Prediction of road traffic death rate using neural networks optimised by genetic algorithm

Social, economic, and legislative factors and global road traffic fatalities

BACKGROUND

Road traffic fatalities (RTF) is the 8th cause of mortality around the world. At the end of the Decade of Action, it would be of utmost importance to revisit our knowledge on the determinants of RTF. The aim of this study is to assess factors related to RTF at global level.

METHODS

We used road safety development index which accounts for the interactions between system, human and products to assess the RTF in 115 and 113 countries in 2013 and 2016, respectively. To analyze data, three statistical procedures (linear regression, classification and regression trees, and multivariate adaptive regression splines) were employed.

RESULTS

Classification and regression trees has the best performance amongst all others followed by multivariate adaptive regression splines for 2013 and 2016 data set with an R2 around 0.83. Results show that any increase in human development index was associated with RTF reduction. Comparing RTF data of 2013 and 2016, 8 countries experienced a change of more than 30%, which demonstrated a significant relationship with GINI index (named after Corrado Gini). Considering the three components of human development index, it is revealed that education explained most of RTF variation in classification and regression trees model followed by income and life expectancy.

CONCLUSION

Policymakers should consider road collisions as a socio-economic issue. In this regard, they can make provisions to reduce RTF in the long run by focusing on enhancing the three components of human development index, mainly education. However, there is a need to investigate the causation pathway among these three components with RTF with different time-trend procedures.

Probabilistic temporal prediction of the deaths caused by traffic in Colombia. Mortality caused by traffic prediction

BACKGROUND

from probability theory and probabilistic random walk, predictions about the quantity of cases of a given phenomenon for certain year, such as epidemics of dengue, have been previously obtained with results close to 100% in precision.

OBJECTIVE

To confirm the applicability of a methodology based on probability and probabilistic random walk to predict the dynamics of deaths from road traffic injuries in Colombia for 2010.

METHODOLOGY

through the development of a total probability space that analyses the probabilistic behaviour of augments and decreases observed in the variation of the lengths of the death rates caused by traffic in Colombia from 2004 to 2009, the most likely event for 2010 was established for predicting the rate of deaths for that year.

RESULTS

The predicted rate of deaths caused by traffic injuries in Colombia for 2010 was 14.88 with the methodology. When this value is compared with the value reported by national statistics, which was a rate of 12.9, a precision of 86.6% with the prediction was achieved.

CONCLUSIONS

the applicability of the developed methodology to predict the dynamic behaviour of deaths caused by traffic injuries in Colombia for 2010 by means of a probabilistic random walk was confirmed with a good precision, suggesting that this methodology could be useful to verify the efficacy of national road safety strategies implemented to reduce mortality rates.

Geographical Detection of Traffic Accidents Spatial Stratified Heterogeneity and Influence Factors

The purpose of this paper is to investigate the existence of stratification heterogeneity in traffic accidents in Shenzhen, what factors influence the casualties, and the interaction of those factors. Geographical detection methods are used for the analysis of traffic accidents in Shenzhen. Results show that spatial stratification heterogeneity does exist, and the influencing factors of fatalities and injuries are different. The traffic accident causes and types of primary responsible party have a strong impact on fatalities and injuries, followed by zones and time interval. However, road factors, lighting, topography, etc., only have a certain impact on fatalities. Drunk driving, speeding over 50%, and overloading are more likely to cause more casualties than other illegal behaviors. Speeding over 50% and speeding below 50% have significant different influences on fatalities, while the influences on injuries are not obvious, and so do drunk driving (Blood Alcohol Concentration ≥ 0.08) and driving under the influence of alcohol (0.08 > Blood Alcohol Concentration ≥ 0.02). Both pedestrians and cyclists violating the traffic law are vulnerable to fatality. Heavy truck overloading is more likely to cause major traffic accidents than minibuses. More importantly, there are nonlinear enhanced interactions between the influencing factors, the combination of previous non-significant factors and other factors can have a significant impact on the traffic accident casualties. The findings could be helpful for making differentiated prevention and control measures for traffic accidents in Shenzhen and the method selection of subsequent research.

A hybrid clustering and classification approach for predicting crash injury severity on rural roads

As a threat for transportation system, traffic crashes have a wide range of social consequences for governments. Traffic crashes are increasing in developing countries and Iran as a developing country is not immune from this risk. There are several researches in the literature to predict traffic crash severity based on artificial neural networks (ANNs), support vector machines and decision trees. This paper attempts to investigate the crash injury severity of rural roads by using a hybrid clustering and classification approach to compare the performance of classification algorithms before and after applying the clustering. In this paper, a novel rule-based genetic algorithm (GA) is proposed to predict crash injury severity, which is evaluated by performance criteria in comparison with classification algorithms like ANN. The results obtained from analysis of 13,673 crashes (5600 property damage, 778 fatal crashes, 4690 slight injuries and 2605 severe injuries) on rural roads in Tehran Province of Iran during 2011-2013 revealed that the proposed GA method outperforms other classification algorithms based on classification metrics like precision (86%), recall (88%) and accuracy (87%). Moreover, the proposed GA method has the highest level of interpretation, is easy to understand and provides feedback to analysts.