Objectives: The objective of this study was to examine the effects of various roadway characteristics on the incidence of pedestrian–vehicle crashes by developing a set of crash prediction models on 543 km of Malaysia federal roads over a 4-year time span between 2007 and 2010. Methods: Four count models including the Poisson, negative binomial (NB), hurdle Poisson (HP), and hurdle negative binomial (HNB) models were developed and compared to model the number of pedestrian crashes. Results and Conclusions: The results indicated the presence of overdispersion in the pedestrian crashes (PCs) and showed that it is due to excess zero rather than variability in the crash data. To handle the issue, the hurdle Poisson model was found to be the best model among the considered models in terms of comparative measures. Moreover, the variables average daily traffic, heavy vehicle traffic, speed limit, land use, and area type were significantly associated with PCs.

The first field experiment with intelligent speed adaptation (ISA) in Malaysia was held in December 2010 in the State of Penang. Eleven private cars were instrumented with an advisory system. The system used in the present study included a vocal warning message and a visual text message that is activated when the driver attempts to exceed the speed limit. When the driver decreases the speed, the warning stops; otherwise it is continuously repeated. The test drivers drove the vehicles for three months with the installed system, and the speed was continuously logged in all vehicles. The warning was however only activated in the second month of the three month period. The present study aimed to evaluate the effects of an advisory ISA on driving speed, traffic safety, and drivers' attitude, behavior, and acceptance of the system. To examine these effects, both the survey and the logged speed data were analyzed and explored. The results show a significant reduction in the mean, maximum and 85th percentile speed due to the use of the system. However, there was no long-lasting effect on the speed when the system was deactivated. In the post-trial survey, drivers declared that the system helped them well in following the speed limits and that it assisted them in driving more comfortably. Furthermore, the warning method was more accepted compared to a supportive system, such as active accelerator pedal (AAP). After the trial, most drivers were willing to keep an ISA system

Letjen S. Parman road is one of the urban roads with a length of 4.2 km located in West Jakarta area and is a primary arterial road with three two-way lanes divided, where the median is a toll road in the city of Jakarta. This study aims to evaluate road pavement conditions functionally and compare the value of road pavement conditions based on two methods, namely Pavement Condition Index (PCI) and Surface Distress Index (SDI) which are used as the basis for knowing the type of road maintenance handling. This study uses direct observation method in the field by conducting a visual survey of the condition of pavement, where the length of this road is divided into 42 segments with one segment is 100 meters. From the results of the road damage research Letjen. S. Parman using pavement condition index (PCI) and Surface Distress Index (SDI) method there are no significant differences in results. For pavement condition index (PCI) method get a percentage result of 90% with perfect value and 10% with excellent value while with Surface Distress Index (SDI) method get a percentage result of 96.5% with good category and 3.5% with medium category.

A new method of capacity analysis at unsignalized intersections has been developed in this study for Indonesia where the drivers’ behavior, traffic composition, level of roadside activities are different from those in developed countries. Typical cities in developing countries performed by the heterogeneous traffic mixed including fast–moving vehicles (motorized) and slow–moving vehicles (unmotorized). Traffic rules for examples like give-way or lane discipline are neglected in most cases. The study focused on ten three–leg unsignalized intersections in a suburban city in Indonesia. The new method was based on the interactions between conflict streams (six streams and six conflict points) having the average speed and flow of each stream. All possible conflict streams were considered simultaneously and the interactions were taken into account through empirical regression models. The results of capacity analysis from this proposed method correspond properly with the results from the current Indonesian Highway Capacity Manual (IHCM). © 2011 Published by Elsevier Ltd

Since the last two decades, several modeling approaches have been developed in road safety literature to establish the relationship between traffic accidents and road characteristics. However, to the best of the authors’ knowledge, no extensive research work has been published on application of Adaptive Neuro-fuzzy Inference System (ANFIS) on road accident modelling. Therefore, the present paper aims to develop an ANFIS technique for modelling traffic accidents as a function of road and roadside characteristics. To achieve the objective, accident data and road characteristics were collected over a two-year period along the Qazvin-Loshan intercity roadway in Iran. The candidate set of explanatory variables included the Mean Horizontal Curvature (MHC), Shoulder Width (SW), Road Width (RW), Land Use (LU), Access Points (AP), Longitudinal Grade (LG), and Horizontal Curve Density (HCD). The results showed that RW, SW, LU, and AP significantly affected accident frequencies. Using statistical performance indices, the ANFIS model was compared with the Poisson, negative binomial, and non-linear exponential regression models. Based on the comparative results, the proposed model had higher prediction performance than the other three traditional models which has been widely used in the literature. To conclude, the proposed model could be used as a robust approach to handle uncertainty and complexity existed in accident data. In general, ANFIS model can be an effective tool for transportation agencies since intervention decisions and plans aiming at improving road safety depend on the prediction capabilities of a system.

This study focused on the Poisson regression with excess zero outcomes on the response variable. A generalized linear modelling technique such as Poisson regression model and Negative Binomial model was found to be insignificant in explaining and handle over dispersion which due to high amount of zeros thus Zero Inflated model was introduced to overcome the problem. The application work on the number of road accidents on F001 Jalan Jb-Air Hitam. Data on road accident were collected for five-year period from 2010 through 2014. The result from analysis show that ZINB model performed best, in terms of the comparative criteria based on the P value less than 0.05.