Using statistical modelling to analyze risk factors for severe and fatal road traffic accidents

Crash severity analysis: A data-enhanced double layer stacking model using semantic understanding

The crash severity analysis is of significant importance in traffic crash prevention and emergency resource allocation. A range of innovations offers potential traffic crash severity prediction models to improve road safety. However, the semantic information inherent in traffic crash data, which is crucial in enabling a deeper understanding of its underlying factors and impacts, has yet to be fully utilized. Moreover, traffic crash data are commonly characterized by a small sample size, which leads to sample imbalance problem resulting in prediction performance decline. To tackle these problems, we propose a semantic understanding-based data-enhanced double-layer stacking model, named EnLKtreeGBDT, for crash severity prediction. Specifically, to fully leverage the inherent semantic information within traffic crash data and analyze the factors influencing crashes, we design a semantic enhancement module for multi-dimensional feature extraction. This module aims to enhance the understanding of crash semantics and improve prediction accuracy. Then we introduce a data enhancement module that utilizes data denoising and migration techniques to address the challenge of data imbalance, reducing the prediction model's dependence on large sample crash data. Furthermore, we construct a two-layer stacking model that combines multiple linear and nonlinear classifiers. This model is designed to augment the capability of learning linear and nonlinear mixed relationships, thereby improving the accuracy of predicting the severity of crashes on complex urban roads. Experiments on historical datasets of UK road safety crashes validate the effectiveness of the proposed model, and superior performance of prediction precision is achieved compared with the state-of-the-arts. The ablation experiments on both semantic and data enhancement modules further confirm the indispensability of each module in the proposed model.

The impact of temperature, rainfall, and health worker density index on road traffic fatalities in Pakistan

A road traffic accident is a burning issue because the cost of road accidents is about 2% of gross domestic product in Pakistan. This paper explores the relationship between health force density index, temperature, rainfall, road lengths, and road traffic fatalities in Pakistan from 1985 to 2016. The stationarity was determined with the help of four-unit root tests. The existence of long-run cointegration was determined by using the autoregressive distributing lag bound test. The vector error correction model showed the long-run causality of road traffic fatalities, which implies that road traffic fatalities were affected by selected variables in the long-run. The short-run unidirectional causality was running from road traffic fatalities to health force density index; temperature to health force density index; rainfall to health force density index; health force density index to rainfall; road traffic fatalities to high type road length; health force density index to high type road length; and temperature to high type roads. The reduction in road fatalities was 1.713% due to a 1% increase in health force density. But, road fatalities increase by 3.628% due to a 1% increase in temperature. The road fatalities increase by 0.255% and 0.485% due to a 1% increase in rainfall and high type road length, respectively. The governments should increase the number of doctors and nurses for the life-saving of an injured person. Due to the adverse impact of temperature on road safety, the government should formulate a comprehensive environmental policy in order to mitigate global warming. It is recommended to increase the forest area to reduce the level of emission. It is required to modify the system of transportation according to the guidelines of international transportation associations with respect to the quality and maintenance of vehicles, medical check-up of drivers, and construction of roads. Installation of speed cameras is also needed on high type roads to ensure road safety. It is also recommended to increase traffic law enforcement. It is difficult for the Pakistani government to effectively execute road safety plans due to the limitation of resources. However, the government should invest the revenue collected through tax violation fine for the improvement in road safety. It is also needed to invest in the health sector and up-gradation of the hospitals for the safety of human beings. The government should ensure the availability of the latest medical technology in the hospitals and the improvement of emergency services. It is required to develop coordination between various ministries such as transportation, planning, law, education, public health, and information. It is necessary to make the public aware of the social and economic cost of road accidents using electronic, print, and social media. Graphical abstract.