- http://www.uwyo.edu/ahmed/
Room 3082, Engineering Building
Civil and Architectural Engineering
College of Engineering and Applied Science
University of Wyoming
Dept. 3295, 1000 E. University Avenue,
Laramie, Wyoming 82071, USA - +1 307 766 5550
Mohamed Ahmed
University of Wyoming, Civil Engineering, Faculty Member
- Intelligent Transportation Systems, Traffic Safety, Statistical and Econometrics Applications in Transportation Engineering, Advanced Traffic Management, ADVANCED TRAVELER INFORMATION SYSTEM (ATIS), Data Mining, and 12 moreApplied Statistics, Accidents, Risk Management of Freeway, Automatic Vehicle Identification, Expressway Safety, Real-Time Traffic Safety, Real-Time Crash Prediction, Mountainous Freeway Safety, Loop Detectors, Real-Time Proactive Traffic Management, Visibility Related Crashes, and Incident predictionedit
- Dr. Mohamed M. Ahmed, P.E. is an Associate Professor in the Department of Civil and Architectural Engineering at the ... moreDr. Mohamed M. Ahmed, P.E. is an Associate Professor in the Department of Civil and Architectural Engineering at the University of Wyoming (UW). He received the B.sc in Civil Engineering from Al-Azhar University, Cairo, Egypt and the M.Sc. and Ph.D. degrees in Transportation Engineering from the University of Central Florida (UCF). Prior to joining UW, Dr. Ahmed was the Director of Traffic Safety Program at the Center for Advanced Transportation Systems Simulation at UCF.
Dr. Ahmed has over 17 years of experience in the field of transportation engineering with a focus on traffic safety. His research interests include traffic safety analysis, Intelligent Transportation Systems, and statistical and data mining applications in transportation engineering. He has conducted various research projects and provided technical assistance to a number of clients including the Florida Department of Transportation, the Colorado Department of Transportation, the Orlando-Orange County Expressway Authority, and the Wyoming Department of Transportation.
He has authored and co-authored several high profile scientific articles in different peer-reviewed journals, including Accident Analysis and Prevention, Journal of Transportation Research Record, IEEE Transactions on Intelligent Transportation Systems, Transportation Safety and Security, and Transportation Research Part-C.
He has received the Young Researcher Award for best paper from the Transportation Research Board (Safety Data, Analysis and Evaluation Committee (ANB20)) in 2012. He received the Graduate Teaching Assistant Award from the Department of Civil, Environmental and Construction Engineering at UCF in 2010 and the Award for Excellence in Graduate Student Teaching from the College of Engineering and Computer Science - University of Central Florida in 2011.edit
This paper examined the interaction between roadway geometric characteristics and adverse weather conditions and their impact on crash occurrence on rural variable speed limit freeway corridors through mountainous terrain. As a... more
This paper examined the interaction between roadway geometric characteristics and adverse weather conditions and their impact on crash occurrence on rural variable speed limit freeway corridors through mountainous terrain. As a quantitative measure of the effect of geomet-rics in adverse weather conditions, a crash frequency safety performance function that used generalized linear regression was developed with explanatory variables including snow, ice, frost, wind, horizontal curvature , and steep grades. This research concluded that the inter action between grades and horizontal curves with weather variables had a significant impact on crash occurrence. The research suggested that distinct variable speed limit strategies should be implemented on segments with challenging roadway geometry.
Research Interests:
The effect of reduction of visibility on crash occurrence has recently been a major concern. Although visibility detection systems can help to mitigate the increased hazard of limited-visibility, such systems are not widely implemented... more
The effect of reduction of visibility on crash occurrence has recently been a major concern. Although visibility detection systems can help to mitigate the increased hazard of limited-visibility, such systems are not widely implemented and many locations with no systems are experiencing considerable number of fatal crashes due to reduction in visibility caused by fog and inclement weather. On the other hand, airports’ weather stations continuously monitor all climate parameters in real-time, and the gathered data may be utilized to mitigate the increased risk for the adjacent roadways. This study aims to examine the viability of using airport weather information in real-time road crash risk assessment in locations with recurrent fog problems. Bayesian logistic regression was utilized to link six years (2005-2010) of historical crash data to real-time weather information collected from 8 airports in the State of Florida, roadway characteristics and aggregate traffic parameters. The results from this research indicate that real-time weather data collected from adjacent airports are good predictors to assess increased risk on highways.
Research Interests:
Red Light cameras may have a demonstrable impact on reducing the frequency of red light running violations; however, their effect on the overall safety at intersections is still up for debate. This paper examined the safety impacts of Red... more
Red Light cameras may have a demonstrable impact on reducing the frequency of red light running violations; however, their effect on the overall safety at intersections is still up for debate. This paper examined the safety impacts of Red Light Cameras (RLCs) on traffic crashes at signalized intersections using the Empirical Bayes (EB) method. Data were obtained from the Florida Department of Transportation for twenty-five RLC equipped intersections in Orange County, Florida. Additional fifty intersections that remained with no photo enforcement in the vicinity of the treated sites were collected to examine the spillover effects on the same corridors. The safety evaluation was performed at three main levels; only target approaches where RLCs were installed, all approaches on RLC intersections, and non-RLC intersections located on the same travel corridors as the camera equipped intersections. Moreover, the spatial spillover effects of RLCs were also examined on an aggregate level to evaluate the safety impacts on driver behavior at a regional scale. The results from this study indicated that there was a consistent significant reduction in angle and left-turn crashes and a significant increase in rear-end crashes on target approaches, in addition, the magnitude and the direction of these effects, to a lesser degree, were found similar on the whole intersection. Similar trends in shift of crash types were spilled-over to non-RLC intersections in the proximity of the treated sites. On an aggregate county level, there was a moderate spillover benefits with a notable crash migration to the boundary of the county.
Research Interests:
Traditional mainline toll plazas on expressways may have both safety and operational challenges. While many studies demonstrated the operational and environmental impacts of the conversion from traditional toll plazas to a... more
Traditional mainline toll plazas on expressways may have both safety and operational challenges. While many studies demonstrated the operational and environmental impacts of the
conversion from traditional toll plazas to a barrier-free system (Open Road Tolling), there is a lack of research that quantifies the safety benefits of new tolling systems. This study evaluated the safety effectiveness of the conversion from traditional mainline toll plaza design to Hybrid Toll Plazas (HTP) system. Hybrid toll plazas combine both an Open Road Tolling (ORT) on the mainline and separate traditional toll collection to the side. Various observational before-after studies were applied on ninety-eight main toll plazas (two directions) located on approximately 750 miles of toll roads in the State of Florida; thirty of them were upgraded to HTPs. The results indicated that the conversion from traditional toll plaza design to HTP system resulted in a crash reduction of 47 percent, 46 percent and 54 percent for total crashes, fatal–and-injury crashes and property damage only crashes, respectively. The use of HTP design also significantly reduced rear end crashes and lane change related crashes by 65 percent and 55 percent, respectively. Overall, the use of hybrid toll plaza design was proven to be an excellent solution to several traffic operations, environmental and economic problems including capacity, delays and reducing emissions. The results of this study proved that the safety effectiveness across all locations that were upgraded to HTP was significantly improved."
conversion from traditional toll plazas to a barrier-free system (Open Road Tolling), there is a lack of research that quantifies the safety benefits of new tolling systems. This study evaluated the safety effectiveness of the conversion from traditional mainline toll plaza design to Hybrid Toll Plazas (HTP) system. Hybrid toll plazas combine both an Open Road Tolling (ORT) on the mainline and separate traditional toll collection to the side. Various observational before-after studies were applied on ninety-eight main toll plazas (two directions) located on approximately 750 miles of toll roads in the State of Florida; thirty of them were upgraded to HTPs. The results indicated that the conversion from traditional toll plaza design to HTP system resulted in a crash reduction of 47 percent, 46 percent and 54 percent for total crashes, fatal–and-injury crashes and property damage only crashes, respectively. The use of HTP design also significantly reduced rear end crashes and lane change related crashes by 65 percent and 55 percent, respectively. Overall, the use of hybrid toll plaza design was proven to be an excellent solution to several traffic operations, environmental and economic problems including capacity, delays and reducing emissions. The results of this study proved that the safety effectiveness across all locations that were upgraded to HTP was significantly improved."
Research Interests:
This paper investigates the effects of microscopic traffic, weather, and roadway geometric factors on the occurrence of specific crash types for a freeway. The I-70 Freeway was chosen for this paper since automatic vehicle identification... more
This paper investigates the effects of microscopic traffic, weather, and roadway geometric factors on the occurrence of specific crash types for a freeway. The I-70 Freeway was chosen for this paper since automatic vehicle identification (AVI) and weather detection systems are implemented along this corridor. A main objective of this paper is to expand the purpose of the existing intelligent transportation system to incorporate traffic safety improvement and suggest active traffic management (ATM) strategies by identifying the real-time crash patterns. Crashes have been categorized as rear-end, sideswipe, and single-vehicle crashes. AVI segment average speed, real-time weather data, and roadway geometric characteristic data were utilized as explanatory variables in this paper. First, binary logistic regression models were estimated to compare single- with multivehicle crashes and sideswipe with rear-end crashes. Then, a hierarchical logistic regression model that simultaneously fits two conditional logistic regression models for the three crash types has been developed. Results from the models indicate that single-vehicle crashes are more likely to occur in snowy seasons, at moderate slopes, three-lane segments, and under free-flow conditions, whereas the sideswipe crash occurrence differs from rear-end crashes with the visibility situation, segment number of lanes, grades, and their directions (up or down). Furthermore, the innovative way of estimating two conditional logistic regression models simultaneously in the Bayesian framework fits the correlated data structure well. Conclusions from this paper imply that different ATM strategies should be designed for three- and two-lane roadway sections and are also considering the seasonal effects.
This study proposes a new and promising machine learning technique to enhance the reliability of real-time risk assessment on freeways. Stochastic gradient boosting (SGB) is used to identify hazardous conditions on the basis of traffic... more
This study proposes a new and promising machine learning technique to enhance the reliability of real-time risk assessment on freeways. Stochastic gradient boosting (SGB) is used to identify hazardous conditions on the basis of traffic data collected from multiple detection systems such as automatic vehicle identification (AVI), remote traffic microwave sensors (RTMS), real-time weather stations, and roadway geometry. SGB’s key strengths lie in its capability to fit complex nonlinear relationships; it handles different types of predictors and accommodates missing values with no need for prior transformation of the predictor variables or elimination of outliers, as with real-time applications. Boosting multiple simple trees together overcomes the poor prediction accuracy of singletree models and provides fast and superior predictive performance. Three models are calibrated: a full model that augments all available data and another two models to compare explicitly the prediction performance of traffic data collected from different sources (AVI and RTMS) at the same location. The results from the preliminary analysis as well as the
calibrated models indicate that crash prediction by AVI is comparable to that by RTMS data. Moreover, the full model achieves superior classification accuracy by identifying about 89% of crash cases in the validation data set with only a 6.5% false positive rate. Because of its superior classification performance and its minimal required data preparation, SGB is recommended as a promising technique for real-time risk assessment.
calibrated models indicate that crash prediction by AVI is comparable to that by RTMS data. Moreover, the full model achieves superior classification accuracy by identifying about 89% of crash cases in the validation data set with only a 6.5% false positive rate. Because of its superior classification performance and its minimal required data preparation, SGB is recommended as a promising technique for real-time risk assessment.
The increased deployment of non-intrusive detection systems such as Automatic Vehicle Identification (AVI) and Remote Traffic Microwave Sensors (RTMSs) provides access to real-time traffic data from multiple sources. The availability of... more
The increased deployment of non-intrusive detection systems such as Automatic Vehicle Identification (AVI) and Remote Traffic Microwave Sensors (RTMSs) provides access to real-time traffic data from multiple sources. The availability of such rich data enhances the reliability of travel time estimation and route guidance systems, however, utilization of these data is absent in the context of proactive safety management systems. This paper presents a framework for real-time risk assessment on a freeway in Colorado by fusing data from two different detection systems (AVI and RTMS), real-time weather and roadway geometry. Stochastic Gradient Boosting (SGB), a relatively recent and promising machine learning technique is used to calibrate the models. SGB’s key strengths lie in its capability to fit complex nonlinear relationships, handling different types of predictors (nominal and categorical) and accommodating missing values with no need for prior transformation of the predictor variables or elimination of outliers. Boosting multiple simple trees together overcomes the drawback of single tree models of poor prediction accuracy and provides fast and superior predictive performance. The proposed framework is considered a good alternative for real-time risk assessment on freeways because of its high estimation accuracy, robustness and reliability.
Visibility is a critical component to the task of driving on all types of roads. The visibility detection and warning systems provide real-time, automated detection as well as appropriate responses to counteract... more
Visibility is a critical component to the task of driving on all types of roads. The visibility detection and warning systems provide real-time, automated detection as well as appropriate responses to counteract reduced visibility conditions due to fog, heavy rain, snow, smoke, dust or haze by informing drivers of present conditions and lowering the speed limits to match the reduced visibility condition. The objective of this research is to provide a synthesis of visibility detection systems and traffic control techniques that are developed and/or implemented in the US and around the world. This paper provides an overview of the best practices of fixed visibility systems at areas of recurrent dense fog and mobile systems for seasonal visibility reduction for areas of predicted seasonal fog or smoke from wildfires. Ongoing research efforts of developing new camera-based visibility detection systems are also discussed.
Research Interests:
Although numerous studies have attempted the use of data from inductive-loop and radar detectors in real-time crash prediction, there is a lack of safety analyses that have investigated the use of traffic data from an increasingly... more
Although numerous studies have attempted the use of data from inductive-loop and radar detectors in real-time crash prediction, there is a lack of safety analyses that have investigated the use of traffic data from an increasingly prevalent non-intrusive surveillance system; the tag readers on toll roads known as Automatic Vehicle Identification (AVI) Systems.
In particular in this paper, we tackle three main issues 1) explicitly comparing between the prediction performance of a single generic model for all crashes and a specific model for rear-end crashes using AVI data, 2) applying Bayesian updating approach to generate full probability distributions for the coefficients and 3) examining the estimation efficiency of the Semi-parametric Bayesian modeling over the frequentist matched-case control logistic regression.
By contrasting AVI data preceding all crashes and rear-end crashes with matched non-crash data, it was found that rear-end crashes can be identified with a 72% accuracy while the generic all crash model achieved accuracy of only 69% using different validation datasets, moreover, using the Bayesian updating approach increased the accuracy of both models by 3.5%.
In particular in this paper, we tackle three main issues 1) explicitly comparing between the prediction performance of a single generic model for all crashes and a specific model for rear-end crashes using AVI data, 2) applying Bayesian updating approach to generate full probability distributions for the coefficients and 3) examining the estimation efficiency of the Semi-parametric Bayesian modeling over the frequentist matched-case control logistic regression.
By contrasting AVI data preceding all crashes and rear-end crashes with matched non-crash data, it was found that rear-end crashes can be identified with a 72% accuracy while the generic all crash model achieved accuracy of only 69% using different validation datasets, moreover, using the Bayesian updating approach increased the accuracy of both models by 3.5%.
Research Interests:
Real-time crash prediction research attempted the use of data from inductive loop detectors, however, no safety analysis has been carried out using traffic data from one of the most growing non-intrusive surveillance systems; the tag... more
Real-time crash prediction research attempted the use of data from inductive loop detectors, however, no safety analysis has been carried out using traffic data from one of the most growing non-intrusive surveillance systems; the tag readers on toll roads known as Automated Vehicle Identification (AVI) Systems. In this study, for the first time, the identification of freeway locations with high crash potential has been examined using real-time speed data collected from AVI. Travel time and space mean speed data, collected by AVIs and crash data of a total of 78-miles on the expressway network in Orlando in 2008 were collected. Utilizing a random forest technique for significant variable selection and stratified matched case-control to account for the confounding effects of the location, time and season, the log odds of crash occurrence were calculated.
The length of the AVI segment was found to be a crucial factor that affects the usefulness of the AVI traffic data. While the results showed that the likelihood of a crash is statistically related to speed data obtained from AVI segments within average length of 1.5-mile and crashes can be classified with about 70% accuracy, all speed parameters obtained from AVIs spaced at 3-miles or more apart were found to be statistically insignificant to identify crash prone conditions. The findings of this study illustrate a promising real-time safety application for one of the most widely used and already present ITS systems, with many possible advances in the context of Advanced Traffic Management.
The length of the AVI segment was found to be a crucial factor that affects the usefulness of the AVI traffic data. While the results showed that the likelihood of a crash is statistically related to speed data obtained from AVI segments within average length of 1.5-mile and crashes can be classified with about 70% accuracy, all speed parameters obtained from AVIs spaced at 3-miles or more apart were found to be statistically insignificant to identify crash prone conditions. The findings of this study illustrate a promising real-time safety application for one of the most widely used and already present ITS systems, with many possible advances in the context of Advanced Traffic Management.
Research Interests:
This study investigates the effect of the interaction between roadway geometric features, and real-time weather and traffic data on the occurrence of crashes on a mountainous freeway. The Bayesian logistic regression technique was used to... more
This study investigates the effect of the interaction between roadway geometric features, and real-time weather and traffic data on the occurrence of crashes on a mountainous freeway. The Bayesian logistic regression technique was used to link a total of 301 crash occurrences on I-70 in Colorado with the real-time space mean speed collected from the Automatic Vehicle Identification (AVI) system, real-time weather and roadway geometry data. The results suggest that the inclusion of roadway geometrics and real-time weather with AVI data in the context of active traffic management systems is essential, in particular with roadway sections characterized by mountainous terrain and adverse weather. The modeling results showed that the geometric factors are significant in the dry and the snow seasons and the crash likelihood could double during the snow season because of the interaction between the pavement condition and steep grades. The 6-minute average speed at the crash segment during 6-12 minutes prior to the crash time and the 1-hour visibility before the crash time were found to be significant in the dry season while the logarithms of the coefficient of variation in speed at the crash segment during 6-12 minutes prior to the time of the crash, 1-hour visibility as well as the 10-minute precipitation prior to the time of the crash were found to be significant in the snow season. The results from the two models suggest that different active traffic management strategies should be in place during these two distinctive seasons.
Research Interests:
While the most common application of the Automatic Vehicle Identification is electronic toll collection and travel time estimation, there is a promising traffic safety application in the context of Advanced Travel Management. This paper... more
While the most common application of the Automatic Vehicle Identification is electronic toll collection and travel time estimation, there is a promising traffic safety application in the context of Advanced Travel Management. This paper examines the usefulness of traffic data collected from Automatic Vehicle Identification systems and weather data in real-time crash analysis. Matched case-control was used to link real-time space mean speed collected by AVI and real-time weather data and crash likelihood. The 10-minute average speed five minutes before the crash occurrence and the 1-hour visibility both before the crash time were found to be the most significant factors that affect the crash likelihood.
Research Interests:
Freeway crash occurrences are highly influenced by geometric characteristics, traffic status, weather conditions and drivers' behavior. For a mountainous freeway which suffers from adverse weather conditions, it is critical to incorporate... more
Freeway crash occurrences are highly influenced by geometric characteristics, traffic status, weather conditions and drivers' behavior. For a mountainous freeway which suffers from adverse weather conditions, it is critical to incorporate real-time weather information and traffic data in the crash frequency study. In this paper, a Bayesian inference method was employed to model one year's crash data on I-70 in the state of Colorado. Real-time weather and traffic variables, along with geometric characteristics variables were evaluated in the models. Two scenarios were considered in this study, one seasonal and one crash type based case. For the methodology part, the Poisson model and two random effect models with a Bayesian inference method were employed and compared in this study. Deviance Information Criterion (DIC) was utilized as a comparison factor. The correlated random effect models outperformed the others. The results indicate that the weather condition variables, especially precipitation, play a key role in the crash occurrence models. The conclusions imply that different active traffic management strategies should be designed based on seasons, and single-vehicle crashes have different crash mechanism compared to multi-vehicle crashes.
Research Interests:
More researchers started using real-time traffic surveillance data, collected from loop/radar detectors (LDs), for proactive crash risk assessment. However, there is a lack of prior studies that investigated the link between real-time... more
More researchers started using real-time traffic surveillance data, collected from loop/radar detectors (LDs), for proactive crash risk assessment. However, there is a lack of prior studies that investigated the link between real-time traffic data and crash risk of reduced visibility related (VR) crashes. Two issues that have not explicitly been addressed in prior studies are; (1) the possibility of predicting VR crashes using traffic data collected from the Automatic Vehicle Identification (AVI) sensors installed on Expressways and (2) which traffic data are advantageous for predicting VR crashes; LDs or AVIs. Thus, this study attempts to examine the relationships between VR crash risk and real-time traffic data collected from LDs installed on two Freeways in Central Florida (I-4 and I-95) and from AVI sensors installed on two Expressways (SR 408 and SR 417). Also, it investigates which data are better for predicting VR crashes. The approach adopted here involves developing Bayesian matched case control logistic regression models using the historical crashes, LDs and AVI data. Regarding the model estimated based on LDs data, the average speed observed at the nearest downstream station along with the coefficient of variation in speed observed at the nearest upstream station, all at 5–10 min prior to the crash time, were found to have significant effect on VR crash risk. However, for the model developed based on AVI data, the coefficient of variation in speed observed at the crash segment, at 5–10 min prior to the crash time, affected the likelihood of VR crash occurrence. The results showed that both LDs and AVI systems can be used for safety application (i.e., predicting VR crashes). It was found that
up to 73% of VR crashes could be identified correctly. Argument concerning which traffic data (LDs or AVI) are better for predicting VR crashes is also provided and discussed.
up to 73% of VR crashes could be identified correctly. Argument concerning which traffic data (LDs or AVI) are better for predicting VR crashes is also provided and discussed.
Research Interests:
More researchers started using real-time traffic surveillance data, collected from loop/radar detectors (LDs), for proactive crash risk assessment. However, there is a lack of prior studies that investigated the links between real-time... more
More researchers started using real-time traffic surveillance data, collected from loop/radar detectors (LDs), for proactive crash risk assessment. However, there is a lack of prior studies that investigated the links between real-time traffic data and crash risk of reduced visibility related (VR) crashes. Two issues that have not explicitly been addressed in prior studies are; (1) the possibility of predicting VR crashes using traffic data collected from the Automatic Vehicle Identification (AVI) sensors installed on Expressways and (2) which traffic data is advantageous for predicting VR crashes; LDs or AVIs. Thus, this study attempts to examine the relationships between VR crash risk and real-time traffic data collected from LDs installed on two Freeways in Central Florida (I-4 and I-95) and from AVI sensors installed on two Expressways (SR 408 and SR 417). Also, it investigates which data is better for predicting VR crashes. The approach adopted here involves developing Bayesian matched case-control logistic regression using the historical crashes, LDs and AVI data. Regarding models estimated based on LDs data, the average speed observed at the nearest downstream station along with the coefficient of variation in speed observed at the nearest upstream station, all at 5-10 minute prior to the crash time, were found to have significant effect on VR crash risk. However, for the model developed based on AVI data, the coefficient of variation in speed observed at the crash segment, at 5-10 minute prior to the crash time, affected the likelihood of VR crash occurrence. Argument concerning which traffic data (LDs or AVI) is better for predicting VR crashes is also provided and discussed.
Research Interests:
While rural freeways generally have lower crash rates, interactions between driver behavior, traffic and geometric characteristics, and adverse weather conditions may increase the crash risk along some freeway sections. This paper... more
While rural freeways generally have lower crash rates, interactions between driver behavior, traffic and geometric characteristics, and adverse weather conditions may increase the crash risk along some freeway sections. This paper examines the safety effects of roadway geometrics on crash occurrence along a freeway section that features mountainous terrain and adverse weather. Starting from preliminary exploration using Poisson models, Bayesian hierarchical models with spatial and random effects were developed to efficiently model the crash frequencies on road segments on the 20-mile freeway section of study. Crash data for 6 years (2000–2005), roadway geometry, traffic characteristics and weather information in addition to the effect of steep slopes and adverse weather of snow and dry seasons, were used in the investigation. Estimation of the model coefficients indicates that roadway geometry is significantly associated with crash risk; segments with steep downgrades were found to drastically increase the crash risk. Moreover, this crash risk could be significantly increased during snow season compared to dry season as a confounding effect between grades and pavement condition. Moreover, sites with higher degree of curvature, wider medians and an increase of the number of lanes appear to be associated with lower crash rate. Finally, a Bayesian ranking technique was implemented to rank the hazard levels of the roadway segments; the results confirmed that segments with steep downgrades are more crash prone along the study section.
Research Interests: Bayesian, Graphical Models, Safety, Traffic Safety, Accidents, and 22 moreObject Perception, Visual System, Multilevel Modeling, SNOW, Freeway, Curve, Slope, Adverse weather, Belief Propagation, Mountainous Freeway Safety, Additive effects of low-level laser therapy with exercise on subacromial syndrome: a randomised, double-blind, controlled trial, DIC, WInbugs, Hierarchical Bayesian, Inclement Weather, Full Bayesian, Multilevel data structure, Random Effect, Fixed Effect, Illusory Contours, Feedback Connections, and Hierarchical Bayesian Inference
Visibility is critical to the task of driving and reduction in visibility due to fog, smoke or other weather events such as heavy rain is a major traffic operation and safety concern. In Florida, these conditions could be a result of... more
Visibility is critical to the task of driving and reduction in visibility due to fog, smoke or other weather events such as heavy rain is a major traffic operation and safety concern. In Florida, these conditions could be a result of sudden dense fog, fires (whether wild or controlled), and heavy pockets of rain or hail. Real time measurement of visibility may help in warning the drivers when the visibility falls below certain acceptable levels. Devices measuring visibility are the key toward that objective. This paper reports on the design of a visibility warning and detection system that detects any reduction in visibility below a certain limit that would be considered hazardous for normal traffic flow conditions. This system can also respond accordingly in real time to convey specific warning messages to drivers in an effective way and report this information to the appropriate Traffic Management Center (TMC). The innovation in this system is that it was developed from components that are inexpensive and available commercially. Also, this system can be employed as portable or fixed system. A fixed system might be useful in areas that tend to have dense fog (for example, rural sections of freeways). However, the portable system can be used every time a wildfire occurs close to a highway. The system components and a preliminary testing for the system’s performance are discussed and presented in this paper.
Research Interests:
Research Interests:
The Colorado DOT is at the forefront of developing an Active Traffic Management (ATM) system that not only considers operation aspects, but also integrates safety measures. In this research, data collected from Automatic Vehicle... more
The Colorado DOT is at the forefront of developing an Active Traffic Management (ATM) system that not only considers operation aspects, but also integrates safety measures. In this research, data collected from Automatic Vehicle Identification (AVI), Remote Traffic Microwave Sensors (RTMS) and Real-Time weather data were utilized to incorporate safety within the ATM system. Preliminary investigation of crashes along 20-miles of I- 70 revealed that the mountainous terrain and adverse weather during the winter season may increase crash likelihood. A traditional automatic incident detection system is a reactive approach to mitigating the effects of crashes without attempting to avoid primary incidents. To reduce the risk of primary incidents, a more proactive approach that identifies locations where a crash is more likely to happen in real-time can be implemented.
The results from the research study suggest that there is a clear demand to incorporate real-time weather conditions and roadway geometric characteristics within the development of the ATM system. Remote Traffic Microwave Sensors, AVI, weather data, and road geometry information were collected and utilized to develop a real-time risk assessment system. Data Mining (DM) techniques were also used to reveal important data relationships and improve prediction accuracy. Based on the data and DM techniques, models were tested and their performances were compared. Results show that the Full Model which incorporates AVI, RTMS data, weather data, and geometric information outperforms other models by identifying about 89% of crash cases in the validation dataset with only
6.5% false positive.
The results from the research study suggest that there is a clear demand to incorporate real-time weather conditions and roadway geometric characteristics within the development of the ATM system. Remote Traffic Microwave Sensors, AVI, weather data, and road geometry information were collected and utilized to develop a real-time risk assessment system. Data Mining (DM) techniques were also used to reveal important data relationships and improve prediction accuracy. Based on the data and DM techniques, models were tested and their performances were compared. Results show that the Full Model which incorporates AVI, RTMS data, weather data, and geometric information outperforms other models by identifying about 89% of crash cases in the validation dataset with only
6.5% false positive.
Research Interests:
The Highway Safety Manual (HSM) Part D provides a comprehensive list of the effects of safety treatments (countermeasures). These effects are quantified by crash modification factors (CMF), which are based on compilation from past studies... more
The Highway Safety Manual (HSM) Part D provides a comprehensive list of the effects of safety treatments (countermeasures). These effects are quantified by crash modification factors (CMF), which are based on compilation from past studies of the effects of various safety treatments. The HSM Part D provides CMFs for treatments applied to roadway segments (e.g., roadside elements, alignment, signs, rumble strips, etc.), intersections (e.g., control), interchanges, special facilities (e.g., highway-rail crossings), and road networks. Thus, an assessment of the applicability of the HSM in Florida is essential. The objectives of this study are (1) to develop CMFs for various treatments in Florida for the same setting (rural/urban), road type, crash type, and severity level, (2) to evaluate the difference between these Florida-specific CMFs and the CMFs in the HSM, and (3) to recommend whether the CMFs in the HSM can be applied to Florida or new Florida-specific CMFs are
needed. Different methods of observational study – before-after (B-A) and cross-sectional (C-S) – were used to calculate CMFs for a total of 17 treatments applied to roadway segments, intersections and special facilities. The CMFs calculated using the before-after with comparison-group (C-G) and empirical Bayesian (EB) methods, only the CMF with lower standard error was selected. The methods of calculating CMFs were determined based on the availability of the data and the methods used in the HSM, if the CMFs were provided in the HSM. It was found that Florida-specific CMFs were generally statistically significant, and safety effects represented by the CMFs were intuitive, similar to the CMFs in the HSM. It was also found that Florida-specific CMFs for the treatments not included in the HSM showed significant positive effects in reducing crash frequencies.
needed. Different methods of observational study – before-after (B-A) and cross-sectional (C-S) – were used to calculate CMFs for a total of 17 treatments applied to roadway segments, intersections and special facilities. The CMFs calculated using the before-after with comparison-group (C-G) and empirical Bayesian (EB) methods, only the CMF with lower standard error was selected. The methods of calculating CMFs were determined based on the availability of the data and the methods used in the HSM, if the CMFs were provided in the HSM. It was found that Florida-specific CMFs were generally statistically significant, and safety effects represented by the CMFs were intuitive, similar to the CMFs in the HSM. It was also found that Florida-specific CMFs for the treatments not included in the HSM showed significant positive effects in reducing crash frequencies.