Data mining of tree-based models to analyze freeway accident frequency

INTRODUCTION: Statistical models, such as Poisson or negative binomial regression models, have been employed to analyze vehicle accident frequency for many years. However, these models have their own model assumptions and pre-defined underlying relationship between dependent and independent variables. If these assumptions are violated, the model could lead to erroneous estimation of accident likelihood. Classification and Regression Tree (CART), one of the most widely applied data mining techniques, has been commonly employed in business administration, industry, and engineering. CART does not require any pre-defined underlying relationship between target (dependent) variable and predictors (independent variables) and has been shown to be a powerful tool, particularly for dealing with prediction and classification problems. METHOD: This study collected the 2001-2002 accident data of National Freeway 1 in Taiwan. A CART model and a negative binomial regression model were developed to establish the empirical relationship between traffic accidents and highway geometric variables, traffic characteristics, and environmental factors. RESULTS: The CART findings indicated that the average daily traffic volume and precipitation variables were the key determinants for freeway accident frequencies. By comparing the prediction performance between the CART and the negative binomial regression models, this study demonstrates that CART is a good alternative method for analyzing freeway accident frequencies. IMPACT ON INDUSTRY: By comparing the prediction performance between the CART and the negative binomial regression models, this study demonstrates that CART is a good alternative method for analyzing freeway accident frequencies.     

Analyzing pedestrian crash injury severity under different weather conditions

Objective: Pedestrians are the most vulnerable road users due to the lack of mass, speed, and protection compared to other types of road users. Adverse weather conditions may reduce road friction and visibility and thus increase crash risk. There is limited evidence and considerable discrepancy with regard to impacts of weather conditions on injury severity in the literature. This article investigated factors affecting pedestrian injury severity level under different weather conditions based on a publicly available accident database in Great Britain.

Method: Accident data from Great Britain that are publicly available through the STATS19 database were analyzed. Factors associated with pedestrian, driver, and environment were investigated using a novel approach that combines a classification and regression tree with random forest approach.

Results: Significant severity predictors under fine weather conditions from the models included speed limits, pedestrian age, light conditions, and vehicle maneuver. Under adverse weather conditions, the significant predictors were pedestrian age, vehicle maneuver, and speed limit.

Conclusions: Elderly pedestrians are associated with higher pedestrian injury severities. Higher speed limits increase pedestrian injury severity. Based on the research findings, recommendations are provided to improve pedestrian safety.     

Analyzing injury severity of bus passengers with different movements

Objective: Though public transport vehicles are rarely involved in mass casualty accidents, when they are, the number of injuries and fatalities is usually high due to the high passenger capacity. Of the few studies that have been conducted on bus safety, the majority focused on vehicle safety features, road environmental factors, as well as driver characteristics. Nevertheless, few studies have attempted to investigate the underlying risk factors related to bus occupants. This article presents an investigation aimed at identifying the risk factors affecting injury severity of bus passengers with different movements.

Method: Three different passenger movement types including standing, seated, and boarding/alighting were analyzed individually using classification and regression tree (CART) method based on publicly available accident database of Great Britain.

Results: According to the results of exploratory analyses, passenger age and vehicle maneuver are associated with passenger injury severity in all 3 types of accidents. Moreover, the variable “skidding and overturning” is associated with injury severity of seated passengers and driver age is correlated with injury severity of standing and boarding/alighting passengers.

Conclusions: The CART method shows its ability to identify and easily explain the complicated patterns affecting passenger injury severity. Several countermeasures to reduce bus passenger injury severity are recommended.     

Spatial and temporal analysis of vegetation change in agricultural landscapes: A case study of two brigalow (Acacia harpophylla) landscapes in Queensland, Australia

The majority of landscapes around the world have been modified or transformed by human activities to meet the needs of human societies. The loss of native vegetation for agricultural development affects the sustainability of growing proportion of the world's ecosystems. Factors such as land tenure, roads and agricultural intensification, together with biophysical properties, have been cited as drivers of deforestation. This paper combined analysis of the historical drivers of change with analysis of the trends of deforestation since 1945 in two brigalow landscapes (100,000 ha) in sub-tropical Australia. A selection of these drivers were then applied at a property-level (1000 ha) to test their influence on native vegetation retention. Regression trees were used to identify significant human drivers and biophysical properties, and then a generalised linear modelling approach was used to quantify the effect of these factors on the proportion of remnant native vegetation. Results showed that until the mid-20th century, government policies to intensify settlement did not result in increased agricultural production, but since this time, landscape change has been rapid, and has particularly affected ecosystems on fertile clay soils. Although socio-economic factors were critical in driving deforestation, after 60 years of agricultural intensification by far the most significant explanatory variable determining the proportion of native vegetation retained at a property scale was the suitability of the soil for agriculture. Property size was an important secondary influence. The results were not, by and large, consistent with other studies of landscape change and suggest that generalised principles explaining deforestation may be elusive. Solutions to the problem of over-clearance of native vegetation, therefore, need to be tailored to the specific regional situations encountered.     

CART-分类与回归树方法介绍

分类与回归树（CART－ClassificationandRegressionTrees）是一种非常有趣并且十分有效的非参数分类和回归方法．它通过构建二叉树达到预测目的。该方法是四位美国统计学家耗时十多年辛勤劳动的成果。在他们所著的“ClassificationandRegressionTrees（1984）”一书中有该方法的详细说明。笔者认为该方法在古生物化石分类和鉴定以及矿产资源预测等方面颇有用武之地。本文只对该方法作简单介绍,希望能对从事预测工作的读者有所启发。美国加利福尼亚统计软件公司已歼发了CART方法软件。     

城市交通环境对行道树叶片表皮结构影响的研究

以珠江三角洲常见的 8种受到交通环境影响的城市行道树及其对照树作为研究材料 ,对其叶片的上下表皮结构进行了研究。结果表明 ,交通环境引起城市行道树叶片表皮结构如气孔数、气孔口等发生变化 ,但不同的树种的叶片表皮结构对交通环境的响应不同。     

Planting History and Propagule Pressure as Predictors of Invasion by Woody Species in a Temperate Region

Abstract:  We studied 28 alien tree species currently planted for forestry purposes in the Czech Republic to determine the probability of their escape from cultivation and naturalization. Indicators of propagule pressure (number of administrative units in which a species is planted and total planting area) and time of introduction into cultivation were used as explanatory variables in multiple regression models. Fourteen species escaped from cultivation, and 39% of the variance was explained by the number of planting units and the time of introduction, the latter being more important. Species introduced early had a higher probability of escape than those introduced later, with more than 95% probability of escape for those introduced before 1801 and <5% for those introduced after 1892. Probability of naturalization was more difficult to predict, and eight species were misclassified. A model omitting two species with the largest influence on the model yielded similar predictors of naturalization as did the probability of escape. Both phases of invasion therefore appear to be driven by planting and introduction history in a similar way. Our results demonstrate the importance of forestry for recruitment of invasive trees. Six alien forestry trees, classified as invasive in the Czech Republic, are currently reported in nature reserves. In addition, forestry authorities want to increase the diversity of alien species and planting area in the country.     

EFFECTS OF WOODY VEGETATION ON SANDY LEVEE INTEGRITY1

he influence of woody vegetation on the reliability of a sandy levee was investigated using field data in seepage and slope stability analyses. Field data were collected from selected sites within a 10-km segment of a channel levee on the Sacramento River near Elkhorn, California. Root architecture and distribution were determined using the profile-wall method in which root cross sections were exposed in the vertical wall of an excavated trench. Transects running both parallel and perpendicular to the crest of the levee were excavated at six sites. Each site was dominated by different plant species: five sites were adjacent to trees or woody shrubs, while one supported only herbaceous growth. Lateral plant roots were primarily restricted to, and modified, the near-surface soil horizons to a depth of approximately 1 meter. Root area ratios (RARs) did not exceed 2.02 percent and generally decreased exponentially with depth. At depths greater than 20 cm, mean RARs for sites dominated by wood species were not significantly different from the mean RAB for the herbaceous site. No open voids clearly attributable to plant roots were observed. Roots reinforced the levee soil and increased shear resistance in a measurable manner. Infinite slope and circular arc stability analyses were performed on the landward and riverward slopes under different hydraulic loading conditions. Infinite slope analyses indicated increasing root area ratio from 0.01 percent to 1 percent increased the factor of safety from less than one to more than seven. Circular arc analyses indicated that even the lower measured root concentrations sufficed to increase safety factors for arcs with maximum depths of about 1 m from less than one to about 1.2. Our findings suggest that allowing woody shrubs and small trees on levees would provide environmental benefits and would enhance structural integrity without the hazards associated with large trees such as wind-throwing.     

广州城市行道树特征分析

本文运用生态学方法，探讨了广州市区行道树的生物群落，生态质量及空间分布特下。     

行道树对城市道路交通环境的响应研究

以南方常见的8种城市行道树作为研究对象,并以各自在远离城市道路交通环境生长的树种作为对照,对行道树及其对照样品叶片和树皮的重金属铅和镉、电导率、pH值、叶片伤斑率及叶片表皮结构气孔数等进行测定,以探讨不同树种对交通环境的响应.结果表明,与对照树种比较,行道树叶片和树皮能累积城市道路交通环境中的重金属铅和镉,其电导率和叶片的伤斑率增加,pH值下降.叶片气孔数的变化随树种不同有所差别,如阴香〔Cinnamomumbur-manii(Nees)〕等的叶片气孔数比对照少,而细叶榕(FicusmicrocarpaL.)等比对照多.根据行道树的生长状况及净化重金属的能力,8种供试植物中,白兰(MicheliaalbaDC.)和垂叶榕(FicusbenjaminaL.)最适合选作行道树,而阴香因其在交通环境中生长不良,净化效益差,不宜选作交通密集区的行道树种.图3表3参17