Developing a Crash Prediction Model for Deer-vehicle Collisions PDF Download

Author: Neil DeZort
Publisher:
ISBN:
Category : Deer populations
Languages : en
Pages : 27

View

Book Description
The information on the locations where deer-vehicle collisions are likely to occur is of great use to transportation safety officials. Knowing the relationship between average daily traffic, deer population density, and deer-vehicle collisions will allow officials to identify the locations of greatest concern so they can implement mitigation techniques with increased success. This study is the first to specifically investigate the joint relationship in an attempt to create a crash prediction model that will estimate the number of deer-vehicle collisions a roadway segment will experience based on the combination of traffic volumes and deer population density. Data were collected from the Montana Department of Transportation and Montana Fish, Wildlife, and Parks and used to develop several models that attempted to identify a relationship. These models were then analyzed using statistical tests to see if the models were statistically significant. The models showed, based on Montana data, that the deer population surrounding a roadway segment does not have a significant effect on the number of deer-vehicle collisions observed when used in a model combined with the average annual daily traffic. These results suggest that perhaps when a deer population stays within a certain range, the crash rate depends solely on the traffic volume observed. Understanding the relationship between average annual daily traffic, deer population, and the number of collisions observed will help transportation safety officials create a driving environment that is safer for the motorists using a road network.

Author:
Publisher:
ISBN:
Category : Traffic accidents
Languages : en
Pages : 91

View

Book Description

Author: National Research Council (U.S.). Transportation Research Board
Publisher:
ISBN:
Category : Traffic accidents
Languages : en
Pages : 148

View

Book Description
Transportation Research Record contains the following papers: Method for identifying factors contributing to driver-injury severity in traffic crashes (Chen, WH and Jovanis, PP); Crash- and injury-outcome multipliers (Kim, K); Guidelines for identification of hazardous highway curves (Persaud, B, Retting, RA and Lyon, C); Tools to identify safety issues for a corridor safety-improvement program (Breyer, JP); Prediction of risk of wet-pavement accidents : fuzzy logic model (Xiao, J, Kulakowski, BT and El-Gindy, M); Analysis of accident-reduction factors on California state highways (Hanley, KE, Gibby, AR and Ferrara, T); Injury effects of rollovers and events sequence in single-vehicle crashes (Krull, KA, Khattack, AJ and Council, FM); Analytical modeling of driver-guidance schemes with flow variability considerations (Kaysi, I and Ail, NH); Evaluating the effectiveness of Norway's speak out! road safety campaign : The logic of causal inference in road safety evaluation studies (Elvik, R); Effect of speed, flow, and geometric characteristics on crash frequency for two-lane highways (Garber, NJ and Ehrhart, AA); Development of a relational accident database management system for Mexican federal roads (Mendoza, A, Uribe, A, Gil, GZ and Mayoral, E); Estimating traffic accident rates while accounting for traffic-volume estimation error : a Gibbs sampling approach (Davis, GA); Accident prediction models with and without trend : application of the generalized estimating equations procedure (Lord, D and Persaud, BN); Examination of methods that adjust observed traffic volumes on a network (Kikuchi, S, Miljkovic, D and van Zuylen, HJ); Day-to-day travel-time trends and travel-time prediction form loop-detector data (Kwon, JK, Coifman, B and Bickel, P); Heuristic vehicle classification using inductive signatures on freeways (Sun, C and Ritchie, SG).

Author: Mirza Ahammad Sharif
Publisher:
ISBN:
Category :
Languages : en
Pages :

View

Book Description
Motor vehicle crashes in the United States continue to be a serious safety concern for state highway agencies, with over 30,000 fatal crashes reported each year. The World Health Organization (WHO) reported in 2016 that vehicle crashes were the eighth leading cause of death globally. Crashes on roadways are rare and random events that occur due to the result of the complex relationship between the driver, vehicle, weather, and roadway. A significant breadth of research has been conducted to predict and understand why crashes occur through spatial and temporal analyses, understanding information about the driver and roadway, and identification of hazardous locations through geographic information system (GIS) applications. Also, previous research studies have investigated the effectiveness of safety devices designed to reduce the number and severity of crashes. Today, data-driven traffic safety studies are becoming an essential aspect of the planning, design, construction, and maintenance of the roadway network. This can only be done with the assistance of state highway agencies collecting and synthesizing historical crash data, roadway geometry data, and environmental data being collected every day at a resolution that will help researchers develop powerful crash prediction tools. The objective of this research study was to predict vehicle crashes in real-time. This exploratory analysis compared three well-known machine learning methods, including logistic regression, random forest, support vector machine. Additionally, another methodology was developed using variables selected from random forest models that were inserted into the support vector machine model. The study review of the literature noted that this study's selected methods were found to be more effective in terms of prediction power. A total of 475 crashes were identified from the selected urban highway network in Kansas City, Kansas. For each of the 475 identified crashes, six no-crash events were collected at the same location. This was necessary so that the predictive models could distinguish a crash-prone traffic operational condition from regular traffic flow conditions. Multiple data sources were fused to create a database including traffic operational data from the KC Scout traffic management center, crash and roadway geometry data from the Kanas Department of Transportation; and weather data from NOAA. Data were downloaded from five separate roadway radar sensors close to the crash location. This enable understanding of the traffic flow along the roadway segment (upstream and downstream) during the crash. Additionally, operational data from each radar sensor were collected in five minutes intervals up to 30 minutes prior to a crash occurring. Although six no-crash events were collected for each crash observation, the ratio of crash and no-crash were then reduced to 1:4 (four non-crash events), and 1:2 (two non-crash events) to investigate possible effects of class imbalance on crash prediction. Also, 60%, 70%, and 80% of the data were selected in training to develop each model. The remaining data were then used for model validation. The data used in training ratios were varied to identify possible effects of training data as it relates to prediction power. Additionally, a second database was developed in which variables were log-transformed to reduce possible skewness in the distribution. Model results showed that the size of the dataset increased the overall accuracy of crash prediction. The dataset with a higher observation count could classify more data accurately. The highest accuracies in all three models were observed using the dataset of a 1:6 ratio (one crash event for six no-crash events). The datasets with1:2 ratio predicted 13% to 18% lower than the 1:6 ratio dataset. However, the sensitivity (true positive prediction) was observed highest for the dataset of a 1:2 ratio. It was found that reducing the response class imbalance; the sensitivity could be increased with the disadvantage of a reduction in overall prediction accuracy. The effects of the split ratio were not significantly different in overall accuracy. However, the sensitivity was found to increase with an increase in training data. The logistic regression model found an average of 30.79% (with a standard deviation of 5.02) accurately. The random forest models predicted an average of 13.36% (with a standard deviation of 9.50) accurately. The support vector machine models predicted an average of 29.35% (with a standard deviation of 7.34) accurately. The hybrid approach of random forest and support vector machine models predicted an average of 29.86% (with a standard deviation of 7.33) accurately. The significant variables found from this study included the variation in speed between the posted speed limit and average roadway traffic speed around the crash location. The variations in speed and vehicle per hour between upstream and downstream traffic of a crash location in the previous five minutes before a crash occurred were found to be significant as well. This study provided an important step in real-time crash prediction and complemented many previous research studies found in the literature review. Although the models investigate were somewhat inconclusive, this study provided an investigation of data, variables, and combinations of variables that have not been investigated previously. Real-time crash prediction is expected to assist with the on-going development of connected and autonomous vehicles as the fleet mix begins to change, and new variables can be collected, and data resolution becomes greater. Real-time crash prediction models will also continue to advance highway safety as metropolitan areas continue to grow, and congestion continues to increase.

Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 210

View

Book Description
Safety reviews of existing roads are becoming a popular practice of many agencies nationally and internationally. Knowing road safety information is of great importance to both policymakers in addressing safety concerns and travelers in managing their trips. There have been various efforts in developing methodologies to measure and assess road safety in an effective manner. However, the existing research and practices are still constrained by their subjective and reactive nature. The goal of this research is to develop a framework of Road Risk Indices (RRIs) to assess road risks of existing highway infrastructure for both road users and agencies based on road geometrics, traffic conditions, and historical crash data. The proposed RRIs are intended to give a comprehensive and objective view of road safety, so that safety problems can be identified at an early stage before they rise in the form of accidents. A methodological framework of formulating RRIs that integrates results from crash prediction models and historical crash data is proposed, and Linear Referencing tools in the ArcGIS software are used to develop digital maps to publish estimated RRIs. These maps provide basic Geographic Information System (GIS) functions, including viewing and querying RRIs, and performing spatial analysis tasks. A semi-parameter count model and quantile regression based estimation are proposed to capture the specific characteristics of crash data and provide more robust and accurate predictions on crash counts. Crash data collected on Interstate Highways in Washington State for the year 2002 was extracted from the Highway Safety Information System (HSIS) and used for the case study. The results from the case study show that the proposed framework is capable of capturing statistical correlations between traffic crashes and influencing factors, leading to the effective integration of safety information in composite indices.

Author: Nancy Dutta
Publisher:
ISBN:
Category : Traffic accidents
Languages : en
Pages : 0

View

Book Description
Crash analysis methods typically use annual average daily traffic as an exposure measure, which can be too aggregate to capture the safety effects of variations in traffic flow and operations that occur throughout the day. Flow characteristics such as variation in speed and level of congestion play a significant role in crash occurrence and are not currently accounted for in the American Association of State Highway and Transportation Officials' Highway Safety Manual. This study developed a methodology for creating crash prediction models using traffic, geometric, and control information that is provided at sub-daily aggregation intervals. Data from 110 rural four-lane segments and 80 urban six-lane segments were used. The volume data used in this study came from detectors that collect data ranging from continuous counts throughout the year to counts from only a couple of weeks every other year (short counts). Speed data were collected from both point sensors and probe data provided by INRIX. The results showed that models that used data aggregated to an average hourly level reflected the variation in volume and speed throughout the day without compromising model quality. Crash predictions for urban segments underwent a 20% improvement in mean absolute deviation for total crashes and a 9% improvement for injury crashes when models using average hourly volume, geometry, and flow variables were compared to the model based on annual average daily traffic. Corresponding improvements over annual average daily traffic models for rural segments were 11% and 9%. Average hourly speed, standard deviation of hourly speed, and differences between speed limit and average speed had statistically significant relationships with crash frequency. For all models, prediction accuracy was improved across all validation measures of effectiveness when the speed components were added. The positive effect of flow variables was true irrespective of the speed data source. Further investigation revealed that the improvement achieved in model prediction by using a more inclusive and bigger dataset was larger than the effect of accounting for spatial/temporal data correlation. For rural hourly models, mean absolute deviation improved by 52% when short counts were added in comparison to the continuous count station only models. The respective value for urban segments was 58%. This means that using short count stations as a data source does not diminish the quality of the developed models. Thus, a combination of different volume data sources with good quality speed data can lessen the dependency on volume data quality without compromising performance. Although accounting for spatial and temporal correlation improved model performance, it provided smaller benefits than inclusion of the short count data in the models. This study showed that it is possible to develop a broadly transferable crash prediction methodology using hourly level volume and flow data that are currently widely available to transportation agencies. These models have a broad spectrum of potential applications that involve assessing safety effects of events and countermeasures that create recurring and non-recurring short-term fluctuations in traffic characteristics.

Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 226

View

Book Description

Author: Thomas Peel
Publisher:
ISBN: 9780438564732
Category : Automobile driving in bad weather
Languages : en
Pages : 121

View

Book Description
Winter weather conditions can cause many difficulties in traffic and transportation safety. The various conditions experienced during the winter weather season, such as blowing and drifting snow, can create numerous issues for roadway users in the State of Wyoming. As a countermeasure, Wyoming has implemented numerous snow fence sections throughout the state. Historically, snow fences have been regarded as a simple, yet effective method to mitigating the various dangers of winter weather conditions for roadway users; however, it has been found that their traffic safety performance has been under investigated. The American Association of State Highway and Transportation Officials (AASHTO) 2010 Highway Safety Manual (HSM) has been considered a major milestone in the advancement of road safety research and analysis. The HSM offers various safety analysis methods, incorporating methodologies and considerations for roadways and facilities of various types. The tools provided in the 2010 HSM allow for the quantification of traffic safety that can be applied for decision making within transportation planning, design, operation, and maintenance. Although the HSM has recently acted as the primary source for the quantitative evaluation of traffic safety, it is not without limitations, as will be discussed and addressed throughout this document. The primary analysis performed in this paper will result in the development of Crash Modification Factors (CMFs) which act as a numerical representation of the safety effectiveness of a particular roadway countermeasure. The development of CMFs will be achieved through three primary methods: a naïve before-after analysis, a before-after analysis using Empirical Bayes (EB) and simple Safety Performance Functions (SPFs), and a before-after analysis using EB and full SPFs. A naïve before-after analysis acts as a simple and clear preliminary analysis in which only crash frequencies are considered and compared to determine the countermeasure safety effectiveness. The before-after analysis using EB and simple SPFs utilizes crash prediction models in which the traffic volumes are applied in order to predict the number of expected crashes for a given roadway segment, which is then compared so that the safety effectiveness can be evaluated. Finally, a before-after analysis using EB and full SPFs is similar in nature to the previously discussed method; however, the full SPFs, or crash prediction models, utilize additional variables, such as roadway geometry characteristics, traffic conditions and characteristics, and environmental conditions to more accurately predict crash frequencies. The results through these analyses will aim to provide information on the safety effectiveness of snow fence implementations within the State of Wyoming by investigating crashes that occur during the winter weather season as well as investigating crashes of various severity levels. Within traffic safety studies, it is common to utilize basic, aggregated weather conditions, such as snowy or rainy days per year, within the crash prediction models to aid in modeling crash frequencies. However, it was determined, due to the naturally high association between snow fence performance and winter weather conditions, that a separate, additional analysis, with regard to (adverse) winter weather conditions would be performed. Following the crash analyses, a model was developed which investigated individual crash events during the winter weather season and detailed winter weather data, which allowed for the development of a real-time crash probability model based on various winter weather conditions in Wyoming. In total, there were 9 individual Safety Performance Functions that were developed, which led to the determination of 18 individual Crash Modification Factors, which allowed for the quantification of the safety effectiveness of Wyoming snow fence implementations.

Author: Srutha Vavilikolanu
Publisher:
ISBN:
Category : Bayesian statistical decision theory
Languages : en
Pages : 122

View

Book Description
"According to Federal Motor Carrier Safety Administration (FMCSA), truck involvement in fatal crashes is more on rural areas than on urban areas. The Fatality Analysis Reporting System (FARS) encyclopedia also indicates that truck involvement in fatal crashes are approximately 12% of the total fatal crashes in the nation and 14 % in The State of Ohio. One area for potential concern is the role of vertical curves on truck crashes. In the design of vertical curves stopping distance, grade and length of the curve are important factors taken into consideration. Vehicle operations on vertical curves are influenced by the grade of the curve, stopping sight distance and vehicle speed. These factors may create operational issues for vehicles traveling on vertical curves and in turn increase the likelihood for crashes. Truck specific studies in the past have focused on geometric roadway factors associated with crashes on vertical curves. Most of the research studies are focused on crest curve truck crashes, and little research has been done on crashes on vertical sag curves. The main research goal of the study is to develop prediction models to evaluate the impact of geometry, traffic volumes and speed on truck-related crashes on two-lane rural vertical curves. The accomplishment of the research goal is achieved by setting five objectives. The first objective is to develop three crash prediction models using negative binomial regression model. These models are 1. Full model - for all vertical curves 2. Reduced model I - for crest curves only and 3. Reduced model II - for sag curves only. The dataset includes 1,935 vertical curve segments with 205 truck crashes from 2002-2006. In second and third objective, Full Bayes approach is used to enhance the results obtained in the Reduced Models I and II. These results are then compared to the initial models. The fourth objective is evaluating the vertical curve variables which are statistically significant with truck-related crashes. These results show that higher grade change for the length of the vertical curve, total width in the range of 24 to 26ft, more number of passenger cars and trucks, increases the truck-related crashes on both crest and sag curves. Low speed limit on crest curves and high speed limit on sag curves increases truck-related crashes which may seem counter intuitive. The fifth objective is to provide suggestions on effective methods to reduce truck related crashes and improve safety. Some potential areas for design improvement may include flattening of steep vertical curves, advisory speed signs and increasing the roadway width on rural vertical curves in Ohio."--Abstract.

Author: Hojr Momeni
Publisher:
ISBN:
Category :
Languages : en
Pages :

View

Book Description
Driver workload increases on horizontal curves due to more complicated navigation compared to navigation on straight roadway sections. Although only a small portion of roadways are horizontal curve sections, approximately 25% of all fatal highway crashes occur at horizontal curve sections. According to the Fatality Analysis Reporting System (FARS) database, fatalities associated with horizontal curves were more than 25% during last years from 2008 to 2014, reinforcing that investigation of horizontal curve crashes and corresponding safety improvements are crucial study topics within the field of transportation safety. Improved safety of horizontal curve sections of rural transportation networks can contribute to reduced crash severities and frequencies. Statistical methods can be utilized to develop crash prediction models in order to estimate crashes at horizontal curves and identify contributing factors to crash occurrences, thereby correlating to the primary objectives of this research project. Primary data analysis for 221 randomly selected horizontal curves on undivided two-lane two-way highways with Poisson regression method revealed that annual average daily traffic (AADT), heavy vehicle percentage, degree of curvature, and difference between posted and advisory speeds affect crash occurrence at horizontal curves. The data, however, were relatively overdispersed, so the negative binomial (NB) regression method was utilized. Results indicated that AADT, heavy vehicle percentage, degree of curvature, and long tangent length significantly affect crash occurrence at horizontal curve sections. A new dataset consisted of geometric and traffic data of 5,334 horizontal curves on the entire state transportation network including undivided and divided highways provided by Kansas Department of Transportation (KDOT) Traffic Safety Section as well as crash data from the Kansas Crash and Analysis Reporting System (KCARS) database were used to analyze the single vehicle (SV) crashes. An R software package was used to write a code and combine required information from aforementioned databases and create the dataset for 5,334 horizontal curves on the entire state transportation network. Eighty percent of crashes including 4,267 horizontal curves were randomly selected for data analysis and remaining 20% horizontal curves (1,067 curves) were used for data validation. Since the results of the Poisson regression model showed overdispersion of crash data and many horizontal curves had zero crashes during the study period from 2010 to 2014, NB, zero-inflated Poisson (ZIP), and zero-inflated negative binomial (ZINB) methods were used for data analysis. Total number of crashes and severe crashes were analyzed with the selected methods. Results of data analysis revealed that AADT, heavy vehicle percentage, curve length, degree of curvature, posted speed, difference between posted and advisory speed, and international roughness index influenced single vehicle crashes at 4,267 randomly selected horizontal curves for data analysis. Also, AADT, degree of curvature, heavy vehicle percentage, posted speed, being a divided roadway, difference between posted and advisory speeds, and shoulder width significantly influenced severe crash occurrence at selected horizontal curves. The goodness-of-fit criteria showed that the ZINB model more accurately predicted crash numbers for all crash groups at the selected horizontal curve sections. A total of 1,067 horizontal curves were used for data validation, and the observed and predicted crashes were compared for all crash groups and data analysis methods. Results of data validation showed that ZINB models for total crashes and severe crashes more accurately predicted crashes at horizontal curves. This study also investigated the effect of speed limit change on horizontal curve crashes on K-5 highway in Leavenworth County, Kansas. A statistical t-test proved that crash data from years 2006 to 2012 showed only significant reduction in equivalent property damage only (EPDO) crash rate for adverse weather condition at 5% significance level due to speed limit reduction in June 2009. However, the changes in vehicles speeds after speed limit change and other information such as changes in surface pavement condition were not available. According to the results of data analysis for 221 selected horizontal curves on undivided two-lane highways, tangent section length significantly influenced total number of crashes. Therefore, providing more information about upcoming changes in horizontal alignment of the roadway via doubling up warning sings, using bigger sings, using materials with higher retroreflectivity, or flashing beacons were recommended for horizontal curves with long tangent section lengths and high number of crashes. Also, presence of rumble strips and wider shoulders significantly and negatively influenced severe SV crashes at horizontal curve sections; therefore, implementing rumble strips and widening shoulders for horizontal curves with high number of severe SV crashes were recommended.