过优化神经网络对应参数，可优化微波电路。文章用RBF(RadialBasis Function)神经网络对微带变阻器建模、优化，以此为例，进行了较为详细的阐述。%[1] A.H. Zaabab. et al. A neural network model ing approach to circuit optimization and statis tical design, IEEE Trans. MTT , 1995; 43 (6): 1349～1358. [2] P.M. Watson,K. C. Gupta. EM-ANN models for microstrip vias and interconnects in dataset circuits. IEEE Trans. MTT, 1996; 44(12): 2495～2503. [3] P.M. Watson,K. C. Gupta. Design and opti mization of CPW circuits using EM-ANN models for CPW components. IEEE Trans. MTT, 1997 ； 45(12): 2515～2535. [4] D.C. Montgomery. Design and Analysis of Experiments. New York :Wiley, 1991. [5] Acosta F. RBF and related models: an overview. Signal Processing, 1995; 45:37～ 58. ［6] D.R. Huh,B. G. Horne. Progress in super- vised neural networks :what′.s new since lipp mann?. IEEE SP Magazine, 1993 ；10(1 ):8～ 39. [7] J. Park,I. Sandberg. Approximation and RBF networks. Neural Comput, 1993; 5:305～316. ［8] S. Chen,et al. Orthogonal least squares learn ing algorithm for radial basis function net works. IEEE Trans. Neural Networks, 1991; 2(2) :302～309. [9] 陈尚勤，李晓峰．快速自适应信息处理．北京：人民邮电出版社，1993． [10] I. Cha, S. A. Kassam. Channel equalization using adaptive complex radial basis function networks. IEEE J. SAC, 1995;13(1):122 ～131. [11] E.S. Chng, et al. Orthogonal least－square learning algorithm with local adaptation pro cess for the radial basis function networks. IEEE SP Letters, 1996；3(8):253～255. [12] M.J. Orr. Local Smoothing of RBF Net works. http://www. cns. ed. ac. uk/people/ mark
Is neural Darwinism Darwinism?
van Belle, T
1997-01-01
Neural Darwinism is a theory of cognition developed by Gerald Edelman along with George Reeke and Olaf Sporns at Rockefeller University. As its name suggests, neural Darwinism is modeled after biological Darwinism, and its authors assert that the two processes are strongly analogous. both operate on variation in a population, amplifying the more adaptive individuals. However, from a computational perspective, neural Darwinism is quite different from other models of natural selection, such as genetic algorithms. The individuals of neural Darwinism do not replicate, thus robbing the process of the capacity to explore new solutions over time and ultimately reducing it to a random search. Because neural Darwinism does not have the computational power of a truly Darwinian process, it is misleading to label it as such. to illustrate this disparity in adaptive power, one of Edelman's early computer experiments, Darwin I, is revisited, and it is shown that adding replication greatly improves the adaptive power of the system.
李璞; 冯博
2016-01-01
With the rapid development of China's science and technology industry , the rapid development of science and technology industry , machinery automation , computer control system and the continuous development of the measurement industry , making the research of mobile robot has reached an unprecedented level , the robot has been widely used in ag-ricultural production ,industrial production ,National security ,life services and higher research design and other aspects of the design .As a part of the robot ,the mobile robot has concentrated the research results of intelligent sensing technology , mechanical manufacturing ,electronic communication technology ,intelligent instrument and automation control engineering . It is one of the most advanced technology research and design .In this paper , based on genetic algorithm to optimize the RBF network approximation algorithm , based on the characteristics of the robot motion trajectory , the robot motion trajec-tory control technology is studied .Through the real-time sensor online perception system , the robot can plan a trajectory without collision and route .The experimental results show that the design and research of the robot motion trajectory opti-mization technology , with good control effect , which can effectively avoid the obstacles in the course of the road , its reli-ability , good stability , the application prospect is very broad .%随着国力的不断增长，我国科技产业发展突飞猛进，机械自动化、计算机控制系统和测试计量行业的不断发展，使得移动机器人的研究也达到了一个前所未有的高度，机器人已经被广泛地应用到农业生产、工业生产、国家安全、生活服务和高等研究设计等领域的各个方面。移动机器人作为机器人的一部分，集中了智能传感技术、机械制造、电子无线通信技术、智能仪器和自动化控制工程等多学科的研究成果，是当前科技研究与设计最前沿
Dai, Xiaoyan; Guo, Zhongyang; Zhang, Liquan; Xu, Wencheng
2009-12-01
Soft classification methods can be used for mixed-pixel classification on remote sensing imagery by estimating different land cover class fractions of every pixel. However, the spatial distribution and location of these class components within the pixel remain unknown. To map land cover at subpixel scale and increase the spatial resolution of land cover classification maps, in this paper, a prediction model combining wavelet transform and Radial Basis Functions (RBF) neural network, abbreviated as Wavelet-RBFNN, is constructed by predicting high-frequency wavelet coefficients from low-frequency coefficients at the same resolution with RBF network and taking wavelet coefficients at coarser resolution as training samples. According to different land cover class fraction images obtained from mixed-pixel classification, based on the assumption of neighborhood dependence of wavelet coefficients, subpixel mapping on remote sensing imagery can be accomplished through two steps, i.e., prediction of land cover class compositions within subpixels and hard classification. The experimental results obtained with artificial images, QuickBird image and Landsat 7 ETM+ image indicate that the subpixel mapping method proposed in this paper can successfully produce super-resolution land cover classification maps from remote sensing imagery, outperforming cubic B-spline and Kriging interpolation method in visual effect and prediction accuracy. The Wavelet-RBFNN model can also be applied to simulate higher spatial resolution image, and automatically identify and locate land cover targets at the subpixel scales, when the cost and availability of high resolution imagery prohibit its use in many areas of work.
Dynamics of neural cryptography.
Ruttor, Andreas; Kinzel, Wolfgang; Kanter, Ido
2007-05-01
Synchronization of neural networks has been used for public channel protocols in cryptography. In the case of tree parity machines the dynamics of both bidirectional synchronization and unidirectional learning is driven by attractive and repulsive stochastic forces. Thus it can be described well by a random walk model for the overlap between participating neural networks. For that purpose transition probabilities and scaling laws for the step sizes are derived analytically. Both these calculations as well as numerical simulations show that bidirectional interaction leads to full synchronization on average. In contrast, successful learning is only possible by means of fluctuations. Consequently, synchronization is much faster than learning, which is essential for the security of the neural key-exchange protocol. However, this qualitative difference between bidirectional and unidirectional interaction vanishes if tree parity machines with more than three hidden units are used, so that those neural networks are not suitable for neural cryptography. In addition, the effective number of keys which can be generated by the neural key-exchange protocol is calculated using the entropy of the weight distribution. As this quantity increases exponentially with the system size, brute-force attacks on neural cryptography can easily be made unfeasible.
Labrador, I.; Carrasco, R.; Martinez, L.
1996-07-01
This paper describes a practical introduction to the use of Artificial Neural Networks. Artificial Neural Nets are often used as an alternative to the traditional symbolic manipulation and first order logic used in Artificial Intelligence, due the high degree of difficulty to solve problems that can not be handled by programmers using algorithmic strategies. As a particular case of Neural Net a Multilayer Perception developed by programming in C language on OS9 real time operating system is presented. A detailed description about the program structure and practical use are included. Finally, several application examples that have been treated with the tool are presented, and some suggestions about hardware implementations. (Author) 15 refs.
无
2005-01-01
The typical BDI (belief desire intention) model of agent is not efficiently computable and the strict logic expression is not easily applicable to the AUV (autonomous underwater vehicle) domain with uncertainties. In this paper, an AUV fuzzy neural BDI model is proposed. The model is a fuzzy neural network composed of five layers: input ( beliefs and desires) , fuzzification, commitment, fuzzy intention, and defuzzification layer. In the model, the fuzzy commitment rules and neural network are combined to form intentions from beliefs and desires. The model is demonstrated by solving PEG (pursuit-evasion game), and the simulation result is satisfactory.
Souza, Rose Mary Gomes do Prado
2005-07-01
This work presents a methodology based on the artificial neural network technique to predict in real time the power peak factor in a form that can be implemented in reactor protection systems. The neural network inputs were those available in the reactor protection systems, namely, the axial and quadrant power differences obtained from measured ex-core detector signals, and the position of control rods. The response of ex core detector signals was measured in experiments especially performed in the IPEN/MB-01 zero-power reactor. Several reactor states with different power density distribution were obtained by positioning the control rods in different configurations. The power distribution and its peak factor were calculated for each of these reactor states using the Citation code. The obtained results show that the power peak factor correlates well with the control rod position and the quadrant power difference, and with a lesser degree with the axial power differences. The data presented an inherent organisation and could be classified into different classes of power peak factor behaviour as a function of position of control rods, axial power difference and quadrant power difference. The RBF networks were able to identify classes and interpolate the power peak factor values. The relative error for the power peak factor estimation ranged from 0.19 % to 0.67 %, less than the one that was obtained performing a power density distribution map with in-core detectors. It was observed that the positions of control rods bear the detailed and localised information about the power density distribution, and that the axial and the quadrant power difference describe its global variations in the axial and radial directions. The results showed that the RBF and MLP networks produced similar results, and that a neural network correlation can be implemented in power reactor protection systems. (author)
Critical branching neural networks.
Kello, Christopher T
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical branching and, in doing so, simulates observed scaling laws as pervasive to neural and behavioral activity. These scaling laws are related to neural and cognitive functions, in that critical branching is shown to yield spiking activity with maximal memory and encoding capacities when analyzed using reservoir computing techniques. The model is also shown to account for findings of pervasive 1/f scaling in speech and cued response behaviors that are difficult to explain by isolable causes. Issues and questions raised by the model and its results are discussed from the perspectives of physics, neuroscience, computer and information sciences, and psychological and cognitive sciences.
Krogh, Anders Stærmose; Riis, Søren Kamaric
1999-01-01
A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability...... parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum...... likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear...
Neural Oscillators Programming Simplified
Patrick McDowell
2012-01-01
Full Text Available The neurological mechanism used for generating rhythmic patterns for functions such as swallowing, walking, and chewing has been modeled computationally by the neural oscillator. It has been widely studied by biologists to model various aspects of organisms and by computer scientists and robotics engineers as a method for controlling and coordinating the gaits of walking robots. Although there has been significant study in this area, it is difficult to find basic guidelines for programming neural oscillators. In this paper, the authors approach neural oscillators from a programmer’s point of view, providing background and examples for developing neural oscillators to generate rhythmic patterns that can be used in biological modeling and robotics applications.
Neural networks and graph theory
许进; 保铮
2002-01-01
The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.
Carreira, Paulo J.F.; Rosa, Miguel A.; Neto, João Pedro; Costa, José Félix
1998-01-01
In the work of [Siegelmann 95] it was showed that Artificial Recursive Neural Networks have the same computing power as Turing machines. A Turing machine can be programmed in a proper high-level language - the language of partial recursive functions. In this paper we present the implementation of a compiler that directly translates high-level Turing machine programs to Artificial Recursive Neural Networks. The application contains a simulator that can be used to test the resulting networks. W...
Neural cryptography with feedback
Ruttor, Andreas; Kinzel, Wolfgang; Shacham, Lanir; Kanter, Ido
2004-04-01
Neural cryptography is based on a competition between attractive and repulsive stochastic forces. A feedback mechanism is added to neural cryptography which increases the repulsive forces. Using numerical simulations and an analytic approach, the probability of a successful attack is calculated for different model parameters. Scaling laws are derived which show that feedback improves the security of the system. In addition, a network with feedback generates a pseudorandom bit sequence which can be used to encrypt and decrypt a secret message.
Svoboda, Karel
2016-01-01
Since the start of the new millennium, a method called two-photon microscopy has allowed scientists to peer farther into the brain than ever before. Our author, one of the pioneers in the development of this new technology, writes that "directly observing the dynamics of neural networks in an intact brain has become one of the holy grails of brain research." His article describes the advances that led to this remarkable breakthrough-one that is helping neuroscientists better understand neural networks.
1998-01-01
In the work of [Siegelmann 95] it was showed that Artificial Recursive Neural Networks have the same computing power as Turing machines. A Turing machine can be programmed in a proper high-level language - the language of partial recursive functions. In this paper we present the implementation of a compiler that directly translates high-level Turing machine programs to Artificial Recursive Neural Networks. The application contains a simulator that can be used to test the resulting networks. W...
Neural cryptography with feedback.
Ruttor, Andreas; Kinzel, Wolfgang; Shacham, Lanir; Kanter, Ido
2004-04-01
Neural cryptography is based on a competition between attractive and repulsive stochastic forces. A feedback mechanism is added to neural cryptography which increases the repulsive forces. Using numerical simulations and an analytic approach, the probability of a successful attack is calculated for different model parameters. Scaling laws are derived which show that feedback improves the security of the system. In addition, a network with feedback generates a pseudorandom bit sequence which can be used to encrypt and decrypt a secret message.
周敏
2011-01-01
The optimal solution of signal detection is a Nondeterministic Polynomial (NP) problem.Aimed at the problems that Radial Basis Function (RBF) Neural Network is prone to the local optimum and simple genetic algorithm has the shortcoming of slow convergence, a new type of intelligent algorithm is proposed and applied into the M1M0-0FDM detection systems: it makes use of Quantum Genetic Algorithm (QGA) to optimize the initial data of RBF neural network.In this scheme,the output of detector by the QGA as the input of detector by neural network to avoid the bit-error rate for selecting initial data randomly and improve further the detection property.Simulation results show the proposed method is good for the improvement of the detection rate and reduction of bit-error rate.%信号的最优检测在常规条件下是一NP难解问题,针对RBF(径向基函数)神经网络算法易陷入局部极值和简单遗传算法收敛速度慢的问题,提出一种新型智能算法并将其用于MIMO-OFDM系统信号检测中:该算法将量子计算、遗传算法与神经网络相结合,用量子遗传算法(QGA)优化神经网络初始值.由于QGA给RBF网络提供了较好的初始值,故能够使RBF网络快速收敛到最优解,避免了由初始值的随机选取而带来的检测误码.实验结果表明,该算法能够有效地提高系统的信号检测性能,降低误码率.
黄榕波; 郭穗勋
2013-01-01
建立基于径向基函数网络(Radial Basis Function network,RBF)的个体差异与药代动力学参数之间的关系模型.应用主成分分析(Principal Component Analysis,PCA)从个体差异因子中获取主成分作为RBF的输入,降低RBF的输入维数,从而降低了系统的复杂性.通过健康志愿者获得的实验数据对模型进行测试,实验结果表明RBF模型具有良好的拟合能力.
赵文秀; 张晓丽; 李国会
2015-01-01
基于我国南方某河流1965—1999年每年7月的实测流量资料，首先采用随机森林模型筛选预报因子，之后利用筛选的预报因子作为RBF神经网络的输入层，利用RBF神经网络对2000—2008年每年7月的流量进行了“滚动式”预报，并与实测结果进行了对比。结果表明：随机森林模型能有效地筛选影响因子，利用这些因子采用RBF神经网络进行径流预报的相对误差均在10％以内，拟合效果很好；“滚动式”长期径流预报结果相对误差的绝对值均在20％以内。%Based on the measured flow data of each July during the period of 1965 to 1999 of a river in southern China,the random forest model was used to filter the impact factors. Then,the RBF network input layer was trained with the selected factors and was utilized to fore-cast the flow data annually in July during 2000—2008 using rolling type pattern. The results show that the random forest model can effective-ly filter out the main factors. Based on the factors filtered by the random forest model,the relative error of RBF networks prediction results is within 10%. The fitting effect is good. Besides that,the relative error of the long-term prediction results using rolling type pattern is within 20%.
Kuo, R J.; Cohen, P H.
1999-03-01
On-line tool wear estimation plays a very critical role in industry automation for higher productivity and product quality. In addition, appropriate and timely decision for tool change is significantly required in the machining systems. Thus, this paper is dedicated to develop an estimation system through integration of two promising technologies, artificial neural networks (ANN) and fuzzy logic. An on-line estimation system consisting of five components: (1) data collection; (2) feature extraction; (3) pattern recognition; (4) multi-sensor integration; and (5) tool/work distance compensation for tool flank wear, is proposed herein. For each sensor, a radial basis function (RBF) network is employed to recognize the extracted features. Thereafter, the decisions from multiple sensors are integrated through a proposed fuzzy neural network (FNN) model. Such a model is self-organizing and self-adjusting, and is able to learn from the experience. Physical experiments for the metal cutting process are implemented to evaluate the proposed system. The results show that the proposed system can significantly increase the accuracy of the product profile.
徐奉友; 张小刚
2010-01-01
为了提高T-S型模糊RBF神经网络的训练效率, 把Levenberg-Marquardt算法引入到T-S型模糊RBF神经网络的训练过程中,提高了网络训练的收敛速度,减小了训练过程陷入局部极小点的概率,然后基于这种算法推导出T-S型模糊RBF神经网络的快速训练算法,即混合学习算法.最后通过实验验证了这种算法的有效性和实用性.
赫中营; 王根会
2007-01-01
介绍了RBF神经网络模型的结构和训练算法,提出了既有铁路桥梁构件的综合状态评估模型,根据RBF神经网络的自适应性和学习能力,成功的将RBF神经网络应用于既有铁路桥梁构件综合状态评估中去,并给出了便于获取,且能全面准确反映桥梁实际工作状态的输入参数.以某铁路线的若干组实测数据对RBF神经网络进行训练和测试,系统输出与期望输出吻合较好,证明了RBF神经网络评估既有桥梁构件综合状态的准确性、有效性和稳定性.
冯子泉
2011-01-01
基于粗糙集和遗传-RBF神经网络理论建立了钢筋混凝土施工质量诊断的智能模型.从泵送施工故障、搅拌机故障、运输机故障、振动器故障四个方面选取10个因素作为诊断故障的考核指标.研究表明:诊断结果和实际情况完全吻合,通过对潜在故障的诊断,可以避免排除故障时的盲目性,做到有针对性地排除故障,为钢筋混凝土施工质量诊断提供了一条新的途径.
徐智棋; 陈邦红; 徐智龙
2010-01-01
混凝土的早期弹性模量对施工的进度和工程的可靠度有重要的影响.借鉴RBF神经网络具有很强的非线性映射功能,在测定混凝土早期强度的基础上利用RBF神经网络对其弹性模量进行预测.讨论了RBF神经网络的拓扑结构和修正算法.通过对检验结果进行分析比较,证明了利用RBF网络能对混凝土早期的弹性模量进行精确的预测.
罗洪军; 徐秀平; 李柱峰
2010-01-01
与现有预测方法比较,神经网络在混沌时间序列预测中具有优势.利用RBF神经网络对混沌Lorenz时间序列的预测进行仿真研究,仿真结果表明:在单步直接预测、单步间接预测、多步直接预测和多步间接预测中,多步间接预测是其中最有效的方式.
何云斌; 杜卓奇
2009-01-01
针对钢铁件材质缺陷检测问题,介绍了基于初始幅值磁导率法的一种电磁无损检测方法.为了提高检测的效率和准确率,将RBF神经网络设计成为新的识别系统通过对钢铁件样本数据进行的仿真测试表明,RBF神经网络系统识别效率较高且可靠,为电磁无损检测提供了一个新的思路.
李尔国; 俞金寿
2002-01-01
针对传感器故障,提出了一种基于RBF神经网络的集成故障诊断方法.用RBF神经网络建立传感器故障模型,对系统的状态和故障参数进行在线估计,然后将故障参数与修正的Bayes分类算法(MB算法)相结合,进行传感器故障在线检测、分离和估计.对连续搅拌釜式反应器(CSTR)的仿真结果表明,该集成故障诊断方法能够对多重传感器故障进行快速准确的分离和估计,并对传感器故障具有容错性.
Adaptive PID control for warp tension system based on RBF neural network%基于RBF神经网络整定的经纱张力PID控制系统
刘官正; 张森林
2008-01-01
针对目前国内大多织机经纱张力控制系统采用传统PID控制,对数学模型依赖度高,难于达到较好控制效果的缺陷,提出了一种基于Kalman滤波器的RBF径向神经网络整定的PID控制算法.这种控制算法采用3输入、单输出的RBF径向神经网络对系统性能学习以寻找出最佳的PID组合,Kalman滤波器有效地滤掉了织机中的各种噪声,实现经纱张力值的恒定.仿真实验结果表明,基于神经网络整定的经纱张力控制系统的控制效果和动态性能都明显优于传统PID控制.
王希彬; 赵国荣; 高青伟
2008-01-01
针对模型存在误差时传统的Kalman滤波算法误差变大甚至发散的缺点,利用RBF神经网络较强的非线性逼近能力,提出用RBF神经网络辅助Kalman滤波的新算法,将其应用于舰栽机惯导系统的传递对准中,仿真表明该算法优于传统Kalman滤波算法.
FORECAST OF ATMOSPHERE CORROSION FOR ALUMINUM ALLOYS BY RBF NEURAL NETWORK%用RBF人工神经网络构建铝合金大气腐蚀预测模型
韩德盛; 李获
2009-01-01
依据RBF人工神经网络构建原理与腐蚀过程的相似性,以铝合金外场大气腐蚀数据训练并构建了RBF类型的铝合金腐蚀预测人工神经网络模型,并赋予该RBF网络隐节点数据中心是腐蚀敏感区中心的物理意义.该模型以合金成分、环境因素、时间等为网络输入参量,以腐蚀增重为网络输出;由于RBF网络具有局部响应特性,该类腐蚀预测模型尤其适合训练具有区域集中特点的外场腐蚀数据;仿真结果表明该模型具有良好的预测精度.
Artificial neural network model for predicting the evolution of river bank%河道浅滩演变预测的人工神经网络模型
鄂欢; 曲晓辉
2016-01-01
本文主要介绍利用人工神经网络对河道演变进行预测研究，并选取最佳模型对河道演变进行预测。通过对比分析发现RBF网络模型比BP神经网络模型的训练时间短，两模型的预测精度相差不多。结果证实人工神经网络在河道浅滩演变中具有较强的应用性，为河道浅滩演变预测开辟了一条新思路。%This paper mainly introduces the research on river evolution prediction using artificial neural net-work,and select the best model to forecast the river evolution.Through the comparative analysis found that RBF network model is better than BP neural network model of short training time ,the prediction accuracy of two models is not much difference.The results proved that the artificial neural network has strong application in river shoal evolution in river shoal evolution prediction opens up a new way.
S.M. Hosseini-Moghari
2016-10-01
Full Text Available Introduction: Due to economic, social, and environmental perplexities associated with drought, it is considered as one of the most complex natural hazards. To investigate the beginning along with analyzing the direct impacts of drought; the significance of drought monitoring must be highlighted. Regarding drought management and its consequences alleviation, drought forecasting must be taken into account (11. The current research employed multi-layer perceptron (MLP, adaptive neuro-fuzzy inference system (ANFIS, radial basis function (RBF and general regression neural network (GRNN. It is interesting to note that, there has not been any record of applying GRNN in drought forecasting. Materials and Methods: Throughout this paper, Standard Precipitation Index (SPI was the basis of drought forecasting. To do so, the precipitation data of Gonbad Kavous station during the period of 1972-73 to 2006-07 were used. To provide short-term, mid-term, and long-term drought analysis; SPI for 1, 3, 6, 9, 12, and 24 months was evaluated. SPI evaluation benefited from four statistical distributions, namely, Gamma, Normal, Log-normal, and Weibull along with Kolmogrov-Smirnov (K-S test. Later, to compare the capabilities of four utilized neural networks for drought forecasting; MLP, ANFIS, RBF, and GRNN were applied. MLP as a multi-layer network, which has a sigmoid activation function in hidden layer plus linear function in output layer, can be considered as a powerful regressive tool. ANFIS besides adaptive neuro networks, employed fuzzy logic. RBF, the foundation of radial basis networks, is a three-layer network with Gaussian function in its hidden layer, and a linear function in the output layer. GRNN is another type of RBF which is used for radial basis regressive problems. The performance criteria of the research were as follows: Correlation (R2, Root Mean Square Error (RMSE, Mean Absolute Error (MAE. Results Discussion: According to statistical distribution
Neural networks in seismic discrimination
Dowla, F.U.
1995-01-01
Neural networks are powerful and elegant computational tools that can be used in the analysis of geophysical signals. At Lawrence Livermore National Laboratory, we have developed neural networks to solve problems in seismic discrimination, event classification, and seismic and hydrodynamic yield estimation. Other researchers have used neural networks for seismic phase identification. We are currently developing neural networks to estimate depths of seismic events using regional seismograms. In this paper different types of network architecture and representation techniques are discussed. We address the important problem of designing neural networks with good generalization capabilities. Examples of neural networks for treaty verification applications are also described.
Automated Brain Image classification using Neural Network Approach and Abnormality Analysis
P.Muthu Krishnammal
2015-06-01
Full Text Available Image segmentation of surgical images plays an important role in diagnosis and analysis the anatomical structure of human body. Magnetic Resonance Imaging (MRI helps in obtaining a structural image of internal parts of the body. This paper aims at developing an automatic support system for stage classification using learning machine and to detect brain Tumor by fuzzy clustering methods to detect the brain Tumor in its early stages and to analyze anatomical structures. The three stages involved are: feature extraction using GLCM and the tumor classification using PNN-RBF network and segmentation using SFCM. Here fast discrete curvelet transformation is used to analyze texture of an image which be used as a base for a Computer Aided Diagnosis (CAD system .The Probabilistic Neural Network with radial basis function is employed to implement an automated Brain Tumor classification. It classifies the stage of Brain Tumor that is benign, malignant or normal automatically. Then the segmentation of the brain abnormality using Spatial FCM and the severity of the tumor is analysed using the number of tumor cells in the detected abnormal region.The proposed method reports promising results in terms of training performance and classification accuracies.
A Comparative Approach to Hand Force Estimation using Artificial Neural Networks.
Mobasser, Farid; Hashtrudi-Zaad, Keyvan
2012-01-01
In many applications that include direct human involvement such as control of prosthetic arms, athletic training, and studying muscle physiology, hand force is needed for control, modeling and monitoring purposes. The use of inexpensive and easily portable active electromyography (EMG) electrodes and position sensors would be advantageous in these applications compared to the use of force sensors which are often very expensive and require bulky frames. Among non-model-based estimation methods, Multilayer Perceptron Artificial Neural Networks (MLPANN) has widely been used to estimate muscle force or joint torque from different anatomical features in humans or animals. This paper investigates the use of Radial Basis Function (RBF) ANN and MLPANN for force estimation and experimentally compares the performance of the two methodologies for the same human anatomy, ie, hand force estimation, under an ensemble of operational conditions. In this unified study, the EMG signal readings from upper-arm muscles involved in elbow joint movement and elbow angular position and velocity are utilized as inputs to the ANNs. In addition, the use of the elbow angular acceleration signal as an input for the ANNs is also investigated.
A. M. Chandrashekhar
2013-02-01
Full Text Available Intrusion Detection Systems (IDS form a key part of system defence, where it identifies abnormalactivities happening in a computer system. In recent years different soft computing based techniques havebeen proposed for the development of IDS. On the other hand, intrusion detection is not yet a perfecttechnology. This has provided an opportunity for data mining to make quite a lot of importantcontributions in the field of intrusion detection. In this paper we have proposed a new hybrid techniqueby utilizing data mining techniques such as fuzzy C means clustering, Fuzzy neural network / Neurofuzzyand radial basis function(RBF SVM for fortification of the intrusion detection system. Theproposed technique has five major steps in which, first step is to perform the relevance analysis, and theninput data is clustered using Fuzzy C-means clustering. After that, neuro-fuzzy is trained, such that eachof the data point is trained with the corresponding neuro-fuzzy classifier associated with the cluster.Subsequently, a vector for SVM classification is formed and in the last step, classification using RBFSVMis performed to detect intrusion has happened or not. Data set used is the KDD cup 1999 datasetand we have used precision, recall, F-measure and accuracy as the evaluation metrics parameters. Ourtechnique could achieve better accuracy for all types of intrusions. The results of proposed technique arecompared with the other existing techniques. These comparisons proved the effectiveness of ourtechnique.
GEMAN, O.
2014-02-01
Full Text Available Neurological diseases like Alzheimer, epilepsy, Parkinson's disease, multiple sclerosis and other dementias influence the lives of patients, their families and society. Parkinson's disease (PD is a neurodegenerative disease that occurs due to loss of dopamine, a neurotransmitter and slow destruction of neurons. Brain area affected by progressive destruction of neurons is responsible for controlling movements, and patients with PD reveal rigid and uncontrollable gestures, postural instability, small handwriting and tremor. Commercial activity-promoting gaming systems such as the Nintendo Wii and Xbox Kinect can be used as tools for tremor, gait or other biomedical signals acquisitions. They also can aid for rehabilitation in clinical settings. This paper emphasizes the use of intelligent optical sensors or accelerometers in biomedical signal acquisition, and of the specific nonlinear dynamics parameters or fuzzy logic in Parkinson's disease tremor analysis. Nowadays, there is no screening test for early detection of PD. So, we investigated a method to predict PD, based on the image processing of the handwriting belonging to a candidate of PD. For classification and discrimination between healthy people and PD people we used Artificial Neural Networks (Radial Basis Function - RBF and Multilayer Perceptron - MLP and an Adaptive Neuro-Fuzzy Classifier (ANFC. In general, the results may be expressed as a prognostic (risk degree to contact PD.
Interval model updating using perturbation method and Radial Basis Function neural networks
Deng, Zhongmin; Guo, Zhaopu; Zhang, Xinjie
2017-02-01
In recent years, stochastic model updating techniques have been applied to the quantification of uncertainties inherently existing in real-world engineering structures. However in engineering practice, probability density functions of structural parameters are often unavailable due to insufficient information of a structural system. In this circumstance, interval analysis shows a significant advantage of handling uncertain problems since only the upper and lower bounds of inputs and outputs are defined. To this end, a new method for interval identification of structural parameters is proposed using the first-order perturbation method and Radial Basis Function (RBF) neural networks. By the perturbation method, each random variable is denoted as a perturbation around the mean value of the interval of each parameter and that those terms can be used in a two-step deterministic updating sense. Interval model updating equations are then developed on the basis of the perturbation technique. The two-step method is used for updating the mean values of the structural parameters and subsequently estimating the interval radii. The experimental and numerical case studies are given to illustrate and verify the proposed method in the interval identification of structural parameters.
Rule Extraction:Using Neural Networks or for Neural Networks?
Zhi-Hua Zhou
2004-01-01
In the research of rule extraction from neural networks, fidelity describes how well the rules mimic the behavior of a neural network while accuracy describes how well the rules can be generalized. This paper identifies the fidelity-accuracy dilemma. It argues to distinguish rule extraction using neural networks and rule extraction for neural networks according to their different goals, where fidelity and accuracy should be excluded from the rule quality evaluation framework, respectively.
Fuzzy Multiresolution Neural Networks
Ying, Li; Qigang, Shang; Na, Lei
A fuzzy multi-resolution neural network (FMRANN) based on particle swarm algorithm is proposed to approximate arbitrary nonlinear function. The active function of the FMRANN consists of not only the wavelet functions, but also the scaling functions, whose translation parameters and dilation parameters are adjustable. A set of fuzzy rules are involved in the FMRANN. Each rule either corresponding to a subset consists of scaling functions, or corresponding to a sub-wavelet neural network consists of wavelets with same dilation parameters. Incorporating the time-frequency localization and multi-resolution properties of wavelets with the ability of self-learning of fuzzy neural network, the approximation ability of FMRANN can be remarkable improved. A particle swarm algorithm is adopted to learn the translation and dilation parameters of the wavelets and adjusting the shape of membership functions. Simulation examples are presented to validate the effectiveness of FMRANN.
Introduction to Artificial Neural Networks
Larsen, Jan
1999-01-01
The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....
Adaptive Sliding Mode Control for Robot Manipulators Based on Neural Network%基于神经网络的不确定机器人自适应滑模控制
牛玉刚; 杨成梧; 陈雪如
2001-01-01
A neural network-based adaptive sliding model controller is proposed for robot manipulators. This control scheme integrates the theory of VSS and the nonlinear mapping of neural network. A key feature of this scheme is that the prior knowledge of the upper bound of the system uncertainties is not required. A RBF neural network is used to adaptively learn the unknown bounds of system uncertainties, and then the output of the neural network estimator is used to adjust the switching gain. This new controller can guarantee the asymptotic convergence of the tracking error to zero.%提出一种机器人轨迹跟踪的自适应神经滑模控制。该控制方案将神经网络的非线性映射能力与变结构控制理论相结合，利用RBF网络自适应学习系统不确定性的未知上界，神经网络的输出用于自适应修正控制律的切换增益。这种新型控制器能保证机械手位置和速度跟踪误差渐近收敛于零。仿真结果表明了该方案的有效性。
Generalized Adaptive Artificial Neural Networks
Tawel, Raoul
1993-01-01
Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.
Artificial Neural Network and Rough Set for HV Bushings Condition Monitoring
Mpanza, LJ
2011-01-01
Most transformer failures are attributed to bushings failures. Hence it is necessary to monitor the condition of bushings. In this paper three methods are developed to monitor the condition of oil filled bushing. Multi-layer perceptron (MLP), Radial basis function (RBF) and Rough Set (RS) models are developed and combined through majority voting to form a committee. The MLP performs better that the RBF and the RS is terms of classification accuracy. The RBF is the fasted to train. The committee performs better than the individual models. The diversity of models is measured to evaluate their similarity when used in the committee.
Hansen, Lars Kai; Salamon, Peter
1990-01-01
We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....
Interval probabilistic neural network.
Kowalski, Piotr A; Kulczycki, Piotr
2017-01-01
Automated classification systems have allowed for the rapid development of exploratory data analysis. Such systems increase the independence of human intervention in obtaining the analysis results, especially when inaccurate information is under consideration. The aim of this paper is to present a novel approach, a neural networking, for use in classifying interval information. As presented, neural methodology is a generalization of probabilistic neural network for interval data processing. The simple structure of this neural classification algorithm makes it applicable for research purposes. The procedure is based on the Bayes approach, ensuring minimal potential losses with regard to that which comes about through classification errors. In this article, the topological structure of the network and the learning process are described in detail. Of note, the correctness of the procedure proposed here has been verified by way of numerical tests. These tests include examples of both synthetic data, as well as benchmark instances. The results of numerical verification, carried out for different shapes of data sets, as well as a comparative analysis with other methods of similar conditioning, have validated both the concept presented here and its positive features.
周贞贞; 孙桦
2013-01-01
Four algorithms including Gradient Descent(GD) algorithm , Extended Kalman Filter(EKF) algorithm,Unscented Kalman Filter(UKF) algorithm, and the new algorithm combined by Genetic Algorithm and Kalman Filter(GA&KF) algorithm, are adopted in order to establish Radial Basis Function(RBF) neural network based on the adaptive structure. These algorithms have been successfully used to optimize the weights and the center values of RBF neural network. Taking IRIS set as training samples, the detailed comparisons on approximation capability,output error, training effect and recognition accuracy among different algorithms are performed. It is indicated that the proposed method bears strong processing capacity on non-linear system, better adaptive ability and fast learning speed.% 为了提高神经网络模式识别的泛化能力，运用梯度下降、扩展卡尔曼滤波、无先导卡尔曼滤波和一种基于遗传算法与扩展卡尔曼滤波组合的新方法，对径向基神经网络的中心节点和权重进行了优化，建立了自适应结构的径向基神经网络模型，实现了对 IRIS 数据集的识别。通过仿真实验，对基于不同算法的径向基神经网络，从逼近能力、输出误差、学习效率与识别精确度等方面进行了分析比较。本文方法具有很强的非线性处理能力和自适应能力及较快的学习速度。
蒋加伏; 赵怡
2015-01-01
The traditional human action recognition algorithm tends to focus on solving a certain behavior recognition,it cannot be generalized.So,this paper put forward a kind of Local evidence RBF algorithm based high-level characteristic self similarity fusion for human behavior recognition.Firstly,the time-dependent generalized self similarity concept and the spa-tio-temporal interest point optical flow based local features extraction method were used to construct the human behavior description based on self similar matrix.Secondly,after independent individual behavior recognition in the use of SVM algo-rithm,the evidence theory based high level feature fusion was used to realize the optimization for classification of structure, which can improve the accuracy of classification.Simulation results show that the proposed scheme can significantly improve the efficiency and accuracy for human action recognition.%针对传统人体动作识别算法，往往重点解决某一类行为识别，不具有通用性的问题，提出一种局部证据 RBF人体行为高层特征自相似融合识别算法。首先，借用随时间变化的广义自相似性概念，利用时空兴趣点光流场局部特征提取方法，构建基于自相似矩阵的人体行为局部特征描述；其次，在使用 SVM算法进行独立个体行为识别后，利用所提出的证据理论 RBF(Radial Basis Function)高层特征融合，实现分类结构优化，从而提高分类准确度；仿真实验表明，所提方案能够明显提高人体行为识别算法效率和识别准确率。
Neural dynamics based on the recognition of neural fingerprints
José Luis eCarrillo-Medina
2015-03-01
Full Text Available Experimental evidence has revealed the existence of characteristic spiking features in different neural signals, e.g. individual neural signatures identifying the emitter or functional signatures characterizing specific tasks. These neural fingerprints may play a critical role in neural information processing, since they allow receptors to discriminate or contextualize incoming stimuli. This could be a powerful strategy for neural systems that greatly enhances the encoding and processing capacity of these networks. Nevertheless, the study of information processing based on the identification of specific neural fingerprints has attracted little attention. In this work, we study (i the emerging collective dynamics of a network of neurons that communicate with each other by exchange of neural fingerprints and (ii the influence of the network topology on the self-organizing properties within the network. Complex collective dynamics emerge in the network in the presence of stimuli. Predefined inputs, i.e. specific neural fingerprints, are detected and encoded into coexisting patterns of activity that propagate throughout the network with different spatial organization. The patterns evoked by a stimulus can survive after the stimulation is over, which provides memory mechanisms to the network. The results presented in this paper suggest that neural information processing based on neural fingerprints can be a plausible, flexible and powerful strategy.
M.E. Marshall
1981-09-01
Full Text Available Neural tube defects refer to any defect in the morphogenesis of the neural tube, the most common types being spina bifida and anencephaly. Spina bifida has been recognised in skeletons found in north-eastern Morocco and estimated to have an age of almost 12 000 years. It was also known to the ancient Greek and Arabian physicians who thought that the bony defect was due to the tumour. The term spina bifida was first used by Professor Nicolai Tulp of Amsterdam in 1652. Many other terms have been used to describe this defect, but spina bifida remains the most useful general term, as it describes the separation of the vertebral elements in the midline.
Gupta, S; Gupta, Sanjay
2002-01-01
This paper initiates the study of quantum computing within the constraints of using a polylogarithmic ($O(\\log^k n), k\\geq 1$) number of qubits and a polylogarithmic number of computation steps. The current research in the literature has focussed on using a polynomial number of qubits. A new mathematical model of computation called \\emph{Quantum Neural Networks (QNNs)} is defined, building on Deutsch's model of quantum computational network. The model introduces a nonlinear and irreversible gate, similar to the speculative operator defined by Abrams and Lloyd. The precise dynamics of this operator are defined and while giving examples in which nonlinear Schr\\"{o}dinger's equations are applied, we speculate on its possible implementation. The many practical problems associated with the current model of quantum computing are alleviated in the new model. It is shown that QNNs of logarithmic size and constant depth have the same computational power as threshold circuits, which are used for modeling neural network...
Andersen, Rikke K; Johansen, Mathias; Blaabjerg, Morten
2007-01-01
maintained their neurogenic potential throughout 77 days of propagation, while the ability of anterior NTS to generate neurons severely declined from day 40. The present procedure describes isolation and long-term expansion of forebrain SVZ tissue with potential preservation of the endogenous cellular......By combining new and established protocols we have developed a procedure for isolation and propagation of neural precursor cells from the forebrain subventricular zone (SVZ) of newborn rats. Small tissue blocks of the SVZ were dissected and propagated en bloc as free-floating neural tissue......-spheres (NTS) in EGF and FGF2 containing medium. The spheres were cut into quarters when passaged every 10-15th day, avoiding mechanical or enzymatic dissociation in order to minimize cellular trauma and preserve intercellular contacts. For analysis of regional differences within the forebrain SVZ, NTS were...
Kass, Robert E; Brown, Emery N
2014-01-01
Continual improvements in data collection and processing have had a huge impact on brain research, producing data sets that are often large and complicated. By emphasizing a few fundamental principles, and a handful of ubiquitous techniques, Analysis of Neural Data provides a unified treatment of analytical methods that have become essential for contemporary researchers. Throughout the book ideas are illustrated with more than 100 examples drawn from the literature, ranging from electrophysiology, to neuroimaging, to behavior. By demonstrating the commonality among various statistical approaches the authors provide the crucial tools for gaining knowledge from diverse types of data. Aimed at experimentalists with only high-school level mathematics, as well as computationally-oriented neuroscientists who have limited familiarity with statistics, Analysis of Neural Data serves as both a self-contained introduction and a reference work.
Kapil Nahar
2012-12-01
Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information.The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems.Ann’s, like people, learn by example.
Neural networks for triggering
Denby, B. (Fermi National Accelerator Lab., Batavia, IL (USA)); Campbell, M. (Michigan Univ., Ann Arbor, MI (USA)); Bedeschi, F. (Istituto Nazionale di Fisica Nucleare, Pisa (Italy)); Chriss, N.; Bowers, C. (Chicago Univ., IL (USA)); Nesti, F. (Scuola Normale Superiore, Pisa (Italy))
1990-01-01
Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.
Coupled Neural Associative Memories
Karbasi, Amin; Salavati, Amir Hesam; Shokrollahi, Amin
2013-01-01
We propose a novel architecture to design a neural associative memory that is capable of learning a large number of patterns and recalling them later in presence of noise. It is based on dividing the neurons into local clusters and parallel plains, very similar to the architecture of the visual cortex of macaque brain. The common features of our proposed architecture with those of spatially-coupled codes enable us to show that the performance of such networks in eliminating noise is drastical...
Kapil Nahar
2012-12-01
Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems. Ann’s, like people, learn by example.
Compressing Convolutional Neural Networks
Chen, Wenlin; Wilson, James T.; Tyree, Stephen; Weinberger, Kilian Q.; Chen, Yixin
2015-01-01
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as model sizes increase, so do the storage and memory requirements of the classifiers. We present a novel network architecture, Frequency-Sensitive Hashed Nets (FreshNets), which exploits inherent redundancy in both convolutional layers and fully-connected laye...
Artificial neural network modelling
Samarasinghe, Sandhya
2016-01-01
This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling. .
POO; Mu-Ming
2010-01-01
One of the properties of the nervous system is the use-dependent plasticity of neural circuits.The structure and function of neural circuits are susceptible to changes induced by prior neuronal activity,as reflected by short-and long-term modifications of synaptic efficacy and neuronal excitability.Regarded as the most attractive cellular mechanism underlying higher cognitive functions such as learning and memory,activity-dependent synaptic plasticity has been in the spotlight of modern neuroscience since 1973 when activity-induced long-term potentiation(LTP) of hippocampal synapses was first discovered.Over the last 10 years,Chinese neuroscientists have made notable contributions to the study of the cellular and molecular mechanisms of synaptic plasticity,as well as of the plasticity beyond synapses,including activity-dependent changes in intrinsic neuronal excitability,dendritic integration functions,neuron-glia signaling,and neural network activity.This work highlight some of these significant findings.
Pickling Process Model of Zr-4 Alloy Tube Based on RBF Network%基于RBF神经网络法的Zr-4合金管材酸洗工艺模型
卫新民; 袁改焕; 李小宁
2015-01-01
研究了Zr-4合金管材酸洗处理过程中,酸洗去除量、酸水转换时间、冲水时间及酸洗次数对管材氟残留量的影响,并基于径向基(RBF)人工神经网络法建立了Zr4合金管材酸洗工艺与氟残留的神经网络模型.结果表明:冲水酸水转换时间和冲水时间对氟残留量均有影响,且酸水转换时间的影响更为显著;氟残留量与酸洗次数无明显对应关系.Zr4合金酸洗工艺的RBF神经网络模型结构为3-5-1,实际值与模拟值的相对误差为9.2％.该神经网络模型具有较高的可靠性,可为Zr-4合金酸洗工艺参数的优化提供参考.
Afkhami, Abbas; Abbasi-Tarighat, Maryam
2008-06-01
In the present study, chemometric analysis of visible spectral data of phospho-and silico-molybdenum blue complexes was used to develop artificial neural networks (ANNs) for the simultaneous determination of the phosphate and silicate. Combinations of principal component analysis (PCA) with feed-forward neural networks (FFNNs) and radial basis function networks (RBFNs) were built and investigated. The structures of the models were simplified by using the corresponding important principal components as input instead of the original spectra. Number of inputs and hidden nodes, learning rate, transfer functions and number of epochs and SPREAD values were optimized. Performances of methods were tested with root mean square errors prediction (RMSEP, %), using synthetic solutions. The obtained satisfactory results indicate the applicability of this ANN approach based on PCA input selection for determination in highly spectral overlapping. The results obtained by FFNNs and by RBF networks were compared. The applicability of methods was investigated for synthetic samples, for detergent formulations, and for a river water sample.
Qiang Gao
2016-01-01
Full Text Available To satisfy the lightweight requirements of large pipe weapons, a novel electrohydraulic servo (EHS system where the hydraulic cylinder possesses three cavities is developed and investigated in the present study. In the EHS system, the balancing cavity of the EHS is especially designed for active compensation for the unbalancing force of the system, whereas the two driving cavities are employed for positioning and disturbance rejection of the large pipe. Aiming at simultaneously balancing and positioning of the EHS system, a novel neural network based active disturbance rejection control (NNADRC strategy is developed. In the NNADRC, the radial basis function (RBF neural network is employed for online updating of parameters of the extended state observer (ESO. Thereby, the nonlinear behavior and external disturbance of the system can be accurately estimated and compensated in real time. The efficiency and superiority of the system are critically investigated by conducting numerical simulations, showing that much higher steady accuracy as well as system robustness is achieved when comparing with conventional ADRC control system. It indicates that the NNADRC is a very promising technique for achieving fast, stable, smooth, and accurate control of the novel EHS system.
Mohammad Heidari
2013-01-01
Full Text Available In this study, the static pull-in instability of beam-type micro-electromechanical system (MEMS is theoretically investigated. Considering the mid-plane stretching as the source of the nonlinearity in the beam behavior, a nonlinear size dependent Euler-Bernoulli beam model is used based on a modified couple stress theory, capable of capturing the size effect. Two supervised neural networks, namely, back propagation (BP and radial basis function (RBF, have been used for modeling the static pull-in instability of microcantilever beam. These networks have four inputs of length, width, gap, and the ratio of height to scale parameter of beam as the independent process variables, and the output is static pull-in voltage of microbeam. Numerical data employed for training the networks and capabilities of the models in predicting the pull-in instability behavior has been verified. Based on verification errors, it is shown that the radial basis function of neural network is superior in this particular case and has the average errors of 4.55% in predicting pull-in voltage of cantilever microbeam. Further analysis of pull-in instability of beam under different input conditions has been investigated and comparison results of modeling with numerical considerations show a good agreement, which also proves the feasibility and effectiveness of the adopted approach.
Trimaran Resistance Artificial Neural Network
2011-01-01
11th International Conference on Fast Sea Transportation FAST 2011, Honolulu, Hawaii, USA, September 2011 Trimaran Resistance Artificial Neural Network Richard...Trimaran Resistance Artificial Neural Network 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e... Artificial Neural Network and is restricted to the center and side-hull configurations tested. The value in the parametric model is that it is able to
[Artificial neural networks in Neurosciences].
Porras Chavarino, Carmen; Salinas Martínez de Lecea, José María
2011-11-01
This article shows that artificial neural networks are used for confirming the relationships between physiological and cognitive changes. Specifically, we explore the influence of a decrease of neurotransmitters on the behaviour of old people in recognition tasks. This artificial neural network recognizes learned patterns. When we change the threshold of activation in some units, the artificial neural network simulates the experimental results of old people in recognition tasks. However, the main contributions of this paper are the design of an artificial neural network and its operation inspired by the nervous system and the way the inputs are coded and the process of orthogonalization of patterns.
Study on Double-Motor Synchronous System Based on Neural Network Control%基于神经网络控制的两电动机同步系统研究
张运芳; 陈荣; 赵永建
2009-01-01
Taking the multi-variable,non-linear and high coupling synchronization system of AC induction motor as study object,focusing on the system of induction motors powered by current-tract SPWM transducers,the mathematical model of the two motor system was established. Combined with decoupling technology of adaptive neuron decoupling compensator, RBF neural network adaptive PID controller was adopted to design the neural network controller of two-motor synchronous system. Experimental results show that the two-motor synchronous system is decoupled based on neural network control.%以多变量、非线性、强耦合的两电动机同步控制系统为研究对象,对变频器供电的感应电机系统进行重点研究,建立两电机同步系统的数学模型.采用RBF神经网络自适应PID控制器,结合自适应神经元解耦补偿的解耦控制技术,设计了两电机同步调速系统的神经网络控制器,试验结果表明该方法可以实现电机转速和皮带张力的解耦控制.
J. Reyes-Reyes
2000-01-01
Full Text Available In this paper, an adaptive technique is suggested to provide the passivity property for a class of partially known SISO nonlinear systems. A simple Dynamic Neural Network (DNN, containing only two neurons and without any hidden-layers, is used to identify the unknown nonlinear system. By means of a Lyapunov-like analysis the new learning law for this DNN, guarantying both successful identification and passivation effects, is derived. Based on this adaptive DNN model, an adaptive feedback controller, serving for wide class of nonlinear systems with an a priori incomplete model description, is designed. Two typical examples illustrate the effectiveness of the suggested approach.
Backstepping adaptive high maneuvers flight control based on neural network%基于神经网络的反步自适应大机动飞行控制
孙勇; 章卫国; 章萌
2011-01-01
针对飞机大机动飞行时模型非线性和参数不确定性的特点,提出了一种基于全调节神经网络的反步自适应控制方法.飞机模型不确定部分由全调节径向基函数(radical basis function,RBF)神经网络在线补偿,控制律及神经网络参数自适应律由反步法回馈递推得到,并利用一种自适应参数策略的混沌粒子群算法优化控制嚣固定参数,改善动态性能,最后通过加权伪逆控制分配方法得到最终控制信号.仿真结果表明:在较大的模型气动参数不确定及控制增益矩阵未知时,所设计的控制律仍能理想地跟踪飞机大机动指令飞行,神经网络参数估计误差指数收敛到有界紧集,系统具有快速的收敛性和良好的鲁棒性.%A backstepping adaptive control method based on fulIy tuned neural network is proposed in the presence of model nonlinearity and parameters uncertainty for high maneuvers flight. Parameter uncertainties are compensated for online by the fully tuned radical basis function (RBF) neural network. The control law and the adaptive law of neural network are recursively achieved through a backstepping method. The fixed parameters optimization is done using a chaotic particle swarm optimization algorithm with adaptive parameter strategy for achieving a good transient performance. The final control surface deflections are derived by a weighted pseudoinverse control allocation method. Simulation results show that precise high maneuvers can be performed with fast convergence and good robustness properties in spite of large aerodynamic parameters uncertainty and unknown control gain matrix Moreover, the estimation errors of neural networks' parameters are remained in compact sets.
Tagliaferri, Roberto; Longo, Giuseppe; Milano, Leopoldo; Acernese, Fausto; Barone, Fabrizio; Ciaramella, Angelo; De Rosa, Rosario; Donalek, Ciro; Eleuteri, Antonio; Raiconi, Giancarlo; Sessa, Salvatore; Staiano, Antonino; Volpicelli, Alfredo
2003-01-01
In the last decade, the use of neural networks (NN) and of other soft computing methods has begun to spread also in the astronomical community which, due to the required accuracy of the measurements, is usually reluctant to use automatic tools to perform even the most common tasks of data reduction and data mining. The federation of heterogeneous large astronomical databases which is foreseen in the framework of the astrophysical virtual observatory and national virtual observatory projects, is, however, posing unprecedented data mining and visualization problems which will find a rather natural and user friendly answer in artificial intelligence tools based on NNs, fuzzy sets or genetic algorithms. This review is aimed to both astronomers (who often have little knowledge of the methodological background) and computer scientists (who often know little about potentially interesting applications), and therefore will be structured as follows: after giving a short introduction to the subject, we shall summarize the methodological background and focus our attention on some of the most interesting fields of application, namely: object extraction and classification, time series analysis, noise identification, and data mining. Most of the original work described in the paper has been performed in the framework of the AstroNeural collaboration (Napoli-Salerno).
Heiden, Uwe
1980-01-01
The purpose of this work is a unified and general treatment of activity in neural networks from a mathematical pOint of view. Possible applications of the theory presented are indica ted throughout the text. However, they are not explored in de tail for two reasons : first, the universal character of n- ral activity in nearly all animals requires some type of a general approach~ secondly, the mathematical perspicuity would suffer if too many experimental details and empirical peculiarities were interspersed among the mathematical investigation. A guide to many applications is supplied by the references concerning a variety of specific issues. Of course the theory does not aim at covering all individual problems. Moreover there are other approaches to neural network theory (see e.g. Poggio-Torre, 1978) based on the different lev els at which the nervous system may be viewed. The theory is a deterministic one reflecting the average be havior of neurons or neuron pools. In this respect the essay is writt...
Koulakov, Alexei
Olfaction is the final frontier of our senses - the one that is still almost completely mysterious to us. Despite extensive genetic and perceptual data, and a strong push to solve the neural coding problem, fundamental questions about the sense of smell remain unresolved. Unlike vision and hearing, where relatively straightforward relationships between stimulus features and neural responses have been foundational to our understanding sensory processing, it has been difficult to quantify the properties of odorant molecules that lead to olfactory percepts. In a sense, we do not have olfactory analogs of ``red'', ``green'' and ``blue''. The seminal work of Linda Buck and Richard Axel identified a diverse family of about 1000 receptor molecules that serve as odorant sensors in the nose. However, the properties of smells that these receptors detect remain a mystery. I will review our current understanding of the molecular properties important to the olfactory system. I will also describe a theory that explains how odorant identity can be preserved despite substantial changes in the odorant concentration.
Kennis, M.
2016-01-01
The aim of this thesis was to gain more insight in the neural network alterations that may underlie PTSD and trauma-focused therapy outcome. To investigate TheNeural Web of War brain scans of healthy civilians (n=26), and veterans with (n=58) and without (n=29) PTSD were assessed. Structural and fun
The Neural Support Vector Machine
Wiering, Marco; van der Ree, Michiel; Embrechts, Mark; Stollenga, Marijn; Meijster, Arnold; Nolte, A; Schomaker, Lambertus
2013-01-01
This paper describes a new machine learning algorithm for regression and dimensionality reduction tasks. The Neural Support Vector Machine (NSVM) is a hybrid learning algorithm consisting of neural networks and support vector machines (SVMs). The output of the NSVM is given by SVMs that take a
Neural Networks for Optimal Control
Sørensen, O.
1995-01-01
Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....
The Neural Support Vector Machine
Wiering, Marco; van der Ree, Michiel; Embrechts, Mark; Stollenga, Marijn; Meijster, Arnold; Nolte, A; Schomaker, Lambertus
2013-01-01
This paper describes a new machine learning algorithm for regression and dimensionality reduction tasks. The Neural Support Vector Machine (NSVM) is a hybrid learning algorithm consisting of neural networks and support vector machines (SVMs). The output of the NSVM is given by SVMs that take a centr
Neural Networks for Optimal Control
Sørensen, O.
1995-01-01
Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....
VOLTAGE COMPENSATION USING ARTIFICIAL NEURAL NETWORK
VOLTAGE COMPENSATION USING ARTIFICIAL NEURAL NETWORK: A CASE STUDY OF RUMUOLA DISTRIBUTION NETWORK. ... The artificial neural networks controller engaged to controlling the dynamic voltage ... Article Metrics.
Medical diagnosis using neural network
Kamruzzaman, S M; Siddiquee, Abu Bakar; Mazumder, Md Ehsanul Hoque
2010-01-01
This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural networ...
Neural fields theory and applications
Graben, Peter; Potthast, Roland; Wright, James
2014-01-01
With this book, the editors present the first comprehensive collection in neural field studies, authored by leading scientists in the field - among them are two of the founding-fathers of neural field theory. Up to now, research results in the field have been disseminated across a number of distinct journals from mathematics, computational neuroscience, biophysics, cognitive science and others. Starting with a tutorial for novices in neural field studies, the book comprises chapters on emergent patterns, their phase transitions and evolution, on stochastic approaches, cortical development, cognition, robotics and computation, large-scale numerical simulations, the coupling of neural fields to the electroencephalogram and phase transitions in anesthesia. The intended readership are students and scientists in applied mathematics, theoretical physics, theoretical biology, and computational neuroscience. Neural field theory and its applications have a long-standing tradition in the mathematical and computational ...
Li, Ting; Hong, Jun; Zhang, Jinhua; Guo, Feng
2014-03-15
The improvement of the resolution of brain signal and the ability to control external device has been the most important goal in BMI research field. This paper describes a non-invasive brain-actuated manipulator experiment, which defined a paradigm for the motion control of a serial manipulator based on motor imagery and shared control. The techniques of component selection, spatial filtering and classification of motor imagery were involved. Small-world neural network (SWNN) was used to classify five brain states. To verify the effectiveness of the proposed classifier, we replace the SWNN classifier by a radial basis function (RBF) networks neural network, a standard multi-layered feed-forward backpropagation network (SMN) and a multi-SVM classifier, with the same features for the classification. The results also indicate that the proposed classifier achieves a 3.83% improvement over the best results of other classifiers. We proposed a shared control method consisting of two control patterns to expand the control of BMI from the software angle. The job of path building for reaching the 'end' point was designated as an assessment task. We recorded all paths contributed by subjects and picked up relevant parameters as evaluation coefficients. With the assistance of two control patterns and series of machine learning algorithms, the proposed BMI originally achieved the motion control of a manipulator in the whole workspace. According to experimental results, we confirmed the feasibility of the proposed BMI method for 3D motion control of a manipulator using EEG during motor imagery. Copyright © 2013 Elsevier B.V. All rights reserved.
Neural correlates of consciousness.
Negrao, B L; Viljoen, M
2009-11-01
A basic understanding of consciousness and its neural correlates is of major importance for all clinicians, especially those involved with patients with altered states of consciousness. In this paper it is shown that consciousness is dependent on the brainstem and thalamus for arousal; that basic cognition is supported by recurrent electrical activity between the cortex and the thalamus at gamma band frequencies; aand that some kind of working memory must, at least fleetingly, be present for awareness to occur. The problem of cognitive binding and the role of attention are briefly addressed and it shown that consciousness depends on a multitude of subconscious processes. Although these processes do not represent consciousness, consciousness cannot exist without them.
Neural Darwinism and consciousness.
Seth, Anil K; Baars, Bernard J
2005-03-01
Neural Darwinism (ND) is a large scale selectionist theory of brain development and function that has been hypothesized to relate to consciousness. According to ND, consciousness is entailed by reentrant interactions among neuronal populations in the thalamocortical system (the 'dynamic core'). These interactions, which permit high-order discriminations among possible core states, confer selective advantages on organisms possessing them by linking current perceptual events to a past history of value-dependent learning. Here, we assess the consistency of ND with 16 widely recognized properties of consciousness, both physiological (for example, consciousness is associated with widespread, relatively fast, low amplitude interactions in the thalamocortical system), and phenomenal (for example, consciousness involves the existence of a private flow of events available only to the experiencing subject). While no theory accounts fully for all of these properties at present, we find that ND and its recent extensions fare well.
The ART of representation: Memory reduction and noise tolerance in a neural network vision system
Langley, Christopher S.
The Feature Cerebellar Model Arithmetic Computer (FCMAC) is a multiple-input-single-output neural network that can provide three-degree-of-freedom (3-DOF) pose estimation for a robotic vision system. The FCMAC provides sufficient accuracy to enable a manipulator to grasp an object from an arbitrary pose within its workspace. The network learns an appearance-based representation of an object by storing coarsely quantized feature patterns. As all unique patterns are encoded, the network size grows uncontrollably. A new architecture is introduced herein, which combines the FCMAC with an Adaptive Resonance Theory (ART) network. The ART module categorizes patterns observed during training into a set of prototypes that are used to build the FCMAC. As a result, the network no longer grows without bound, but constrains itself to a user-specified size. Pose estimates remain accurate since the ART layer tends to discard the least relevant information first. The smaller network performs recall faster, and in some cases is better for generalization, resulting in a reduction of error at recall time. The ART-Under-Constraint (ART-C) algorithm is extended to include initial filling with randomly selected patterns (referred to as ART-F). In experiments using a real-world data set, the new network performed equally well using less than one tenth the number of coarse patterns as a regular FCMAC. The FCMAC is also extended to include real-valued input activations. As a result, the network can be tuned to reject a variety of types of noise in the image feature detection. A quantitative analysis of noise tolerance was performed using four synthetic noise algorithms, and a qualitative investigation was made using noisy real-world image data. In validation experiments, the FCMAC system outperformed Radial Basis Function (RBF) networks for the 3-DOF problem, and had accuracy comparable to that of Principal Component Analysis (PCA) and superior to that of Shape Context Matching (SCM), both
Artificial Neural Network Analysis System
2007-11-02
Contract No. DASG60-00-M-0201 Purchase request no.: Foot in the Door-01 Title Name: Artificial Neural Network Analysis System Company: Atlantic... Artificial Neural Network Analysis System 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) Powell, Bruce C 5d. PROJECT NUMBER 5e. TASK NUMBER...34) 27-02-2001 Report Type N/A Dates Covered (from... to) ("DD MON YYYY") 28-10-2000 27-02-2001 Title and Subtitle Artificial Neural Network Analysis
Cooperating attackers in neural cryptography.
Shacham, Lanir N; Klein, Einat; Mislovaty, Rachel; Kanter, Ido; Kinzel, Wolfgang
2004-06-01
A successful attack strategy in neural cryptography is presented. The neural cryptosystem, based on synchronization of neural networks by mutual learning, has been recently shown to be secure under different attack strategies. The success of the advanced attacker presented here, called the "majority-flipping attacker," does not decay with the parameters of the model. This attacker's outstanding success is due to its using a group of attackers which cooperate throughout the synchronization process, unlike any other attack strategy known. An analytical description of this attack is also presented, and fits the results of simulations.
黄江涛; 高正红; 白俊强; 周铸; 赵轲
2014-01-01
The vetex deformation pattern of multi-block grids is developed based on RBF technique cou-pling with Delaunay graphic mapping to establishe grid deformation platform.The Delaunay cell is generated using the grid sparse points and block vetexs.When aerodynamic configuration deforms,the block vetex will be moved by RBF technique and the Delaunay cells will be deformed,consequently,the mapping relation could be obtained to realize grid deformation.A certain lateral aerobus is taken as an typical example,jig shape is proposed firstly,static aeroelastic analysis is processed then to get the cruise shape of jig configura-tion,and the comparison with cruise design shape is investigated.The results show that the correction of jig shape design method established in this paper is validated.On the other hand,the “mapping surface”can be used to realized CFD/CSD data transformation effectively.%基于 RBF 径向基函数建立了多块对接网格块顶点运动模式，进一步耦合 Delaunay 图映射建立网格变形技术；利用基准网格的稀疏序列节点以及区域顶点建立 Delaunay 四面体映射单元，利用 RBF 技术操作区域顶点运动，使映射单元进行变形，从而应用映射关系实现网格变形；针对某型支线客机进行了型架外形设计，并进一步进行对型架外形进行静气动弹性计算与设计巡航外形对比，验证了所建立的型架外形设计方法的正确性；静气动弹性计算中，通过建立共用的“映射曲面”，实现 CFD/CSD 数据高效交换。
Morphogenetic movements in the neural plate and neural tube: mouse.
Massarwa, R'ada; Ray, Heather J; Niswander, Lee
2014-01-01
The neural tube (NT), the embryonic precursor of the vertebrate brain and spinal cord, is generated by a complex and highly dynamic morphological process. In mammals, the initially flat neural plate bends and lifts bilaterally to generate the neural folds followed by fusion of the folds at the midline during the process of neural tube closure (NTC). Failures in any step of this process can lead to neural tube defects (NTDs), a common class of birth defects that occur in approximately 1 in 1000 live births. These severe birth abnormalities include spina bifida, a failure of closure at the spinal level; craniorachischisis, a failure of NTC along the entire body axis; and exencephaly, a failure of the cranial neural folds to close which leads to degeneration of the exposed brain tissue termed anencephaly. The mouse embryo presents excellent opportunities to explore the genetic basis of NTC in mammals; however, its in utero development has also presented great challenges in generating a deeper understanding of how gene function regulates the cell and tissue behaviors that drive this highly dynamic process. Recent technological advances are now allowing researchers to address these questions through visualization of NTC dynamics in the mouse embryo in real time, thus offering new insights into the morphogenesis of mammalian NTC.
不确定性机器人的神经网络自适应控制%Adaptive Control for Uncertain Robot Based on Neural Network
周景雷
2011-01-01
A kind of neural network adaptive control for a sort of uncertain robotic system is presented. First,the multi-joint robotic dynamical model based on the lagrange equation is transformed into a two-order system via feedback control technique. Then,combine the two-order system with the neural network adaptive control, finding out a new way to study the robotic systems. This way is to use the RBF neural network adaptive control methods to design the controller,which can guarantee the actual tracks of robot asymptotically tail after the given desired tracks without any error. At last,take a two-joint robot as an example and give its simulation results.%针对一类不确定性机器人轨迹跟踪问题,提出了一种神经网络自适应控制.首先利用反馈控制技术把基于拉格朗日方程的多关节机器人动力学模型转化成二阶系统.其次,将神经网络自适应控制方法和所转化的二阶系统相结合,找到了一种新方法来研究机器人系统,该方法是应用RBF神经网络自适应控制思想来设计控制器,所设计的控制器能够保证机器人的实际运动轨迹渐近无误差地跟踪给定的期望轨迹.最后,以两关节机器人系统为例,给出其仿真试验结果.
Complex-Valued Neural Networks
Hirose, Akira
2012-01-01
This book is the second enlarged and revised edition of the first successful monograph on complex-valued neural networks (CVNNs) published in 2006, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. In the second edition the recent trends in CVNNs research are included, resulting in e.g. almost a doubled number of references. The parametron invented in 1954 is also referred to with discussion on analogy and disparity. Also various additional arguments on the advantages of the complex-valued neural networks enhancing the difference to real-valued neural networks are given in various sections. The book is useful for those beginning their studies, for instance, in adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, robotics inspired by human neural systems, and brain-like information processing, as well as interdisciplina...
Artificial intelligence: Deep neural reasoning
Jaeger, Herbert
2016-10-01
The human brain can solve highly abstract reasoning problems using a neural network that is entirely physical. The underlying mechanisms are only partially understood, but an artificial network provides valuable insight. See Article p.471
Logic Mining Using Neural Networks
Sathasivam, Saratha
2008-01-01
Knowledge could be gained from experts, specialists in the area of interest, or it can be gained by induction from sets of data. Automatic induction of knowledge from data sets, usually stored in large databases, is called data mining. Data mining methods are important in the management of complex systems. There are many technologies available to data mining practitioners, including Artificial Neural Networks, Regression, and Decision Trees. Neural networks have been successfully applied in wide range of supervised and unsupervised learning applications. Neural network methods are not commonly used for data mining tasks, because they often produce incomprehensible models, and require long training times. One way in which the collective properties of a neural network may be used to implement a computational task is by way of the concept of energy minimization. The Hopfield network is well-known example of such an approach. The Hopfield network is useful as content addressable memory or an analog computer for s...
Neural correlates of consciousness reconsidered.
Neisser, Joseph
2012-06-01
It is widely accepted among philosophers that neuroscientists are conducting a search for the neural correlates of consciousness, or NCC. Chalmers (2000) conceptualized this research program as the attempt to correlate the contents of conscious experience with the contents of representations in specific neural populations. A notable claim on behalf of this interpretation is that the neutral language of "correlates" frees us from philosophical disputes over the mind/body relation, allowing the science to move independently. But the experimental paradigms and explanatory canons of neuroscience are not neutral about the mechanical relation between consciousness and the brain. I argue that NCC research is best characterized as an attempt to locate a causally relevant neural mechanism and not as an effort to identify a discrete neural representation, the content of which correlates with some actual experience. It might be said that the first C in "NCC" should stand for "causes" rather than "correlates."
Neural Networks in Control Applications
Sørensen, O.
The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...
Neural Networks in Control Applications
Sørensen, O.
examined, and it appears that considering 'normal' neural network models with, say, 500 samples, the problem of over-fitting is neglible, and therefore it is not taken into consideration afterwards. Numerous model types, often met in control applications, are implemented as neural network models....... - Control concepts including parameter estimation - Control concepts including inverse modelling - Control concepts including optimal control For each of the three groups, different control concepts and specific training methods are detailed described.Further, all control concepts are tested on the same......The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...
Neural communication in posttraumatic growth.
Anders, Samantha L; Peterson, Carly K; James, Lisa M; Engdahl, Brian; Leuthold, Arthur C; Georgopoulos, Apostolos P
2015-07-01
Posttraumatic growth (PTG), or positive psychological changes following exposure to traumatic events, is commonly reported among trauma survivors. In the present study, we examined neural correlates of PTG in 106 veterans with PTSD and 193 veteran controls using task-free magnetoencephalography (MEG), diagnostic interviews and measures of PTG, and traumatic event exposure. Global synchronous neural interactions (SNIs) were significantly modulated downward with increasing PTG scores in controls (p = .005), but not in veterans with PTSD (p = .601). This effect was primarily characterized by negative slopes in local neural networks, was strongest in the medial prefrontal cortex, and was much stronger and more extensive in the control than the PTSD group. The present study complements previous research highlighting the role of neural adaptation in healthy functioning.
Neural components of altruistic punishment
Emily eDu
2015-02-01
Full Text Available Altruistic punishment, which occurs when an individual incurs a cost to punish in response to unfairness or a norm violation, may play a role in perpetuating cooperation. The neural correlates underlying costly punishment have only recently begun to be explored. Here we review the current state of research on the neural basis of altruism from the perspectives of costly punishment, emphasizing the importance of characterizing elementary neural processes underlying a decision to punish. In particular, we emphasize three cognitive processes that contribute to the decision to altruistically punish in most scenarios: inequity aversion, cost-benefit calculation, and social reference frame to distinguish self from others. Overall, we argue for the importance of understanding the neural correlates of altruistic punishment with respect to the core computations necessary to achieve a decision to punish.