Crash Reports Research Articles

STUDY ON ROAD TRAFFIC MULTIMODAL SIMULATION, COMPARITIVE STUDY ON SIMULATION SOFTWARES ON INTERSECTION AND ITS ROAD SAFETY AUDIT

In today’s world of advancements transportation engineering is the most focused branch in terms of software development. In order to provide a small part to this branch a comparative study is a must to identify the most efficient software for providing this work is important. To do this study in the project we need to identify the best software for simulations of vehicles in multimodal means is also of that importance. This also suggests the need of this softwares in use also. To do this designing a intersection is optimum. Also the Ministry of Works, Housing and Communications has a duty of care to all road users, and so has always been concerned with the safety of its roads. However, the significant increase in road crashes in recent years has prompted the Ministry to intensify its efforts to promote road safety. One small part of this effort are new procedures to ensure that the safety of all road schemes is checked by specialists before construction this is called safety auditing. demand for transportation, safety is an issue of major social concern and an area of extensive research work. The rate of Crashes in developing countries like India increases year by year. A Crash is an unplanned and uncontrolled event, which occurred on a road open to a public traffic resulting in personal injury, damages to the property and loss of life in which at least one moving vehicle was involved. In the world, India has world’s largest heavy traffic and accidents also. It is necessary to provide the safety to roads. Lack of infrastructure, interaction of vulnerable road users (VRU) with high-speed traffic, and faulty geometric design are some of the most alarming safety deficiencies identified through the audit process. The insights obtained from the RSA report could not have been gained from the Crash reports alone. Finally, countermeasures need to be suggested based on the observations made during the RSA.

Examining demographic, work, and sleep characteristics among older South Asian American yellow taxi drivers in New York City: A brief report

ObjectivesThis exploratory study examines workplace factors, sleep, sleep disorders, and safety among older (age 50 years and above) yellow taxi drivers in New York City (NYC) of South Asian descent. MethodsUsing street intercept methods, quantitative data was collected among yellow taxi drivers in NYC (n = 27) from January–March 2020. ResultsAmong drivers, higher than normal sleepiness was identified in 33%, sleeping fewer than 7 hours on worknights work nights was reported by 52%, and 37% were at high risk for obstructive sleep apnea (OSA). Among drivers, 11% (n = 3) reported a motor vehicle accident in the past year and all drivers who reported an accident were at high risk for OSA. ConclusionsFindings from this hard-to-reach and understudied population revealed that most drivers did not report sufficient sleep on work nights. Results found over one-third of drivers had high OSA risk and drivers at high risk for OSA contributed to all reports of motor vehicle crashes.

Database selection matters: A case study in child restraint use and injury patterns using North Carolina motor vehicle traffic crash report and trauma registry data

Objective While proper restraint use is protective against motor traffic vehicle crash (MVTC)-associated morbidity and mortality, it is inconsistently measured across health and MVTC data sources. This project addresses this gap by assessing differences in child restraint measures between two North Carolina (NC) datasets and comparing the utility of these sources to evaluate patterns of child restraint use and associated health outcomes. Methods We analyzed 2018 NC MVTC and NC Trauma Registry (NCTR) data for children ≤15 years old, both separately and as linked MVTC-NCTR records. We calculated mean and standard deviation for continuous variables and frequency and proportion for categorical variables. Among linked records, we compared reported restraint use and performed age-adjusted logistic regression to estimate associations between restraint use and severe injury. Results A lower proportion of pediatric MVTC victims were reported as unrestrained in the MVTC (14.7%) versus NCTR (25.8%) data. Among linked MVTC-NCTR records, only 41.3% featured perfect concordance of restraint information between datasets. Among linked records, child restraint was reported for 31.3% of children, while the NCTR data allowed more granular coding of child restraint (30.3% overall), including child booster seat (13.5%), child car seat (8.7%), infant car seat (4.8%), and unrestrained in child car seat (3.4%). Age-adjusted regression analyses of the linked data revealed that lap/shoulder seatbelt use was significantly associated with lower likelihood of severe injury compared to being unrestrained whether informed by MVTC (OR = 0.39; 95% CI: 0.16, 0.93) or NCTR (OR = 0.38; 95% CI: 0.15, 0.96) data. While the association between reported use of a child car seat and severe injury was not statistically significant in the MVTC data (OR = 0.50; 95% CI: 0.19, 1.32), child car seat use reported in the NCTR data revealed a significant association (OR = 0.16; 95% CI: 0.03, 0.93). Conclusions Linked crash and trauma center data allow for identifying important patterns of restraint use among pediatric passengers in MVTCs. Dataset-dependent differences in measuring restraint use have critical public health implications and illustrate the importance of careful dataset selection prior to analysis, as the use of different data sources may impact overall study conclusions.

Factors related to highway crash severity in Brazil through a multinomial logistic regression model

Reducing the number of deaths by road crashes is an important priority for many countries around the world. Although focusing on the occurrence of crashes can provide safety policies that help reduce its numbers, studying their severity can provide different measures that may help further reduce the number of deaths by focusing on the most severe problems first. In this paper, a multinomial logistic regression model is fitted to nationwide highway crash data in Brazil from 2017 to 2019 to identify and estimate the associated factors to crash severity. Severity is classified as without injury, with injured victims or with fatal victims. Amongst other observations, results indicate that pedestrian involvement in highway crashes increase dramatically their severity. Also, conditions that favor greater speeds (clear weather, times when there are fewer vehicles on the road) are also related to an increase in crash severity, pointing to a proportional relation with traffic fluidity. Moreover, some observed limitations on the data may indicate that Brazil would benefit greatly from national crash records standards and unified databases, especially crossmatching crash reports with health data.

An investigation on the safety of children on the roads of Gaza, Palestine

The traffic safety system in Palestine needs major improvements. Traffic accident data in Gaza Strip are collected from crash reports recorded by the local Police. In many cases, roads are constructed without proper consideration of children’s needs. However, children and young kids use the roads as pedestrians, bicyclists, and occupants of vehicles. Moreover, they might choose to play on the road. This paper aims to investigate the situation of traffic safety of children in the Gaza Strip and to recommend measures to reduce their risk. This research is based on accident statistics recorded in the period between 2008 and 2018. Analysis was carried out to determine critical locations that have a high number of accidents, focusing on accidents that resulted in casualties and fatalities of children. Results show that the highest rate of children fatalities in the Gaza Strip was on Arterial Roads. According to the data collected in 2016, 2017, and 2018, the percentage of road traffic deaths of children are 60%, 68% and 59% respectively, which is higher than the average rate of child mortality in the world (52%) according to the world organization statistics. Gaza city has the largest number of children fatalities caused by road accidents in the Gaza Strip. This might be due to the high population density and heavy traffic. In order to reduce road accidents for children, it is necessary to control the speed of vehicles at school zones and to provide more safety measures for children on the roads, including illuminated pedestrian crossings for children. It is very important to provide children at schools and kindergartens with proper training on how to cross the street. It is also helpful to teach them some important traffic signs.

Road Traffic Accidents in Port Harcourt, Rivers State: Pattern of Injuries That Caused Death, Risk Factors, Anatomical Sites Affected, and Autopsy Findings

Background: Road traffic accident (RTA) is one of the commonest causes of death among the healthy population and it’s among the leading cause of death due to human errors. Globally, it has contributed significantly to reducing the workforce as well as increasing the family expenditure on preventable health conditions. It is grossly underreported with no clear data on annual death reports, especially in most developing countries. Objectives: To determine the rate of death from a head injury due to road traffic accidents, risk factors; the commonly injured anatomical regions and immediate cause of death from autopsy examination of victims. Methods: This was a prospective longitudinal study in which 86 victims with CORONER FORM D were sampled recruited for the study. Primary data were obtained using the Crash Report Form (CRF) from the Federal Road Safety Corps, oral interviews from deceased relatives and security personnel who brought the victims, and subsequently, Coroner form D was used to obtain /record the findings of autopsy examination. Data was analysed using Statistical Product and Service Solutions (SPSS) version 25.0 (Armonk, NY). Results: The rate of death from a head injury due to RTA in Port Harcourt was 48.84%. The mean age of victims examined at autopsy was 28.61 ± 9.22 with a modal age group of 20-29. Majority of the victims were males [52(65.82%)], passengers [36(42%)], had superficial autopsy [32(37.20%)], multiple injuries [40 (46.51%)]. The commonest cause of immediate fatality was head injury (48.8%) followed by haemorrhage and shock 31(36.1%). Over speeding was the most common human risk factor (50%), followed by sleep/fatigue (10%). The commonest mechanical and environmental risk factors identified were brake failure and burst tyres (8%), and potholes (6%) respectively. Conclusion: The commonest cause of death among victims of RTA in Port Harcourt, Rivers State, Nigeria is head injury. Over speeding, sleep/fatigue, brake failure and burst tyres and pot holes are the risk factors for RTA in Port Harcourt. Measures targeted at controlling these risk factors would help reduce morbidity and mortalities associated with RTA.

Analysis of pedestrian accident injury-severities at road junctions and crossings using an advanced random parameter modelling framework: The case of Scotland

This paper investigates the determinants of injury severities in pedestrian-motor vehicle accidents at signalised and unsignalised junctions, and at physically-controlled and human-controlled crossings in Scotland. The accident data were drawn from the official police crash report database of the UK spanning a period between 2010 and 2018. Correlated random parameter ordered probit models with heterogeneity in the means were developed in order to account for the multi-layered impact of unobserved heterogeneity on statistical estimation. The model estimation results showed that the severities of accident injuries are affected by roadway, location, weather, vehicle, and driver characteristics as well as temporal attributes (including time and day of the accident). Factors such as the urban context, lighting and weather conditions and road surface conditions were found to result in correlated random parameters, thus capturing the intricate, yet interactive effects of unobserved heterogeneity, and particularly the unobserved behavioural response of road users to different traffic control types at junctions and crossings. Vehicle type, driver’s gender and day-of-the-week were observed to influence the random parameters' distributions. Empirically, the results showcase variations in the determinants of injury severities at signalised and unsignalised junctions, and at physically-controlled and human-controlled crossings. Even though most of these variations were related to the magnitude of impact of the determinants, differences in the directional effects on injury severities were also identified, mainly for factors related to weather conditions, hazard presence on the road, and temporal characteristics of the accidents.

DROWTECT – VIBRATING CHAIR AND SPRAY NOZZLE TO PREVENT SLEEPINESS IN CAR DRIVERS BASED ON IMAGE PROCESSING WITH DROWSINESS DETECTION ALGORITHM

Based on data from the police of the Republic of Indonesia from 2014 to 2018 there was a significant increase in the number of motorized vehicles, namely 6.49% per year (Indonesian Central Statistics Agency, 2018: 22). This increase in the number of vehicles occurs in all types of vehicles every year according to police data, in Indonesia an average of 3 people die every hour due to traffic accidents. The data also states that the large number of accidents is caused by several factors, including 61% caused by humans related to the driver's character, 9% due to vehicle technical requirements, and 30% caused by infrastructure and the environment (Kominfo, 2017). Based on these data, many traffic accidents occur because of the character of the driver, such as not focusing and traveling. According to Rau et al (2005) in the United States about 100,000 accidents per year (1.6% of 6.3 million) are identified in the Police Crash Report (PCR) due to problematic drivers. accidents experienced by drivers in circumstances have general characteristics that are usually observed by traffic safety officers including, during the late hours of the night (2:00 to 6:00) or after the day (3:00 to 17:00) ) , driving on highways or toll roads, only young drivers, not using brakes, one person in the car, lack of security at the accident site, the level of drivers exceeding the limit for safe driving (Kamran, et al. 2019). Driver's drowsiness is a major factor in road accidents (Kumar, et al. 2018). Drowsiness while driving is very dangerous because it can cause an accident that can be found in death. Death due to traffic accidents caused by drivers is an event that can be avoided and minimized. To reduce the number of traffic accidents and their impacts, it is necessary to have a role from all parties. Based on this, the purpose of our research is to create a detection device system using image processing that is used to detect the eyes of the car driver, if the driver detects the data from the image processing will communicate and to a tool called a nozzle, then the nozzle will issue The air sprays into the driver's face slowly and in the driver's seat is also installed a dc motor that can cause a low level of shock to the driver, so that the driver can regain consciousness and focus on the traffic.
 
 Keywords: Image Processing, Nozzle, Accident, Driver, Image Processing, Nozzle

Understanding the role of Speeding and Speed in Serious Crash Trauma: A Case Study of New Zealand

Multiple sources of evidence address the contribution of speed and speeding in crashes: police crash reports, in-depth crash investigations, studies of speed and serious crash risk, assessments of survival and injury rates for various impact speeds, and evaluations of the safety outcomes of speed management interventions. These sources of evidence all indicate that speed is a major factor in crash trauma, but appear to differ in estimates of the extent of the role of speed. This paper employs New Zealand as a country case study, undertaking a targeted assessment of data from the different sources to better determine the roles of speed and speeding in serious crashes. We find that apparent mismatches of estimates of the role of speed from different sources largely arise for two reasons. First, the studies vary in methodology and thus validity, and second the data from the different sources provide answers to fundamentally different questions, which are then incorrectly subsumed into the general question of the role of speed. Finally, we answer the question: ‘What is the extent of the role of speed in crashes, and particularly deaths and serious injuries?’ by providing answers to the different ways of couching these questions. Depending on the question, correct answers range from 20% to 100% of serious crashes. By combining evidence from different sources, we estimate that speeding is involved in around 60% of fatal crashes in New Zealand, and that speeds above New Zealand’s Safe and Appropriate Speeds are involved in around 71% of injury crashes.

Data linkage for crash outcome assessment: Linking police-reported crashes, emergency response data, and trauma registry records

Introduction: Traffic crash reports lack detailed information about emergency medical service (EMS) responses, the injuries, and the associated treatments, limiting the ability of safety analysts to account for that information. Integrating data from other sources can enable a better understanding of characteristics of serious crashes and further explain variance in injury outcomes. In this research, an approach is proposed and implemented to link crash data to EMS run data, patient care reports, and trauma registry data. Method: A heuristic framework is developed to match EMS run reports to crashes through time, location, and other indicators present in both datasets. Types of matches between EMS and crashes were classified. To investigate the fidelity of the match approach, a manual review of a sample of data was conducted. A comparative bias analysis was implemented on several key variables. Results: 72.2% of EMS run reports matched to a crash record and 69.3% of trauma registry records matched with a crash record. Females, individuals between 11 and 20 years old, and individuals involved in single vehicle or head on crashes were more likely to be present in linked data sets. Using the linked data sets, relationships between EMS response time and reported injury in the crash report, and between police-reported injury and injury severity score were examined. Conclusion: Linking data from other sources can greatly enhance the information available to address road safety issues, data quality issues, and more. Linking data has the potential to result in biases that must be investigated as they relate to the use-case for the data. Practical implications: This research resulted in a transferable heuristic approach that can be used to link data sets that are commonly collected by agencies across the world. It also provides guidance on how to check the linked data for biases and errors.

Automobile Crash Investigation Based on Vehicle System Related Causes: Systematic Literature Review

Automobile accidents are one of the leading causes of death worldwide. Every year, over 1.24 million people are killed in traffic accidents. Even though automobiles are designed to help people, they have been used to kill them in large numbers. Automobile accident research has primarily focused on past tragedies to develop and implement policies to combat this pandemic. The aim of this systematic review is to assess the different methods used to investigate the vehicle system-related cause factors of road traffic accidents. Police report reports have served as a foundation for providing historical facts about the causes of automobile accidents. It has been observed that police reports have limitations when it comes to reporting the involvement of vehicle systems in causing a traffic accident. The majority of the research was conducted on articles that investigated vehicle system risk factors using statistical data. Following articles that used statistical data to investigate vehicle system risk factors, the inclusion criteria were chosen. Articles on traffic accidents published in Cameroon were included on the condition that they studied at least one traffic accident risk factor. Two hundred twenty-five distinct records were identified, and 155 full texts were screened for inclusion, resulting in the inclusion of 25 studies in the review. According to the findings, failure to break the braking system, tyre puncture, poor driving, speeding, and overtaking are the leading causes of automobile crash reports reported by police. The majority of the study’s conclusions lamented that accusing vehicle systems was based on assumptions and the reporter’s judgment. It was determined that the use of stringent vetting procedures to investigate vehicle systems is the cause of a traffic accident. As a result, stakeholders will require accurate facts from a traffic crash investigation.

Exploring the associations between driving volatility and autonomous vehicle hazardous scenarios: Insights from field operational test data

With the promising development and deployment trends of autonomous vehicles (AVs), AVs’ operation safety has become a key issue worldwide. Studies have been conducted to reveal the risk factors of AV operation safety based upon AV-involved crash reports. However, the crash data sample size was limited and the crash reports only recorded static information, thus it failed to identify crash contributing factors and further provide feedbacks to AV algorithm development. In this study, the risk factors were investigated based upon hazardous scenarios, which were claimed to possess consistent causal mechanisms with crash events. First, contributing factors were extracted from both vehicle kinematics and traffic environment aspects, and their volatility features were obtained. Then, path analysis models were developed to reveal the concurrent relationships between scenario volatility and hazardous scenario occurrence probability. Besides, to understand the varying risk factors for hazardous scenarios caused by human drivers and AVs, a logit regression model was further established. The modeling results showed that large volatility of space headway held direct impacts on increasing the AV driving risks. And the volatility of the drivable road area had no significant impacts on AV driving risks while it indirectly influenced human driving risks. Finally, result implications for AV driving behavior improvements have been discussed.

Oil Fumes, Flight Safety, and the NTSB

During its investigations into a series of ten aircraft crashes from 1979 to 1981, US National Transportation Safety Board (NTSB) officials were presented with a hypothesis that “several” of the crashes could have been caused by pilot impairment from breathing oil fumes inflight. The NTSB and their industry partners ultimately dismissed the hypothesis. The authors reviewed the crash reports, the mechanics of the relevant engine oil seals, and some engine bleed air data to consider whether the dismissal was justified. Four of the nine aircraft crash reports include details which are consistent with pilot impairment caused by breathing oil fumes. None of the tests of ground-based bleed air measurements of a subset of oil-based contaminants generated in the engine type on the crashed aircraft reproduced the inflight conditions that the accident investigators had flagged as potentially unsafe. The NTSB’s conclusion that the hypothesis of pilot incapacitation was “completely without validity” was inconsistent with the evidence. Parties with a commercial conflict of interest should not have played a role in the investigation of their products. There is enough evidence that pilots can be impaired by inhaling oil fumes to motivate more stringent design, operation, and reporting regulations to protect safety of flight.

Association of human mobility with road crashes for pandemic-ready safer mobility: A New York City case study

BackgroundThe COVID-19 pandemic has reshaped our cities in many ways. The number of motor vehicles on the road has plummeted during lockdowns, and an increasing number of people are turning to walking and biking. From a road safety perspective, the overall question is what effects the human behavior shift brings on the crash occurrence and, more importantly, how to support decision-makers on safer mobility policies? MethodBased on anonymous mobile phone location and crash report data in New York City, this study attempts to provide some new insights by using survival analysis (the hazard function approach) to explore the effects of human mobility changes due to the pandemic on crashes that involve injuries and fatalities (of pedestrian, cyclist or motorist). Results(1) the increased percentage of people staying at home improves pedestrian and cyclist safety, which adds evidence for making walking and cycling more appealing; (2) the increased percentage of people staying at home raises the likelihood of injuries for motor vehicle drivers, suggesting that it will be critical to monitor the driving behavior and establish new speed limits during the future pandemic waves and in the post-pandemic era as well; (3) non-work trips (e.g., shopping, recreation, personal business, etc.) are positively associated with crash injuries for motor vehicle drivers as well as pedestrian and cyclist; (4) human mobility factors were found not related to crash fatalities; (5) control NPIs implemented increased the motor vehicle drivers’ crash risk.

Investigating the Effect of Social and Cultural Factors on Drivers in Malaysia: A Naturalistic Driving Study.

Road accidents are increasing every year in Malaysia, and it is always challenging to collect reliable pre-crash data in the transportation community. Existing studies relied on simulators, police crash reports, questionnaires, and surveys to study Malaysia’s drivers’ behavior. Researchers previously criticized such methods for being biased and unreliable. To fill in the literature gap, this study presents the first naturalistic driving study in Malaysia. Thirty drivers were recruited to drive an instrumented vehicle for 750 km while collecting continuous driving data. The data acquisition system consists of various sensors such as OBDII, lidar, ultrasonic sensors, IMU, and GPS. Irrelevant data were filtered, and experts helped identify safety criteria regarding multiple driving metrics such as maximum acceptable speed limits, safe accelerations, safe decelerations, acceptable distances to vehicles ahead, and safe steering behavior. These thresholds were used to investigate the influence of social and cultural factors on driving in Malaysia. The findings show statistically significant differences between drivers based on gender, age, and cultural background. There are also significant differences in the results for those who drove on weekends rather than weekdays. The study presents several recommendations to various public and governmental sectors to help prevent future accidents and improve traffic safety.

Two-vehicle driver-injury severity: A multivariate random parameters logit approach

Two-vehicle crashes have been dominating all types of traffic accidents, wherein the vehicle drivers have been sustaining the highest risk of injury among all vehicle occupants. To understand the critical factors to the drivers’ injury severity of two-vehicle crashes, we employed the random parameters multinomial logit model as a data analyzing tool. To capture the unobserved heterogeneity and potential temporal instability, we combined two strategies: Bayesian random parameter logit and explicitly correlated outcomes. The random parameter logit models were validated with a nine-year large-scale dataset compiled by combining the Crash Report Sampling System (CRSS) and General Estimates Sampling (GES) databases. The results underscore the importance of explicit modeling of inter-outcome correlation, which captured the potential transition probability between adjacent levels of injury severity and improved the model’s predictability. Our model also highlighted substantial per-case and per-driver heterogeneity, which respectively explained 22.8% and 29.4% of the total variance (minor injury) and 25.4% and 24.9% of the variance (severe injury). We found that the female drivers, old (⩾65 years) drivers, unbuckled drivers, speeding drivers sustained a higher injury risk in their corresponding groups. Drivers in lighter and older vehicles suffer higher injury risks. Several other factors also considerably affect the injury severity outcomes, such as the road’s speed limit and variables that are proxies of traffic volume (intersection type, whether at the peak hours). Regarding Bayesian modeling, we observed that using weakly informative prior distribution has little effect on the parameter estimates. We also pointed to the directions to further improve the proposed modeling framework.

Pattern recognition from light delivery vehicle crash characteristics

In the era of food delivery and grocery delivery startups, traffic crashes associated with light delivery vehicles have increased significantly. Since the number of these crashes is increasing, it is important to investigate light vehicle crashes to gain insights into potential contributing factors. This study collected seven years (2010-2016) of data from traffic crash narrative reports and structured traffic crash data from Louisiana. Using text search options and manual exploration, a database of 1,623 light delivery-related crashes was examined with a comparatively robust clustering method known as cluster correspondence analysis. The findings identified six clusters with specific traits. The key clusters are fatigue, alcohol impairment, young drivers on low to moderate speed roadways, open country and moderate speed state/U.S. highways, and interstate-related crashes due to inattention. Policymakers can use the findings of the current study to perform data-driven policy development and promote safety for delivery-related travels.

Identifying Patterns of Key Factors in Sun Glare-Related Traffic Crashes

Sun glare is one of the major environmental issues contributing to traffic crashes. Every year, many traffic crashes in the United States are attributed to sun glare. However, quantitative analysis of the influence of sun glare on traffic crashes has not been widely undertaken. This study used traffic crash narrative data for 7 years (2010–2016) from Louisiana to identify crash reports that provided evidence of drivers indicating sun glare as the primary contributing factor of the crashes. Additional geometry and traffic information was collected to identify the list of key crash-contributing factors. This study used cluster correspondence analysis to perform the data analysis. After performing several iterations, six clusters were identified that provided additional insight in relation to sun glare-related crashes. The six clusters are associated with mixed (business and residential) localities, intersection-related crashes on U.S. roadways, single-vehicle crashes on residential two-lane undivided roadways, curve-related crashes on parish roadways in residential localities, interstate-related crashes in open country localities, and curve-related crashes in open country localities. The findings of the current study can add insights to the ongoing safety analysis on sun glare-related crashes.

Classifying features of freeway crashes using machine learning

The identification and control of features influencing traffic crashes have become a concern in safety and human factor engineering. The decision tree algorithm can play an effective role in the identification of these features by discovering hidden patterns in traffic crash data. The present study was conducted to identify the most important features influencing the prediction of the types of crashes on a freeway in Iran using the decision tree algorithm. Reports were collected on 2039 traffic crashes on the freeway during 2015–2017. Each crash report form included 35 features, each of which had more sub-features. To optimize the features, the participle swarm optimization (PSO) approach was adopted. The remaining features from the optimization process were analyzed based on the decision tree algorithm in MATLAB. Applying PSO, 13 features were introduced to the decision tree algorithm. Based on the calculations of the algorithm, a decision tree model was constructed. The model demonstrated that seven features generated the highest separation for determining crash types on the freeway, including the complete cause of the crash, road surface conditions, the geometry of the crash location, weather conditions, time of the crash, the human component, and helmet/safety belt. The overall prediction accuracy of the model was found to be 72.21%. The prediction accuracy of the model was also separately calculated for different types of crashes. The prediction accuracy results were 93.62%, 64.20%, and 65.47% for fatal, injury, and damage crashes, respectively. This study can be regarded as the intersection of crash data, data mining, safety sciences. The results can be used to develop strategies and control/supervision plans in order to reduce crash and injury rates.

Crash Prediction Models for Horizontal Curve Segments on Two-Lane Rural Roads in Thailand

The number of road crashes continues to rise significantly in Thailand. Curve segments on two-lane rural roads are among the most hazardous locations which lead to road crashes and tremendous economic losses; therefore, a detailed examination of its risk is required. This study aims to develop crash prediction models using Safety Performance Functions (SPFs) as a tool to identify the relationship among road alignment, road geometric and traffic conditions, and crash frequency for two-lane rural horizontal curve segments. Relevant data associated with 86,599 curve segments on two-lane rural road networks in Thailand were collected including road alignment data from a GPS vehicle tracking technology, road attribute data from rural road asset databases, and historical crash data from crash reports. Safety Performance Functions (SPFs) for horizontal curve segments were developed, using Poisson regression, negative binomial regression, and calibrated Highway Safety Manual models. The results showed that the most significant parameter affecting crash frequency is lane width, followed by curve length, traffic volume, curve radius, and types of curves (i.e., circular curves, compound curves, reverse curves, and broken-back curves). Comparing among crash prediction models developed, the calibrated Highway Safety Manual SPF outperforms the others in prediction accuracy.