IATSS Research最新文献

The color of road signs is a critical aspect of road safety, as it helps drivers quickly and accurately identify and respond to these signs. Properly colored road signs improve visibility during the day and make it easier for drivers to make informed decisions while driving. In order to ensure the safety and efficiency of road traffic, it is essential to maintain the appropriate color level of road signs.

The objective of this study was to analyze the color status and daylight chromaticity of in-use road signs using supervised machine learning models, and to explore the correlation between road sign's age and daylight chromaticity. Three algorithms were employed: Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN). The data used in this study was collected from road signs that were in-use on roads in Sweden.

The study employed classification models to assess the color status (accepted or rejected) of the road signs based on minimum acceptable color levels according to standards, and regression models to predict the daylight chromaticity values. The correlation between road sign's age and daylight chromaticity was explored through regression analysis. Daylight chromaticity describes the color quality of road signs in daylight, that is expressed in terms of X and Y chromaticity coordinates.

The study revealed a linear relationship between the road sign's age and daylight chromaticity for blue, green, red, and white sheeting, but not for yellow. The lifespan of red signs was estimated to be around 12 years, much shorter than the estimated lifespans of yellow, green, blue, and white sheeting, which are 35, 42, 45, and 75 years, respectively.

The supervised machine learning models successfully assessed the color status of the road signs and predicted the daylight chromaticity values using the three algorithms. The results of this study showed that the ANN classification and ANN regression models achieved high accuracy of 81% and R² of 97%, respectively. The RF and SVM models also performed well, with accuracy values of 74% and 79% and R² ranging from 59% to 92%. The findings demonstrate the potential of machine learning to effectively predict the status and daylight chromaticity of road signs and their impact on road safety in the Swedish context.

Pedestrian distraction is a major causal factor reported in pedestrian fatalities worldwide. Even though many observational studies and laboratory-based research have been conducted to examine the influence of pedestrian distraction on road safety, there is little understanding of the determinants of pedestrian beliefs that influence distracted walking behaviour. The present study examines the associations of pedestrian beliefs related to engagement in mobile phone distraction with psychological factors such as mobile phone addiction, boredom proneness, and mindfulness. Five hundred and fifty-one participants completed a questionnaire about their distraction beliefs (behavioural, normative, and control), mobile phone addiction, boredom proneness, and mindfulness. A Structural Equation Model (SEM) was developed to investigate the influence of mobile phone addiction, boredom proneness, and mindfulness on the three types of beliefs. Mobile phone addiction was significantly associated with behavioural beliefs (factor loading = 0.38) and control beliefs (factor loading = 0.23) but not with normative beliefs. Further, significant associations of boredom proneness were observed with all three types of beliefs: behavioural (factor loading = 0.15), normative (factor loading = 0.13), and control (factor loading = 0.15). Mindfulness showed significant relationships with normative beliefs (factor loading = 0.13) and control beliefs (factor loading = 0.11) but not with behavioural beliefs. This study is the first attempt to investigate the predictors of pedestrian distraction beliefs in the Indian context. The findings can assist the policymakers in understanding the pedestrian psychology behind their distracted walking behaviour.

The use of advanced models to investigate the determinants of injury severity outcomes for motorized and non-motorized-involved crashes are sparse. Therefore, random-parameter ordered probit models with heterogeneity in means and variances were developed to estimate factors affecting injury severity for motorized and non-motorized-involved crashes. Data covering a five-year period comprising 5976 and 634 cases for motorized and non-motorized-involved crashes respectively, was retrieved from the database of the National Road Safety Authority, State Insurance Company and Driver and Vehicle Licensing Authority in Ghana and used for model estimation. The results show that factors have varying significant effects on injury severity outcomes for motorized and non-motorized models. Marginal effects indicate that old age occupants, head-on-collision, exceeding a posted speed limit of 100 km/h and crash during weekends contributed greatly to the likelihood of severe injury outcomes in motorized model. Additionally, male non-motorists, non-use of helmet, rear-end collision, right-angle collision and crash on urban roads and during weekends, contributed significantly to the severe injury outcomes of non-motorized models. The direction of effect of the factors on severe injury was observed to have varying degrees of estimated coefficients. The difference in estimated coefficients shows that crashes involving non-motorized vehicles were more likely to result in severe injury compared to motorized vehicles. The motorized model had heterogeneity in means of five (5) random parameters observed, while the non-motorized model had heterogeneity in means of four (4) random parameters observed with two variables affecting the variance of three random parameters. Based on the results, various countermeasures were proposed to enhance road traffic safety.

The present study aimed to propose new pedestrian delay models for Signalized Midblock Crosswalks (SMC) for mixed traffic conditions. A detailed study of the literature revealed that most of the existing pedestrian delay models were developed for signalized intersections. Thus, the need for the study was established and data were collected at eight SMC in Hyderabad, one of the most densely populated metropolitan cities in India, using video-graphic technique. Two delay models were developed based on the compliance behaviour and non-compliance behaviour of pedestrians. Both models have two components i.e., waiting delay and crossing delay where the latter has two subset components i.e., frictional delay and pedestrian-vehicle interaction delay. The bidirectional effect (pedestrian-pedestrian interaction while crossing the road) of pedestrians was addressed as frictional delay while the non-compliance behaviour by pedestrians and vehicles was addressed as pedestrian-vehicle interaction delay in the present models. The waiting delay component was defined by modifying the Webster delay model for non-uniform pedestrian arrivals. The proposed delay models yielded an error of 5% and 7% for compliance behaviour model and non-compliance behaviour model respectively. The proposed models can be used for optimizing the signal timings and defining Level of Service (LOS) of facilities.

The primary condition for society to benefit from autonomous vehicle (AV) advantages is the acceptance of these vehicles by people. In this regard, the factors which affect the acceptance of these vehicles among different countries should be identified. In previous studies, a major focus has been on developing autonomous vehicle acceptance models, neglecting the moderating variables' effect on these models. The main aim of this research is to investigate the effect of moderating variables including demographic characteristics, psychological characteristics, traffic experience collision, and travel/driving behavior on the autonomous vehicle acceptance model (AVAM). The AVAM was developed via structural equations modeling by participating 553 Tehrani citizens by extending the unified theory of acceptance and use of technology. It was indicated that the negative relationship of the perceived risk on the intention of using AVs has been higher for individualistic people, culprit drivers with a history of more than one property damage-only collision, and those without a driving license. Also, the results showed that emphasis on the advantages and benefits of autonomous vehicles in collectivist people as compared to individualistic people would lead to a greater intention to use these vehicles.

Centerline rumble strips are low-cost effective countermeasures installed on the center of the highway segments to reduce crashes, especially roadway departure crashes. For safety evaluation of centerline rumble strips, methodologies such as naïve before-after analysis and cross-sectional study with Empirical Bayes have been widely utilized. The implementation of these methodologies may be limited due to the lack of relevant control groups, and/or other temporal variations in crashes such as seasonality and serial autocorrelation. This study aims to explore Intervention Time Series Analysis approach as an alternative method for the safety evaluation of centerline rumble strips on rural-two-lane undivided highways in Louisiana. Two different methodologies are explored in the intervention time series approach including the Forecast modeling technique and the Auto-regressive Integrated Moving Average intervention model. The forecast models are based on the exponential smoothing technique, state-space framework, and neural network model. The database consists of monthly observations of total and target crashes on 312 highway segments of 1274 miles in length in which centerline rumble strips were installed during the 2010–2012 period. The time frame 2005–2012 is defined as the pre-intervention period whereas the time frame 2013–2017 is defined as the post-intervention period. The analysis revealed that the Auto-regressive Integrated Moving Average intervention model performed better in terms of error estimates including root means square error, mean absolute error, and mean absolute percentage error. The proposed Auto-regressive Integrated Moving Average intervention model reveals a 17.75% total and 40.54% target crash reduction on the selected rural-two-lane undivided highway segments during the post-intervention period. All the findings are found statistically significant at a 95% confidence level.

Most road crashes at work are caused by Driver Behavioral Drift (DBD). This DBD has become a recurring issue on congested road sections.

In this context, this study proposes a method called (MASOCU-DBD) which allows to analyze this DBD problem in two steps: assessment of the dynamics of DBD occurrence using a model called BM-NSA and analysis of DCC using a Cost-Benefit Analysis (CBA) weighted by the Analysis Hierarchical Process (AHP).

The application of the MASOCU-DBD on a road section of an Algerian city's entry highlighted the problem of the DBD in terms of its occurrence and uselessness in the studied section.

The merit of the proposed method is that it uses multi-criteria analysis tools (AHP and CBA) as well as a mathematical model (BM-NSA) to analyze professional drivers' behavioral deviations.

Mixed traffic conditions present a complex problem for analysis by transportation engineers and policymakers, due to the inherent heterogeneity and lane indiscipline. The chaotic arrangements make it difficult to identify and analyze basic riding behaviour such as following and filtering. Moreover, the smaller lateral dimensions of Motorized Two Wheelers (MTWs) and their higher manoeuvreability add to the difficulty. Presence of different types of vehicles in traffic mix, following the leader with or without obliqueness, filtering through tight pores between leader vehicles, etc. are some of the aspects that require special attention. In this respect, this study is aimed at investigating the attributes related to following and filtering manoeuvres of MTWs in such disordered traffic conditions. Real world data from two Indian cities was used for the analysis, which showed that the behaviour of MTWs is heavily influenced by the type of leader vehicle(s), Clear Lateral Gap (CLG), speed, etc. Safety analysis carried out using Time-To-Collision (TTC) showed that about 8.2% of the interactions were risky. Support Vector Machine (SVM) technique was used to investigate the choice of filtering based on Clear Lateral Gap (CLG) and relative speed. Moreover, analysis of the observed parameters was conducted to obtain their specific distributions based on leader vehicle type, following regime and choice of filtering. The analysis will give directions for further research on developing driving behaviour models of MTWs in mixed traffic. The results will also find potential application in traffic flow theories, safety studies, microsimulation, implementation of MTW infrastructure, etc.

Road traffic crashes have increased over the years leading to greater injury severity among children who are mostly vehicle occupants in high-income countries. This adversely affects the healthy development of children and might lead to death. However, studies in the literature have focused on predicting crash injuries among adults while children have different crash injury risks as well as crash kinematics compared to adults. To address this gap, this paper presents a new dataset for child occupant crash injury severity prediction collected over 8 years (2012 to 2019) in the United Arab Emirates (UAE). The performance of state-of-the-art machine learning algorithms was then evaluated using the proposed dataset. In addition, feature selection techniques and logistic regression model were employed to extract the most significant features for crash injury severity prediction among child occupants. Furthermore, the impact of data balancing approaches on the prediction performance was analyzed as the dataset is highly imbalanced. The experimental results showed that Adaboost, Bagging REP, ZeroR, OneR, and Decision Table algorithms predicts child occupant injury severity with the highest accuracy. Child occupant seating position, emirate, crash location, crash type and crash cause were observed as significant features that predicts injury severity by both the feature selection and logistic regression models.