A sequential method for the development of visual interactive meta-simulation models using neural networks

This paper proposes a practical and efficient method for the development of visual interactive meta-simulation models using neural networks. The method first uses a randomised simulation experimental design to obtain a set of results from a previously validated simulation model. The bootstrap technique is used on these results to generate a series of neural network models that are then trained using back propagation. The visual interactive meta-simulation model consists of the collective response from the trained neural network models. The accuracy of the meta-simulation model is assessed using the bootstrap technique and improved accuracy obtained by increasing the size of the randomised simulation experimental design set and re-training. This paper describes the approach, gives results for five example problems and suggests that the method is a practical extension to visual interactive simulation.     

Using 3D Animation Techniques to Help with the Experimental Design and Analysis Phase of a Visual Interactive Simulation Project

This paper describes an interactive 3D animation approach that may help with the investigation, understanding and interpretation of results for a Visual Interactive Simulation (VIS) project. The method uses a graphics algorithm to draw on a computer screen ‘3D contour maps’ which show the response of a simulation model to changes in its input parameters. A previous paper showed that it is possible for a neural network to learn the response of a simulation. This paper shows that the speed of response of a neural network can be exploited so that 3D animation sequences of the simulation's results can be produced. It is possible to rotate the ‘3D contour map’, zoom, pan, or generally view the projection from different perspectives. Two example problems are described. The paper suggests that this approach can further improve the quality of VIS by being able to give comprehensive graphic 3D sensitivity analyses to the original problem under investigation.     

An example of simulation optimisation using a neural network metamodel: finding the optimum number of kanbans in a manufacturing system

A method of finding the optimum solution for a stochastic discrete-event system is described. A simulation model of the system is first built and then used to train a neural network metamodel. The optimisation process consists of using the metamodel to find an approximate optimum solution. This solution is then used by the simulation as the starting point in a more precise search for an optimum. The approach is demonstrated with an example that finds the optimum number of kanbans needed to control a manufacturing system.     

Solving a class of geometric programming problems by an efficient dynamic model

In this paper, a neural network model is constructed on the basis of the duality theory, optimization theory, convex analysis theory, Lyapunov stability theory and LaSalle invariance principle to solve geometric programming (GP) problems. The main idea is to convert the GP problem into an equivalent convex optimization problem. A neural network model is then constructed for solving the obtained convex programming problem. By employing Lyapunov function approach, it is also shown that the proposed neural network model is stable in the sense of Lyapunov and it is globally convergent to an exact optimal solution of the original problem. The simulation results also show that the proposed neural network is feasible and efficient.     

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.     

Multicriteria order acceptance decision support in over-demanded job shops: A neural network approach

Order acceptance is an important issue in job shop production systems where demand exceeds capacity. In this paper, a neural network approach is developed for order acceptance decision support in job shops with machine and manpower capacity constraints. First, the order acceptance decision problem is formulated as a sequential multiple criteria decision problem. Then a neural network based preference model for order prioritization is described. The neural network based preference model is trained using preferential data derived from pairwise comparisons of a number of representative orders. An order acceptance decision rule based on the preference model is proposed. Finally, a numerical example is discussed to illustrate the use of the proposed neural network approach. The proposed neural network approach is shown to be a viable method for multicriteria order acceptance decision support in over-demanded job shops.     

Reliability analysis of a consecutive r-out-of-n: F system based on neural networks

In this paper, we present a generalized Markov reliability and fault-tolerant model, which includes the effects of permanent fault and intermittent fault for reliability evaluations based on neural network techniques. The reliability of a consecutive r-out-of-n: F system was obtained with a three-layer connected neural network represents a discrete time state reliability Markov model of the system. Such that we fed the neural network with the desired reliability of the system under design. Then we extracted the parameters of the system from the neural weights at the convergence of the neural network to the desired reliability. Finally, we obtain simulation results.     

A new criterion to global exponential periodicity for discrete-time BAM neural network with infinite delays

The discrete-time bidirectional associative memory neural network with periodic coefficients and infinite delays is studied. And not by employing the continuation theorem of coincidence degree theory as other literatures, but by constructing suitable Liapunov function, using fixed point theorem and some analysis techniques, a sufficient criterion is obtained which ensures the existence and global exponential stability of periodic solution for the type of discrete-time BAM neural network. The obtained result is less restrictive to the BAM neural networks than previously known criteria. Furthermore, it can be applied to the BAM neural network which signal transfer functions are neither bounded nor differentiable. In addition, an example and its numerical simulation are given to illustrate the effectiveness of the obtained result.     

An interactive visual simulation system for industrial management

This paper describes a discrete event interactive simulation system which allows a user to watch the progress of a simulation model on a visual display terminal. The user may interact with the model in a flexible manner, in order to explore the consequence of alternative decisions or strategies. Output from the simulation may be directed, in an animated form, to a refresh display computer graphics screen, a black and white visual display unit or an intelligent colour visual display divice. The interactive system has been specifically designed to assist in decision making processes associated with industrial management problem situations.     

First principles versus artificial neural network modelling of a solar desalination system with experimental validation

ABSTRACT

The present study mainly focuses on enhancing the performance of solar still unit using solar energy through cylindrical parabolic collector and solar panels. A 300 W solar panel is used to heat saline water by thermal elements outside the solar still unit. Solar panels are cooled during the hot hours of the day; thus, reducing their temperature may lead to an increase in solar panel efficiency followed by an increase in the efficiency of the solar still unit. The maximum amount of freshwater used in the experiment was 2.132 kg/day. The experiments were modelled using ANNs. Based on neural network simulation results, there is a significant correlation between experimental data and neural network modelling. This paper compares experimental data with data obtained from mathematical modelling and ANNs. As a conclusion, the artificial neural network prediction has been more accurate than the simplified first principles model presented.     

Global exponential stability of impulsive Cohen–Grossberg neural network with time-varying delays

In this paper, the impulsive Cohen–Grossberg neural network model with time-varying delays is considered. Applying the idea of vector Lyapunov function, M-matrix theory and inequality technique, several new sufficient conditions are obtained to ensure global exponential stability of equilibrium point for impulsive Cohen–Grossberg neural network with time-varying delays. These results generalize a few previous known results and remove some restrictions on the neural network. An example is given to show the effectiveness of the obtained results. It is believed that these results are significant and useful for the design and applications of the Cohen–Grossberg neural network.     

基于径向基函数神经网络的流程企业供应链预测仿真

本文在比较预测方法的基础上，采用径向基函数（RBF）神经网络技术建立流程企业供应链预测模型，进行了实例预测仿真，并将预测结果与BP网络的预测结果进行了比较。结果表明，RBF网络误差小于BP网络，其中平方根RBF网络的预测仿真误差最小，而BP网络的误差最大。     

Portfolio selection in the Spanish stock market by interactive multiobjective programming

This study examines new versions of two interactive methods to address multiobjective problems, the aim of which is to enable the decision maker to reach a solution within the range of those considered efficient in a portfolio selection model, in which several objectives are pursued concerning risk and return and given that these are clearly conflicting objectives, the profile of the model proposed is multicriteria. Normally the range of efficient portfolios is fairly extensive thus making the selection of a single one an onerous task. In order to facilitate this process, interactive methods are used aimed at guiding the decision maker towards the optimal solution based on his preferences. Several adaptations were carried out on the original methods in order to facilitate the interactive process, improving the quality of the obtained portfolios, and these were applied to data obtained from the Madrid Stock Market, interaction taking place with two decision makers, one of whom was more aggressive than the other in their selections made.     

具有变时滞和脉冲效应的Hopfield神经网络的全局指数稳定性

讨论了一类具有变时滞和脉冲效应的Hopfield神经网络模型．利用按段连续的向量Liapunov思想方法,研究了脉冲时滞神经网络的全局指数稳定性．例子及其数值仿真说明了结果的有效性．推广和改进了已有文献的一些结果．     

基于遗传算法和半参数回归的神经网络集成股市预测研究

股票时间序列预测在经济和管理领域具有重要的应用前景,也是很多商业和金融机构成功的基础.首先利用奇异谱分析对股市时间序列重构,降低噪声并提取趋势序列.再利用C-C算法确定股市时间序列的嵌入维数和延迟阶数,对股市时间序列进行相空间重构,生成神经网络的学习矩阵.进一步利用Boosting技术和不同的神经网络模型,生成神经网络集成个体.最后采用带有惩罚项的半参数回归模型进行集成,并利用遗传算法选择最优的光滑参数,以此建立遗传算法和半参数回归的神经网络集成股市预测模型.通过上证指数开盘价进行实例分析,与传统的时间序列分析和其他集成方法对比,发现该方法能获得更准确的预测结果.计算结果表明该方法能充分反映股票价格时间序列趋势,为金融时间序列预测提供一个有效方法.     

一类二元离散神经网络模型的渐近性

本文考虑的是一类具有分段常数非线性时滞差分系统,该系统可作为二元人工神经网络模型的离散形式,本文得到了系统解的渐近性的一些结果。     

An Investigation of Visual Interactive Simulation Methods Using the Job-Shop Scheduling Problem

This paper describes the use of the job-shop scheduling problem in order to investigate the potential of visual interactive simulation methods. Batch simulation methods are compared with visual interactive simulation methods for the job-shop problem. The paper shows that improved solutions can be obtained by having a visual, dynamic representation of a job-shop problem.     

Representing and Learning Distributions with the Aid of a Neural Network

This paper describes a method by which a neural network learns to fit a distribution to sample data. The neural network may be used to replace the input distributions required in a simulation or mathematical model and it allows random variates to be generated for subsequent use in the model. Results are given for several data sets which indicate the method is robust and can represent different families of continuous distributions. The neural network is a three-layer feed-forward network of size (1-3-3-1). This paper suggests that the method is an alternative approach to the problem of selection of suitable continuous distributions and random variate generation techniques for use in simulation and mathematical models.     

Bursting synchronization in networks with long-range coupling mediated by a diffusing chemical substance

Many networks of physical and biological interest are characterized by a long-range coupling mediated by a chemical which diffuses through a medium in which oscillators are embedded. We considered a one-dimensional model for this effect for which the diffusion is fast enough so as to be implemented through a coupling whose intensity decays exponentially with the lattice distance. In particular, we analyzed the bursting synchronization of neurons described by two timescales (spiking and bursting activity), and coupled through such a long-range interaction network. One of the advantages of the model is that one can pass from a local (Laplacian) type of coupling to a global (all-to-all) one by varying a single parameter in the interaction term. We characterized bursting synchronization using an order parameter which undergoes a transition as the coupling parameters are changed through a critical value. We also investigated the role of an external time-periodic signal on the bursting synchronization properties of the network. We show potential applications in the control of pathological rhythms in biological neural networks.