Predictive models for influence of primary delays using high-speed train operation records

Primary delays are the driving force behind delay propagation, and predicting the number of affected trains (NAT) and the total time of affected trains (TTAT) due to primary delay (PD) can provide reliable decision support for real-time train dispatching. In this paper, based on real operation data from 2015 to 2016 at several stations along the Wuhan–Guangzhou high-speed railway, NAT and TTAT influencing factors were determined after analyzing the PD propagation mechanism. The eXtreme Gradient BOOSTing (XGBOOST) algorithm was used to establish a NAT predictive model, and several machine learning methods were compared. The importance of different delayinfluencing factors was investigated. Then, the TTAT predictive model (using support vector regression (SVR) algorithms) was established based on the NAT predictive model. Results indicated that the XGBOOST algorithm performed well with the NAT predictive model, and SVR was the optimal model for TTAT prediction under the verification index (i.e., the ratio of the difference between the actual and predicted value was less than 1/2/3/4/5 min). Real operational data in 2018 were used to test the applicability of the NAT and TTAT models over time, and findings suggest that these models exhibit sound applicability over time based on XGBOOST and SVR, respectively.     

Analysis of the relationship between LSTM network traffic flow prediction performance and statistical characteristics of standard and nonstandard data

The effectiveness of road traffic control systems can be increased with the help of a model that can accurately predict short-term traffic flow. Therefore, the performance of the preferred approach to develop a prediction model should be evaluated with data sets with different statistical characteristics. Thus a correlation can be established between the statistical properties of the data set and the model performance. The determination of this relationship will assist experts in choosing the appropriate approach to develop a high-performance short-term traffic flow forecasting model. The main purpose of this study is to reveal the relationship between the long short-term memory network (LSTM) approach's short-term traffic flow prediction performance and the statistical properties of the data set used to develop the LSTM model. In order to reveal these relationships, two different traffic prediction models with LSTM and nonlinear autoregressive (NAR) approaches were created using different data sets, and statistical analyses were performed. In addition, these analyses were repeated for nonstandardized traffic data indicating unusual fluctuations in traffic flow. As a result of the analyses, LSTM and NAR model performances were found to be highly correlated with the kurtosis and skewness changes of the data sets used to train and test these models. On the other hand, it was found that the difference of mean and skewness values of training and test sets had a significant effect on model performance in the prediction of nonstandard traffic flow samples.     

基于改进神经网络的厚煤层采煤方法预测模型

针对厚煤层采煤方法选择多目标非线性的问题,在影响因素分析的基础上,建立了预测仿真模型,利用神经网络改进算法训练网络,通过早停的方式解决网络过拟合问题。通过计算机仿真结合现场应用表明,该模型给出了最优方案,可为厚煤层采煤方法的合理选择和工作面主要经济技术指标的预测提供一种新的研究思路,在煤矿开采中具有广阔的应用前景。     

基于贝叶斯网络的变压器故障诊断及重要度分析

以云南电网公司提供的500 kV变压器历史运行数据为依据,利用贝叶斯网络和数据挖掘技术,结合变压器油中溶解气体分析的改良三比值法,针对500 kV变压器建立故障诊断模型,并对引起变压器故障的各影响因素进行重要度分析。最后,利用变压器实时运行数据进行试验,验证了模型的有效性和实用性。     

牵引供电扩能系统仿真研究

改善电气化铁道牵引供电能力不足的有效措施之一是进行牵引供电扩能改造,应用综合补偿技术是牵引供电扩能的最佳方法.但其影响因素较多,且时变性和相关性强,不易建立精确的数学模型.本文采用基于列车牵引计算的仿真方法,针对增设不同的扩能补偿设备,结合半定量分析方法时补偿设备的安装位置和投切容量等参数选取、有效控制策略的选择等建立了牵引供电扩能仿真系统,通过分析列车的运行工况来评价投入不同补偿设备所达到的扩能效果,系统的应用结果表明该仿真模型是行之有效的.     

On the forecasting of high-frequency financial time series based on ARIMA model improved by deep learning

Through empirical research, it is found that the traditional autoregressive integrated moving average (ARIMA) model has a large deviation for the forecasting of high-frequency financial time series. With the improvement in storage capacity and computing power of high-frequency financial time series, this paper combines the traditional ARIMA model with the deep learning model to forecast high-frequency financial time series. It not only preserves the theoretical basis of the traditional model and characterizes the linear relationship, but also can characterize the nonlinear relationship of the error term according to the deep learning model. The empirical study of Monte Carlo numerical simulation and CSI 300 index in China show that, compared with ARIMA, support vector machine (SVM), long short-term memory (LSTM) and ARIMA-SVM models, the improved ARIMA model based on LSTM not only improves the forecasting accuracy of the single ARIMA model in both fitting and forecasting, but also reduces the computational complexity of only a single deep learning model. The improved ARIMA model based on deep learning not only enriches the models for the forecasting of time series, but also provides effective tools for high-frequency strategy design to reduce the investment risks of stock index.     

路基上双块式无碴轨道道床板疲劳特性影响因素分析

以路基上双块式无碴轨道为研究对象,建立钢筋与混凝土纵向相互作用力学模型、双块式无碴轨道三维有限元静力学模型、列车-双块式无碴轨道垂向耦合动力学模型.根据轴向温度荷载、混凝土收缩荷载、温度梯度荷载及列车荷载作用下道床板混凝土及钢筋应力时程曲线,运用雨流计数法,得到耦合荷载作用下的应力谱.利用Miner线性疲劳累积损伤准则...     

Enhancing survey‐based investment forecasts

We investigate the accuracy of capital investment predictors from a national business survey of South African manufacturing. Based on data available to correspondents at the time of survey completion, we propose variables that might inform the confidence that can be attached to their predictions. Having calibrated the survey predictors' directional accuracy, we model the probability of a correct directional prediction using logistic regression with the proposed variables. For point forecasting, we compare the accuracy of rescaled survey forecasts with time series benchmarks and some survey/time series hybrid models. In addition, using the same set of variables, we model the magnitude of survey prediction errors. Directional forecast tests showed that three out of four survey predictors have value but are biased and inefficient. For shorter horizons we found that survey forecasts, enhanced by time series data, significantly improved point forecasting accuracy. For longer horizons the survey predictors were at least as accurate as alternatives. The usefulness of the more accurate of the predictors examined is enhanced by auxiliary information, namely the probability of directional accuracy and the estimated error magnitude.     

Using social media mining technology to improve stock price forecast accuracy

Many stock investors make investment decisions based on stock-price-related chip indicators. However, in addition to quantified data, financial news often has a nonnegligible impact on stock price. Nowadays, as new reviews are posted daily on social media, there may be value in using web opinions to improve the performance of stock price prediction. To this end, we use logistic regression to screen the chip indicators and establish a basic stock price prediction model. Then, we employ text mining technology to quantify the unstructured data of social media opinions on stock-related news into sentiment scores, which are found to correlate significantly with the change extent of the stock price. Based on the findings that the higher the sentiment scores, the lower the prediction accuracy of the logistic regression model, we propose an improved prediction approach that integrates sentiment scores into the logistic regression model. Our results show that the proposed model can improve the prediction accuracy for stock prices, and can thus provide a new reference for investment strategies for stock investors.     

Identifying US business cycle regimes using dynamic factors and neural network models

We use dynamic factors and neural network models to identify current and past states (instead of future) of the US business cycle. In the first step, we reduce noise in data by using a moving average filter. Dynamic factors are then extracted from a large-scale data set consisted of more than 100 variables. In the last step, these dynamic factors are fed into the neural network model for predicting business cycle regimes. We show that our proposed method follows US business cycle regimes quite accurately in-sample and out-of-sample without taking account of the historical data availability. Our results also indicate that noise reduction is an important step for business cycle prediction. Furthermore, using pseudo real time and vintage data, we show that our neural network model identifies turning points quite accurately and very quickly in real time.     

Severity Prediction of Traffic Accident Using an Artificial Neural Network

In this paper, an artificial neural network (ANN) was used to predict the injury severity of traffic accidents based on 5973 traffic accident records occurred in Abu Dhabi over a 6‐year period (from 2008 to 2013). For each accident record, 48 different attributes had been collected at the time of the accident. After data preprocessing, the data were reduced to 16 attributes and four injury severity classes. In this study, WEKA (Waikato Environment for Knowledge Analysis) data‐mining software was used to build the ANN classifier. The traffic accident data were used to build two classifiers in two different ways. The whole data set were used for training and validating the first classifier (training set), while 90% of the data were used for training the second classifier and the remaining 10% were used for testing it (testing set). The experimental results revealed that the developed ANN classifiers can predict accident severity with reasonable accuracy. The overall model prediction performance for the training and testing data were 81.6% and 74.6%, respectively. To improve the prediction accuracy of the ANN classifier, traffic accident data were split into three clusters using a k‐means algorithm. The results after clustering revealed significant improvement in the prediction accuracy of the ANN classifier, especially for the training dataset. In this work, and in order to validate the performance of the ANN model, an ordered probit model was also used as a comparative benchmark. The dependent variable (i.e. degree of injury) was transformed from ordinal to numerical (1, 2, 3, 4) for (minor, moderate, sever, death). The R tool was used to perform an ordered probit. For each accident, the ordered probit model showed how likely this accident would result in each class (minor, moderate, severe, death). The accuracy of 59.5% obtained from the ordered probit model was clearly less than the ANN accuracy value of 74.6%. Copyright © 2016 John Wiley & Sons, Ltd.     

Permissible idealizations for the purpose of prediction

Every model leaves out or distorts some factors that are causally connected to its target phenomenon—the phenomenon that it seeks to predict or explain. If we want to make predictions, and we want to base decisions on those predictions, what is it safe to omit or to simplify, and what ought a causal model to describe fully and correctly? A schematic answer: the factors that matter are those that make a difference to the target phenomenon. There are several ways to understand differencemaking. This paper advances a view as to which is the most relevant to the forecaster and the decision-maker. It turns out that the right notion of differencemaking for thinking about idealization in prediction is also the right notion for thinking about idealization in explanation; this suggests a carefully circumscribed version of Hempel’s famous thesis that there is a symmetry between explanation and prediction.     

基于形式化测试的实时系统变更后安全性验证

变更后系统实现的安全性验证是安全攸关系统维护过程中必不可少的环节,也是其面临的主要挑战之一.软件模型检测和程序验证是目前常用的作用于代码层面的自动化安全性验证技术.本文站在系统行为角度,基于形式化方法,提出了一种将变更后系统实现的安全性验证问题归结为一致性测试的方法,尝试通过自动生成的一致性测试用例在系统行为级别上判定系统实现是否安全.为此,首先以时间输入输出自动机及其语义模型为基础,构建了该方法的证明体系,证明了该方法的正确性;其次,建立了变更后系统实现安全性验证的回归测试生成框架.相对于其它实时系统测试方法,这种测试方法不仅可以发现实时系统中常规的不一致性缺陷,而且为变更后系统实现在运行时是否满足指定的安全性属性提供了依据.最后,以轨道交通系统中的列车自动防护功能的变更情景为案例研究,说明了方法的具体应用.     

Dynamic Latent Class Model Averaging for Online Prediction

We consider the problem of online prediction when it is uncertain what the best prediction model to use is. We develop a method called dynamic latent class model averaging, which combines a state‐space model for the parameters of each of the candidate models of the system with a Markov chain model for the best model. We propose a polychotomous regression model for the transition weights to assume that the probability of a change in time depends on the past through the values of the most recent time periods and spatial correlation among the regions. The evolution of the parameters in each submodel is defined by exponential forgetting. This structure allows the ‘correct’ model to vary over both time and regions. In contrast to existing methods, the proposed model naturally incorporates clustering and prediction analysis in a single unified framework. We develop an efficient Gibbs algorithm for computation, and we demonstrate the value of our framework on simulated experiments and on a real‐world problem: forecasting IBM's corporate revenue. Copyright © 2014 John Wiley & Sons, Ltd.     

物联网服务建模：一种基于环境建模的方法

物联网服务是传统Web服务通过传感器网络向物理环境的延伸,它通过传感器网络感知物理环境中的实体,也向物理环境实体施加作用.与传统Web服务相比,由于物联网服务受到所依赖的物理环境的时间受限性、资源受限性和设备潜在故障概率的影响,物联网服务的响应速度、服务能耗和容错能力等特性成为影响物联网系统整体特性的重要因素.因此,对物联网服务进行全面建模,对物联网服务所处的外部环境进行形式化描述,并结合物理环境模型对物联网服务的性质进行分析,对于确保物联网系统的正确性、稳定性非常必要.本文针对物联网服务的特点,结合基于环境建模的需求工程思想,提出一种基于环境的物联网服务三元问题域建模框架,给出了物联网服务建模本体以及相应的建模原则.在此基础上,提出了一种物联网服务行为建模方法,该方法将物联网服务和物理环境建模为概率时间自动机,将用户期望的服务特性描述为时序逻辑公式,为物联网服务功能行为正确性验证和非功能性约束可满足性验证奠定了基础.     

Modelling exchange rate dynamics new perspectives from the frequency domain

In this paper the dynamics of foreign exchange rates is sought to be studied via new frequency domain techniques. Stationarity properties of the rates are analysed via a unit root test as well as a test based on the evolutionary spectrum. Linearity and Gaussianity are analysed via bispectral tests and compared with the more frequently employed time domain tests, such as the McLeod-Li and Tsay tests. Finally, an evaluation of the out-of-sample forecasting properties for eight methods—Random Walk, ARMA, Bilinear, State dependent model, dynamic linear model, ARCH, GARCH, and Garch-in-mean—is made. The methods used here seem to shed a great deal of light on hitherto neglected aspects of exchange rate dynamics.     

基于移动设备云迁移的节能决策算法

随着云计算的兴起,云迁移计算开始成为移动设备获取计算资源和降低功耗的有效方式.云迁移的主要想法是将移动终端的复杂任务经由无线网络迁移到云端执行,然后再接收计算结果.然而,无线网络的不稳定性和数据传输的高功耗限制了云迁移计算在移动设备中的应用.不同于已有工作,本文通过引入数据压缩的方法完善了云迁移计算决策模型,并且基于对未来时段网络期望的预测,提出了一种节能迁移计算决策算法——EPVAD.基于实际的3G网络带宽数据和开发测试平台,实验结果显示:EPVAD算法的节能效果较同类算法平均优14.9%,并且算法自身的系统开销可忽略.     

Forecasting air pollution PM2.5 in Beijing using weather data and multiple kernel learning

PM_2.5 mass concentration prediction is an important research issue because of the increasing impact of air pollution on the urban environment. In this paper, a PM_2.5 forecasting framework incorporating meteorological factors based on multiple kernel learning (MKL) is proposed to forecast the near future PM_2.5. In addition, we develop a novel two-step algorithm for solving the primal MKL problem. Compared with most existing MKL 2-step algorithms, the proposed algorithm does not require the optimal step size for updating kernel combination coefficients by linear search. To demonstrate the performance of the proposed forecasting framework, its performance is compared to single kernel-based support vector regression (SVR). Data sets of an inland city Beijing acquired from UCI are used to train and validate both of two methods. Experiments show that our proposed method outperforms the SVR.     

A new insight into combining forecasts for elections: The role of social media

This study is devoted to gain insight into a timely, accurate, and relevant combining forecast by considering social media (Facebook), opinion polls, and prediction markets. We transformed each type of raw data into the possibility of victory as a forecasting model. Besides the four single forecasts, namely Facebook fans, Facebook “people talking about this” (PTAT) statistics, opinion polls, and prediction markets, we generated three combined forecasts by associating various combinations of the four components. Then, we examined the predictive performance of each forecast on vote shares and the elected/non‐elected outcome across the election period. Our findings, based on the evidence of Taiwan's 2018 county and city elections, showed that incorporating the Facebook PTAT statistic with polls and prediction markets generates the most powerful forecast. Moreover, we recognized the matter of the time horizons where the best proposed model has better accuracy gains in prediction—in the “late of election,” but not in “approaching election”. The patterns of the trend of accuracy across time for each forecasting model also differ from one another. We also highlighted the complementarity of various types of data in the paper because each forecast makes important contributions to forecasting elections.     

Forecasting US inflation by Bayesian model averaging

Recent empirical work has considered the prediction of inflation by combining the information in a large number of time series. One such method that has been found to give consistently good results consists of simple equal‐weighted averaging of the forecasts from a large number of different models, each of which is a linear regression relating inflation to a single predictor and a lagged dependent variable. In this paper, I consider using Bayesian model averaging for pseudo out‐of‐sample prediction of US inflation, and find that it generally gives more accurate forecasts than simple equal‐weighted averaging. This superior performance is consistent across subsamples and a number of inflation measures. Copyright © 2008 John Wiley & Sons, Ltd.