Supervised and unsupervised techniques to analyze risk factors associated with motorcycle crash

PURPOSE

Motorcycles are one of the highly used modes of transport in Barcelona, Spain, in particular, and in many different regions, in general. This situation is compromising safety on the road and may be attributed to a potential increase in traffic crashes. Therefore, this study examines several risk factors and their consequential impacts on the level of injury that is resulted in case of a traffic crash.

METHODS

Two approaches are employed to analyze the risk factors, including a supervised learning technique which is a binary probit model, and an unsupervised technique which is the Kohonen clustering.

RESULTS

The results for both models show that alcoholism and road in poor condition can indeed increase the probability of having different levels of injuries as reasons for the crash. Elderly users are less likely to be involved in motorcycle crash injuries compared to other age categories, especially the age group that ranges from 25 to 40 years old which has the highest odds. For both techniques, the performance in analyzing the utilized data shows that both approaches can be successfully utilized for this type of dataset.

CONCLUSION

This study highlights the considerable danger faced by motorcyclists due to various risk factors. It stresses the critical importance of maintaining roads in optimal condition not just for efficient travel but also to enhance motorcyclists' safety. Additionally, the research underscores the significant threat posed by speeding, particularly exceeding speed limits, to motorcyclists' safety, emphasizing the urgent need for more 30 km/h speed limit zones and stricter enforcement of speed regulations. As a result, the research has identified several risk factors that increase the likelihood of severe or fatal injuries among motorcyclists in Barcelona and has suggested certain recommendations to mitigate their impact.

Analysis of risk factors affecting traffic accident injury in United Arab Emirates (UAE)

The mortality and severe injuries due to traffic accidents in United Arab Emirates (UAE) are hastening the necessity for a study that can identify the consequential risk factors. This study was conducted by utilizing a 5740 traffic accidents police reports that occurred in Abu Dhabi, UAE between 2008 and 2013. A multinomial logit regression model was applied to determine the significant factors among the 14 potential risk factors that were used in this study. The dependent variable was the level of injury that consisted of four categories: slight injury, medium injury, severe injury, and fatal injury. The results showed that pedestrian, the unutilized seatbelt, roads that had four or more than four lanes, male casualty, 100 km/h speed limit or higher, and casualty older than 60 years were found to be the factors that can increase the probability of being involved in a fatal traffic accident. In contrast, rear-end collisions and intersections had a lower probability of causing fatal injury. Then, the eight significant predictors were included in a neural network to compare the performance of both methods and to identify the normalized importance values for the significant independent variables. The neural network had proven to be more accurate in general than the traditional regression models such as the multinomial logit model.

Traffic accident severity analysis in Barcelona using a binary probit and CHAID tree

Traffic accidents are still wide causation for fatalities around the globe. The set of alarm for this cause of deaths is still on, since the number of fatalities is still representing an enormous issue and a challenge for most governments. In Barcelona, similar to the rest of the world, traffic accidents are threatening lives and raising the need to lessen the number of both fatalities and severities. This study is conducted to grasp the correlations between different classification factors with accident severities and fatalities. A total of 47,153 traffic accident cases that occurred between 2016 and 2019 are utilized. Then, a binary probit model and Chi-square automatic interaction detector are exploited to grasp the impact of several risk factors. The results confirmed that males and 65 years and older injured persons are more exposed to severe or fatal injuries compared to other categories. Pedestrians and drivers are found to have higher probabilities compared to passengers in being involved in severe or fatal injuries. Weekends, afternoon, night timings all have higher odds of having severe or fatal traffic accidents. The findings of this study can help road authorities in targeting these risk factors to mitigate their impact to achieve Vision Zero.

Risk analysis of traffic accidents' severities: An application of three data mining models

Traffic accidents are costing the world more than a million lives yearly alongside monetary losses, especially in the Gulf Cooperation Council region. This situation raised the need to examine potential risk factors contributing to traffic accident severities. In this paper, three data mining models were applied to provide a comprehensive analysis of risk factors related to traffic accidents' severities. One of the used models was a decision tree to examine the correlations between potential risk factors. The other applied models were Bayesian Network and linear Support Vector Machine. The results confirmed that pedestrians were the most vulnerable road users compared to drivers and passengers. Male drivers and front seat-passengers were more exposed to severe or fatal injury. Similarly, elderly drivers had higher odds of having severe or fatal injuries. Road classifications and accident types were also considered significant variables related to traffic accidents' injuries. Utilizing seat belt could lessen the level of injury. Regarding the performance of the applied models, Bayesian network was more accurate in predicting the variables compared to other models.

Vehicle inspection policy and emission analysis in Kuwait

Technical vehicle inspection centers are widespread in Kuwait. All vehicles should pass the test every 2 years if not older than 6 years or every 1 year for other vehicles. This study provided an insight into the data collected from test centers and the emission test utilized in Kuwait. Data were collected from test centers in the six Kuwaiti governorates. European standards were selected as limits for emission violations. Independent variables included the place of vehicle manufacture, vehicle's age, and odometer reading. A multinomial logit model was used to identify the significant predictors and determine the correlation between dependent and independent variables. Artificial neural network was employed to compare prediction estimates of neural network and multinomial logit. The findings showed that the place of vehicle's manufacture, vehicle's age, and odometer reading were significant regarding violating emission standards of carbon monoxide (CO). Asian vehicles, vehicles with more than 150,000 km mileage, and vehicles older than 15 years had a higher probability of failing the CO test compared to the place of manufacture. In contrast, the odometer reading was the only significant indicator for vehicles that have failed the hydrocarbons test, especially for vehicles with 150,000 km odometer reading. The findings of this study can reduce air-pollution, time, and money by targeting the most polluting vehicles; thus, more efficient test can be performed.