Regression using hybrid Bayesian networks: Modelling landscape–socioeconomy relationships

Modelling environmental systems becomes a challenge when dealing directly with continuous and discrete data simultaneously. The aim in regression is to give a prediction of a response variable given the value of some feature variables. Multiple linear regression models, commonly used in environmental science, have a number of limitations: (1) all feature variables must be instantiated to obtain a prediction, and (2) the inclusion of categorical variables usually yields more complicated models. Hybrid Bayesian networks are an appropriate approach to solve regression problems without such limitations, and they also provide additional advantages. This methodology is applied to modelling landscape–socioeconomy relationships for different types of data (continuous, discrete or hybrid). Three models relating socioeconomy and landscape are proposed, and two scenarios of socioeconomic change are introduced in each one to obtain a prediction. This proposal can be easily applied to other areas in environmental modelling.     

基于知识图谱的跨项目安全缺陷报告预测方法

安全缺陷报告可以描述软件产品中的安全关键漏洞.为了消除软件产品的安全攻击风险,安全缺陷报告(security bug report, SBR)预测越来越受到研究人员的关注.但在实际软件开发场景中,需要进行软件安全漏洞预测的项目可能是来自新公司或属于新启动的项目,没有足够的已标记安全缺陷报告供在实践中构建此软件安全漏洞预测模型.一种简单的解决方案就是使用迁移模型,即利用其他项目已经标记过的数据来构建预测模型.受到该领域最近的两项研究工作的启发,以安全关键字过滤为思路提出一种融合知识图谱的跨项目安全缺陷报告预测方法KG-SBRP (knowledge graph of security bug report prediction).使用安全缺陷报告中的文本信息域结合CWE(common weakness enumeration)与CVE Details (common vulnerabilities and exposures)共同构建三元组规则实体,以三元组规则实体构建安全漏洞知识图谱,在图谱中结合实体及其关系识别安全缺陷报告.将数据分为训练集和测试集进行模型拟合和性能评估.所构建的模型...     

Time variance and defect prediction in software projects

It is crucial for a software manager to know whether or not one can rely on a bug prediction model. A wrong prediction of the number or the location of future bugs can lead to problems in the achievement of a project’s goals. In this paper we first verify the existence of variability in a bug prediction model’s accuracy over time both visually and statistically. Furthermore, we explore the reasons for such a high variability over time, which includes periods of stability and variability of prediction quality, and formulate a decision procedure for evaluating prediction models before applying them. To exemplify our findings we use data from four open source projects and empirically identify various project features that influence the defect prediction quality. Specifically, we observed that a change in the number of authors editing a file and the number of defects fixed by them influence the prediction quality. Finally, we introduce an approach to estimate the accuracy of prediction models that helps a project manager decide when to rely on a prediction model. Our findings suggest that one should be aware of the periods of stability and variability of prediction quality and should use approaches such as ours to assess their models’ accuracy in advance.     

The effects of joint angle variability and different driving load scenarios on maximum muscle activity – A driving posture simulation study

To date, no studies have been conducted on the main and interaction effects of joint angles on maximum muscle activity in different driving load scenarios. To investigate the influence of joint angle variability on the muscular system, this study calculated maximum muscle activity during three static driving load scenarios through the use of musculoskeletal inverse dynamic simulation. Six joint angles in sagittal plane were varied with reference to reported driving posture angles in the literature. A digital manikin with a height of 180 cm and weight of 70 kg was used with simple muscles and a minimum fatigue criterion for muscle activation optimization. Three static driving load scenarios were simulated: sitting with no external forces except gravity, steering, and pedaling operation. Prediction models were developed for each driving load scenario using Least Squares Support Vector Machine. Finally, the Pareto optimization method was applied for multi-objective optimization combining the three developed models.The results indicate that the developed models can be used for the prediction of simulated maximum muscle activity. The six joint angles explain a higher percentage of maximum muscle activity variance in the steering and pedaling operation scenarios compared to the sitting scenario. The six joint angles differ in their main and interaction effects on maximum muscle activity depending on the driving load scenario. The optimum joint angle values of the driving posture depend on the driving load scenarios. The different driving postures based on minimum maximum muscle activity are presented for the three driving load scenarios.Relevance to industryThe results of this study can be utilized in establishing driving posture simulation models to improve vehicle interiors during the early development stage. Furthermore, the results of this study can provide base data for the development of a tool for real driving posture evaluation of maximum muscle activity.     

基于相关性分析的瓦斯灾害选择集成预测模型

针对瓦斯灾害危险性预测中预测性能低的问题，对一种基于矿井内瓦斯浓度与环境因素相关性分析的瓦斯灾害选择集成预测方法进行了研究。首先，分析实验数据中样本属性与瓦斯浓度的相关性，并根据相关性分析结果进行属性约简得到新的数据集；其次，训练基学习器并应用优化集成前序选择方法建立选择集成回归学习模型；最后，将模型应用于瓦斯灾害预测。实验结果表明，基于相关性分析的选择集成回归学习模型对瓦斯灾害危险性的识别率比未进行相关性分析的四个基学习器平均提高了24%，比未进行相关性分析的选择集成回归学习模型提高了7.6%。     

基于可解释集成学习的信贷违约预测

人工智能促进了风控行业的发展,智能风控的核心在于风险控制,信贷违约预测模型是解决这一问题必须倚靠的手段.传统的解决方案是基于人工和广义线性模型建立的,然而现在通过网络完成的交易数据,具有高维性和多重来源等特点,远远超出了现有模型的处理能力,对于传统风控提出了巨大的挑战.因此,本文提出一种基于融合方法的可解释信贷违约预测模型,首先选取LightGBM、DeepFM和CatBoost作为基模型,CatBoost作为次模型,通过模型融合提升预测结果的准确性,然后引入基于局部的、与模型无关的可解释性方法LIME,解释融合模型的预测结果.基于真实数据集的实验结果显示,该模型在信贷违约预测任务上具有较好的精确性和可解释性.     

Monetary pricing of software development risks: A method and empirical illustration

The ability to price (monetize) software development risks can benefit various aspects of software development decision-making. This paper presents a risk pricing method that estimates two parameters for every individual risk factor: extra cost incurred per unit exposure, and project sensitivity, to that factor. Since variability is a widely used measure of risk in finance and decision sciences, the method derives risk pricing parameters by relating variability in risk factors to variability in project cost. This approach rests on the fact that a parametric cost estimator predicts project cost by adjusting the “nominal” cost of a project based on the expected values of risk factors (cost drivers), but the actual project cost often deviates from prediction because the actual values of risk factors normally deviate from expectations. In addition, to illustrate the viability of the method, the paper applies the method empirically with COCOMO data, to approximate risk pricing parameters for four risk factors (Personnel Capability, Process Maturity, Technology Platform, and Application Task). Importantly, though, the method could work equally well with data recorded based on other parametric cost estimators. The paper also discusses several areas that can benefit from benchmark risk pricing parameters of the kind we obtain.     

Structural model updating and prediction variability using Pareto optimal models

A multi-objective identification method for structural model updating based on modal residuals is presented. The method results in multiple Pareto optimal structural models that are consistent with the experimentally measured modal data and the modal residuals used to measure the discrepancies between the measured and model predicted modal characteristics. These Pareto optimal models are due to uncertainties arising from model and measurement errors. The relation between the multi-objective identification method and the conventional single-objective weighted modal residuals method for model updating is investigated. Using this relation, an optimally weighted modal residuals method is also proposed to rationally select the most preferred model among the alternative multiple Pareto optimal models for further use in structural model prediction studies. Computational issues related to the reliable solution of the resulting multi-objective and single optimization problems are addressed. The model updating methods are compared and their effectiveness is demonstrated using experimental results obtained from a three-story laboratory structure tested at a reference and a mass modified configuration. The variability of the Pareto optimal models and their associated response prediction variability are explored using two structural model classes, a simple 3-DOF model class and a higher fidelity 546-DOF finite element model class. It is demonstrated that the Pareto optimal structural models and the corresponding response and reliability predictions may vary considerably, depending on the fidelity of the model class and the size of measurement errors.     

基于DCGRU-RF模型的路网短时交通流预测

随着城市化进程的加快,我国城市机动车数量快速增加,使得现有路网容量难以满足交通运输需求,交通拥堵、环境污染、交通事故等问题与日俱增。准确高效的交通流预测作为智能交通系统的核心,能够有效解决交通出行和管理方面的问题。现有的短时交通流预测研究往往基于浅层的模型方法,不能充分反映交通流特性。文中针对复杂的交通网络结构,提出了一种基于DCGRU-RF(Diffusion Convolutional Gated Recurrent Unit-Random Forest)模型的短时交通流预测方法。首先,使用DCGRU(Diffusion Convolutional Gated Recurrent Unit)网络刻画交通流时间序列数据中的时空相关性特征;在获取数据中的依赖关系和潜在特征后,选择RF(Random Forest)模型作为预测器,以抽取的特征为基础构建非线性预测模型,得出最终的预测结果。实验以两条城市道路中的38个检测器为实验对象,选取了5周工作日的交通流数据,并将所提方法与其他常见交通流量预测模型进行比较。结果表明,DCGRU-RF模型能够进一步提高预测精度,准确度可达95%。     

Defect Prediction Using Akaike and Bayesian Information Criterion

Data available in software engineering for many applications contains variability and it is not possible to say which variable helps in the process of the prediction. Most of the work present in software defect prediction is focused on the selection of best prediction techniques. For this purpose, deep learning and ensemble models have shown promising results. In contrast, there are very few researches that deals with cleaning the training data and selection of best parameter values from the data. Sometimes data available for training the models have high variability and this variability may cause a decrease in model accuracy. To deal with this problem we used the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) for selection of the best variables to train the model. A simple ANN model with one input, one output and two hidden layers was used for the training instead of a very deep and complex model. AIC and BIC values are calculated and combination for minimum AIC and BIC values to be selected for the best model. At first, variables were narrowed down to a smaller number using correlation values. Then subsets for all the possible variable combinations were formed. In the end, an artificial neural network (ANN) model was trained for each subset and the best model was selected on the basis of the smallest AIC and BIC value. It was found that combination of only two variables’ ns and entropy are best for software defect prediction as it gives minimum AIC and BIC values. While, nm and npt is the worst combination and gives maximum AIC and BIC values.     

智慧农业中时序数据组合预测模型

智慧农业是实现农业精准化的技术解决方案,智慧农业系统可以实时监测植物生长的各类环境参数,并可以应用相应的预测模型来模拟农作物生长环境的变化趋势,为科学决策提供依据。近年来有很多学者提出了时间序列的预测模型算法,在预测稳定性方面取得了不错的效果。为了进一步提升时间序列的预测精度,提出一种基于差分整合移动平均自回归模型和小波神经网络的组合预测模型。该组合模型结合2个单项模型优点,用差分整合移动平均自回归模型来拟合序列的线性部分,用小波神经网络来校正其残差,使其拟合曲线更接近于实际值,采用温室内的历史温度数据来验证该组合模型的精确度,最后将组合模型与传统预测模型的预测结果进行对比。结果表明,该组合模型用于温室温度预测的精确度更高,拟合效果更好,相比于传统模型预测算法计算效能提高了20%左右。     

Probabilistic characterisation of model error using Gaussian mixture model—With application to Charpy impact energy prediction for alloy steel

A novel approach to characterise the model prediction errors using a Gaussian mixture model is proposed. The motivation for this work lies behind many data models that are developed through prediction error minimisation with the assumption of a normal noise distribution. When the noise is non-normal, which may often be the case in complicated data modelling scenarios, the model prediction errors may contain rich information, which can be further exploited for model refinement and improvement. The key contents presented in this paper include: choosing the relevant variables to form the error data, optimising the number of Gaussian components required for the error data modelling, and fitting the Gaussian mixture parameters using an expectation-maximisation algorithm. Application of the proposed method for further model improvement, within the framework of hybrid deterministic/stochastic modelling, is also discussed. Preliminary results on the real industrial Charpy impact energy data for heat-treated steels show its effectiveness for model error characterisation, and the potential for model performance improvement in terms of prediction accuracy as well as providing accurate prediction confidence intervals.     

基于路网结构的城市交通事故短期风险预测方法

城市交通事故一般都发生在公共道路上,然而现有的交通事故风险预测算法都通过对预测区域进行规则网格化来确定预测空间单位,导致预测精度不高且实用价值较低。本文将道路路段作为预测单位,采用图卷积和长短期记忆网络,构建了一种基于路网结构的城市交通事故短期风险预测方法(traffic accidents risk prediction based on road network,TARPBRN)。该方法能对指定路段短期内的交通事故风险进行预测,从而可以有针对性地进行治理,减少交通事故的发生。本文使用杭州市西湖区的交通事故数据对模型进行了训练,并与4种常用的计量经济学模型和3种已有的深度学习预测算法进行了对比。实验结果证明本文算法在准确度、正确率和漏报率等方面都优于已有算法。     

Environmental data mining and modeling based on machine learning algorithms and geostatistics

The paper presents some contemporary approaches to spatial environmental data analysis. The main topics are concentrated on the decision-oriented problems of environmental spatial data mining and modeling: valorization and representativity of data with the help of exploratory data analysis, spatial predictions, probabilistic and risk mapping, development and application of conditional stochastic simulation models. The innovative part of the paper presents integrated/hybrid model—machine learning (ML) residuals sequential simulations—MLRSS. The models are based on multilayer perceptron and support vector regression ML algorithms used for modeling long-range spatial trends and sequential simulations of the residuals. ML algorithms deliver non-linear solution for the spatial non-stationary problems, which are difficult for geostatistical approach. Geostatistical tools (variography) are used to characterize performance of ML algorithms, by analyzing quality and quantity of the spatially structured information extracted from data with ML algorithms. Sequential simulations provide efficient assessment of uncertainty and spatial variability. Case study from the Chernobyl fallouts illustrates the performance of the proposed model. It is shown that probability mapping, provided by the combination of ML data driven and geostatistical model based approaches, can be efficiently used in decision-making process.     

Flexible latent variable models for multi-task learning

Given multiple prediction problems such as regression or classification, we are interested in a joint inference framework that can effectively share information between tasks to improve the prediction accuracy, especially when the number of training examples per problem is small. In this paper we propose a probabilistic framework which can support a set of latent variable models for different multi-task learning scenarios. We show that the framework is a generalization of standard learning methods for single prediction problems and it can effectively model the shared structure among different prediction tasks. Furthermore, we present efficient algorithms for the empirical Bayes method as well as point estimation. Our experiments on both simulated datasets and real world classification datasets show the effectiveness of the proposed models in two evaluation settings: a standard multi-task learning setting and a transfer learning setting.     

Two online dam safety monitoring models based on the process of extracting environmental effect

In this paper, the complex relationship between environmental variables and dam static response is expressed using composition of functions, including nonlinear mapping and linear mapping. The environmental effect and noise disturbance is successfully separated from the monitoring data by analysis of the covariance matrix of multivariate monitoring data of dam response. Based on this separation process, two multivariate dam safety monitoring models are proposed. In model I, the upper control limits (UCLs) are calculated by performing kernel density estimation (KDE) on the square prediction error (SPE) of the offline data. For new monitoring data, we can judge whether they are abnormal by comparing the newly calculated SPE with the UCL. When abnormal data are detected, the SPE contribution plots and the SPE control chart of the new monitoring data are jointly used to qualitatively identify the reason for the abnormalities. Model II is a dam monitoring model based on latent variables that can be calculated from the separation process of the environmental and noise effects. The least squares support vector machines (LS-SVMs) model is adopted to simulate the nonlinear mapping from environmental variables to latent variables. The latent variables are predicted, and the prediction interval is calculated to provide a control range for the future monitoring data. The two monitoring models are applied to analyze the monitoring data of the horizontal displacement and hydraulic uplift pressure of a roller-compacted concrete (RCC) gravity dam. The analysis results demonstrate the good performance of the two models.     

Models of daily rainfall cross-correlation for the United Kingdom

Automated easy-to-use tools capable of generating spatial-temporal weather scenarios for the present day or downscaled future climate projections are highly desirable. Such tools would greatly support the analysis of hazard, risk and reliability of systems such as urban infrastructure, river catchments and water resources. However, the automatic parameterization of such models to the properties of a selected scenario requires the characterization of both point and spatial statistics. Whilst point statistics, such as the mean daily rainfall, may be described by a map, spatial properties such as cross-correlation vary according to a pair of sample points, and should ideally be available for every possible pair of locations. For such properties simple automatic representations are needed for any pair of locations.To address this need simple empirical models are developed of the lag-zero cross-correlation-distance (XCD) properties of United Kingdom daily rainfall. Following error and consistency checking, daily rainfall timeseries for the period 1961–1990 from 143 raingauges are used to calculate observed XCD properties. A three parameter double exponential expression is then fitted to appropriate data partitions assuming isotropic and piecewise-homogeneous XCD properties. Three models are developed: 1) a national aseasonal model; 2) a national model partitioned by calendar month; and 3) a regional model partitioned by nine UK climatic regions and by calendar month. These models provide estimates of lag-zero cross-correlation properties of any two locations in the UK.These cross-correlation models can facilitate the development of automated spatial rainfall modelling tools. This is demonstrated through implementation of the regional model into a spatial modelling framework and by application to two simulation domains (both ∼10,000 km²), one in north-west England and one in south-east England. The required point statistics are generally well simulated and a good match is found between simulated and observed XCD properties.The models developed here are straightforward to implement, incorporate correction of data errors, are pre-calculated for computational efficiency, provide smoothing of sample variability arising from sporadic coverage of observations and are repeatable. They may be used to parameterise spatial rainfall models in the UK and the methodology is likely to be easily adaptable to other regions of the world.     

Advancing scenario planning through integrating urban growth prediction with future flood risk models

High uncertainty about future urbanization and flood risk conditions limits the ability to increase resiliency in traditional scenario-based urban planning. While scenario planning integrating urban growth prediction modeling is becoming more common, these models have not been effectively linked with future flood plain changes due to sea level rise. This study advances scenario planning by integrating urban growth prediction models with flood risk scenarios. The Land Transformation Model, a land change prediction model using a GIS based artificial neural network, is used to predict future urban growth scenarios for Tampa, Florida, USA, and future flood risks are then delineated based on the current 100-year floodplain using NOAA level rise scenarios. A multi-level evaluation using three urban prediction scenarios (business as usual, growth as planned, and resilient growth) and three sea level rise scenarios (low, high, and extreme) is conducted to determine how prepared Tampa's current land use plan is in handling increasing resilient development in lieu of sea level rise. Results show that the current land use plan (growth as planned) decreases flood risk at the city scale but not always at the neighborhood scale, when compared to no growth regulations (business as usual). However, flood risk when growing according to the current plan is significantly higher when compared to all future growth residing outside of the 100-year floodplain (resilient growth). Understanding the potential effects of sea level rise depends on understanding the probabilities of future development options and extreme climate conditions.     

Nonlinear MPC based on a Volterra series model for greenhouse temperature control using natural ventilation

Suitable environmental conditions are a fundamental issue in greenhouse crop growth and can be achieved by advanced climate control strategies. In different climatic zones, natural ventilation is used to regulate both the greenhouse temperature and humidity. In mild climates, the greatest problem faced by far in greenhouse climate control is cooling, which, for dynamical reasons, leads to natural ventilation as a standard tool. This work addresses the design of a nonlinear model predictive control (NMPC) strategy for greenhouse temperature control using natural ventilation. The NMPC strategy is based on a second-order Volterra series model identified from experimental input/output data of a greenhouse. These models, representing the simple and logical extension of convolution models, can be used to approximate the nonlinear dynamic effect of the ventilation and other environmental conditions on the greenhouse temperature. The developed NMPC is applied to a greenhouse and the control performance of the proposed strategy will be illustrated by means of experimental results.     

A long short-term memory-based model for greenhouse climate prediction

Greenhouses can grow many off-season vegetables and fruits, which improves people's quality of life. Greenhouses can also help crops resist natural disasters and ensure the stable growth of crops. However, it is highly challenging to carefully control the greenhouse climate. Therefore, the proposal of a greenhouse climate prediction model provides a way to solve this challenge. We focus on the six climatic factors that affect crops growth, including temperature, humidity, illumination, carbon dioxide concentration, soil temperature and soil humidity, and propose a GCP_lstm model for greenhouse climate prediction. The climate change in greenhouse is nonlinear, so we use long short-term memory (LSTM) model to capture the dependence between historical climate data. Moreover, the short-term climate has a greater impact on the future trend of greenhouse climate change. Therefore, we added a 5-min time sliding window through the analysis experiment. In addition, sensors sometimes collect wrong climate data. Based on the existence of abnormal data, our model still has good robustness. We experienced our method on the data sets of three vegetables: tomato, cucumber and pepper. The comparison shows that our method is better than other comparison models.