Machine Learning for Severity Classification of Accidents Involving Powered Two Wheelers

Hadjidimitriou, Natalia Selini; Lippi, Marco; Dell’Amico, Mauro; Skiera, Alexander

doi:10.1109/tits.2019.2939624

Cited by 28 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis results uncovered that, among the machine learning paradigms considered, the hybrid decision tree-neural network method outperformed others. To classify the crash severity involving Powered Two Wheelers, another work used Logistic Regression, Random Forest, Support Vector Machines, and Deep Neural Network [2]. The authors analyzed the prediction of the models in the full set of attributes and some reduced attributes.…”

Section: Related Workmentioning

confidence: 99%

“…Recent research has focused on the prediction of collision severity using machine learning methods [1], [2]. Moreover, some works have also identified and analyzed multiple factors associated with the severity of the crash [3], [4], [5].…”

Section: Introductionmentioning

confidence: 99%

“…Previous works with deep learning have used the dataset with four thousand to four hundred and ten thousand records from a 2-8 years period [2], [7], [8], [9]. As a contrast, the study in this paper predicts the crash severity by employing traditional and deep learning methods on a large data set with approximately 5.8 million records collected over 20 years.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fatality Prediction for Motor Vehicle Collisions: Mining Big Data Using Deep Learning and Ensemble Methods

Emu

Kamal

Choudhury

et al. 2022

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Motor vehicle crashes are one of the most common causes of fatalities on the roads. Real-time severity prediction of such crashes may contribute towards reducing the rate of fatality. In this study, the fundamental goal is to develop machine learning models that predict whether the outcome of a collision will be fatal or not. A Canadian road crash dataset containing 5.8 million records is utilized in this research. In this study, ensemble models have been developed using majority and soft voting to address the class imbalance in the dataset. The prediction accuracy of approximately 75% is achieved using Convolutional Neural Networks. Moreover, a comprehensive analysis of the attributes that are important in distinguishing between fatal vs. non-fatal motor vehicle collisions has been presented in this paper. In-depth information content analysis reveals the factors that contribute the most in the prediction model. These include roadway characteristics and weather conditions at the time of the crash, vehicle type, time when the collision happen, road user class and their position, any safety device used, and the status of traffic control. With real-time data based on weather and road conditions, an automated warning system can potentially be developed utilizing the prediction model employed in this study.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fatality Prediction for Motor Vehicle Collisions: Mining Big Data Using Deep Learning and Ensemble Methods

Emu

Kamal

Choudhury

et al. 2022

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…The proposition of data mining and machine learning algorithm has offered an innovative and effective way for research of traffic accident severity [15][16][17][18][19][20][21][22]. AlKheder applied Decision Tree, Bayesian Network and linear Support Vector Machine to analyze the traffic accidents' severities, and found that Bayesian network has the optimal prediction accuracy, and road and accident type were the most important features for the model [15].…”

Section: Introductionmentioning

confidence: 99%

“…AlKheder applied Decision Tree, Bayesian Network and linear Support Vector Machine to analyze the traffic accidents' severities, and found that Bayesian network has the optimal prediction accuracy, and road and accident type were the most important features for the model [15]. Hadjidimitriou conducted different machine learning algorithms, such as random forest, support vector machine and deep networks, to classify the severity of accidents [16]. Ji compared multiple machine learning models and concluded that ensemble learning models outperformed individual models [17].…”

Section: Introductionmentioning

confidence: 99%

Analysis and Visualization of Accidents Severity Based on Lightgbm-Tpe

Liu

2022

SSRN Journal

View full text Add to dashboard Cite

Performance Analysis of Machine Learning and Deep Learning Algorithms for Smart Cities: The Present State and Future Directions

Bedi¹,

Goyal²,

Islam³

et al. 2022

Cognitive Computing Models in Communication Systems

View full text Add to dashboard Cite

Machine Learning for Severity Classification of Accidents Involving Powered Two Wheelers

Cited by 28 publications

References 34 publications

Fatality Prediction for Motor Vehicle Collisions: Mining Big Data Using Deep Learning and Ensemble Methods

Fatality Prediction for Motor Vehicle Collisions: Mining Big Data Using Deep Learning and Ensemble Methods

Analysis and Visualization of Accidents Severity Based on Lightgbm-Tpe

Performance Analysis of Machine Learning and Deep Learning Algorithms for Smart Cities: The Present State and Future Directions

Contact Info

Product

Resources

About