Spatio-temporal analysis of road traffic accidents in Tunisia

Turki, Zeineb; Ghedira, Aymen; Ouni, Fedy; Kahloul, Amani

doi:10.1109/logistiqua55056.2022.9938067

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They reveal connections between spatial phenomena that may remain hidden when using non-spatial databases [28,29]. In recent decades, a plethora of studies has explored the application of GIS in traffic safety and accident analysis, with numerous organizations and researchers documenting its efficacy [30,31]. Such analyses encompass various techniques, including intersection analysis [32], segment analysis [33], cluster analysis [34], and density analysis modeling [34].…”

Section: Literature Review 21 Traditional Methods For Black Spot Iden...mentioning

confidence: 99%

Leveraging Positive-Unlabeled Learning for Enhanced Black Spot Accident Identification on Greek Road Networks

Sevetlidis,

Pavlidis,

Mouroutsos

et al. 2024

Computers

View full text Add to dashboard Cite

Identifying accidents in road black spots is crucial for improving road safety. Traditional methodologies, although insightful, often struggle with the complexities of imbalanced datasets, while machine learning (ML) techniques have shown promise, our previous work revealed that supervised learning (SL) methods face challenges in effectively distinguishing accidents that occur in black spots from those that do not. This paper introduces a novel approach that leverages positive-unlabeled (PU) learning, a technique we previously applied successfully in the domain of defect detection. The results of this work demonstrate a statistically significant improvement in key performance metrics, including accuracy, precision, recall, F1-score, and AUC, compared to SL methods. This study thus establishes PU learning as a more effective and robust approach for accident classification in black spots, particularly in scenarios with highly imbalanced datasets.

show abstract

Section: Literature Review 21 Traditional Methods For Black Spot Iden...mentioning

confidence: 99%

Leveraging Positive-Unlabeled Learning for Enhanced Black Spot Accident Identification on Greek Road Networks

Sevetlidis,

Pavlidis,

Mouroutsos

et al. 2024

Computers

View full text Add to dashboard Cite

show abstract

“…The Kernel Density Estimation (KDE) method has been effectively utilized to detect concentrated areas of road accidents during peak time periods, predict hourly trends in pedestrian-vehicle collisions, and investigate temporal fluctuations in high-risk locations [8] . Moreover, a separate study introduces the innovative concept of "hazardous probable lengths," aimed at predicting future traffic crashes and enhancing the ability to examine specific lanes for potential hazards [9] . Furthermore, additional studies employ the Spatial Data Analysis Method, specifically Moran's I and Getis-Ord, to effectively identify spatial concentration locations of "black zones" associated with road accidents and further classifying them based on their respective danger levels [10,11] .…”

Section: Introductionmentioning

confidence: 99%

Exploring traffic accidents patterns: Spatial distribution and socio-economic determinants

Abdullah,

Sipos

2023

View full text Add to dashboard Cite

<p class="Els-keywords">This study employs a machine learning methodology, specifically the decision tree algorithm, in conjunction with the Quantum Geographic Information System (QGIS), to conduct a rigorous analysis of traffic accident data. The research aims to investigate various factors associated with traffic accidents, with a particular emphasis on their spatial distribution and the socio-economic determinants contributing to recurring accidents caused by drivers. The study focuses on the city of Duhok, located in the Kurdistan Region of Iraq, and utilizes a questionnaire to collect data from drivers regarding accident locations and the frequency of accidents within the past decade (from 2010 to 2020). The findings of the study reveal that the city center experiences the highest concentration of accidents, while severe collisions tend to occur in specific “black spots” scattered across the city’s road network. The decision tree model, employed to classify drivers with multiple accidents, identifies the primary causes of accidents as traffic conditions, traffic law violations, and overspeeding. Furthermore, the accident locations are found to be influenced by various factors, including different types of road hierarchy. The age and gender of drivers also contribute to accident patterns. These research findings have practical implications for enhancing road safety measures and reducing the frequency of traffic accidents. The utilization of machine learning techniques, combined with the analysis of spatial data through QGIS, provides a comprehensive understanding of the underlying factors contributing to accidents. Moreover, this research contributes novel insights to the field of road traffic accidents and safety, particularly in the context of the city of Duhok in Kurdistan Region, Iraq, and provides a valuable reference for future studies in the domain of road safety and urban planning.</p>

show abstract

Spatio-temporal analysis of road traffic accidents in Tunisia

Cited by 2 publications

References 14 publications

Leveraging Positive-Unlabeled Learning for Enhanced Black Spot Accident Identification on Greek Road Networks

Leveraging Positive-Unlabeled Learning for Enhanced Black Spot Accident Identification on Greek Road Networks

Exploring traffic accidents patterns: Spatial distribution and socio-economic determinants

Contact Info

Product

Resources

About