No abstract

Road traffic fatality is a burden towards low- and middle-income countries including Malaysia. Seeing that Selangor has the highest number of road traffic fatalities in Malaysia for the year 2019, therefore the state is selected as a case study. The aim of the article is 1) to understand the road traffic crash pattern and road traffic fatality pattern in Selangor 2) to determine the ability of 16 road traffic features in classifying road traffic fatality occurrence. The preliminary data screening shows that road traffic crash patterns and road traffic fatality patterns in Selangor have many similarities. However, both of them also have few dissimilarities such as crash time of occurrence, day of occurrence, number of vehicles involved in a crash, and type of vehicle first hit for the crash. Supervised machine learning algorithm in Orange data mining software was considered in this analysis. The analysed algorithms among others are neural network, random forest, decision tree, logistic regression, naïve Bayes, and support vector machine. Neural network was seen as the best algorithm to classify road traffic fatality occurrence with 97.0% classification accuracy outperform other algorithms. The result of the article can be used by the relevant traffic stakeholders to execute safety intervention in a more focused manner in Selangor to reduce the number of road traffic fatalities.

No abstract

Reckless driving behavior might result in a higher risk of an accident. Many factors are known to be the cause of this driving behavior. One of the factors is the socio-demographic background of the driver. This study aims to review currently available literature that investigates the relationship between driving behavior and any known socio-demographic characteristics. The review also focuses on the method used in the data collection as well as the tools used to perform the analysis to correlate the driving behavior and socio-demographic background. The review found that the influence of socio-demographic background on driving behavior study has not been explored in detail especially from the ethnicity point of view. With regards to the data collection, most of the study utilised the self- report survey, in which the targeted respondents are young adults. There are also studies covering all age groups that made use of the Driving Behaviour Questionnaire, data of traffic accidents or police reports, and virtual reality to collect the data. SAS/STAT statistical software package was found to be a popular choice among researchers when analyzing the data. This review concludes that driving behavior study in the multi-racial country for instance in Malaysia should explore further the relationship between driving behavior and socio-demographic background, especially from the ethnic perspective.

Many road traffic accidents occur in Malaysia every year. Road fatalities has been one of the main causes of death in Malaysia. More than half of these fatalities were among motorcyclists. An accident between a passenger car and a motorcycle might be caused by the blind spot of the car driver, in which the driver was unable to notice an incoming motorcycle from behind or the side. Blind spot monitoring system has been developed using recent technology. However, this active blind spot monitoring system is expensive and only available in luxury cars. Another type of blind spot monitoring is known as passive blind spot monitoring by means of a convex mirror. Many convex blind mirrors are being sold nationwide that come in various shapes. Nonetheless, the effectiveness of this convex mirror has never been quantified. This study aims to experimentally quantify the effectiveness of this mirror by using a spotlight, projecting a direct light to the side mirror. A circular convex mirror was placed at four different locations, one at a time. It is hypothesised that the reflection of the light on a flat, white wall indicates the driver’s field of view. The area of the reflection was calculated using image processing, and the values of all five cases were compared. It was found that the circular convex mirror increases the field of view by up to 211 %. The position of the convex mirror plays an important role to ensure a maximum field of view is achieved. This paper has demonstrated that the usage of a circular convex mirror does increase the driver's field of view.