PLS分析与RBF神经网络耦合环境模型

鉴于城市大气环境质量受到诸多复杂因素影响,且各因素间存在多重相关性,本文将偏最小二乘(PLS)分析与人工神经网络径向基网络(RBF)耦合,建立偏最小二乘径向基神经网络模型(PLSRBF),应用于贵阳大气环境质量的检验和预测。实例表明:PLSRBF模型可对原多自变量模型进行降维简化,并可有效提取解释变量信息,防止信息丢失,且具有较强的拟合能力。     

Application of RBF neural network improved by peak density function in intelligent color matching of wood dyeing

According to the characteristics of wood dyeing, we propose a predictive model of pigment formula for wood dyeing based on Radial Basis Function (RBF) neural network. In practical application, however, it is found that the number of neurons in the hidden layer of RBF neural network is difficult to determine. In general, we need to test several times according to experience and prior knowledge, which is lack of a strict design procedure on theoretical basis. And we also don’t know whether the RBF neural network is convergent. This paper proposes a peak density function to determine the number of neurons in the hidden layer. In contrast to existing approaches, the centers and the widths of the radial basis function are initialized by extracting the features of samples. So the uncertainty caused by random number when initializing the training parameters and the topology of RBF neural network is eliminated. The average relative error of the original RBF neural network is 1.55% in 158 epochs. However, the average relative error of the RBF neural network which is improved by peak density function is only 0.62% in 50 epochs. Therefore, the convergence rate and approximation precision of the RBF neural network are improved significantly.     

Nonlinear Dynamic Modelling of a Gas Engine Using an RBF-Network

A Radial Basis Function network (RBFN) is used to obtain a model of a gas engine, an unstable two-input/single-output system (MISO-system), to be used for the design of the speed control system. The RBFN-centers are chosen using the stepwise orthogonalization algorithm, and an input space compression which helps to avoid sparse data sets is presented. The influence of noisy data is investigated in a nonlinear system example, in order to find the cause of the model errors in the case of the gas engine model. The quality of the nonlinear RBFN-model is demonstrated by comparing measured and simulated data.     

Forecasting foreign exchange rates with adaptive neural networks using radial-basis functions and Particle Swarm Optimization

The motivation for this paper is to introduce a hybrid neural network architecture of Particle Swarm Optimization and Adaptive Radial Basis Function (ARBF–PSO), a time varying leverage trading strategy based on Glosten, Jagannathan and Runkle (GJR) volatility forecasts and a neural network fitness function for financial forecasting purposes. This is done by benchmarking the ARBF–PSO results with those of three different neural networks architectures, a Nearest Neighbors algorithm (k-NN), an autoregressive moving average model (ARMA), a moving average convergence/divergence model (MACD) plus a na?¨ve strategy. More specifically, the trading and statistical performance of all models is investigated in a forecast simulation of the EUR/USD, EUR/GBP and EUR/JPY ECB exchange rate fixing time series over the period January 1999–March 2011 using the last 2 years for out-of-sample testing.     

A patient adaptable ECG beat classifier based on neural networks

A novel supervised neural network-based algorithm is designed to reliably distinguish in electrocardiographic (ECG) records between normal and ischemic beats of the same patient. The basic idea behind this paper is to consider an ECG digital recording of two consecutive R-wave segments (RRR interval) as a noisy sample of an underlying function to be approximated by a fixed number of Radial Basis Functions (RBF). The linear expansion coefficients of the RRR interval represent the input signal of a feed-forward neural network which classifies a single beat as normal or ischemic. The system has been evaluated using several patient records taken from the European ST-T database. Experimental results show that the proposed beat classifier is very reliable, and that it may be a useful practical tool for the automatic detection of ischemic episodes.     

Optimization of window-openings design for thermal comfort in naturally ventilated buildings

In the present study, a novel computational method to optimize window design for thermal comfort in naturally ventilated buildings is described. The methodology is demonstrated by means of a prototype case, which corresponds to a single-room, rural-type building. Initially, the airflow in and around the building is simulated using a Computational Fluid Dynamics model. Local climate data are recorded by a weather station and the prevailing conditions are imposed in the CFD model as inlet boundary conditions. The produced airflow patterns are utilized to predict thermal comfort indices, i.e. the PMV and its modifications for non-air-conditioned buildings, with respect to various occupant activities. Mean values of these indices (output/objective variables) within the occupied zone are calculated for different window-to-door configurations and building directions (input/design variables), to generate a database of input-output data pairs. The database is then used to train and validate Radial Basis Function Artificial Neural Network (RBF ANN) input-output “meta-models”. The produced meta-models are used to formulate an optimization problem, which takes into account thermal comfort constraints recommended by design guidelines. It is concluded that the proposed methodology provides the optimal window designs, which correspond to the best objective variables for both single and several activity levels.     

3标度层次分析法下盘锦人口预测方法的优选

基于目前我国人口数量预测方法繁多,优缺点不一的现状,以盘锦市1978～2008年人口数据为基础,分别采用曲线回归、GM(1,1)与等维递补灰色模型、BP神经网络与RBF神经网络、马尔萨斯模型与费尔哈斯模型、宋健模型与Leslie矩阵方法分别对盘锦市2030、2050、2070、2090年人口进行预测,并根据预测结果设置了盘锦市人口预测方法的多目标定量优选体系,并采用Matla,b2009b软件运用3标度层次分析法方法进行了预测方法的优选.优选结果显示在盘锦市人口预测中,径向基网络(RBF)为最优方案.     

Identification of nonlinear system using extreme learning machine based Hammerstein model

In this paper, a new method for nonlinear system identification via extreme learning machine neural network based Hammerstein model (ELM-Hammerstein) is proposed. The ELM-Hammerstein model consists of static ELM neural network followed by a linear dynamic subsystem. The identification of nonlinear system is achieved by determining the structure of ELM-Hammerstein model and estimating its parameters. Lipschitz quotient criterion is adopted to determine the structure of ELM-Hammerstein model from input–output data. A generalized ELM algorithm is proposed to estimate the parameters of ELM-Hammerstein model, where the parameters of linear dynamic part and the output weights of ELM neural network are estimated simultaneously. The proposed method can obtain more accurate identification results with less computation complexity. Three simulation examples demonstrate its effectiveness.     

An adaptive least-squares collocation radial basis function method for the HJB equation

We present a novel numerical method for the Hamilton–Jacobi–Bellman equation governing a class of optimal feedback control problems. The spatial discretization is based on a least-squares collocation Radial Basis Function method and the time discretization is the backward Euler finite difference. A stability analysis is performed for the discretization method. An adaptive algorithm is proposed so that at each time step, the approximate solution can be constructed recursively and optimally. Numerical results are presented to demonstrate the efficiency and accuracy of the method.     

Improving Prediction of Neural Networks: A Study of Two Financial Prediction Tasks

Neural networks are excellent mapping tools for complex financial data. Their mapping capabilities however do not always result in good generalizability for financial prediction models. Increasing the number of nodes and hidden layers in a neural network model produces better mapping of the data since the number of parameters available to the model increases. This is detrimental to generalizability of the model since the model memorizes idiosyncratic patterns in the data. A neural network model can be expected to be more generalizable if the model architecture is made less complex by using fewer input nodes. In this study we simplify the neural network by eliminating input nodes that have the least contribution to the prediction of a desired outcome. We also provide a theoretical relationship of the sensitivity of output variables to the input variables under certain conditions. This research initiates an effort in identifying methods that would improve the generalizability of neural networks in financial prediction tasks by using mergers and bankruptcy models. The result indicates that incorporating more variables that appear relevant in a model does not necessarily improve prediction performance.     

Neural network as a simulation metamodel in economic analysis of risky projects

An artificial neural network (ANN) model for economic analysis of risky projects is presented in this paper. Outputs of conventional simulation models are used as neural network training inputs. The neural network model is then used to predict the potential returns from an investment project having stochastic parameters. The nondeterministic aspects of the project include the initial investment, the magnitude of the rate of return, and the investment period. Backpropagation method is used in the neural network modeling. Sigmoid and hyperbolic tangent functions are used in the learning aspect of the system. Analysis of the outputs of the neural network model indicates that more predictive capability can be achieved by coupling conventional simulation with neural network approaches. The trained network was able to predict simulation output based on the input values with very good accuracy for conditions not in its training set. This allowed an analysis of the future performance of the investment project without having to run additional expensive and time-consuming simulation experiments.     

Numerical solution of the system of second-order boundary value problems using the local radial basis functions based differential quadrature collocation method

In this research, we propose a numerical scheme to solve the system of second-order boundary value problems. In this way, we use the Local Radial Basis Function Differential Quadrature (LRBFDQ) method for approximating the derivative. The LRBFDQ method approximates the derivatives by Radial Basis Functions (RBFs) interpolation using a small set of nodes in the support domain of any node. So the new scheme needs much less computational work than the globally supported RBFs collocation method. We use two techniques presented by Bayona et al. (2011, 2012) [29], [30] to determine the optimal shape parameter. Some examples are presented to demonstrate the accuracy and easy implementation of the new technique. The results of numerical experiments are compared with the analytical solution, finite difference (FD) method and some published methods to confirm the accuracy and efficiency of the new scheme presented in this paper.     

基于模糊径向基函数神经网络的模糊数据建模研究

提出将模糊径向基函数神经网络(FRBFN)用于模糊数据的建模,并提出融和圆锥模糊向量的聚类方法和模糊线性回归的学习算法。仿真研究表明．FRBFN及其算法在模糊数据建模方面有一定的优势。     

导弹武器系统费用预测的径向基函数网络方法

提出采用径向基函数网络理论来估算导弹武器系统的费用,武器系统的费用与武器特征参数的关系可通过神经网络的阈值和权值来表现,并且对几种用于导弹武器系统费用分析的数据分析结果进行比较分析.通过实例说明了应用径向基函数网络进行导弹武器系统费用分析不但算法可行性好、拟合精度高,而且具有运算简单,结果可靠的特点.     

On the Generalization Problem

The generalization problem considered in this paper assumes that a limited amount of input and output data from a system is available, and that from this information an estimate of the output produced by another input is required. The ideas arose in the study of neural networks, but apply equally to any approximation approach. The main result is that the type of neural network to be used for generalization should be determined by the prior knowledge about the nature of the output from the system. Without such information, either of two networks matching the training data is equally likely to be the better at estimating the output generated by the same system at a new input. Therefore, the search for an optimum generalization network for use on all problems is inappropriate.For both (0, 1) and accurate real outputs, it is shown that simple approximations exist that fit the data, so these will be equally likely to generalize better than more sophisticated networks, unless prior knowledge is available that excludes them. For noisy real outputs, it is shown that the standard least squares approach forces the neural network to approximate an incorrect process; an alternative approach is outlined, which again is much easier to learn and use.     

Applications of information theory,genetic algorithms,and neural models to predict oil flow

This work introduces a new information-theoretic methodology for choosing variables and their time lags in a prediction setting, particularly when neural networks are used in non-linear modeling. The first contribution of this work is the Cross Entropy Function (XEF) proposed to select input variables and their lags in order to compose the input vector of black-box prediction models. The proposed XEF method is more appropriate than the usually applied Cross Correlation Function (XCF) when the relationship among the input and output signals comes from a non-linear dynamic system. The second contribution is a method that minimizes the Joint Conditional Entropy (JCE) between the input and output variables by means of a Genetic Algorithm (GA). The aim is to take into account the dependence among the input variables when selecting the most appropriate set of inputs for a prediction problem. In short, theses methods can be used to assist the selection of input training data that have the necessary information to predict the target data. The proposed methods are applied to a petroleum engineering problem; predicting oil production. Experimental results obtained with a real-world dataset are presented demonstrating the feasibility and effectiveness of the method.     

A discrete adapted hierarchical basis solver for radial basis function interpolation

In this paper we develop a discrete Hierarchical Basis (HB) to efficiently solve the Radial Basis Function (RBF) interpolation problem with variable polynomial degree. The HB forms an orthogonal set and is adapted to the kernel seed function and the placement of the interpolation nodes. Moreover, this basis is orthogonal to a set of polynomials up to a given degree defined on the interpolating nodes. We are thus able to decouple the RBF interpolation problem for any degree of the polynomial interpolation and solve it in two steps: (1) The polynomial orthogonal RBF interpolation problem is efficiently solved in the transformed HB basis with a GMRES iteration and a diagonal (or block SSOR) preconditioner. (2) The residual is then projected onto an orthonormal polynomial basis. We apply our approach on several test cases to study its effectiveness.     

An improvement of chaos-based hash function in cryptanalysis approach: An experience with chaotic neural networks and semi-collision attack

In this paper, the chaos-based hash function is analyzed, then an improved version of chaos-based hash function is presented and discussed using chaotic neural networks. It is based on the piecewise linear chaotic map that is used as a transfer function in the input and output of the neural network layer. The security of the improved hash function is also discussed and a novel type of collision resistant hash function called semi-collision attack is proposed, which is based on the collision percentage between the two hash values. In the proposed attack particle swarm optimization algorithm is used to define the fitness function parameters. Finally, numerical and simulation results provides strong collision resistance and high performance efficiency.     

Evaluation of fuzzy regression models by fuzzy neural network

In this paper, a novel hybrid method based on fuzzy neural network for approximate fuzzy coefficients (parameters) of fuzzy linear and nonlinear regression models with fuzzy output and crisp inputs, is presented. Here a neural network is considered as a part of a large field called neural computing or soft computing. Moreover, in order to find the approximate parameters, a simple algorithm from the cost function of the fuzzy neural network is proposed. Finally, we illustrate our approach by some numerical examples.     

基于BP网络的混凝土耗能器骨架曲线拟合

结合5种混凝土延性柱耗能器在低周期反复荷载作用下的试验数据研究,利用神经网络的工作原理,通过建立神经网络的输入层、隐含层、输出层,确定输入单元、输出单元和隐含层节点数,从而建立了BP神经网络的模型,并根据已有的部分试验数据数据.对网络进行训练,对各种混凝土延性柱耗能器骨架曲线进行了预测拟合,实现混凝土延性柱耗能器骨架曲线的数字化,使其成为具有分析和判断的拟合曲线功能,完整的描绘混凝土延性柱耗能器的骨架曲线,为后续混凝土延性柱耗能器性能研究的仿真模拟提供了可靠的数据模型.结果表明,这种方法是可行的.