1
|
Aboulola OI. Improving traffic accident severity prediction using MobileNet transfer learning model and SHAP XAI technique. PLoS One 2024; 19:e0300640. [PMID: 38593130 PMCID: PMC11003624 DOI: 10.1371/journal.pone.0300640] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Accepted: 03/03/2024] [Indexed: 04/11/2024] Open
Abstract
Traffic accidents remain a leading cause of fatalities, injuries, and significant disruptions on highways. Comprehending the contributing factors to these occurrences is paramount in enhancing safety on road networks. Recent studies have demonstrated the utility of predictive modeling in gaining insights into the factors that precipitate accidents. However, there has been a dearth of focus on explaining the inner workings of complex machine learning and deep learning models and the manner in which various features influence accident prediction models. As a result, there is a risk that these models may be seen as black boxes, and their findings may not be fully trusted by stakeholders. The main objective of this study is to create predictive models using various transfer learning techniques and to provide insights into the most impactful factors using Shapley values. To predict the severity of injuries in accidents, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Residual Networks (ResNet), EfficientNetB4, InceptionV3, Extreme Inception (Xception), and MobileNet are employed. Among the models, the MobileNet showed the highest results with 98.17% accuracy. Additionally, by understanding how different features affect accident prediction models, researchers can gain a deeper understanding of the factors that contribute to accidents and develop more effective interventions to prevent them.
Collapse
Affiliation(s)
- Omar Ibrahim Aboulola
- College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia
| |
Collapse
|
2
|
Golfiroozi S, Nikbakht HA, Fahim Yegane SA, Gholami Gharab S, Shojaie L, Ahmad Hosseini S, Rajabi A, Ghelichi-Ghojogh M. Effective factors of severity of traffic accident traumas based on the Haddon matrix: a systematic review and meta-analysis. Ann Med Surg (Lond) 2024; 86:1622-1630. [PMID: 38463059 PMCID: PMC10923285 DOI: 10.1097/ms9.0000000000001792] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Accepted: 01/19/2024] [Indexed: 03/12/2024] Open
Abstract
Objective This study aims to investigate the factors affecting the severity of trauma caused by traffic accidents based on martrix Haddon; a systematic review and meta-analysis. Methods In this study searched five international databases in this study, including Medline/PubMed, ProQuest, Scopus, Web of Knowledge, and Google Scholar, for published articles by the end of 2022. Data were entered into the statistical program and analyses were performed using STATA 17.0 software. Odds ratio (OR) values were computed for severity accidents. Results Results of study showed that among the risk factors related to the host, not using helmet increased the risk of injury severity by 3.44 times compared to people who have used helmets (OR Not using helmet/Using helmet = 3.44, 95% CI: 2.27-5.00, P=0.001, I2=0.00%). Also, crossing over a centre divider has a protective role for the risk of injury severity compared to undertaking (OR crossing over a centre divider/undertaking=0.39, 95% CI: 0.20-0.75, P=0.01, I2=25.79%). in terms of the type of accident, accident of car-car reduces the risk of injury severity by 23% compared to accident of car-pedestrian (OR accident of car-car/accident of car-pedestrian=0.77, 95% CI: 0.61-0.96, P=0.02, I2=0.00%). Conclusions It is necessary to pay attention to the intersection of human, vehicle and environmental risks and their contribution and how they interact. Based on the Haddon matrix approach, special strategies can be designed to prevent road damage. Safety standards for vehicles should also be addressed through stricter legal requirements and inspections.
Collapse
Affiliation(s)
| | - Hossein-Ali Nikbakht
- Social Determinants of Health Research Center, Health Research Institute, Babol University of Medical Sciences, Babol
| | | | - Saeed Gholami Gharab
- Emergency Medicine, Management Research Center, Health Management Reaearch Institute, Iran University of Medical Sciences, Tehran, Iran
| | - Layla Shojaie
- Department of Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA
| | - Seyed Ahmad Hosseini
- Neonatal and Children’s Research Center, Department of Biostatistics and Epidemiology, School of Health, Faculty of Health, Golestan University of Medical Sciences, Gorgan, Iran
| | - Abdolhalim Rajabi
- Environmental Health Research Center, Faculty of Health, Golestan University of Medical Sciences, Gorgan
| | - Mousa Ghelichi-Ghojogh
- Neonatal and Children’s Research Center, Department of Biostatistics and Epidemiology, School of Health, Faculty of Health, Golestan University of Medical Sciences, Gorgan, Iran
| |
Collapse
|
3
|
Zhang Q, Lu Y, Feng F, Hu J. Causal analysis of coach and bus accidents in China based on road alignments. Heliyon 2023; 9:e15231. [PMID: 37089282 PMCID: PMC10114227 DOI: 10.1016/j.heliyon.2023.e15231] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2022] [Revised: 03/30/2023] [Accepted: 03/30/2023] [Indexed: 04/25/2023] Open
Abstract
Given the complexity and the difficulty of controlling contributors effectively, road passenger transport often results in serious injuries and fatalities. The purpose of this study is to identify the main contributors to coach and bus accidents and to provide policy recommendations for making improvements in accident prevention. The Driving Reliability and Error Analysis Method 3.0 (DREAM 3.0) was modified and used to analyze the contributing factors (i.e. phenotypes and genotypes in DREAM) and their casual mechanisms. By having statistical analysis and social network analysis (SNA) adopted, the main genotypes and phenotypes of the DREAM charts were identified. The results of the study showed that A2.1 (too high speed) was the key phenotype and the main genotypic process chain leading to the phenotype was "inadequate safety management → inadequate training → inadequate skills/knowledge → misjudgment of the situation → too high speed" on all types of road. For A2.1 (too high speed), C2 (misjudgment of the situation) was the dominant genotype, while N5 (inadequate safety management) was the root cause of most genotypes. This suggests that road passenger transport companies, as the responsible parties, often fail to implement or violate safety prevention and control systems. Government regulators should promote the policy system and incentivize them to fulfil their safety management responsibilities. The government should also educate the public and improve the road environment to reduce passenger-related risks and the impact of environmental factors on drivers.
Collapse
Affiliation(s)
- Qingxia Zhang
- School of Public Management, Gansu University of Political Science and Law, Lanzhou, China
| | - Yao Lu
- School of Management, Lanzhou University, Lanzhou, China
| | - Fan Feng
- School of Foreign Languages, Shenyang Normal University, Shenyang, China
| | - Junyan Hu
- College of Social Development and Public Administration, Northwest Normal University, Lanzhou, China
- Corresponding author.
| |
Collapse
|
4
|
A Review of Different Components of the Intelligent Traffic Management System (ITMS). Symmetry (Basel) 2023. [DOI: 10.3390/sym15030583] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/25/2023] Open
Abstract
Traffic congestion is a serious challenge in urban areas. So, to address this challenge, the intelligent traffic management system (ITMS) is used to manage traffic on road networks. Managing traffic helps to focus on environmental impacts as well as emergency situations. However, the ITMS system has many challenges in analyzing scenes of complex traffic. New technologies such as computer vision (CV) and artificial intelligence (AI) are being used to solve these challenges. As a result, these technologies have made a distinct identity in the surveillance industry, particularly when it comes to keeping a constant eye on traffic scenes. There are many vehicle attributes and existing approaches that are being used in the development of ITMS, along with imaging technologies. In this paper, we reviewed the ITMS-based components that describe existing imaging technologies and existing approaches on the basis of their need for developing ITMS. The first component describes the traffic scene and imaging technologies. The second component talks about vehicle attributes and their utilization in existing vehicle-based approaches. The third component explains the vehicle’s behavior on the basis of the second component’s outcome. The fourth component explains how traffic-related applications can assist in the management and monitoring of traffic flow, as well as in the reduction of congestion and the enhancement of road safety. The fifth component describes the different types of ITMS applications. The sixth component discusses the existing methods of traffic signal control systems (TSCSs). Aside from these components, we also discuss existing vehicle-related tools such as simulators that work to create realistic traffic scenes. In the last section named discussion, we discuss the future development of ITMS and draw some conclusions. The main objective of this paper is to discuss the possible solutions to different problems during the development of ITMS in one place, with the help of components that would play an important role for an ITMS developer to achieve the goal of developing efficient ITMS.
Collapse
|
5
|
Peiris S, Newstead S, Berecki-Gisolf J, Fildes B. Quantifying the Foregone Benefits of Intelligent Speed Assist Due to the Limited Availability of Speed Signs across Three Australian States. SENSORS (BASEL, SWITZERLAND) 2022; 22:7765. [PMID: 36298134 PMCID: PMC9610991 DOI: 10.3390/s22207765] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/15/2022] [Revised: 10/03/2022] [Accepted: 10/08/2022] [Indexed: 06/16/2023]
Abstract
By being able to communicate the speed limit to drivers using speed sign recognition cameras, Intelligent Speed Assist (ISA) is expected to bring significant road safety gains through increased speed compliance. In the absence of complete digital speed maps and due to limited cellular connectivity throughout Australia, this study estimated the forgone savings of ISA in the event that speed signs are solely relied upon for optimal advisory ISA function. First, speed-related fatalities and serious injuries (FSI) in the Australian states of Victoria, South Australia, and Queensland (2013-2018) were identified, and published effectiveness estimates of ISA were applied to determine the potential benefits of ISA. Subsequently, taking into account speed sign presence across the three states, the forgone savings of ISA were estimated as FSI that would not be prevented due to absent speed signage. Annually, 27-35% of speed-related FSI in each state are unlikely to be prevented by ISA because speed sign infrastructure is absent, equating to economic losses of between AUD 62 and 153 million. Despite a number of assumptions being made regarding ISA fitment and driver acceptance of the technology, conservative estimates suggest that the benefits of speed signs placed consistently across road classes and remoteness levels would far outweigh the costs expected from the absence of speed signs. The development and utilisation of a methodology for estimating the foregone benefits of ISA due to suboptimal road infrastructure constitutes a novel contribution to research. This work provides a means of identifying where infrastructure investments should be targeted to capitalise on benefits offered by advanced driver assist technologies.
Collapse
|
6
|
Spatiotemporal Analysis of Traffic Accidents Hotspots Based on Geospatial Techniques. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION 2022. [DOI: 10.3390/ijgi11040260] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
Abstract
This paper aims to explore the spatiotemporal pattern of traffic accidents using five years of data between 2015 and 2019 for the Irbid Governorate, Jordan. The spatial pattern of traffic-accident hotspots and their temporal evolution were identified along the internal and arterial roads network in the study area using spatial autocorrelation (Global Moran I index) and local hotspot analysis (Getis–Ord Gi*) techniques within the GIS environment. The study showed a gradual increase in the reported traffic accidents of approximately 38% at the year level. The analysis of traffic accidents at the severity level showed a distinguished spatial distribution of hotspot locations. The less severe traffic accidents (~95%) occurred on the internal road network in the Irbid Governorate’s towns where the highest traffic volume exist. The spatial autocorrelation analysis and the Getis–Ord Gi* statistics with 99% of significance level showed clustering patterns of traffic accidents along the internal and the arterial road network segments. Between 2015 and 2019, a notable evolution of the traffic-accident hotspots clusters was pronounced. The results can be used to guide traffic managers and decision makers to take appropriate actions for enhancing the hotspot locations and improving their traffic safety status.
Collapse
|
7
|
Analysis of Crash Severity of Texas Two Lane Rural Roads Using Solar Altitude Angle Based Lighting Condition. SUSTAINABILITY 2022. [DOI: 10.3390/su14031692] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/10/2022]
Abstract
Many studies have examined the impact of factors affecting accident severity in rural areas; however, little attention has been paid to different lighting conditions (LCs), and less to the detailed categories and precise determining of twilight. In this paper, solar altitude angle (SAA), as a basis for differentiating and categorizing LCs, is proposed to investigate explanatory variables in much greater detail. For each LC, namely, dark, twilight, dark lit (dark with street lights) and daylight, separate random parameter models are developed to investigate the impacts of some factors on crash injury severity data of 2017 and 2018 in two lane rural roads of Texas. The model estimation results indicated that different LCs have various contributing factors, indeed, to each injury severity, further stressing the significance of investigating crashes based on SAA. The key differences include crash location, marked lane, grade direction, no passing zone, shoulder width, weekday and collision type. The important findings were that developing artificial lighting at intersections and LED raised pavement markers on two lane rural roads could lead to enhanced road safety under dark LCs. Furthermore, increasing shoulder width in straight segments of two lane rural roads is important for decreasing severe injury in daylight conditions.
Collapse
|
8
|
Entropy Method of Road Safety Management: Case Study of the Russian Federation. ENTROPY 2022; 24:e24020177. [PMID: 35205472 PMCID: PMC8870753 DOI: 10.3390/e24020177] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/08/2021] [Revised: 01/16/2022] [Accepted: 01/21/2022] [Indexed: 11/23/2022]
Abstract
Within the framework of this paper, the author’s entropy method of road safety management in large-sized systems is considered. The road safety management system in the Russian Federation, the largest country in the world, was selected for this case study. The purpose of the article is to present the opportunities and methodology of the use of quantitative assessments of the orderliness of the road accident rate formation process in regional transport systems for road safety management. Orderliness, in other words, systemic anti-chaos, can be quantified using the C. Shannon informational entropy H. The article consists of the results of the issue’s state analysis; methodology of assessment of the orderliness of the road accident rate formation process based on the using of the cause-and-effect chain; entropic method of the road safety management in large-scale systems, in particular, the algorithm of management of regional road safety in Russia taking into account the level of its entropic orderliness; and examples of the quantitative evaluation of the orderliness of regional road safety provision systems in Russia. The key results of the research are spatio-temporal patterns of the change of the orderliness of the road safety provision systems in the Russian Federation in 2004–2020. Based on the results, conclusions and recommendations about the practical application of the entropic method of road safety management in large federal states with complex administrative structures were formulated. These results give an idea of the possibilities of the usage of entropic approaches in road safety management to assess the orderliness of the regional transport systems and the advantages of the entropic method over other managerial methods.
Collapse
|
9
|
Inkeaw P, Srikummoon P, Chaijaruwanich J, Traisathit P, Awiphan S, Inchai J, Worasuthaneewan R, Theerakittikul T. Automatic Driver Drowsiness Detection Using Artificial Neural Network Based on Visual Facial Descriptors: Pilot Study. Nat Sci Sleep 2022; 14:1641-1649. [PMID: 36132745 PMCID: PMC9482962 DOI: 10.2147/nss.s376755] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Accepted: 08/26/2022] [Indexed: 11/23/2022] Open
Abstract
PURPOSE Driving while drowsy is a major cause of traffic accidents globally. Recent technologies for detection and alarm within automobiles for this condition are limited by their reliability, practicality, cost, and lack of clinical validation. In this study, we developed an early drowsiness detection algorithm and device based on the "gold standard brain biophysiological signal" and facial expression digital data. METHODS The data were obtained from 10 participants. Artificial neural networks (ANN) were adopted as the model. Composite features of facial descriptors (ie, eye aspect ratio (EAR), mouth aspect ratio (MAR), face length (FL), and face width balance (FWB)) extracted from two-second video frames were investigated. RESULTS The ANN combined with the EAR and MAR features had the most sensitivity (70.12%) while the ANN combined with the EAR, MAR, and FL features had the most accuracy and specificity (60.76% and 58.71%, respectively). In addition, by applying the discrete Fourier transform (DFT) to the composite features, the ANN combined with the EAR and MAR features again had the highest sensitivity (72.25%), while the ANN combined with the EAR, MAR, and FL features had the highest accuracy and specificity (60.40% and 54.10%, respectively). CONCLUSION The ANN with DFT combined with the EAR, MAR, and FL offered the best performance. Our direct driver sleepiness detection system developed from the integration of biophysiological information and internal validation provides a valuable algorithm, specifically toward alertness level.
Collapse
Affiliation(s)
- Papangkorn Inkeaw
- Data Science Research Center, Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Pimwarat Srikummoon
- Department of Statistics, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand.,Data Science Research Center, Department of Statistics, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Jeerayut Chaijaruwanich
- Data Science Research Center, Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand.,Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Patrinee Traisathit
- Department of Statistics, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand.,Data Science Research Center, Department of Statistics, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand.,Research Center in Bioresources for Agriculture, Industry and Medicine, Department of Statistics, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Suphakit Awiphan
- Data Science Research Center, Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand.,Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Juthamas Inchai
- Division of Pulmonary, Critical Care and Allergy, Department of Internal Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Ratirat Worasuthaneewan
- Sleep Disorder Center, Center for Medical Excellence, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Theerakorn Theerakittikul
- Division of Pulmonary, Critical Care and Allergy, Department of Internal Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand.,Sleep Disorder Center, Center for Medical Excellence, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand
| |
Collapse
|