Crash Severity Research Articles

Examining Fatal Motorcycle Crashes in Malaysia: Rider Age, Road Attributes and Collision Partner Dynamics

Abstract: - High severity crashes involving motorcycles in Malaysia were analyzed to understand the crash characteristics, crash partner, and crash scenarios. This would involve studying how these variables influence the occurrence and severity of fatal crashes. Based on the examination, countermeasures are emphasized from the perspective of technologies, particularly those available on passenger vehicles. The objective of this study is to identify key risk factors and provide insights for improving road safety policies and intervention strategies. The highest age group involved in motorcycle crashes are among 16-20, followed by 21-25. 62.7% occurred in daylight, 90.5% during good weather and 75.4% occurred in midblock. By comparing the engine capacity to the total industry volume, the highest risk is on motorcycles>250 cc, as the production is only 0.29%, but contributes to 4.55% of fatal crashes. The highest crash partners are passenger cars at 30.84%, followed by trucks at 26.64% and single-vehicle accidents at 19.64%. In single crash accidents, road departure represents 56.7%, and control loss, 43.3%. The mandatory ABS in new motorcycles in Malaysia may help in reducing the number of stability losses during emergency braking. Except for rear-end crashes, passenger cars are the highest collision partner in all crash scenarios. Considering the frequency of crash scenarios and crash compatibility, crash avoidance technologies that could help reduce fatalities include autonomous emergency braking, blind spot detection, and lane-keeping assist.

Modeling Rollover Crash Risks: The Influence of Road Infrastructure and Traffic Stream Characteristics

Rollover crashes are among the most prevalent types of accidents in developing countries. Various factors may contribute to the occurrence of rollover crashes. However, limited studies have simultaneously investigated both traffic stream and road-related variables. For instance, the effects of T-intersection density, U-turns, roadside parking lots, the entry and exit ramps of side roads, as well as traffic stream characteristics (e.g., standard deviation of vehicle speeds, speed violations, presence or absence of speed cameras, and road surface deterioration) have not been thoroughly explored in previous research. Additionally, the simultaneous modeling of crash frequency and intensity remains underexplored. This study examines single-vehicle rollover crashes in Yazd Province, located in central Iran, as a case study and simultaneously evaluates all the variables. A dataset comprising three years of crash data (2015–2017) was collected and analyzed. A crash index was developed based on the weight of crash intensity, road type, road length (as dependent variables), and road infrastructure and traffic stream properties (as independent variables). Initially, the dataset was refined to determine the significance of explanatory variables on the crash index. Correlation analysis was conducted to assess the linear independence between variable pairs using the variance inflation factor (VIF). Subsequently, various models were compared based on goodness of fit (GOF) indicators and odds ratio (OR) calculations. The results indicated that among ten crash modeling techniques, namely, Poisson, negative binomial (NB), zero-truncated Poisson (ZTP), zero-truncated negative binomial (ZTNB), zero-inflated Poisson (ZIP), zero-inflated negative binomial (ZINB), fixed-effect Poisson (FEP), fixed-effect negative binomial (FENB), random-effect Poisson (REP), and random-effect negative binomial (RENB), the FENB model outperformed the others. The Akaike information criterion (AIC) and Bayesian information criterion (BIC) values for the FENB model were 1305.7 and 1393.6, respectively, demonstrating its superior performance. The findings revealed a declining trend in the frequency and severity of rollover crashes.

Geospatial and econometric approaches or older driver safety: Analysis of crash injury severity of regional highways.

This study tried to focus on the older drivers' group and explore the impact factors of injury severity involving older drivers from geo-spatial analysis. To reach the goal, a spatial analysis was proposed employing geographic information systems (GIS) with a case study application to two counties in Nevada. First, crash clusters were explored using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) approach to investigate the spatial crash pattern for older drivers, and determine high risk locations of injury severity. Next, Bayesian spatial binary probit model was presented in order to determine the significant impact factors of injury severity involving older drivers. It was found that at-fault driver condition and vehicle condition, not-at-fault vehicle action and road factors were significant factors for injury severity of older drivers. Results revealed that DBSCAN provides a solid option for hotspot identification of injury severity and Bayesian spatial binary probit model addresses the factor determinants spatially. The GIS-based spatial analysis can benefit more reliable older driver-concentrated evaluation and injury severity analysis.

Single-vehicle injury crashes on rural roads in Iceland: contribution of unforgiving roadsides to fatal and serious injuries of vehicle occupants

About 50% of the most severe crashes on rural roads in Iceland are run-off-road crashes. Many existing roads were designed before the concept of forgiving roadsides became prevailing in road design in Iceland. This research aimed to find the roadside elements that significantly increase the probability of high severity of single-vehicle injury crashes compared to low severity crashes on rural roads to prioritize safety improvements under limited budgets. In this research, 712 police records on single-vehicle injury crashes on rural state roads in Iceland in 2016–2018 were investigated. Crash data developed from police reports do not typically include information on roadside elements even though such information is often visible in photographs or written in words by police officers in their crash reports. This limits research on roadside elements and unforgiving roadsides. In this study, the original written police reports and crash photographs were reviewed. Based on this, additional data regarding the roadside elements were coded and added to the standard crash data. A binary logit model for the most severe injury in each crash was developed to statistically test the effect of roadside elements on the probability of fatal and serious injury versus low severity. The model results showed that two roadside elements, rocks and steep transverse slopes (e.g. where an access road enters a main road), hit by a vehicle in a run-off-road crash, more than doubled the probability of high severity. Road safety measures where roadside rocks are removed or steep transverse slopes are reduced, thereby making roadsides more smooth and forgiving, can be especially beneficial for safety because road users are unlikely to adapt their behavior to increased safety from such improvements. This is because such improvements are likely not easily noticed by road users; hence they reduce the probability of compensatory behavior such as increased driving speed, which could outweigh the safety benefits. The results revealed other contributing factors which more than double the probability of high severity of single-vehicle injury crashes on rural roads. Driver intoxication had the strongest effect, a problem which interestingly was limited to drivers living in Iceland. Not a single foreign tourist driver in this data was noted as being under the influence of alcohol or illegal drugs. To strengthen the analysis of the contribution of roadside elements to the severity of run-off-road crashes and to monitor the effects of improvements in the future, it is recommended that additional information on roadside elements be coded and added to the standard police record crash data.

SUV-pedestrian crash severity modelling considering unobserved heterogeneity in means and variances

SUV-type vehicles (light trucks, minivans, vans, SUVs) pose significant risks to pedestrians due to their size and weight. This study analyzed pedestrian crashes involving SUVs using Louisiana traffic crash data (2017–2021) with a random parameter ordered probit model to account for unobserved heterogeneity. Factors linked to higher pedestrian injury severity include winter conditions, divided roads, midblock crossings, business/residential areas, and drivers aged 25–65. Lower injury severity is associated with state highways, city streets, low-speed roads (<25 mph), undivided two-way roads, and intersections. Stability of parameters was observed over time, particularly for crashes involving single SUVs and pedestrians in normal conditions. Variations in variables like "white dashed line" and "proceeding straight ahead" highlight the influence of daylight and speed limits. At the policy level, integrating these findings into traffic management and urban development practices can support a more effective approach to reducing pedestrian injuries in SUV-related crashes.

Analyzing Crash Severity: Human Injury Severity Prediction Method Based on Transformer Model

Traffic accident-related injuries and fatalities are a serious global public health and social development challenge. The accurate prediction of crash severity improves road safety and reduces casualties, as well as serving road managers and policy makers. Prediction models need to learn and analyze the various characteristic factors of traffic accidents and capture from them the inherent complex relationship between accident characteristics and the severity of traffic accidents. However, most accident prediction studies lack analytical predictions of injury severity, and predictive models rely on the content and quality of accident datasets. To increase the robustness and accuracy of prediction models, this paper leverages a Transformer-based architecture for the severity prediction of traffic collisions from human injury severity. This framework learns both text and sequence data from accident datasets. After comparative analysis, the framework can achieve the prediction of human injury severity under different data categories and show good prediction performance at low injury severity levels using only textual data or sequence data.

Classifying crash causation patterns in 2-vehicle collisions between autonomous and conventional vehicles.

This study aims to investigate the causes of 2-vehicle collisions involving an autonomous vehicle (AV) and a conventional vehicle (CV). Prior research has primarily focused on the causes of crashes from the perspective of AVs, often neglecting the interactions with CVs. To address this limitation, the study proposes a classification framework for crash causation patterns in 2-vehicle collisions involving an AV and a CV, considering their interactions. The framework categorizes the crash causation patterns into 5 distinct types: (1) failure of the AV system, (2) failure of takeover control, (3) driver error after takeover, (4) CV failure to adapt to unforeseen changes in AV behaviors, and (5) other factors related to the CV. Utilizing the AV crash data set proposed by Zheng etal., this study extracted 450 two-vehicle collisions involving AVs and CVs for our analysis. Our analysis reveals that the majority of 2-vehicle collisions are triggered by CVs, specifically identified in patterns 4 and 5. Pattern 4 is the primary crash causation factor, accounting for 55% of total collisions. The leading contributing factor to pattern 4 is the improper response of CVs to AVs stopping. There are notable variations in crash injury severity, collision type, and environmental conditions across different causation patterns. Crashes stemming from human drivers' errors (patterns 3, 4, and 5) are more likely to result in moderate to severe injuries. Specifically, pattern 4 notably exhibits the highest likelihood of causing rear-end collisions, whereas patterns 1 and 5 are more prone to causing side collisions. Additionally, crashes associated with pattern 4 are more frequently observed in locations with traffic controls or obstacles. Based on our findings, we propose several recommendations for manufacturers to enhance AV safety performance. These include minimizing planning errors in autonomous driving algorithms, improving communication abilities between AVs and other road users for smoother interactions and better anticipation of actions, and providing specialized driver training for navigating mixed environments with both AVs and CVs.

Evaluating urban intersections: a comparative study of roundabouts versus protected U-turns—which is better?

Effective urban traffic management is a significant challenge in rapidly urbanizing areas with increased vehicular usage, impacting both congestion and safety. Busy cities, like many urban centers, face these issues. Roundabouts, known for their ability to reduce severe crashes, represent a traditional approach to intersection design. However, in high-traffic conditions, roundabouts can become less efficient, leading to increased congestion. Alternatively, protected U-turns, which are a relatively modern approach, are designed to handle high traffic volumes more effectively. They potentially reduce waiting times and improve overall traffic flow but may pose different safety and longitudinal challenges. This study aims to explore these complexities by analyzing the effectiveness of roundabouts and protected U-turns in the context of the unique urban landscape of the Hail City in Saudi Arabia. PTV VISSIM was used for dynamic traffic simulation, providing a realistic representation of traffic patterns in Hail City. Parameters such as vehicle queuing lengths, wait times, and overall intersection capacity are comprehensively evaluated. The simulation settings are adjusted to reflect different traffic densities and patterns, thus ensuring a thorough understanding of the performance of each intersection type under varied conditions. Additionally, various statistical analysis techniques were used to better understand the relationship between the independent and dependent variables. Results showed scenarios of high traffic volume, roundabouts led to longer vehicle queues and increased wait times. On the other hand, protected U-turns exhibited a notable capability to manage high-volume traffic, effectively reducing congestion and improving intersection throughput. This research may contribute to urban traffic management literature, offering insightful guidelines for future intersection design and traffic flow optimization in rapidly urbanizing cities.

Evaluating crash severity at highway-rail grade crossings using an analytic hierarchy process-based hazard index model.

Due to the substantial mass disparity between trains and highway vehicles, crashes at Highway-Rail Grade Crossings (HRGCs) are often severe. Therefore, it is essential to develop systematic frameworks for allocating federal and state funds to improve safety at the highest-risk grade crossings. Common techniques for hazard prioritization at HRGCs include the hazard index and the collision prediction formula. A few research projects and state departments of transportation (DOTs) have employed hybrid models that integrate crash hazard indices with prediction models to create comprehensive safety decision-making frameworks. In addition, ranking grade crossings based on their forecasted crash severity likelihood remains largely unexplored, partly due to the complexity of integrating crash severity outputs with hazard indices. This research introduces a new mixed hazard ranking model, the Analytic Hierarchy Process Hazard Index (AHP-HI), which serves as a decision-making tool for ranking grade crossings based on their potential for crash severity. The AHP-HI model combines the analytic hierarchy process (AHP) and the competing risk model (CRM), a prediction model that estimates the likelihood of crash severity for crossings. Risk analysis using the AHP-HI model categorizes public grade crossings in North Dakota into four risk levels, with 4.73% of the crossings identified as high risk.

Partially temporally constrained modeling of speeding crash-injury severities on freeways and non-freeways before, during, and after the stay-at-home order.

Speeding crashes remain high injury severities after the stay-at-home order in California, highlighting a need for further investigation into the fundamental cause of this increment. To systematically explore the temporal impacts of the stay-at-home order on speeding behaviors and the corresponding crash-injury outcomes, this study utilizes California-reported single-vehicle speeding crashes on freeways (access-controlled) and non-freeways (non-access-controlled) before, during, and after the order. Significant injury factors and in-depth heterogeneity across observations are identified by random parameter logit models with heterogeneity in means and variances. Without segmenting the data by periods, the partially temporally constrained approach is employed to statistically determine varying and stabilized parameters over time through the whole dataset. Different likelihood ratio tests reveal significant temporal instabilities and stabilities of factors between two roadways and three periods. The potential impacts of observation selection issues on the marginal effect calculations of the partially constrained models are also systematically investigated. Significant variations in the probability of severe injury rate per week after the order are also found based on the Mann-Whitney U tests. The hysteretic effects of the order on the crash frequency and severity are observed on both freeways and non-freeways. Overall, seven variables are found to have stable effects, while fifteen variables exhibit unstable effects over time. Significant temporal variations in driver behaviors, including driving under the influence, cell phone usage, hit-and-run, failure to use seat belt, entering or leaving the ramp, and reaction to previous collisions, are observed before, during, or after the order. Specific countermeasures and effects of heterogeneity in means and variances are also discussed. These findings provide insights into understanding the temporal impacts of the stay-at-home order on injury severities, which are valuable to decision-makers and researchers for future order practice, restriction improvement, and complementary policy development.

E-bike crashes: Who they affect and which circumstances to avoid?

In the last decade, the popularity of e-bikes has increased as they have shown potential to relieve congestion and aid the environment. However, with the increase of their popularity, there has been also an increase in their traffic crashes. This study aims to understand factors playing a role in the e-bike crash injury outcomes. The analysis uses 1,351 records of e-bike crashes to estimate random parameters multinomial logit models with heterogeneity in the means and variances of random parameters in four groups. This paper also seeks to provide insights into e-bike crash injury severities across gender (female versus male) and lighting conditions (daytime and nighttime) specific models. Numerous likelihood ratio tests were performed to justify splitting the data. It was found that a variety of factors relating to the weather and road characteristics, crash type, and rider’s demographics play a role in crash outcomes. Particularly interesting are findings relating to the rollover crashes increasing the likelihood of severe outcomes as well as gender specific effects with, for example, male riders have a higher probability of severe injuries during peak traffic hours. The findings can be used to support e-bike safety as well as advocate for a more nuanced and inclusive approach relating to e-bike travel.

Analysis of School Zone Crash Severities with an Equity Lens: A Random Parameters Modeling Approach

Because of the potentially higher loss of human years in collisions involving young children, school zone safety is a significant public health concern. Past studies have identified several factors that are associated with school zone crashes, including inadequate traffic controls, poor speed management, and lack of enforcement. However, school zone safety remains relatively unexplored as an equity issue. Toward that end, crash data about vulnerable road users (VRUs), (i.e., pedestrians/bicyclists) from elementary schools in Los Angeles County, California, U.S., were collected, alongside information about the proportion of students who were enrolled in the free and reduced cost meals program. The latter served as a proxy for the socioeconomic statuses of the schools’ neighborhoods. The severity outcomes of those VRU collisions were analyzed via the random parameters, or mixed, ordinal probit regression structure to gauge the impact of the crash-contributing factors on the injury severity risks. According to the results of this study, the socioeconomic status of the school’s neighborhood was found to induce mixed effects on the injury severity risk. As such, the results suggested that more detailed investigations on the interaction of the factors describing the crash characteristics with equity are required to propose appropriate road safety countermeasures. This is because the impact of the socioeconomic status of the schools on crash severity risk varied across the data.

Investigating Factor Associations in Barrier Crashes through Cluster Correspondence Analysis

Roadside and median barriers have proven effective in preventing crashes; however, a significant number of crashes still occur that involve road barriers across United States. This study focuses on analyzing the factors related to barrier crashes across Texas. The dataset includes 63,475 crashes involving road barriers and covering six years of crash data (2017–2022). Using cluster correspondence analysis (CCA) data mining approach, the study identifies six different clusters of crashes. Each cluster identifies factors contributing to barrier-related crashes. Before implying the CCA, variable importance analysis is also performed to identify the significance of the variables. The analysis highlighted that dry road surface conditions and clear weather are highly associated with high-speed crashes. Driver distraction and absence of traffic control devices can attribute to the crashes on roads with lower speed limits. Moreover, along with other factors, adverse weather conditions are also found to be a contributing factor that can influence the crash frequency and type of crashes. The analysis also implies that non-complex crash type related to a single vehicle are highly correlated with barrier crashes. The study concludes by making several policy-making implications to assist the transportation planners in reducing the frequency and severity of barrier-related crashes.

Evolution of the risk of death and hospitalisation in drivers involved in road crashes in spain, 1993–2020: an age-period-cohort analysis

BackgroundA prerequisite for understanding temporal changes in road crash severity is an unbiased description of this phenomenon. The aim of this study was to estimate the independent association trends of age, period and cohort with severity, encompassing the risk of death (RD) and the risk of death or hospitalisation (RDH) within 24 h, for drivers of passenger cars involved in road crashes with casualties in Spain from 1993 to 2020.MethodsThe study population comprised 2,453,911 drivers of passenger cars aged 18 to 98 years involved in road crashes included in the registers of the General Directorate of Traffic. Crash- and driver-related variables with sufficient continuity over time were included, establishing RD and RDH as study outcomes. Temporal trends of both outcomes were analysed using multivariable Poisson regression and multivariable age-period-cohort intrinsic estimator models. An additional sensitivity analysis was performed for the subset of single crashes.ResultsSeverity estimates showed some variation across strategies. The APC model identified: (1) a J-shaped pattern for the effect of age on severity, (2) a decline in severity between 2001 and 2004 and 2013–2016, and (3) a birth cohort effect for both RD and RDH. In particular, the 1952–1958 cohort had the highest risk (RD = 1.17; 95%CI = 1.11–1.24 and RDH = 1.16; 95%CI = 1.13–1.19), followed by a decreasing trend in subsequent cohorts. Restricting the analysis to single crashes yielded similar results, with the exception of the age effect (severity increased with age). Furthermore, sex differences were observed–female sex was inversely associated with severity, especially for RD.ConclusionsRD and RDH decreased during the first decade of the 21st century, but seemed to stabilise from 2013 onwards. Evidence from this study support that birth cohort is associated with road crash severity, independent of age and period. This cohort effect might be due, at least partially, to improvements in general and road safety education. Further studies are needed to elucidate the causes of our findings and to identify factors accounting for sex differences.

Predicting freeway non-recurring congestion via a spatio-temporal deep learning approach

Freeway unexpected events, such as car crashes, result in non-recurring congestion, which does not follow repetitive patterns in space and/or time and increases the challenge of freeway management. Existing prediction approaches of Freeway Non-recurring Congestion (FNC) are either qualitative with information loss or single-step quantitative for a short period. To address these limitations, this paper develops a quantitative, interpretability-enhanced, and spatial-temporal approach using a 2-Encoder-Decoder Model with an Attention Layer (Att-2ED) for FNC prediction. The model leverages Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP) as two encoders to process time-series speed profiles and static crash features independently. It also employs an LSTM-based decoder to generate a spatio-temporal sequence output and an attention mechanism to prioritise the weights of input sequences at each time step. The model has been trained and tested using real-world freeway data. The proposed model demonstrates superior performance in predicting traffic conditions across both spatial and temporal dimensions compared to existing benchmarks, achieving a Mean Absolute Error (MAE) of 3.74 for 15-minute-ahead predictions. Its effectiveness is further underscored through a comparative analysis of prediction accuracy across various congestion levels and crash severities. For instance, the MAE ranges from 2.77 to 7.00 for severe crashes and from 2.68 to 6.47 for peak-hour crashes, with prediction horizons spanning from 5 min to 60 min ahead. Moreover, the attention mechanisms incorporated in the model provide interpretability-enhanced predictions, highlighting the significance of the last 10-min input in the prediction.

How does distraction affect cyclists' severe crashes? A hybrid CatBoost-SHAP and random parameters binary logit approach.

Cyclists are among the most vulnerable road users, increasingly subject to various sources of distraction, including the use of mobile phones and engagement in other tasks while navigating urban environments. Understanding and mitigating the impact of these distractions on cyclist safety is crucial. Despite the importance of this issue, the effect of distraction on injury severity in cycling crashes has not been extensively studied. This research analyzes four years of U.S. crash data (2019-2022) from the Crash Report Sampling System (CRSS) database, employing a hybrid framework that integrates CatBoost-based SHAP algorithm and the random parameters binary logit model with heterogeneity in means and variances (RPBL-HMV). The proposed approach confirms the significant role of cyclist distraction in crash injury severity. Subsequently, the analysis identifies several factors influencing the likelihood of severe injuries in distracted cyclist crashes. Crashes involving the front of motor vehicles, occurring in rural areas, on two-way roads, at higher speed limits, and during weekends were associated with a higher probability of severe injuries. Conversely, crashes at T-intersections, involving the side or rear of motor vehicles, where cyclists wore helmets, or during rush hour were linked to a reduced likelihood of severe injuries. Notably, interaction effects reveal nuanced patterns. For instance, while crossing roadway actions and rush hour periods individually decrease the likelihood of severe crashes, their combination increases the probability of such outcomes. The findings suggest targeted safety measures and policy interventions aimed at enhancing cyclist safety and promoting safer cycling environments by mitigating distraction-related risks.

Severity Analysis of Pedestrian and Bike Crashes in School Buffer Zones

Pedestrian and bicyclist safety in school zones is critical because of the vulnerability of children and adult pedestrians to vehicle crashes. This paper explores vehicle–pedestrian/bike crash severity within a 15-min walking time buffer around schools in Detroit, Michigan, and San Jose, California—cities with high pedestrian/bike fatality rates. Using 2016–2020 crash data, we employed random-parameter multinomial logit models with heterogeneity in means and variances to understand unobserved relationships between variables. Key random parameters identified include the number of buffer zones that each crash falls into, daylight conditions, and the number of units involved in a crash, all significantly affecting injury severity. Spatial stability was investigated to see if variable effects were consistent across locations. Results revealed spatial instability across Detroit and San Jose. Factors such as Covid lockdown, dark lighting, arterial road presence, bicycle crashes, and the number of units involved showed stable effects with varying magnitudes in both cities. Network buffer zones highlighted that crash proximity to multiple schools affects injury severity. Additionally, the study found that various behavioral, roadway, weather, lighting, and school-related factors influence injury severity in school zones. These findings provide valuable insights for policymakers and planners to develop countermeasures, making school areas safer for children, adult pedestrians, and bicyclists.

Examining the injury severity of public bus–taxi crashes: a random parameters logistic model with heterogeneity in means approach

Public buses and taxis play crucial roles in urban transportation. Ensuring their safety is of paramount importance to develop sustainable communities. This study investigated the significant factors contributing to the injury severity of bus–taxi crashes, using the crash data recorded by the police in Hong Kong from 2009 to 2019. To account for the unobserved heterogeneity, the random parameters logistic model with heterogeneity in means was elaborately developed. The results revealed that taxi driver age, bus age, traffic congestion, and taxi driver behavior had significantly heterogeneous effects on the injury severity of bus–taxi crashes and that the mean value of the random parameter for severe traffic congestion was likely to increase if the taxi’s age was <5 years. Taxi driver gender, rainfall, time of day, crash location, bus driver behavior, and collision type were found to significantly affect the bus–taxi crash severity. Specifically, female taxi drivers, old taxis, rainfall, midnight, improper manipulation of bus and taxi drivers, head-on and sideswipe collision types, and non-intersections were associated with a higher likelihood of fatal and severe crashes. Based on our findings, targeted countermeasures were proposed to mitigate the injury severity of bus–taxi crashes.

Identifying accident prone areas and factors influencing the severity of crashes using machine learning and spatial analyses

Identifying accident prone areas and the contributing environmental factors can save lives and enhance infrastructure durability. This research presents an innovative use of two hierarchical clustering methods (Agglomerative Hierarchical and BIRCH clustering algorithms) to detect accident hotspots with high accident rates on the Yazd-Kerman road, in Iran. These approaches identified clusters of accidents, highlighting significant clusters and categorizing their overlap as two accident prone areas. The high percentage of overlapping results from both methods indicates a high level of consistency in the findings. Through observations, field visits, police report analysis, and interviews with locals, the primary causes of accidents in accident prone areas were identified. In one of the accident prone areas, the most significant reasons for accidents included the presence of a resting area, insufficient lighting at curves, and poor road signage, which created a dilemma zone for drivers. In another accident prone area, the main contributing factor was reduced visibility during dust storms. Then, K-Nearest Neighbors and Random Forests machine learning algorithms were employed to predict the severity of accidents, using various input attributes such as lighting, climate, alignment slope, and road geometry. The K-Nearest Neighbor surpassed the Random Forest technique, achieving an overall accuracy of 71% in contrast to 60%. This study effectively evaluated the outcomes of clustering, uncovering the underlying causes of accidents to inform future practical interventions. Moreover, by predicting the severity of accidents along the road, a framework was developed to propose strategies for risk reduction.

Effect of Qatar-based law amendment on pedestrians’ behavioral intentions: A PLS-SEM based analysis

Pedestrian violations are among the biggest concerns for administration as they contribute to increased frequency and severity of pedestrian-related crashes. Typically for ensuring pedestrian safety, law enforcement measures such as pedestrian penalties are used. To assess the efficacy of such enforcements, pedestrian sentiments towards these law enforcements need to be determined. There is a general lack of studies assessing the effect of pedestrian law enforcement on pedestrians’ behavior. Using Qatar based data, this study assessed the effectiveness of a recent law amendment in State of Qatar to improve pedestrians’ behavioral intentions. Based on 645 survey responses, a Partial Least Squares Structural Equation Modelling (PLS-SEM) approach was used to verify quantitative relationships among law amendment, risk perception, safety effectiveness perception, and pedestrians’ behavioral intentions. The results indicate that the pedestrians’ behavioral intentions are strongly influenced by law emphasis, risk perception, and safety effectiveness perception. Moderating role of respondent attributes such as their demographics, personal experiences of respondents with traffic issues, and experience regarding law enforcement are also determined. The structural path between risk perception and behavioral intentions was significantly moderated by gender and jaywalk frequency. Further, nationality and education showed moderating effects on structural path between behavioral intentions and law effectiveness and safety effectiveness perception. Findings from this study contribute to the theoretical understanding of pedestrians’ behavior and can be used for planning and implementation of targeted law enforcement to improve pedestrian safety.