An alternative source of Bangladesh road crash data

Road traffic injuries are one of the primary reasons for death, especially in developing countries like Bangladesh. Safety in land transport is one of the major concerns for road safety authorities and other policymakers. For this reason, contributory factors identification associated with crashes is necessary for reducing road crashes and ensuring transportation safety. This paper presents an analytical approach to identifying significant contributing factors of Bangladesh road crashes by evaluating the road crash data, considering three different severity levels (non-fetal, severe, and extremely severe).

Generally, official crash databases are compiled from police-reported crash records. Though the official datasets are focusing on compiling a wide array of attributes, an assorted number of unreported issues can be observed that demands an alternative source of crash data. Therefore, this proposed approach considers compiling crash data from newspapers in Bangladesh which could be complimentary to the official crash database.

To conduct the analysis, first, we filtered the useful features from compiled crash data using three popular feature selection techniques: chi-square, Two-way ANOVA, and Regression analysis. Then, we employed three machine learning classifiers: Decision Tree, Random Forest, and Naïve Bayes over the extracted features. A confusion matrix was considered to evaluate the proposed model, including classification accuracy, sensitivity, and specificity. The predictive machine learning model, namely, Random Forest using Label Encoder with chi-square and Two-way ANOVA feature selection process, seems the best option for crash severity prediction that provides high prediction accuracy. The resulting model highlights nine out of fourteen independent features as responsible factors. Significant features associated with crash severities include driver characteristics (gender, license type, seat belts), vehicle characteristics (vehicle type), road characteristics (road surface type, road classification), environmental conditions (day of crash occurred, time of crash), and injury localisation. This outcome may contribute to improving traffic safety of Bangladesh.

In this study, we have compiled 441 crash records reported in three newspapers of Bangladesh for the year 2019. We opted for the most famous and oldest newspapers among several newspapers: Daily Prothom Alo, Daily Jugantor, and Bdnews24. The detailed information on different crashes reported in this newspaper is collected and compiled from the e-archive of these newspapers. The crash severity was reported in the database as a three-point severity scale variable: non-fatal injury, severe injury, and extremely severe injury.

道路交通事故伤害是主要致死原因之一，在孟加拉国等发展中国家尤为突出。陆路交通安全是道路安全监管机构及其他政策制定者高度关注的核心议题。为此，识别与道路碰撞相关的促成因素，对于减少道路碰撞事故、保障交通运输安全至关重要。本文基于孟加拉国道路碰撞数据展开分析，考量三类碰撞严重程度等级（非致命、严重及极严重），提出一种识别孟加拉国道路碰撞显著促成因素的分析方法。

通常而言，官方碰撞数据库依托警方上报的碰撞记录编制而成。尽管官方数据集致力于收录多维度的属性信息，但仍存在大量未上报的事故案例，亟需替代性的碰撞数据来源。因此，本研究提出的方案将从孟加拉国报纸中采集碰撞数据，作为官方碰撞数据库的补充数据源。

为开展本次分析，研究团队首先采用三种主流特征选择技术：卡方检验（chi-square）、双向方差分析（Two-way ANOVA）以及回归分析（Regression analysis），从已编制的碰撞数据中筛选有效特征。随后，基于提取得到的特征，分别运用三种机器学习分类器：决策树（Decision Tree）、随机森林（Random Forest）与朴素贝叶斯（Naïve Bayes）进行建模。本研究采用混淆矩阵（confusion matrix）对所提模型进行评估，评估指标涵盖分类准确率、灵敏度与特异度。经测试，结合标签编码器（Label Encoder）、卡方检验与双向方差分析特征选择流程的随机森林预测模型，表现为碰撞严重程度预测的最优方案，可实现较高的预测精度。该模型将14项独立特征中的9项识别为关键影响因素，与碰撞严重程度相关的显著特征包括：驾驶员特征（性别、驾照类型、是否佩戴安全带）、车辆特征（车辆类型）、道路特征（路面类型、道路等级）、环境条件（事故发生日期、事故发生时段）以及受伤部位。该研究成果可为改善孟加拉国的道路交通安全状况提供参考。

本研究共收集了2019年孟加拉国三家报纸报道的441条碰撞事故记录。研究选取了当地最具知名度与历史底蕴的三家报纸：《每日普罗塔姆阿洛报（Daily Prothom Alo）》、《每日朱甘托报（Daily Jugantor）》以及Bdnews24。上述报纸的电子存档中收录的各类事故详细信息，被逐一收集并整理为本研究的数据集。本数据库将碰撞严重程度设定为三点式等级变量：非致命伤害、严重伤害与极严重伤害。