A Machine Learning Approach for Classifying Road Accident Hotspots

Amorim, Brunna de Sousa Pereira; Firmino, Anderson Almeida; Baptista, Cláudio de Souza; Bráz, Geraldo; Paiva, Anselmo Cardoso de; Júnior, Francisco Edeverton de Almeida

doi:10.3390/ijgi12060227

Cited by 8 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This machine learning method was instrumental in identifying accident hot spots during peak and off-peak hours. SVM, random forest, and a multi-layer perceptron neural network were used in [51] to classify road accident hot spots on the Brazilian federal road network. The neural network model was notably effective, achieving the highest accuracy of 83% in predicting severe or non-severe accident risks.…”

Section: Machine Learning In Black Spot Identificationmentioning

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: Machine Learning In Black Spot Identificationmentioning

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

“…Improving highway safety is one of the most developed areas of ML application in ITSs. It includes security analysis of the road network and its elements [56][57][58], improving information security in ITSs [59,60], and detecting anomalies in sensor data of connected and autonomous vehicles [61][62][63]. It also involves intelligent analysis of road traffic accidents to identify critical factors in their occurrence, essential for preventing similar incidents in the future [64].…”

Section: Machine Learning For Intelligent Transport System Technologiesmentioning

confidence: 99%

Machine Learning-Driven Calibration of Traffic Models Based on a Real-Time Video Analysis

Lopukhova,

Abdulnagimov,

Voronkov

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Accurate traffic simulation models play a crucial role in developing intelligent transport systems that offer timely traffic information to users and efficient traffic management. However, calibrating these models to represent real-world traffic conditions accurately poses a significant challenge due to the dynamic nature of traffic flow and the limitations of traditional calibration methods. This article introduces a machine learning-based approach to calibrate macroscopic traffic simulation models using real-time traffic video stream data. The proposed method for creating and calibrating a traffic simulation model has significantly improved the statistical correspondence between the generated vehicle characteristics and real data about cars on the simulated road section. The correspondence has increased from 37% to 73%. Machine learning models trained on generated data and tested on real data show improved accuracy rates. Mean absolute error, mean square error, and mean absolute percentage error decreased by more than two orders of magnitude. The coefficient of determination has also increased, approaching 1. This method eliminates the need to deploy wireless sensor networks, which can reduce the cost of implementing intelligent transport systems.

show abstract

“…Amorim et al developed a model using ML algorithms to identify accident hotspots by collecting data on accident dates, road types, and weather conditions. They devised methods for drivers on the Brazilian Federal Highway to alert them to potential highway risk areas in advance [23].…”

Section: Risk Prediction Using Algorithmsmentioning

confidence: 99%

Estimating Accident Reduction Rate after Maritime Traffic Safety Assessment Using Synthetic Minority Oversampling Technique and Machine Learning Algorithm

Won,

Lim,

Kang

2024

Applied Sciences

View full text Add to dashboard Cite

This study was focused on deriving the MTSA-related accident reduction rate (ARR) required to calculate the safety benefits before and after expanding the scope of the system. By performing spatial analysis using geographic information system technology, MTSA-related accidents were identified on maritime routes near both assessed and unassessed project sites from 2010 to 2014. Subsequently, by applying the synthetic minority oversampling technique to balance the data, the algorithm learned from the random forest using the operational data of coastal passenger ship operations and accident data near unassessed locations where MTSA is not implemented. Then, the trained model was applied to predict accident occurrence in the absence of MTSA near the latest operational information of coastal passenger ship operations at the assessed project sites. The MTSA-related ARR was then calculated by applying the actual accident occurrences during operation near the assessed project sites where MTSA was implemented. The MTSA-marine ARR calculated at 17.41% can be applied to the calculation of safety benefit for MTSA. The results of this study can provide quantitative evidence for the application of higher-level systems considering the burden on regulatory targets when improving MTSA or similar systems.

show abstract

A Machine Learning Approach for Classifying Road Accident Hotspots

Cited by 8 publications

References 38 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

Machine Learning-Driven Calibration of Traffic Models Based on a Real-Time Video Analysis

Estimating Accident Reduction Rate after Maritime Traffic Safety Assessment Using Synthetic Minority Oversampling Technique and Machine Learning Algorithm

Contact Info

Product

Resources

About