Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians

Yang, Lei; Aghaabbasi, Mahdi; Ali, Mujahid; Jan, Amin; Bouallegue, Belgacem; Javed, Muhammad Faisal; Salem, Nermin M.

doi:10.3390/su141710467

Open AccessArticle

Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians

by

Lei Yang

^1,*,

Mahdi Aghaabbasi

^2,*

,

Mujahid Ali

³

,

Amin Jan

⁴

,

Belgacem Bouallegue

^5,6,

Muhammad Faisal Javed

⁷

and

Nermin M. Salem

⁸

¹

Department of Computer Science and Technology, Lyuliang University, Lvliang 033000, China

²

Transportation Institute, Chulalongkorn University, Bangkok 10330, Thailand

³

Department of Civil and Environmental Engineering, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia

⁴

Faculty of Hospitality, Tourism and Wellness, Universiti Malaysia Kelantan, City Campus, Kota Bharu 16100, Malaysia

⁵

College of Computer Science, King Khalid University, Abha 62529, Saudi Arabia

⁶

Electronics and Micro-Electronics Laboratory (E. μ. E. L.), Faculty of Sciences of Monastir, University of Monastir, Monastir 09023, Tunisia

⁷

Department of Civil Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad 22060, Pakistan

⁸

Electrical Engineering, Faculty of Engineering and Technology, Future University in Egypt, New Cario 11835, Egypt

^*

Authors to whom correspondence should be addressed.

Sustainability 2022, 14(17), 10467; https://doi.org/10.3390/su141710467

Submission received: 8 July 2022 / Revised: 11 August 2022 / Accepted: 11 August 2022 / Published: 23 August 2022

(This article belongs to the Special Issue Urban Design, Urban Planning and Traffic Safety)

Download

Browse Figures

Versions Notes

Abstract

Over the past three decades, more than 8000 pedestrians have been killed in Australia due to vehicular crashes. There is a general assumption that pedestrians are often the most vulnerable to crashes. Sustainable transportation goals are at odds with the high risk of pedestrian fatalities and injuries in car crashes. It is imperative that the reasons for pedestrian injuries be identified if we are to improve the safety of this group of road users who are particularly susceptible. These results were obtained mostly through the use of well-established statistical approaches. A lack of flexibility in managing outliers, incomplete, or inconsistent data, as well as rigid pre-assumptions, have been criticized in these models. This study employed three well-known machine learning models to predict road-crash-related pedestrian fatalities (RCPF). These models included support vector machines (SVM), ensemble decision trees (EDT), and k-nearest neighbors (KNN). These models were hybridized with a Bayesian optimization (BO) algorithm to find the optimum values of their hyperparameters, which are extremely important to accurately predict the RCPF. The findings of this study show that all the three models’ performance was improved using the BO. The KNN model had the highest improvement in accuracy (+11%) after the BO was applied to it. However, the ultimate accuracy of the SVM and EDT models was higher than that of the KNN model. This study establishes the framework for employing optimized machine learning techniques to reduce pedestrian fatalities in traffic accidents.

Keywords: road-crash-related pedestrian fatalities; Bayesian optimization algorithm; hyperparameters; sustainable safety of pedestrians

Share and Cite

MDPI and ACS Style

Yang, L.; Aghaabbasi, M.; Ali, M.; Jan, A.; Bouallegue, B.; Javed, M.F.; Salem, N.M. Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians. Sustainability 2022, 14, 10467. https://doi.org/10.3390/su141710467

AMA Style

Yang L, Aghaabbasi M, Ali M, Jan A, Bouallegue B, Javed MF, Salem NM. Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians. Sustainability. 2022; 14(17):10467. https://doi.org/10.3390/su141710467

Chicago/Turabian Style

Yang, Lei, Mahdi Aghaabbasi, Mujahid Ali, Amin Jan, Belgacem Bouallegue, Muhammad Faisal Javed, and Nermin M. Salem. 2022. "Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians" Sustainability 14, no. 17: 10467. https://doi.org/10.3390/su141710467

APA Style

Yang, L., Aghaabbasi, M., Ali, M., Jan, A., Bouallegue, B., Javed, M. F., & Salem, N. M. (2022). Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians. Sustainability, 14(17), 10467. https://doi.org/10.3390/su141710467

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI