A neural network approach to long-run exchange rate prediction

In the economics literature on exchange rate determination no theory has yet been found that performs well in out-of-sample prediction experiments. Until today the simple random walk model has never been significantly outperformed. We have identified a set of fundamental long-run exchange rate models from literature that are well-known among economists. This paper investigates whether a neural network representation of these structural exchange rate models improves the out-of-sample prediction performance of the linear versions. Empirical results are reported in the case of the US dollar-Deutsche Mark exchange rate.     

纤维素类高分子玻璃化温度的QSPR研究

玻璃化温度是表征聚合物性能的一个重要的物理化学参数,研究玻璃化温度对聚合物分子设计和改性具有重要意义.本文采用密度泛函论在B3LYP/6-31G(d)水平上优化22种纤维素结构单元,得到分子总能量EHF、热力学能ETHERMAL、最高占据轨道能EHOMO、最低空轨道能ELUMO、最大净负电荷q-、偶极距μ、取代基长度L等7个量子化学参数,并用逐步线性回归方法探讨这些参数与纤维素玻璃化温度(Tg)的关系,建立定量结构-性质模型(QSPR):Tg=94.343-581.544q+0.114EHF-309.152ELUMO.该模型判定系数R2=0.940,表明所选自变量与因变量相关性很高,各参数方差膨胀因子VIF均远小于10,不存在多重共线性问题.最后,用留一法(LOO)检测模型的可信度,结果表明,预测值和实验值吻合较好,交叉验证相关系数为0.888,说明本文所得模型可靠,可用于研究纤维素类聚合物的玻璃化温度,为设计和改性纤维素分子提供理论指导.     

甘油-水二元低温保护液玻璃化转变温度的理论预测

玻璃化是牛物器官低温保存的最有效方式,玻璃化转变温度(Tg)是表征和研究低温保护液玻璃化过程的重要参数.目前,测定玻璃化转变温度最常用方法是差示扫描量热法(DSC)和动态热机械分析法(DMA).本文初次尝试利用等温等压下的分子动力学模拟预测甘油水溶液(60%,wt/%)的玻璃化转变温度.在90 K～273 K范围内,逐个温度点模拟计算体系的恒压热容(Cp)、密度(P)、无定形晶胞体积(Vcell)、特征原子的径向分布函数和氧键的形成几率等状态参数.通过这些参数随温度的变化规律和拐点,确定甘油水溶液的Tg值.分子模拟计算结果表明:模拟计算的Tg值(160.06 K～167.51 K)与DSC实验测定结果(163.60 K～167.10 K)几乎一样.可见,分子动力学模拟(MD)可以预测甘油-水二元低温保护液的玻璃化转变温度,这种方法也可推广到其他的多元低温保护液.     

A neural network approach to freeway network traffic control

The paper investigates the application of a feedforward neural network approach to freeway network control via variable direction recommendations at bifurcation locations. A nonlinear control problem is formulated and solved first by use of computationally expensive nonlinear optimization techniques. A feedforward neural network is then trained by optimally adjusting its weights so as to reproduce the optimal control law for a limited number of traffic scenarios. Generalisation properties of the neural network are investigated and a discussion of advantages and disadvantages compared with alternative control approaches is provided.     

A neural network approach to job-shop scheduling

A novel analog computational network is presented for solving NP-complete constraint satisfaction problems, i.e. job-shop scheduling. In contrast to most neural approaches to combinatorial optimization based on quadratic energy cost function, the authors propose to use linear cost functions. As a result, the network complexity (number of neurons and the number of resistive interconnections) grows only linearly with problem size, and large-scale implementations become possible. The proposed approach is related to the linear programming network described by D.W. Tank and J.J. Hopfield (1985), which also uses a linear cost function for a simple optimization problem. It is shown how to map a difficult constraint-satisfaction problem onto a simple neural net in which the number of neural processors equals the number of subjobs (operations) and the number of interconnections grows linearly with the total number of operations. Simulations show that the authors' approach produces better solutions than existing neural approaches to job-shop scheduling, i.e. the traveling salesman problem-type Hopfield approach and integer linear programming approach of J.P.S. Foo and Y. Takefuji (1988), in terms of the quality of the solution and the network complexity.     

A neural network approach to tiling problems

The family of tiling problems comprises combinatorial optimization problems involving a grid and a number of shapes. Appropriate placements of the shapes on the grid are sought such that specific constraints concerning shape overlap and grid coverage are satisfied. The family of tiling problems has links with graph theory and is, thus, interesting from a theoretical point of view. Being related to VLSI circuit design, tiling problems are also of practical importance. In this piece of research, parallel implementations of representative tiling problems are proposed by employing three distinct harmony theory‐based artificial neural networks. Optimal solutions are always produced for appropriately selected values of the network parameters. Problem complexity has been found to affect the computational complexity of the solution. © 2001 John Wiley & Sons, Inc.     

An innovative neural network approach for stock market prediction

The Journal of Supercomputing - This paper aims to develop an innovative neural network approach to achieve better stock market predictions. Data were obtained from the live stock market for...     

Human lower extremity joint moment prediction: A wavelet neural network approach

Joint moment is one of the most important factors in human gait analysis. It can be calculated using multi body dynamics but might not be straight forward. This study had two main purposes; firstly, to develop a generic multi-dimensional wavelet neural network (WNN) as a real-time surrogate model to calculate lower extremity joint moments and compare with those determined by multi body dynamics approach, secondly, to compare the calculation accuracy of WNN with feed forward artificial neural network (FFANN) as a traditional intelligent predictive structure in biomechanics.To aim these purposes, data of four patients walked with three different conditions were obtained from the literature. A total of 10 inputs including eight electromyography (EMG) signals and two ground reaction force (GRF) components were determined as the most informative inputs for the WNN based on the mutual information technique. Prediction ability of the network was tested at two different levels of inter-subject generalization. The WNN predictions were validated against outputs from multi body dynamics method in terms of normalized root mean square error (NRMSE (%)) and cross correlation coefficient (ρ).Results showed that WNN can predict joint moments to a high level of accuracy (NRMSE < 10%, ρ > 0.94) compared to FFANN (NRMSE < 16%, ρ > 0.89). A generic WNN could also calculate joint moments much faster and easier than multi body dynamics approach based on GRFs and EMG signals which released the necessity of motion capture. It is therefore indicated that the WNN can be a surrogate model for real-time gait biomechanics evaluation.     

A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem

We propose a threshold-varying artificial neural network (TV-ANN) approach for solving the binary classification problem. Using a set of simulated and real-world data set for bankruptcy prediction, we illustrate that the proposed TV-ANN fares well, both for training and holdout samples, when compared to the traditional backpropagation artificial neural network (ANN) and the statistical linear discriminant analysis. The performance comparisons of TV-ANN with a genetic algorithm-based ANN and a classification tree approach C4.5 resulted in mixed results.     

A neural network approach to the classification problem

The task of classifying observations into known groups is a common problem in decision making. A wealth of statistical approaches, commencing with Fisher's linear discriminant function, and including variations to accomodate a variety of modeling assumptions, have been proposed. In addition, nonparametric approaches based on various mathematical programming models have also been proposed as solutions. All of these proposed aolutions have performed well when conditions favorable to the specific model are present. The modeler, therefore, can usually be assured of a good solution to his problem of he chooses a model which fits his situation. In this paper, the performance of a neural network as a classifier is evaluated. It is found that the performance of the neural network is comparable to the best of otheother methods under a wide variety of modeling assumptions. The use of neural networks as classifiers thus relieves the modeler of testing assumptions which would otherwise be critical to the performance of the usual classification techniques.     

A modular neural network approach to fault diagnosis

Certain real-world applications present serious challenges to conventional neural-network design procedures. Blindly trying to train huge networks may lead to unsatisfactory results and wrong conclusions about the type of problems that can be tackled using that technology. In this paper a modular solution to power systems alarm handling and fault diagnosis is described that overcomes the limitations of "toy" alternatives constrained to small and fixed-topology electrical networks. In contrast to monolithic diagnosis systems, the neural-network-based approach presented here accomplishes the scalability and dynamic adaptability requirements of the application. Mapping the power grid onto a set of interconnected modules that model the functional behavior of electrical equipment provides the flexibility and speed demanded by the problem. After a preliminary generation of candidate fault locations, competition among hypotheses results in a fully justified diagnosis that may include simultaneous faults. The way in which the neural system is conceived allows for a natural parallel implementation.     

A neural network approach to decision alternative prioritization

A common decision problem faced by managers in organizations is that of decision alternative prioritization. There have been many proposed approaches to the problem where the decision maker constructs a pairwise comparison matrix of the alternatives under study. All existing ranking methods possess major shortcomings for the general problem. This paper illustrates the usefulness of a neural network model in such prioritization problems, which considers these shortcomings of previous methods. Use of the model is shown through the use of example ranking scenarios.     

一种融合KPCA和BP神经网络的用水总量预测方法

针对影响用水总量的相关用水因子的不确定性和非线性多维特点,论文研究并提出了一种融合KPCA和思维优化BP神经网络的用水总量预测方法。首先运用相关系数法确定预测因子,然后利用核主成分分析（KPCA）对所述预测因子进行降维处理,解决数据之间的非线性特征,最后采用BP神经网络建立用水总量预测模型,同时采用思维进化学习算法优化BP神经网络的权值和阈值。该方法在国家统计局的2007-2016年度开放统计用水数据中实验,通过实验比较,该模型的相对预测误差小于5%,结果表明,融合 KPCA和思维优化BP神经网络的用水总量预测模型能很好的预测未来用水总量。     

A neural network approach to a Bayesian statistical decisionproblem

Generalized mean-squared error (GMSE) objective functions are proposed that can be used in neural networks to yield a Bayes optimal solution to a statistical decision problem characterized by a generic loss function.     

A genetic approach to automatic neural network architecture optimization

The use of artificial neural networks for various problems has provided many benefits in various fields of research and engineering. Yet, depending on the problem, different architectures need to be developed and most of the time the design decision relies on a trial and error basis as well as on the experience of the developer. Many approaches have been investigated concerning the topology modelling, training algorithms, data processing. This paper proposes a novel automatic method for the search of a neural network architecture given a specific task. When selecting the best topology, our method allows the exploration of a multidimensional space of possible structures, including the choice of the number of neurons, the number of hidden layers, the types of synaptic connections, and the use of transfer functions. Whereas the backpropagation algorithm is being conventionally used in the field of neural networks, one of the known disadvantages of the technique represents the possibility of the method to reach saddle points or local minima, hence overfitting the output data. In this work, we introduce a novel strategy which is capable to generate a network topology with overfitting being avoided in the majority of the cases at affordable computational cost. In order to validate our method, we provide several numerical experiments and discuss the outcomes.

     

优化Elman神经网络用于网络流量预测

对量子粒子群优化(QPSO)算法进行研究,提出了自适应量子粒子群优化(Adaptive QPSO)算法,用于优化Elman神经网络的参数,改进了Elman神经网络的泛化能力.利用网络流量时间序列数据进行预测,实验结果表明,采用AQPSO算法优化获得的Elman神经网络模型不但具有较强的泛化能力,而且具有良好的稳定性,在网络流量时间序列数据的预测中具有一定的实用价值.     

人工神经网络在成矿预测中的应用

成矿预测正从定性描述性预测向定量成矿预测转变,数理统计方法和技术逐渐引入地学研究。传统统计方法多假想包含地学现象的空间为均质,假定在一个尺度上的地学关系在另一个尺度上也是相同的,而在实际应用中这样的地质条件是不可能存在的。而非线性科学正具有不满足线性叠加原理的性质,因此将非线性科学如人工神经网络与成矿预测相结合是未来矿产资源预测的发展方向。采用Kohonen聚类模型和BP预测模型相结合的方法,对包古图金矿区1 444个矿点的地球化学数据进行聚类分析并建立成矿预测模型,预测正确率为85.2%。该方法性能良好,具有一定的实际意义,为解决成矿预测提供了一种新的手段。     

基于GRNN人工神经网络的寡核苷酸解链温度预测

解链温度预测在引物和探针设计中具有重要的作用,本研究以384条寡核苷酸的解链温度数据为材料,随机分为训练集(279条)和测试集(69条)样本,利用训练集样本对建立的GRNN人工神经网络进行训练;再利用训练好的人工神经网络对测试集样本的解链温度进行预测,发现本研究所建立的GRNN人工神经网络的平均预测误差为2.44±0.98℃,最大误差为5.77℃,说明本研究建立的GRNN人工神经网络具有较好的预测性能,完全可以用于寡核苷酸解链温度的预测.同时比较了CRNN人工神经网络与目前常用的3种邻近法在预测寡核苷酸解链温度上的差异,发现Breslauer(1986)建立的预测方法误差较大,其平均误差为6.81±3.90℃,Santalucia(1996)建立的预测方法次之,平均误差为2.41±1.96℃,Sugimoto(1996)建立的预测方法最准确,其平均误差为1.57±0.96℃,分析了各种预测方法产生误差的原因,为今后开发新的寡核苷酸解链温度预测工具提供了新的思路和方法.