Stereoscopic neuro-vision for three-dimensional object recognition

Neural network technology has provided new methodologies for solving difficult computational problems in many areas of science and engineering. Neural networks, along with their varied learning techniques, have replaced complicated mathematical models, complex estimation techniques, or optimization procedures in several applications. One particular area seeing much benefit from these new computational paradigms is machine vision. The machine vision field has long needed approaches offering robust operation, massive parallel and distributed computational capabilities, and graceful system degradation. Neural networks offer these capabilities along with the potential of direct hardware implementation.This article demonstrates several novel uses of artificial neural networks in the processing of stereoscopic images for three-dimensional object recognition. It will be shown that several different types of neural networks can be combined, with a rule base and conventional processing techniques, for the creation of a powerful 3-D object recognition system. This hybrid system has been tested on several simple objects and the results are presented.     

Evaluación de la habitabilidad de edificios afectados por sismo utilizando la teoría de conjuntos difusos y las redes neuronales artificiales

The fuzzy sets theory and the artificial neural networks are computational intelligence tools which are nowadays widely used in earthquake engineering. This paper develops a method and a computer program which use these computational intelligence tools in order to support the damage and safety evaluation of buildings after strong earthquakes. The model uses an artificial neural network with three layers and a Kohonen learning algorithm; it also uses fuzzy sets in order to manage subjective information such as linguistic qualification of the damage levels in buildings and a fuzzy rule base to support the decision making process. All these techniques are incorporated in the developed computer program. The input data is the subjective and incomplete information about the building state obtained by possibly non experienced evaluators in the field of the seismic performance of buildings. The proposed method is implemented in a tool especially useful in the emergency response phase, when it supports the decision making regarding the building habitability and reparability. In order to show its effectiveness, two examples are included for two different types of buildings.     

What is a universal computing machine?

A computer is classically formalised as a universal Turing machine or a similar device. However over the years a lot of research has focused on the computational properties of dynamical systems other than Turing machines, such cellular automata, artificial neural networks, mirrors systems, etc.In this paper we propose a unifying formalism derived from a generalisation of Turing’s arguments. Then we review some of universal systems proposed in the literature and show that are particular case of this formalism. Finally, we review some of the attempts to understand the relation between dynamical and computational properties of a system.     

Modeling of thermotransport phenomenon in metal alloys using artificial neural networks

Thermodiffusion in molten metals, also known as thermotransport, a phenomenon in which constituent elements of an alloy separate under the influence of non-uniform temperature field, is of significance in several applications. However, due to the complex inter-particle interactions, there is no theoretical formulation that can model this phenomenon with adequate accuracy. Keeping in mind the severe deficiencies of the present day thermotransport models and an urgent need of a reliable method in several engineering applications ranging from crystal growth to integrated circuit design to nuclear reactor designs, an engineering approach has been taken in which neurocomputing principles have been employed to develop artificial neural network models to study and quantify the thermotransport phenomenon in binary metal alloys. Unlike any other thermotransport model for molten metals, the neural network approach has been validated for several types of binary alloys, viz., concentrated, dilute, isotopic and non-isotopic metals. Additionally, to establish the soundness of the model and to highlight its potential as a unified computational analysis tool, it ability to capture several thermotransport trends has been shown. Comparison with other models from the literature has also been made indicating a superior performance of this technique with respect to several other well established thermotransport models.     

Forecasting nonlinear time series with a hybrid methodology

In recent years, artificial neural networks (ANNs) have been used for forecasting in time series in the literature. Although it is possible to model both linear and nonlinear structures in time series by using ANNs, they are not able to handle both structures equally well. Therefore, the hybrid methodology combining ARIMA and ANN models have been used in the literature. In this study, a new hybrid approach combining Elman’s Recurrent Neural Networks (ERNN) and ARIMA models is proposed. The proposed hybrid approach is applied to Canadian Lynx data and it is found that the proposed approach has the best forecasting accuracy.     

Differentiating between good credits and bad credits using neuro-fuzzy systems

To evaluate consumer loan applications, loan officers use many techniques such as judgmental systems, statistical models, or simply intuitive experience. In recent years, fuzzy systems and neural networks have attracted the growing interest of researchers and practitioners. This study compares the performance of artificial neuro-fuzzy inference systems (ANFIS) and multiple discriminant analysis models to screen potential defaulters on consumer loans. Using a modeling sample and a test sample, we find that the neuro-fuzzy system performs better than the multiple discriminant analysis approach to identify bad credit applications. Further, neuro-fuzzy systems have many advantages over traditional computational methods. Neuro-fuzzy system models are flexible, more tolerant of imprecise data, and can model non-linear functions of arbitrary complexity.     

An airfoil optimization technique for wind turbines

Optimization algorithms coupled with computational fluid dynamics are used for wind turbines airfoils design. This differs from the traditional aerospace design process since the lift-to-drag ratio is the most important parameter and the angle of attack is large. Computational fluid dynamics simulations are performed with the incompressible Reynolds-averaged Navier–Stokes equations in steady state using a one equation turbulence model. A detailed validation of the simulations is presented and a computational domain larger than suggested in literature is shown to be necessary. Different approaches to parallelization of the computational code are addressed. Single and multiobjective genetic algorithms are employed and artificial neural networks are used as a surrogate model. The use of artificial neural networks is shown to reduce computational time by almost 50%.     

The use of cascade-correlation neural networks in University fund raising

In recent years, many Colleges and Universities in the USA have been facing a serious financial crisis since many state governments have reduced their support for higher education. There is no doubt that one of the solutions to this crisis depends on the successful implementation of University fund raising programs. Identifying the potential donors is an important part of this process. The objective of this research was to develop a cascade-correlation neural network to predict the types of people who would most likely be potential donors. A comparison of the classification accuracy between neural networks and multiple discriminant analyses (MDA) was also conducted. Our results indicated that neural networks could perform as well as MDA in overall accuracy. Furthermore, neural networks could predict with a lot more accuracy the actual donor (Type I hit) than MDA. Our study is the first published case study on the use of artificial neural networks for University fund raising.     

Recurrent neural dynamic models for equilibrium and eigenvalue problems

Neural networks (NN) have been used in a number of interesting applications. In this paper, two neural dynamic models which belong to the class of recurrent neural networks (RNN) have been formulated for the solution of equilibrium and eigenvalue problems. The RNN is comprised of two layers, namely, variable layer and constraint layer, which correspond to the number of design variables in the problem. In addition, the recurrent connections and feed forward connections are used to represent the incremental values in the design parameters. The stability of the neural dynamic model for the equilibrium problem has been guaranteed using Lyapunov's function. Illustrative examples and results of the computer simulation of the neural dynamic model have also been presented.     

Approximating Unknown Mappings: An Experimental Evaluation

Different methodologies have been introduced in recent years with the aim of approximating unknown functions. Basically, these methodologies are general frameworks for representing non-linear mappings from several input variables to several output variables. Research into this problem occurs in applied mathematics (multivariate function approximation), statistics (nonparametric multiple regression) and computer science (neural networks). However, since these methodologies have been proposed in different fields, most of the previous papers treat them in isolation, ignoring contributions in the other areas. In this paper we consider five well known approaches for function approximation. Specifically we target polynomial approximation, general additive models (Gam), local regression (Loess), multivariate additive regression splines (Mars) and artificial neural networks (Ann).Neural networks can be viewed as models of real systems, built by tuning parameters known as weights. In training the net, the problem is to find the weights that optimize its performance (i.e. to minimize the error over the training set). Although the most popular method for Ann training is back propagation, other optimization methods based on metaheuristics have recently been adapted to this problem, outperforming classical approaches. In this paper we propose a short term memory tabu search method, coupled with path relinking and BFGS (a gradient-based local NLP solver) to provide high quality solutions to this problem. The experimentation with 15 functions previously reported shows that a feed-forward neural network with one hidden layer, trained with our procedure, can compete with the best-known approximating methods. The experimental results also show the effectiveness of a new mechanism to avoid overfitting in neural network training.     

基于卷积神经网络模型数值求解双曲型偏微分方程的研究

人工神经网络近年来得到了快速发展,将此方法应用于数值求解偏微分方程是学者们关注的热点问题.相比于传统方法其具有应用范围广泛(即同一种模型可用于求解多种类型方程)、网格剖分条件要求低等优势,并且能够利用训练好的模型直接计算区域中任意点的数值.该文基于卷积神经网络模型,对传统有限体积法格式中的权重系数进行优化,以得到在粗粒...     

A Neural Network Application in Personnel Scheduling

In this paper, we present and evaluate a neural network model for solving a typical personnel-scheduling problem, i.e. an airport ground staff rostering problem. Personnel scheduling problems are widely found in servicing and manufacturing industries. The inherent complexity of personnel scheduling problems has normally resulted in the development of integer programming-based models and various heuristic solution procedures. The neural network approach has been admitted as a promising alternative to solving a variety of combinatorial optimization problems. While few works relate neural network to applications of personnel scheduling problems, there is great theoretical and practical value in exploring the potential of this area. In this paper, we introduce a neural network model following a relatively new modeling approach to solve a real rostering case. We show how to convert a mixed integer programming formulation to a neural network model. We also provide the experiment results comparing the neural network method with three popular heuristics, i.e. simulated annealing, Tabu search and genetic algorithm. The computational study reveals some potential of neural networks in solving personnel scheduling problems.     

Optimization of manufacturing systems using a neural network metamodel with a new training approach

In this study, two manufacturing systems, a kanban-controlled system and a multi-stage, multi-server production line in a diamond tool production system, are optimized utilizing neural network metamodels (tst_NNM) trained via tabu search (TS) which was developed previously by the authors. The most widely used training algorithm for neural networks has been back propagation which is based on a gradient technique that requires significant computational effort. To deal with the major shortcomings of back propagation (BP) such as the tendency to converge to a local optimal and a slow convergence rate, the TS metaheuristic method is used for the training of artificial neural networks to improve the performance of the metamodelling approach. The metamodels are analysed based on their ability to predict simulation results versus traditional neural network metamodels that have been trained by BP algorithm (bp_NNM). Computational results show that tst_NNM is superior to bp_NNM for both of the manufacturing systems.     

人工神经网络在评定射击效率中的应用研究

将BP、RB、GRNN等人工神经网络引入火炮射击效率评定的计算中.通过实例运算,分析了各种神经网络在实际应用中各自的特点和需注意的问题,得到了有益的结论.     

On the Analysis of the Virtual Waiting Time in Open Queueing Networks

The model of an open queueing network in heavy traffic has been developed. These models are mathematical models of computer networks in heavy traffic. A limit theorem has been presented for the virtual waiting time of a customer in heavy traffic in open queueing networks. Finally, we present an application of the theorem—a reliability model from computer network practice.     

人工神经网络在SARS疫情分析与预测中的应用

讨论人工神经网络在 SARS疫情分析与预测中的应用 .采用三层结构的反向传播网络 ( Backpropagation network,简称 BP网络 ) ,对 SARS在中国的传播与流行趋势及控制策略建立了网络模型 .并利用实际数据拟合参数 ,针对北京、山西的疫情进行了计算仿真 .结果表明 ,该网络模型算法收敛速度较快 ,预测精度很高     

Mittag-Leffler stability and adaptive impulsive synchronization of fractional order neural networks in quaternion field

Fractional order quaternion-valued neural networks are a type of fractional order neural networks for which neuron state, synaptic connection strengths, and neuron activation functions are quaternion. This paper is dealing with the Mittag-Leffler stability and adaptive impulsive synchronization of fractional order neural networks in quaternion field. The fractional order quaternion-valued neural networks are separated into four real-valued systems forming an equivalent four real-valued fractional order neural networks, which decreases the computational complexity by avoiding the noncommutativity of quaternion multiplication. Via some fractional inequality techniques and suitable Lyapunov functional, a brand new criterion is proposed first to ensure the Mittag-Leffler stability for the addressed neural networks. Besides, the combination of quaternion-valued adaptive and impulsive control is intended to realize the asymptotically synchronization between two fractional order quaternion-valued neural networks. Ultimately, two numerical simulations are provided to check the accuracy and validity of our obtained theoretical results.     

Artificial neural networks in bankruptcy prediction: General framework and cross-validation analysis

In this paper, we present a general framework for understanding the role of artificial neural networks (ANNs) in bankruptcy prediction. We give a comprehensive review of neural network applications in this area and illustrate the link between neural networks and traditional Bayesian classification theory. The method of cross-validation is used to examine the between-sample variation of neural networks for bankruptcy prediction. Based on a matched sample of 220 firms, our findings indicate that neural networks are significantly better than logistic regression models in prediction as well as classification rate estimation. In addition, neural networks are robust to sampling variations in overall classification performance.     

Modelling framework for artificial hybrid dynamical systems

Many current industry branches use hybrid approaches to solve complex application problems. Over the last decades, different tools for the simulation of such hybrid systems (e.g. Hysdel and YAMLIP) as well as the identification of hybrid systems (e.g. HIT, MLP and OAF NN) have been developed. The framework presented in this work facilitates the integration of artificial feed-forward neural networks in the modelling process of hybrid dynamical systems (HDS). Additionally, the framework provides a structured language for characterising these feed-forward networks itself. Therefore, an interdisciplinary exchange in the field of neural networks and its integration into hybrid dynamical systems is enabled. Focusing on hybrid systems with autonomous events, two different approaches, namely the artificial hybrid model and the artificial hybrid dynamics, are introduced. Challenges of the modelling process of HDS are reflected and advantages as well as disadvantages are discussed. The case study includes two common examples of HDS and analyses the simulation results and examines limitations of the modelling framework.     

Estimations of trout density and biomass: a neural networks approach

In this paper, we report the use of artificial neural networks to predict the density and biomass of trout in the Pyrenees mountains from 8 physical parameters of the environment. The results obtained with a three-layered neural network are presented. Studies have been undertaken with 1 or 4 variables in the output layer of the network. Results on the test set (generalization of models) are satisfactory with determination coefficients R² exceeding 0.76.