1
|
Wu YW, Hsu TP. Mid-term prediction of at-fault crash driver frequency using fusion deep learning with city-level traffic violation data. ACCIDENT; ANALYSIS AND PREVENTION 2021; 150:105910. [PMID: 33302233 DOI: 10.1016/j.aap.2020.105910] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/04/2020] [Revised: 09/08/2020] [Accepted: 11/25/2020] [Indexed: 06/12/2023]
Abstract
Traffic violations and improper driving are behaviors that primarily contribute to traffic crashes. This study aimed to develop effective approaches for predicting at-fault crash driver frequency using only city-level traffic enforcement predictors. A fusion deep learning approach combining a convolution neural network (CNN) and gated recurrent units (GRU) was developed to compare predictive performance with one econometric approach, two machine learning approaches, and another deep learning approach. The performance comparison was conducted for (1) at-fault crash driver frequency prediction tasks and (2) city-level crash risk prediction tasks. The proposed CNN-GRU achieved remarkable prediction accuracy and outperformed other approaches, while the other approaches also exhibited excellent performances. The results suggest that effective prediction approaches and appropriate traffic safety measures can be developed by considering both crash frequency and crash risk prediction tasks. In addition, the accumulated local effects (ALE) plot was utilized to investigate the contribution of each traffic enforcement activity on traffic safety in a scenario of multicollinearity among predictors. The ALE plot illustrated a complex nonlinear relationship between traffic enforcement predictors and the response variable. These findings can facilitate the development of traffic safety measures and serve as a good foundation for further investigations and utilization of traffic violation data.
Collapse
Affiliation(s)
- Yuan-Wei Wu
- Department of Civil Engineering, National Taiwan University, Taipei, 106, Taiwan.
| | - Tien-Pen Hsu
- Department of Civil Engineering, National Taiwan University, Taipei, 106, Taiwan
| |
Collapse
|
2
|
Fathollahi S, Saeedi Moghaddam S, Rezaei N, Jafari A, Peykari N, Haghshenas R, Shams-Beyranvand M, Damerchilu B, Mehregan A, Khezrian M, Hasan M, Momen Nia Rankohi E, Darman M, Moghisi A, Farzadfar F. Prevalence of behavioural risk factors for road-traffic injuries among the Iranian population: findings from STEPs 2016. Int J Epidemiol 2020; 48:1187-1196. [PMID: 30843066 DOI: 10.1093/ije/dyz021] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/12/2019] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND To achieve Sustainable Development Goal 3.6 in Iran, we need to have a comprehensive understanding of the distribution of risky behaviours regarding road-traffic injuries at national and sub-national levels. Little is known about the road-use vulnerability patterns of road-traffic injuries in Iran. The aim of this study is to describe the prevalence of self-reported human risk factors in road-traffic injuries using the findings from a large-scale cross-sectional study based on the World Health Organization's stepwise approach to surveillance of non-communicable diseases (STEPs). METHODS A cross-sectional survey study in 2016 assessed the road-use pattern and prevalence of risky behaviours of people more than 18 years old. In this study, we planned to recruit 31 050 individuals as a representative sample at national and provincial levels. In practice, 30 541 individuals (3105 clusters) from urban and rural areas of Iran were selected. Basic socio-demographic data, major behavioural risk factors such as seatbelt and helmet non-compliance, drunk driving and occupant in a car with a drunk driver were assessed through baseline interviews gathered through an Android tablet-based questionnaire. RESULTS The overall prevalence of seatbelt and helmet compliance was 75.2% (95% confidence interval: 74.7-75.7) and 13.9% (13.4-14.5), respectively, at the national level. The prevalence of risk-taking behaviours such as drink driving was 0.5% (0.4-0.6) and for being an occupant in a car with a drunk driver was 3.5% (3.2-3.8). At the provincial level, the highest age-standardized prevalence of seatbelt compliance (89.6%) was almost 1.5 times higher than the lowest provincial prevalence (58.5%). In 63% of provinces, the lowest prevalence of seatbelt compliance was observed among people aged 18-24 years old. CONCLUSIONS In Iran, existing disease-prevention and health-promotion programmes should be expanded to target vulnerable subgroups that have more prevalent human risk factors for road-traffic injuries. Further research is required to investigate the context-specific proximal human risk factors and vulnerability patterns in Iran.
Collapse
Affiliation(s)
- Soraya Fathollahi
- Department of Health in Emergencies and Disasters, Tehran University of Medical Sciences, Tehran, Iran.,Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Sahar Saeedi Moghaddam
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Nazila Rezaei
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Ayyoob Jafari
- Faculty of Electrical, Biomedical and Mechatronics Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran
| | - Niloofar Peykari
- Deputy for Education, Ministry of Health and Medical Education, Tehran, Iran
| | - Rosa Haghshenas
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mehran Shams-Beyranvand
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Bahman Damerchilu
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Ashkan Mehregan
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Maryam Khezrian
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Milad Hasan
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Ezzatollah Momen Nia Rankohi
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran.,Biomedical Engineering, Tonekabon Branch, Islamic Azad University, Tonekabon, Iran
| | - Mahboobeh Darman
- Department of Epidemiology, Iran University of Medical Sciences, Tehran, Iran
| | - Alireza Moghisi
- Deputy of Health, Ministry of Health and Medical Education, Tehran, Iran and
| | - Farshad Farzadfar
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran.,Endocrinology and Metabolism Research Center, Endocrinology and Metabolism Clinical Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
3
|
Duddu VR, Penmetsa P, Pulugurtha SS. Modeling and comparing injury severity of at-fault and not at-fault drivers in crashes. ACCIDENT; ANALYSIS AND PREVENTION 2018; 120:55-63. [PMID: 30086438 DOI: 10.1016/j.aap.2018.07.036] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/06/2018] [Revised: 06/22/2018] [Accepted: 07/30/2018] [Indexed: 06/08/2023]
Abstract
This paper examines and compares the effect of selected variables on driver injury severity of, both, at-fault and not at-fault drivers. Data from the Highway Safety Information System (HSIS) for the state of North Carolina was used for analysis and modeling. A partial proportional odds model was developed to examine the effect of each variable on injury severity of at-fault driver and not at-fault driver, and, to examine how each variable affects these two drivers' injury severity differently. Road characteristics, weather condition, and geometric characteristics were observed to have a similar effect on injury severity in a crash to at-fault and not at-fault drivers. Age of the driver, physical condition, gender, vehicle type, and, the number and type of traffic rule violations were observed to play a significant role in the injury severity of not at-fault drivers when compared to at-fault drivers in the crash. Moreover, motorcyclists and drivers 70 years or older are observed to be the most vulnerable road users.
Collapse
Affiliation(s)
- Venkata R Duddu
- Civil & Environmental Engineering Department / IDEAS Center, The University of North Carolina at Charlotte, 9201 University City Boulevard, Charlotte, NC, 28223-0001, USA.
| | - Praveena Penmetsa
- Alabama Transportation Institute, The University of Alabama, 201 7th Avenue, Tuscaloosa, AL, 35487, USA.
| | - Srinivas S Pulugurtha
- Civil & Environmental Engineering Department / IDEAS Center, The University of North Carolina at Charlotte, 9201 University City Boulevard, Charlotte, NC, 28223-0001, USA.
| |
Collapse
|