Forecast Combination by Using Artificial Neural Networks

One of the efficient ways for obtaining accurate forecasts is usage of forecast combination method. This approach consists of combining different forecast values obtained from different forecasting models. Also artificial neural networks and fuzzy time series approaches have proved their success in the field of forecasting. In this study, a new forecast combination approach based on artificial neural networks is proposed. The forecasts obtain from different fuzzy time series models are combined by utilizing artificial neural networks. The proposed method is applied to index of Istanbul stock exchange (IMKB) time series and the results are compared to other forecast combination methods available in the literature. As a result of the implementation, it is seen that the proposed forecast combination approach produces better forecasts than those produced by other methods.     

引文作者主题演化模型在专家检索方面的应用

目前基于科技文献的专家检索方法大多数是静态地获取专家信息,而动态演化的分析方法很少考虑文献的作者、引文作者等外部信息,且很少应用于专家检索领域。基于此,在CAT和ToT模型的基础上构建了引文作者主题演化（CAToT）模型,并给出了一种估计CAToT模型参数的吉布斯采样方法以及该模型在专家检索方面应用的方法。该模型集成了CAT和ToT模型的优势,不仅可以揭示科技文献中隐含的主题、与主题相关的作者和引文作者,而且可以挖掘主题随时间变化的规律以及专家排名的演化规律。以1 557篇ACL、CONLL、EMNLP的会议论文集作为实验数据,通过与CAT模型的对比分析验证了CAToT模型的可行性和有效性。     

Modified genetic algorithm-based feature selection combined with pre-trained deep neural network for demand forecasting in outpatient department

A well-performed demand forecasting can provide outpatient department (OPD) managers with essential information for staff scheduling and rostering, considering the non-reservation policy of OPD in China. Based on the results reported by relevant studies, most approaches have focused on forecasting the overall amount of patient flow and ignored the demand for other key resources in OPD or similar department. Moreover, few studies have conducted feature selection before training a forecast model, which is a significant pre-processing operation of data mining and widely applied for knowledge discovery in expert and intelligent system. This study develops a novel hybrid methodology to forecast the patients’ demand for different key resources in OPD, by combining a new feature selection method and a deep learning approach. A modified version of genetic algorithm (MGA) is proposed for feature selection. The key operators of normal genetic algorithm are redesigned to utilize useful information provided by filter-based feature selection and feature combinations. A feedforward deep neural network is introduced as the forecast model, and the initial parameter set is generated from a stacked autoencoder-based pre-training process to overcome the optimization challenges in constructing deep architectures. In order to evaluate the performance of our methodology, it is applied to an OPD located at Northeast China. The results are compared with those obtained from combinations of other feature selection methods and demand forecasting models. Compared with GA and PCA, MGA improves the quality and efficiency of feature selection, with less selected features to get higher forecast accuracy. Pre-trained DNN optimally strengthens the advantage of MGA, compared with MLR, ARIMAX and SANN. The combination of MGA and pre-trained DNN possesses strongest predictive power among all involved combinations. Furthermore, the results of proposed methodology are crucial prerequisites for staff scheduling and resource allocation in OPD. Elite features obtained by MGA can provide practical insights on potential association between manifold feature combinations and demand variance.     

基于波谱库的特色农作物智能专家分类系统设计

农作物的长势监测和产量估算一直是遥感技术应用的重要方面,而一个好的农作物分类算法对于农作物产量和长势进行监测十分关键。目前对于一些特色农作物而言,这方面的研究比较缺乏。因此拳研究设计了符合特色农作物的长势监测和产量测算功能模块,将数据挖掘和知识发现应用到专家分类算法中,自行开发了适合农作物数据发现和挖掘的归纳学习算法,充分利用了波谱库中大量的波谱数据、相关属性和空间数据,形成了基于波谱库的特色农作物智能专家分类系统。     

石油价格预测专家系统OPFES的设计与实现

本文以国际市场石油价格预测问题为背景,采用了大型专家系统设计方法,论述了一个石油价格预测专家系统 OPFES(Oil Price Forecast Expert System)的设计方法.在系统中采用了广义知识表达树作为知识表达方法,系统结构上采用了四库结构(模型库、方法库、数据库、知识库).在推理机方面采用了二级推理:元知识级推理与对象级推理的灵活方式.在人机接口方面,采用了多级菜单驱动方式与有限的自然语言理解方式.整个系统的原型系统用 Turbo-Prolog 语言已在 PC/AT 机上实现.     

基于HP-LSTM模型的股指价格预测方法

股指价格时间序列受到长期和短期不同因素的影响,且具有非平稳、非线性等特点,传统计量模型的预测精度较低。为提高预测精度,一些研究将人工神经网络模型用于金融时间序列预测,取得了比传统计量模型更好的效果。提出了一种融合了HP滤波（Hodrick-Prescott Filter）和LSTM神经网络模型的股指价格预测模型,模型使用HP滤波将股指价格时间序列分解为长期趋势和短期波动,利用LSTM神经网络模型分别学习长期趋势和短期波动序列的特征,并分别进行长期趋势和短期波动预测,将预测结果融合得出股指价格预测结果。实验结果表明,提出的HP-LSTM混合模型不仅可以有效捕捉到股指价格时间序列的长期趋势和短期波动的变化规律,提高了股指价格预测精度,并且长期趋势和短期波动都具有相应的经济含义,提高了模型的可解释性。     

Taking decisions in the expert intelligent system to support maintenance of a technical object on the basis information from an artificial neural network

In this paper, an intelligent operation system, which consists of an intelligent diagnostic subsystem (with a neural network) and an intelligent maintenance subsystem (with an expert system), was presented and discussed. The artificial neural network and the expert system, which use the information developed in the neural network, perform a special function in this system. The functional combination of the artificial neural network and the expert system together created a new solution in the form of an intelligent system, which was referred to as an intelligent maintenance system. This article also covers decision-making methods that are used in an expert maintenance system and whose purpose is an organization and control of the process of the prevention of technical objects. For this purpose, the method was described of taking decisions by an expert for complex parametric type hypotheses and for simple finished type hypotheses in the set of possible decisions’ hypotheses. A considerable part of this paper covers the presentation of the method to transform diagnostic information into the required form of maintenance information. For this purpose, an algorithm of the work of maintenance system was performed and descried. In the creation process of the maintenance knowledge base, the specialist knowledge of a human specialist was also used. Hence, a skilful and proper taking of decisions by an expert to create this set of information is essential. Two inference methods were characterized and described in this paper. The theoretical results obtained were verified in the examination of the influence of each of these decision-making inference methods on the final results of the process of the prevention treatment of an object.     

网格计算环境下任务执行时间的组合预测

有效的资源调度算法提高了任务的执行时间，对优化资源的使用起着非常重要的作用。在网格计算环境下，需要用统计预测的方法对任务的执行时间进行估计。该文提出了任务执行时间的组合预测方法，以任务过去执行时间的观察值为基础，用多种预测方法对任务的执行时间进行估计，用多种预测方法得出的估计值进行组合预测，给出任务执行时间的估计值。实验表明，组合预测要优于单一模型 预测。     

Comparison of forecasting methods with an application to predicting excess equity premium

This paper reviews various forecast methods including combination using theoretically optimal weights and those under model selection approaches. In addition, we suggest two modified simple averaging forecast combination methods—a mean corrected and a mean and scale corrected method. We conclude that due to the fact that real data is usually subject to structural breaks, rolling forecasting scheme has a better performance than fixed window and continuously updating scheme. In addition, methods that use less information appear to perform better than methods using all the sample information about the covariance structure of the available forecasts. The mean and scale corrected simple average approach yield smaller mean squared forecast error than the three widely used regression approaches suggested by Granger and Ramanathan [11].     

Reliability Parameters to Improve Combination Strategies in Multi-Expert Systems

Recognition systems based on a combination of different experts have been widely investigated in the recent past. General criteria for improving the performance of such systems are based on estimating the reliability associated with the decision of each expert, so as to suitably weight its response in the combination phase. According to the methods proposed to-date, when the expert assigns a sample to a class, the reliability of such a decision is estimated on the basis of the recognition rate obtained by the expert on the chosen class during the training phase. As a consequence, the same reliability value is associated with every decision attributing a sample to a same class, even though it seems reasonable to take into account its dependence on the quality of the specific sample. We propose a method for estimating the reliability of each single recognition act of an expert on the basis of information directly derived from its output. In this way, the reliability value of a decision is more properly estimated, thus allowing a more precise weighting during the combination phase. The definition of the reliability parameters for widely used classification paradigms is discussed, together with the combining rules employing them for weighting the expert opinions. The results obtained by combining four experts in order to recognise handwritten numerals from a standard character database are presented. Comparison with classical combining rules is also reported, and the advantages of the proposed approach outlined. Received: 3 August 1997?Received in revised form: 24 November 1998?Accepted: 11 December 1998     

Grouped Gaussian processes for solar power prediction

We consider multi-task regression models where the observations are assumed to be a linear combination of several latent node functions and weight functions, which are both drawn from Gaussian process priors. Driven by the problem of developing scalable methods for forecasting distributed solar and other renewable power generation, we propose coupled priors over groups of (node or weight) processes to exploit spatial dependence between functions. We estimate forecast models for solar power at multiple distributed sites and ground wind speed at multiple proximate weather stations. Our results show that our approach maintains or improves point-prediction accuracy relative to competing solar benchmarks and improves over wind forecast benchmark models on all measures. Our approach consistently dominates the equivalent model without coupled priors, achieving faster gains in forecast accuracy. At the same time our approach provides better quantification of predictive uncertainties.

     

Extrapolation of fuzzy values from incomplete data bases

This paper presents different approaches which enable a data base management system to obtain a plausible fuzzy estimate for an attribute value of an item for which the information is not explicitly stored in the data base. This can be made either by a kind of analogical reasoning from information about particular items or by means of expert rules which specify the (fuzzy) sets of possible values of the attribute under consideration, for various classes of items. Another kind of expert rules enables the system to compute an estimate from the attribute value of another item provided that, in other respects, this latter item sufficiently resembles the item, the value of which we are interested in; then these expert rules are used either for controlling the analogical reasoning process or for enlarging the scope of application of the first kind of expert rules. The different approaches are discussed in the framework of possibility theory.     

基于文本生成语言模型的股指预测

股指预测是金融领域中一个重要课题. 随着计算能力和技术的发展, 从在线新闻中识别和量化有价值的信息为提高股指预测表现创造了机会. 本文为将关于股票指数预测框架的计量经济学文献扩展到高维文本数据提出了一种基于生成语言模型的股票指数预测框架. 该预测框架可以分为两个步骤. 首先, 使用有监督生成语言模型快速过滤噪声词语, 并将剩余文本聚合成可以充分解释股指变动的新闻指数. 其次, 将该新闻指数和历史股指数据共同作为时变参数预测模型的自变量来预测股指未来价值. 该框架不仅丰富了股票指数预测的影响因素并且揭示了这些因素与股票指数价值之间的时变动态关系. 实证研究展示了该预测框架解释能力和样本外预测能力. 在预测的6个行业股指中, 本文提出的预测框架得到的均方误差普遍小于传统时间序列和机器学习方法. 与没有考虑新闻信息的时变参数预测模型和长短期记忆网络相比该预测框架也表现了更好的预测性能.     

ARIMA和RBF神经网络相融合的股票价格预测研究

针对股票价格的突变性、非线性和随机性,单一预测方法仅能描述股票价格片断信息等缺陷,提出一种股票价格组合预测模型。采用自回归移动平均模型（ARIMA）对股票价格进行预测,捕捉股票价格线性变化趋势。采用RBF神经网络对非线性、随机变化规律进行预测。将两者结果组合得到股票价格预测结果。采用组合模型对包钢股份（600010）股票收盘价进行仿真实验,结果表明,相对于单一预测模型,组合预测模型更加全面、准确刻画了股票价格的变化规律,提高了股票价格预测精度。     

Explaining Environmental Sustainability in Supply Chains Using Graph Theory

The need for theory building in environmental supply chains has been at the centre of many discussions in recent years. Existing research, however, does not typically consider methods that aim at theory generation. Current methods such as econometric modelling or structural equation modelling face challenges related to how causality is established due to potential issues regarding cross-sectional data sets. To address this gap, this paper suggests a total interpretive structural modelling based approach. We use graph theory logic to synthesize expert interpretations in the form of a theoretical supply chain model. This method may prove to be an alternative method to econometric based modelling or structural equation modelling. We provide an application of the method in exploring the drivers of low carbon supply chain and their relationships. Limitations and future research opportunities are also provided.     

Pooling for Combination of Multilevel Forecasts

In this paper, we provide a theoretical analysis of effects of applying different forecast diversification methods on the structure of the forecast error covariance matrices and decomposed forecast error components based on the bias-variance-Bayes error decomposition of James and Hastie. We express the "diversity” of different forecasts in relation to different error components and propose a measure in order to quantify it. We illustrate and discuss typical inhomogeneities frequently occurring in the forecast error covariance matrices and show that previously proposed pooling based only on error variances cannot fully exploit the complementary information present in a set of diverse forecasts to be combined. If covariance values could be reliably calculated, they could be taken into account during the pooling process. We study the difficult case in which covariance information cannot be measured properly and propose a novel simplified representation of the covariance matrix, which is only based on knowledge about the forecast generation process. Finally, we propose a new pooling approach that avoids inhomogeneities in the forecast error covariance matrix by considering the information contained in the simplified covariance representation and compare it with the error-variance-based pooling approach introduced by Aiolfi and Timmermann. Applying our approach more than once leads to the generation of multistep and multilevel forecast combination structures, which have generated significantly improved forecasts in our previous extensive experimental work; the summary of which is also provided.     

Generative adversarial network (GAN) and enhanced root mean square error (ERMSE): deep learning for stock price movement prediction

The prediction of stock price movement direction is significant in financial circles and academic. Stock price contains complex, incomplete, and fuzzy information which makes it an extremely difficult task to predict its development trend. Predicting and analysing financial data is a nonlinear, time-dependent problem. With rapid development in machine learning and deep learning, this task can be performed more effectively by a purposely designed network. This paper aims to improve prediction accuracy and minimizing forecasting error loss through deep learning architecture by using Generative Adversarial Networks. It was proposed a generic model consisting of Phase-space Reconstruction (PSR) method for reconstructing price series and Generative Adversarial Network (GAN) which is a combination of two neural networks which are Long Short-Term Memory (LSTM) as Generative model and Convolutional Neural Network (CNN) as Discriminative model for adversarial training to forecast the stock market. LSTM will generate new instances based on historical basic indicators information and then CNN will estimate whether the data is predicted by LSTM or is real. It was found that the Generative Adversarial Network (GAN) has performed well on the enhanced root mean square error to LSTM, as it was 4.35% more accurate in predicting the direction and reduced processing time and RMSE by 78 s and 0.029, respectively. This study provides a better result in the accuracy of the stock index. It seems that the proposed system concentrates on minimizing the root mean square error and processing time and improving the direction prediction accuracy, and provides a better result in the accuracy of the stock index.

     

Econometric Estimation of a Continuous Time Macroeconomic Model of the United Kingdom with Segmented Trends

The exact Gaussian estimation of complicated higher order continuous time econometric models from discrete stock and flow data has only recently been feasible given recent advances in computing processing power. In this paper we estimate a second order continuous time macroeconomic model of the United Kingdom developed by Bergstrom, Nowman and Wymer (1992) recently. The model is extended to include segmented time trends and estimated using recently developed exact Gaussian estimation methods for continuous time econometric models.     

Using planning poker for combining expert estimates in software projects

When producing estimates in software projects, expert opinions are frequently combined. However, it is poorly understood whether, when, and how to combine expert estimates. In order to study the effects of a combination technique called planning poker, the technique was introduced in a software project for half of the tasks. The tasks estimated with planning poker provided: (1) group consensus estimates that were less optimistic than the statistical combination (mean) of individual estimates for the same tasks, and (2) group consensus estimates that were more accurate than the statistical combination of individual estimates for the same tasks. For tasks in the same project, individual experts who estimated a set of control tasks achieved estimation accuracy similar to that achieved by estimators who estimated tasks using planning poker. Moreover, for both planning poker and the control group, measures of the median estimation bias indicated that both groups had unbiased estimates, because the typical estimated task was perfectly on target. A code analysis revealed that for tasks estimated with planning poker, more effort was expended due to the complexity of the changes to be made, possibly caused by the information provided in group discussions.     

信息系统集成方法研究

随着信息源的不断增多,如何在多个信息系统中迅速查找用户感兴趣的信息越来越受到人们的关注。信息集成是指将多个信息源进行整合,并为用户提供一个统一的数据视图和访问接口。对信息系统的集成方法进行了研究,分析和比较了两种主要的信息集成方法:数据仓库方法和中介模式方法,并对未来的一些研究热点进行了前瞻。