A CART technique to adjust production from longwall coal operations under ventilation constraints

Methane emissions in longwall coal mines can arise from a variety of geologic and production factors, where ventilation and degasification are primary control measures to prevent excessive methane levels. However, poor ventilation practices or inadequate ventilation may result in accumulation of dangerous methane-air mixtures. The need exists for a set of rules and a model to be used as guidelines to adjust coal production according to expected methane emissions and current ventilation conditions.In this paper, hierarchical classification and regression tree (CART) analyses are performed as nonparametric modeling efforts to predict methane emissions that can arise during extraction of a longwall panel. These emissions are predicted for a range of coal productivities while considering specific operational, panel design and geologic parameters such as gas content, proximate composition of coal, seam height, panel width, cut height, cut depth, and panel size. Analyses are conducted for longwall mines with and without degasification of the longwall panel. These models define a range of coal productivities that can be achieved without exceeding specified emissions rates under given operating and geological conditions.Finally, the technique was applied to longwall mines that operate with and without degasification system to demonstrate its use and predictive capability. The predicted results proved to be close to the actual measurements to estimate ventilation requirements. Thus, the CART-based model that is given in this paper can be used to predict methane emission rates and to adjust operation parameters under ventilation constrains in longwall mining.     

考虑颜色特征最优组合的CART决策树火灾图像识别方法*

针对火灾图像识别过程中颜色特征数量多、特征间相关性复杂、难以在多维特征融合过程中有效融合图像颜色特征等问题,提出1种考虑颜色特征最优组合的CART决策树火灾图像识别方法。首先,在Lab、RGB、HSV 3种色彩模式下基于图像颜色特征提取火灾图像特征序列;其次,分别在3种色彩模式下基于精细决策树与特征随机排列组合方法提取颜色特征中最优组合特征;最后,将提取的火灾图像最优组合特征序列作为CART决策树输入进行模型训练,并通过测试样本以及其他机器学习方法进行模型泛化能力的分析。研究结果表明:本文方法寻找出识别火灾图像的最优颜色特征组合为“Kb1+Var1+Kg+Kb2+Var2+Kh+Ks+Kv”;CART决策树方法对于火灾图像识别的测试准确度可达84.5%,其分类效果明显优于其他决策树类与集成树类方法;9折为最佳交叉验证折数,其测试准确度可达86.47%,与5折交叉验证相比明显提升14.77%。研究结果可为火灾图像识别提供方法基础。     

典型城市轻型汽油车尾气排放模式分析

为建立典型城市机动车驾驶模式并量化其尾气排放,研究选取成都市内26辆满足国Ⅴ排放标准（GB 18352.5-2013《轻型汽车污染物排放限值及测量方法（中国第五阶段）》）的轻型汽油车,利用便携式尾气测量系统测量其现实条件下的行驶工况及尾气排放,并根据实际情况结合分类回归树方法构建本地化的驾驶模式并分析各模式的尾气排放。结果表明：划分的加速、减速、匀速、怠速、停走5种驾驶模式,可以反映车辆行驶过程中尾气排放和油耗特征。不同驾驶模式间的尾气排放有显著差异。通常情况下,以加速最大,其次为匀速、停走、减速,以怠速最小。根据污染物不同,不同模式间的尾气排放差异可达到12倍。此外,现实条件下车辆尾气超标排放的情况严重,且存在间歇性高排放的现象。这说明构建典型城市驾驶模式并分析其模式排放特征有助于估算小尺度的机动车尾气排放清单,并为交通管理和尾气排放控制提供数据参考。     

Using and comparing two nonparametric methods (CART and MARS) to model the potential distribution of gullies

Gully erosion represents an important soil degradation process in rangelands. In order to take preventive or control measures and to reduce its environmental damages and economical costs it is useful to localize the points in the landscape where gullying takes place and to determine the importance of the different factors involved. The study is carried out in Extremadura, southwest Spain. The main objectives of this work are: (a) comparing two nonparametric schemes to model the potential distribution of gullies, (b) evaluating the importance of the different factors involved in gullying processes, (c) analyzing the role of prevalence in the success of the model and finally, (d) implementing and mapping the results with the help of a Geographical Information System (GIS). Two methods were used to model the response of a dependent variable (gullying) from a set of independent variables: Classification And Regression Trees (CART) and Multivariate Adaptive Regression Splines (MARS). Three different datasets were used; the first one for constructing the model (training dataset) and the others for validating the model (external datasets). These datasets are formed by a target variable (presence or absence of gullies) and a set of independent variables. The dependent variable was obtained by mapping the locations of gullies with the help of a GPS and high resolution aerial ortophotographs. A set of 32 independent variables reflecting topography, lithology, soil type, climate, land use and vegetation cover of each area were used. The performance of the models was evaluated using a non-dependent threshold method: the Receiver Operating Characteristic (ROC) curve. The results showed a better performance of MARS for predicting gullying with areas under the ROC curve of 0.98 and 0.97 for the validation datasets, while CART presented values of 0.96 and 0.66.     

Quantifying ecological thresholds from response surfaces

Ecological thresholds are abrupt changes of ecological state. While an ecological threshold is a widely accepted concept, most empirical methods detect them in time or across geographic space. Although useful, these approaches do not quantify the direct drivers of threshold response. Causal understanding of thresholds detected empirically requires their investigation in a multi-factor domain containing the direct drivers (often referred to as state space). Here, we present an approach to quantify thresholds from response surfaces modeled empirically in state space. We present two indices of shape attributes measured from response surfaces. The response surfaces are built using a regression method in state space. The indices are threshold strength (T) and diagonality (D). We use 48 simulated response surfaces of different shapes to test the efficacy of the indices in 3D. Our results show that T is sensitive to the steepness of the transition from one state to the next, with various forms of abrupt, centralized thresholds yielding the highest values among the simulated surfaces. D represents the orientation of the response surface or the simultaneous influence of more than one predictor in eliciting the response gradient. Strongly diagonal surfaces have the most diagonal surface area demonstrated by sharply undulating diagonal surfaces. Given that the success of T and D requires a regression method to accurately capture any shape of complex data structure, we also test the accuracy of empirical regression methods known to be tractable with complex data. We test classification and regression trees (CART), Random Forest, and non-parametric multiplicative regression (NPMR) for binary and continuous responses. We use the 48 simulated response surfaces to test the methods, and we find that prediction accuracy depends on both the T and D of the simulated data for each method. We choose the most accurate method among those we test for capturing any shape of response surface from real data, NPMR. Finally, we use NPMR to build response surfaces and quantify T and D from real ecological data sets. We demonstrate how measuring threshold strength and diagonality from multi-factor response surfaces can advance ecology.     

Hierarchical Correlates of Bird Assemblage Structure on Northeastern U.S.A. Lakes

We investigated the factorsstructuring lake shore bird assemblages of thenortheastern U.S.A. using data collected from 158 lakesbetween 1992 and 1994. The assemblage data wereaggregated and standardized to produce assemblagecompositions consisting of proportions of individualsemploying different foraging, dietary, and migratorystrategies. The assemblage data were then re-expressedusing compositional analysis techniques and subjectedto regression tree analysis to identify environmentalcorrelates over a range of scales. Regionally, humandensity in the watershed was the most importantpredictor for the foraging, dietary, and migratorycompositions. A combination of anthropogenic andnon-anthropogenic factors likely contributed to thesebroad-scale associations because land use was largelyconfounded with climate and geomorphology. Morelocally, associations with lake shoreresidential-urban development were identified as beingimportant for the foraging and dietary compositions,as were associations with lake shore wetlands, butonly contingent there being little human developmentpresent locally and regionally. Assemblages wereassociated with increasing local and regional humandevelopment such that: hawking, aerial foraging, andground gleaning individuals increased relative tohover-and-gleaners, foliage gleaners, and barkgleaners; omnivores increased relative toinsectivores; and residents increased relative toneotropical migrants. The observed changes in birdcommunity structure were consistent with declines inforest interior species relative to edge species inresponse to forest fragmentation and suggest thatanthropogenic factors have played a prominent role instructuring lake shore bird assemblages of this region.     

Analyzing injury severity factors at highway railway grade crossing accidents involving vulnerable road users: A comparative study

Objective: The main objective of this study is to identify the main factors associated with injury severity of vulnerable road users (VRUs) involved in accidents at highway railroad grade crossings (HRGCs) using data mining techniques.

Methods: This article applies an ordered probit model, association rules, and classification and regression tree (CART) algorithms to the U.S. Federal Railroad Administration's (FRA) HRGC accident database for the period 2007–2013 to identify VRU injury severity factors at HRGCs.

Results: The results show that train speed is a key factor influencing injury severity. Further analysis illustrated that the presence of illumination does not reduce the severity of accidents for high-speed trains. In addition, there is a greater propensity toward fatal accidents for elderly road users compared to younger individuals. Interestingly, at night, injury accidents involving female road users are more severe compared to those involving males.

Conclusions: The ordered probit model was the primary technique, and CART and association rules act as the supporter and identifier of interactions between variables. All 3 algorithms' results consistently show that the most influential accident factors are train speed, VRU age, and gender. The findings of this research could be applied for identifying high-risk hotspots and developing cost-effective countermeasures targeting VRUs at HRGCs.     

白塔堡河底泥DOM组成结构的荧光光谱与多元统计模型表征

利用三维荧光光谱,结合平行因子(PARAFAC)分析、层次聚类分析(HCA)和分类回归树(CART)模型,以东北典型城镇化河流——白塔堡河为研究对象,分别在该河的农村段、城镇段和城市段采集表层底泥样品,研究表层底泥中溶解性有机质(DOM)的荧光组分,分析荧光组分空间特征,识别DOM特征的关键因子,并辨识污染源。结果表明:白塔堡河底泥DOM中包含6个DOM荧光组分,即类富里酸(C1)、微生物代谢产物(C2)、类胡敏酸(C3)、类色氨酸(C4)、类酪氨酸(C5)、酚类物质(C6);白塔堡河城镇段DOM荧光物质浓度最高,城市段次之,农村段最低;白塔堡河农村段底泥DOM以内源为主,城镇段与城市段受陆源和内源物质的双重影响;白塔堡河底泥污染程度为城镇段>城市段>农村段,底泥DOM呈现出农村段、城镇段和城市段分异特征;类酪氨酸与类富里酸是识别底泥DOM特征的2个关键因子。     

Implications of dispersal and life history strategies for the persistence of Linyphiid spider populations

Linyphiid spiders have evolved the ability to disperse long distances by a process known as ballooning. It has been hypothesized that ballooning may allow populations to persist in the highly disturbed agricultural areas that the spiders prefer. In this study, I develop a stochastic population model to explore how the propensity for this type of long distance dispersal influences long term population persistence in a heterogeneous landscape where catastrophic mortality events are common. Analysis of this model indicates that although some dispersal does indeed decrease the probability of extinction of the population, the frequency of dispersal is only important in certain extremes. Instead, both the mean population birth and death rates, and the landscape composition, are much more important in determining the probability of extinction than the dispersal process. Thus, in order to develop effective conservation strategies for these spiders, better understanding of life history processes should be prioritized over an understanding of dispersal strategies.