Railroad accident analysis using extreme gradient boosting
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Raj Bridgelall, Denver D. Tolliver (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 19, 2021 Category: Accident Prevention Source Type: research

Decision-adjusted driver risk predictive models using kinematics information
This study demonstrates the value of kinematic driving behavior in crash risk prediction and the necessity for a systematic approach for extracting prediction features. The proposed method can benefit broad applications, including fleet safety management, use-based insurance, driver behavior intervention, as well as connected-vehicle safety technology development.PMID:33866156 | DOI:10.1016/j.aap.2021.106088 (Source: Accident; Analysis and Prevention.)
Source: Accident; Analysis and Prevention. - April 18, 2021 Category: Accident Prevention Authors: Huiying Mao Feng Guo Xinwei Deng Zachary R Doerzaph Source Type: research

Application of different negative binomial parameterizations to develop safety performance functions for non-federal aid system roads
This study examined the application of traditional negative binomial and zero-favored negative binomial models (i.e., negative binomial-Lindley). Both groups of models were formulated by different variance and dispersion structures. Using crash, roadway inventory, and traffic volume data from 2014 to 2018 in Virginia, the results showed that the NB-L models perform better than the traditional NB models. Furthermore, an appropriate variance structure along with a reasonably chosen dispersion function can further improve the model performance.PMID:33866155 | DOI:10.1016/j.aap.2021.106103 (Source: Accident; Analysis and Prevention.)
Source: Accident; Analysis and Prevention. - April 18, 2021 Category: Accident Prevention Authors: Ali Khodadadi Ioannis Tsapakis Subasish Das Dominique Lord Yingfeng Li Source Type: research

Decision-adjusted driver risk predictive models using kinematics information
This study demonstrates the value of kinematic driving behavior in crash risk prediction and the necessity for a systematic approach for extracting prediction features. The proposed method can benefit broad applications, including fleet safety management, use-based insurance, driver behavior intervention, as well as connected-vehicle safety technology development.PMID:33866156 | DOI:10.1016/j.aap.2021.106088 (Source: Accident; Analysis and Prevention.)
Source: Accident; Analysis and Prevention. - April 18, 2021 Category: Accident Prevention Authors: Huiying Mao Feng Guo Xinwei Deng Zachary R Doerzaph Source Type: research

Application of different negative binomial parameterizations to develop safety performance functions for non-federal aid system roads
This study examined the application of traditional negative binomial and zero-favored negative binomial models (i.e., negative binomial-Lindley). Both groups of models were formulated by different variance and dispersion structures. Using crash, roadway inventory, and traffic volume data from 2014 to 2018 in Virginia, the results showed that the NB-L models perform better than the traditional NB models. Furthermore, an appropriate variance structure along with a reasonably chosen dispersion function can further improve the model performance.PMID:33866155 | DOI:10.1016/j.aap.2021.106103 (Source: Accident; Analysis and Prevention.)
Source: Accident; Analysis and Prevention. - April 18, 2021 Category: Accident Prevention Authors: Ali Khodadadi Ioannis Tsapakis Subasish Das Dominique Lord Yingfeng Li Source Type: research

Using SHRP2 NDS data to examine infrastructure and other factors contributing to older driver crashes during left turns at signalized intersections
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Tracy Zafian, Alyssa Ryan, Ravi Agrawal, Siby Samuel, Michael Knodler (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 17, 2021 Category: Accident Prevention Source Type: research

Safety effects of law enforcement cameras at non-signalized crosswalks: A case study in China
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Haojie Li, Ziqian Zhang, N.N. Sze, Haodong Hu, Hongliang Ding (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 17, 2021 Category: Accident Prevention Source Type: research

Changes in car drivers’ attitudes and behaviours, and cyclist numbers following the introduction of a cyclist minimum passing distance law
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Laura S. Fruhen, Isabel Rossen, Lisette Kanse (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 17, 2021 Category: Accident Prevention Source Type: research

Validation of driver support system based on real-world bicycle and motor vehicle flows
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Toshiya Hirose, Takumi Takada, Shoko Oikawa, Yasuhiro Matsui (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 17, 2021 Category: Accident Prevention Source Type: research

Evaluation of pedestrian critical gap and crossing speed at midblock crossing using image processing
Accid Anal Prev. 2021 Apr 14;156:106127. doi: 10.1016/j.aap.2021.106127. Online ahead of print.ABSTRACTPedestrians confront risky situations at midblock sections due to the unyielding behavior of drivers. Thus, pedestrians have to wait for an appropriate gap to cross. This research investigates pedestrians' gap acceptance and crossing speed for midblock crossings by image processing methods in Izmir, Turkey. A total of 498 pedestrians have been tracked at two midblock crossings. The data were collected for one hour at each midblock crossing during the evening peak hour between 5.00-6.00 p.m. Three synchronized cameras were...
Source: Accident; Analysis and Prevention. - April 17, 2021 Category: Accident Prevention Authors: Y Alver P Onelcin A Cicekli M Abdel-Aty Source Type: research

Evaluation of pedestrian critical gap and crossing speed at midblock crossing using image processing
Accid Anal Prev. 2021 Apr 14;156:106127. doi: 10.1016/j.aap.2021.106127. Online ahead of print.ABSTRACTPedestrians confront risky situations at midblock sections due to the unyielding behavior of drivers. Thus, pedestrians have to wait for an appropriate gap to cross. This research investigates pedestrians' gap acceptance and crossing speed for midblock crossings by image processing methods in Izmir, Turkey. A total of 498 pedestrians have been tracked at two midblock crossings. The data were collected for one hour at each midblock crossing during the evening peak hour between 5.00-6.00 p.m. Three synchronized cameras were...
Source: Accident; Analysis and Prevention. - April 17, 2021 Category: Accident Prevention Authors: Y Alver P Onelcin A Cicekli M Abdel-Aty Source Type: research

Decision-adjusted driver risk predictive models using kinematics information
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Huiying Mao, Feng Guo, Xinwei Deng, Zachary R. Doerzaph (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 16, 2021 Category: Accident Prevention Source Type: research

Driving after marijuana use among U.S. adolescents: Prevalence profiles and related behaviors
CONCLUSIONS: Among adolescent marijuana users, the prevalence of driving after using marijuana was high. Enhanced surveillance, prevention, and control measures are necessary to mitigate the negative impacts of marijuana consumption and related behaviors.PMID:33861655 | DOI:10.1080/15389588.2021.1906870 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 16, 2021 Category: Accident Prevention Authors: Bart Hammig Robert Davis Ches Jones Source Type: research

Sleep-deprived car-following: Indicators of rear-end crash potential
Accid Anal Prev. 2021 Apr 13;156:106123. doi: 10.1016/j.aap.2021.106123. Online ahead of print.ABSTRACTSafety assessment among sleep-deprived drivers is a challenging research area with only a few sleep-related studies investigating safety performance during car-following. Therefore, this study aimed to measure the effects of partial sleep deprivation on driver safety during car-following. Fifty healthy male drivers with no prior history of any sleep-related disorders, drove the driving simulator in three conditions of varying sleep duration: a baseline (no sleep deprivation), test session (TS1) after one night of PSD (sle...
Source: Accident; Analysis and Prevention. - April 16, 2021 Category: Accident Prevention Authors: Kirti Mahajan Nagendra R Velaga Source Type: research

Driving after marijuana use among U.S. adolescents: Prevalence profiles and related behaviors
CONCLUSIONS: Among adolescent marijuana users, the prevalence of driving after using marijuana was high. Enhanced surveillance, prevention, and control measures are necessary to mitigate the negative impacts of marijuana consumption and related behaviors.PMID:33861655 | DOI:10.1080/15389588.2021.1906870 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 16, 2021 Category: Accident Prevention Authors: Bart Hammig Robert Davis Ches Jones Source Type: research

Driving after marijuana use among U.S. adolescents: Prevalence profiles and related behaviors
CONCLUSIONS: Among adolescent marijuana users, the prevalence of driving after using marijuana was high. Enhanced surveillance, prevention, and control measures are necessary to mitigate the negative impacts of marijuana consumption and related behaviors.PMID:33861655 | DOI:10.1080/15389588.2021.1906870 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 16, 2021 Category: Accident Prevention Authors: Bart Hammig Robert Davis Ches Jones Source Type: research

Driving after marijuana use among U.S. adolescents: Prevalence profiles and related behaviors
CONCLUSIONS: Among adolescent marijuana users, the prevalence of driving after using marijuana was high. Enhanced surveillance, prevention, and control measures are necessary to mitigate the negative impacts of marijuana consumption and related behaviors.PMID:33861655 | DOI:10.1080/15389588.2021.1906870 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 16, 2021 Category: Accident Prevention Authors: Bart Hammig Robert Davis Ches Jones Source Type: research

Application of different negative binomial parameterizations to develop safety performance functions for non-federal aid system roads
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Ali Khodadadi, Ioannis Tsapakis, Subasish Das, Dominique Lord, Yingfeng Li (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 16, 2021 Category: Accident Prevention Source Type: research

Evaluation of pedestrian critical gap and crossing speed at midblock crossing using image processing
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Y. Alver, P. Onelcin, A. Cicekli, M. Abdel-Aty (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 14, 2021 Category: Accident Prevention Source Type: research

Evaluation of the 30km/h speed limit trial in the City of Yarra, Melbourne, Australia
CONCLUSION: The findings give support for the likely safety benefits of the 30 km/h trial with increased support from the residents. Speed reductions in the control region suggested a carry-over of the effects of the trial but also added support by local residents for reduced speed limits in the region. Potential injury savings were estimated at a 4% reduction in the risk of a pedestrian injury from the observed treatment effect in the trial region.PMID:33849362 | DOI:10.1080/15389588.2021.1895990 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: B Lawrence B Fildes L Thompson J Cook S Newstead Source Type: research

A new model to estimate pedestrian deaths from speed-related interventions
CONCLUSIONS: A new model has been developed to estimate changes in pedestrian fatalities resulting from changes in traffic speed. The application of the model using four speed-related interventions emphasize that deterrence of a small proportion of drivers using speed enforcement can have large implications for pedestrian safety.PMID:33849342 | DOI:10.1080/15389588.2021.1908544 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: Rahul Goel Source Type: research

Severity analysis of road transport accidents of hazardous materials with machine learning
CONCLUSIONS: Different data have unique characteristics, and the best modeling and analysis method should be chosen accordingly. The safety of road transport of hazardous materials in China is poor, and the losses caused by accidents are substantial. Strengthening the monitoring of travel speed and travel time; improving driver safety awareness, driving skills and the ability to mitigate emergencies; improving the configuration of vehicle safety equipment and the linkage with the control center and rescue center; improving the environmental differences between inside a tunnel and outside a tunnel; reducing the design of lo...
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: Xiaoyan Shen Shanshan Wei Source Type: research

Evaluation of the 30km/h speed limit trial in the City of Yarra, Melbourne, Australia
CONCLUSION: The findings give support for the likely safety benefits of the 30 km/h trial with increased support from the residents. Speed reductions in the control region suggested a carry-over of the effects of the trial but also added support by local residents for reduced speed limits in the region. Potential injury savings were estimated at a 4% reduction in the risk of a pedestrian injury from the observed treatment effect in the trial region.PMID:33849362 | DOI:10.1080/15389588.2021.1895990 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: B Lawrence B Fildes L Thompson J Cook S Newstead Source Type: research

A new model to estimate pedestrian deaths from speed-related interventions
CONCLUSIONS: A new model has been developed to estimate changes in pedestrian fatalities resulting from changes in traffic speed. The application of the model using four speed-related interventions emphasize that deterrence of a small proportion of drivers using speed enforcement can have large implications for pedestrian safety.PMID:33849342 | DOI:10.1080/15389588.2021.1908544 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: Rahul Goel Source Type: research

Severity analysis of road transport accidents of hazardous materials with machine learning
CONCLUSIONS: Different data have unique characteristics, and the best modeling and analysis method should be chosen accordingly. The safety of road transport of hazardous materials in China is poor, and the losses caused by accidents are substantial. Strengthening the monitoring of travel speed and travel time; improving driver safety awareness, driving skills and the ability to mitigate emergencies; improving the configuration of vehicle safety equipment and the linkage with the control center and rescue center; improving the environmental differences between inside a tunnel and outside a tunnel; reducing the design of lo...
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: Xiaoyan Shen Shanshan Wei Source Type: research

Evaluation of the 30km/h speed limit trial in the City of Yarra, Melbourne, Australia
CONCLUSION: The findings give support for the likely safety benefits of the 30 km/h trial with increased support from the residents. Speed reductions in the control region suggested a carry-over of the effects of the trial but also added support by local residents for reduced speed limits in the region. Potential injury savings were estimated at a 4% reduction in the risk of a pedestrian injury from the observed treatment effect in the trial region.PMID:33849362 | DOI:10.1080/15389588.2021.1895990 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: B Lawrence B Fildes L Thompson J Cook S Newstead Source Type: research

A new model to estimate pedestrian deaths from speed-related interventions
CONCLUSIONS: A new model has been developed to estimate changes in pedestrian fatalities resulting from changes in traffic speed. The application of the model using four speed-related interventions emphasize that deterrence of a small proportion of drivers using speed enforcement can have large implications for pedestrian safety.PMID:33849342 | DOI:10.1080/15389588.2021.1908544 (Source: Traffic Injury Prevention)
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: Rahul Goel Source Type: research

Severity analysis of road transport accidents of hazardous materials with machine learning
CONCLUSIONS: Different data have unique characteristics, and the best modeling and analysis method should be chosen accordingly. The safety of road transport of hazardous materials in China is poor, and the losses caused by accidents are substantial. Strengthening the monitoring of travel speed and travel time; improving driver safety awareness, driving skills and the ability to mitigate emergencies; improving the configuration of vehicle safety equipment and the linkage with the control center and rescue center; improving the environmental differences between inside a tunnel and outside a tunnel; reducing the design of lo...
Source: Traffic Injury Prevention - April 14, 2021 Category: Accident Prevention Authors: Xiaoyan Shen Shanshan Wei Source Type: research

Sleep-deprived car-following: Indicators of rear-end crash potential
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Kirti Mahajan, Nagendra R. Velaga (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 13, 2021 Category: Accident Prevention Source Type: research

Fuzzy analysis of students' perception of traffic safety in school environments: the case of a small Brazilian city
Int J Inj Contr Saf Promot. 2021 Apr 12:1-11. doi: 10.1080/17457300.2021.1909625. Online ahead of print.ABSTRACTThousands of lives are lost every year due to traffic accidents worldwide, and youths are the most affected. The goal of this paper is to analyze the differences in young students' perceptions about traffic safety in school surroundings in order to help in the formulation of public policies and the development of infrastructure to make school travels safer. A questionnaire was used to obtain the perception of high school students from institutions with different urban characteristics. Data modelling with fuzzy lo...
Source: International Journal of Injury Control and Safety Promotion - April 13, 2021 Category: Accident Prevention Authors: Let ícia Oestreich T ânia Batistela Torres Alejandro Ruiz-Padillo Source Type: research

Rule discovery to identify patterns contributing to overrepresentation and severity of run-off-the-road crashes
Accid Anal Prev. 2021 Apr 10;155:106119. doi: 10.1016/j.aap.2021.106119. Online ahead of print.ABSTRACTThe main objective of this paper was to analyse the roadway, environmental, and driver-related factors associated with an overrepresentation of frequency and severity of run-off-the-road (ROR) crashes. The data used in this study refer to the 6167 crashes occurred in the section Naples-Candela of A16 motorway, Italy in the period from 2001 to 2011. The analysis was carried out using the rule discovery technique due to its ability of extracting knowledge from large amounts of data previously unknown and indistinguishable b...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Alfonso Montella Filomena Mauriello Mariano Pernetti Maria Rella Riccardi Source Type: research

Toward a crowdsourcing solution to identify high-risk highway segments through mining driving jerks
This study reports on a new crowdsourcing solution to identify high-risk highway segments by analyzing driving jerks. Driving jerks represent the abrupt changes of acceleration, which have been shown to be closely related to traffic risks. In this study, we first calculate driving jerks from each participant's naturalistic driving data and identify "unsafe" drivers based on their jerk-ratio. Then, we innovatively propose an improved line-constrained clustering method to identify each participant's jerk clusters on each road. These individual-specific jerk clusters are overlapped with road networks to identify pot...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Xiao Li Seyedeh Maryam Mousavi Bahar Dadashova Dominique Lord Brian Wolshon Source Type: research

Using long short term memory and convolutional neural networks for driver drowsiness detection
Accid Anal Prev. 2021 Apr 10;156:106107. doi: 10.1016/j.aap.2021.106107. Online ahead of print.ABSTRACTFatigue negatively affects the safety and performance of drivers on the road. In fact, drowsiness and fatigue are the cause of a substantial number of motor vehicle accidents. Drowsiness among the drivers can be detected using variety of modalities, including electroencephalogram (EEG), eye movement, and vehicle driving dynamics. Among these EEG is highly accurate but very intrusive and cumbersome. On the other hand, vehicle driving dynamics are very easy to acquire but accuracy is not very high. Eye movement based approa...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Azhar Quddus Ali Shahidi Zandi Laura Prest Felix J E Comeau Source Type: research

Fuzzy analysis of students' perception of traffic safety in school environments: the case of a small Brazilian city
Int J Inj Contr Saf Promot. 2021 Apr 12:1-11. doi: 10.1080/17457300.2021.1909625. Online ahead of print.ABSTRACTThousands of lives are lost every year due to traffic accidents worldwide, and youths are the most affected. The goal of this paper is to analyze the differences in young students' perceptions about traffic safety in school surroundings in order to help in the formulation of public policies and the development of infrastructure to make school travels safer. A questionnaire was used to obtain the perception of high school students from institutions with different urban characteristics. Data modelling with fuzzy lo...
Source: International Journal of Injury Control and Safety Promotion - April 13, 2021 Category: Accident Prevention Authors: Let ícia Oestreich T ânia Batistela Torres Alejandro Ruiz-Padillo Source Type: research

Rule discovery to identify patterns contributing to overrepresentation and severity of run-off-the-road crashes
Accid Anal Prev. 2021 Apr 10;155:106119. doi: 10.1016/j.aap.2021.106119. Online ahead of print.ABSTRACTThe main objective of this paper was to analyse the roadway, environmental, and driver-related factors associated with an overrepresentation of frequency and severity of run-off-the-road (ROR) crashes. The data used in this study refer to the 6167 crashes occurred in the section Naples-Candela of A16 motorway, Italy in the period from 2001 to 2011. The analysis was carried out using the rule discovery technique due to its ability of extracting knowledge from large amounts of data previously unknown and indistinguishable b...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Alfonso Montella Filomena Mauriello Mariano Pernetti Maria Rella Riccardi Source Type: research

Toward a crowdsourcing solution to identify high-risk highway segments through mining driving jerks
This study reports on a new crowdsourcing solution to identify high-risk highway segments by analyzing driving jerks. Driving jerks represent the abrupt changes of acceleration, which have been shown to be closely related to traffic risks. In this study, we first calculate driving jerks from each participant's naturalistic driving data and identify "unsafe" drivers based on their jerk-ratio. Then, we innovatively propose an improved line-constrained clustering method to identify each participant's jerk clusters on each road. These individual-specific jerk clusters are overlapped with road networks to identify pot...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Xiao Li Seyedeh Maryam Mousavi Bahar Dadashova Dominique Lord Brian Wolshon Source Type: research

Using long short term memory and convolutional neural networks for driver drowsiness detection
Accid Anal Prev. 2021 Apr 10;156:106107. doi: 10.1016/j.aap.2021.106107. Online ahead of print.ABSTRACTFatigue negatively affects the safety and performance of drivers on the road. In fact, drowsiness and fatigue are the cause of a substantial number of motor vehicle accidents. Drowsiness among the drivers can be detected using variety of modalities, including electroencephalogram (EEG), eye movement, and vehicle driving dynamics. Among these EEG is highly accurate but very intrusive and cumbersome. On the other hand, vehicle driving dynamics are very easy to acquire but accuracy is not very high. Eye movement based approa...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Azhar Quddus Ali Shahidi Zandi Laura Prest Felix J E Comeau Source Type: research

Fuzzy analysis of students' perception of traffic safety in school environments: the case of a small Brazilian city
Int J Inj Contr Saf Promot. 2021 Apr 12:1-11. doi: 10.1080/17457300.2021.1909625. Online ahead of print.ABSTRACTThousands of lives are lost every year due to traffic accidents worldwide, and youths are the most affected. The goal of this paper is to analyze the differences in young students' perceptions about traffic safety in school surroundings in order to help in the formulation of public policies and the development of infrastructure to make school travels safer. A questionnaire was used to obtain the perception of high school students from institutions with different urban characteristics. Data modelling with fuzzy lo...
Source: International Journal of Injury Control and Safety Promotion - April 13, 2021 Category: Accident Prevention Authors: Let ícia Oestreich T ânia Batistela Torres Alejandro Ruiz-Padillo Source Type: research

Rule discovery to identify patterns contributing to overrepresentation and severity of run-off-the-road crashes
Accid Anal Prev. 2021 Apr 10;155:106119. doi: 10.1016/j.aap.2021.106119. Online ahead of print.ABSTRACTThe main objective of this paper was to analyse the roadway, environmental, and driver-related factors associated with an overrepresentation of frequency and severity of run-off-the-road (ROR) crashes. The data used in this study refer to the 6167 crashes occurred in the section Naples-Candela of A16 motorway, Italy in the period from 2001 to 2011. The analysis was carried out using the rule discovery technique due to its ability of extracting knowledge from large amounts of data previously unknown and indistinguishable b...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Alfonso Montella Filomena Mauriello Mariano Pernetti Maria Rella Riccardi Source Type: research

Toward a crowdsourcing solution to identify high-risk highway segments through mining driving jerks
This study reports on a new crowdsourcing solution to identify high-risk highway segments by analyzing driving jerks. Driving jerks represent the abrupt changes of acceleration, which have been shown to be closely related to traffic risks. In this study, we first calculate driving jerks from each participant's naturalistic driving data and identify "unsafe" drivers based on their jerk-ratio. Then, we innovatively propose an improved line-constrained clustering method to identify each participant's jerk clusters on each road. These individual-specific jerk clusters are overlapped with road networks to identify pot...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Xiao Li Seyedeh Maryam Mousavi Bahar Dadashova Dominique Lord Brian Wolshon Source Type: research

Using long short term memory and convolutional neural networks for driver drowsiness detection
Accid Anal Prev. 2021 Apr 10;156:106107. doi: 10.1016/j.aap.2021.106107. Online ahead of print.ABSTRACTFatigue negatively affects the safety and performance of drivers on the road. In fact, drowsiness and fatigue are the cause of a substantial number of motor vehicle accidents. Drowsiness among the drivers can be detected using variety of modalities, including electroencephalogram (EEG), eye movement, and vehicle driving dynamics. Among these EEG is highly accurate but very intrusive and cumbersome. On the other hand, vehicle driving dynamics are very easy to acquire but accuracy is not very high. Eye movement based approa...
Source: Accident; Analysis and Prevention. - April 13, 2021 Category: Accident Prevention Authors: Azhar Quddus Ali Shahidi Zandi Laura Prest Felix J E Comeau Source Type: research

Fuzzy analysis of students' perception of traffic safety in school environments: the case of a small Brazilian city
Int J Inj Contr Saf Promot. 2021 Apr 12:1-11. doi: 10.1080/17457300.2021.1909625. Online ahead of print.ABSTRACTThousands of lives are lost every year due to traffic accidents worldwide, and youths are the most affected. The goal of this paper is to analyze the differences in young students' perceptions about traffic safety in school surroundings in order to help in the formulation of public policies and the development of infrastructure to make school travels safer. A questionnaire was used to obtain the perception of high school students from institutions with different urban characteristics. Data modelling with fuzzy lo...
Source: International Journal of Injury Control and Safety Promotion - April 13, 2021 Category: Accident Prevention Authors: Let ícia Oestreich T ânia Batistela Torres Alejandro Ruiz-Padillo Source Type: research

Toward a crowdsourcing solution to identify high-risk highway segments through mining driving jerks
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 155Author(s): Xiao Li, Seyedeh Maryam Mousavi, Bahar Dadashova, Dominique Lord, Brian Wolshon (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 13, 2021 Category: Accident Prevention Source Type: research

Using long short term memory and convolutional neural networks for driver drowsiness detection
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 156Author(s): Azhar Quddus, Ali Shahidi Zandi, Laura Prest, Felix J.E. Comeau (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 11, 2021 Category: Accident Prevention Source Type: research

Rule discovery to identify patterns contributing to overrepresentation and severity of run-off-the-road crashes
Publication date: June 2021Source: Accident Analysis & Prevention, Volume 155Author(s): Alfonso Montella, Filomena Mauriello, Mariano Pernetti, Maria Rella Riccardi (Source: Accident Analysis and Prevention)
Source: Accident Analysis and Prevention - April 11, 2021 Category: Accident Prevention Source Type: research

Speed violation analysis of heavy vehicles on highways using spatial analysis and machine learning algorithms
In this study, data regarding the speed violations committed by heavy vehicles in Turkey, were used. Speed violations were divided into 10 classes according to the intensity of speed violation rates. After this process, all provinces were classified according to support vector machines (SVM), naive bayes (NB) and k-nearest neighbors (KNN) algorithms. When the accuracy values and error scales of all three algorithms are examined, it has been determined that the algorithm that gives the most accurate results is the NB algorithm. Based on the classification of this algorithm, speed violation density maps of types of heavy veh...
Source: Accident; Analysis and Prevention. - April 10, 2021 Category: Accident Prevention Authors: Emre Ku şkapan M Yasin Çodur Ahmet Atalay Source Type: research

Speed violation analysis of heavy vehicles on highways using spatial analysis and machine learning algorithms
In this study, data regarding the speed violations committed by heavy vehicles in Turkey, were used. Speed violations were divided into 10 classes according to the intensity of speed violation rates. After this process, all provinces were classified according to support vector machines (SVM), naive bayes (NB) and k-nearest neighbors (KNN) algorithms. When the accuracy values and error scales of all three algorithms are examined, it has been determined that the algorithm that gives the most accurate results is the NB algorithm. Based on the classification of this algorithm, speed violation density maps of types of heavy veh...
Source: Accident; Analysis and Prevention. - April 10, 2021 Category: Accident Prevention Authors: Emre Ku şkapan M Yasin Çodur Ahmet Atalay Source Type: research

Speed violation analysis of heavy vehicles on highways using spatial analysis and machine learning algorithms
In this study, data regarding the speed violations committed by heavy vehicles in Turkey, were used. Speed violations were divided into 10 classes according to the intensity of speed violation rates. After this process, all provinces were classified according to support vector machines (SVM), naive bayes (NB) and k-nearest neighbors (KNN) algorithms. When the accuracy values and error scales of all three algorithms are examined, it has been determined that the algorithm that gives the most accurate results is the NB algorithm. Based on the classification of this algorithm, speed violation density maps of types of heavy veh...
Source: Accident; Analysis and Prevention. - April 10, 2021 Category: Accident Prevention Authors: Emre Ku şkapan M Yasin Çodur Ahmet Atalay Source Type: research