Citation

Ahammad SH, Sukesh M, Narender M, Ettyem SA, Al-Majdi K, Saikumar K, Sharma DK, Peng SL, Sharma R, Jeon G. Lect. Notes Netw. Syst. 2023; 617: 367-377.

Copyright

(Copyright © 2023, Holtzbrinck Springer Nature Publishing Group)

DOI

10.1007/978-981-19-9512-5_34

PMID

unavailable

Abstract

The expansion of nations and communities has resulted in a variety of externalities, such as an increase in traffic accidents. Many attempts have been undertaken to minimize the injuries and fatalities and their intensity. Traffic safety modeling is a most significant technique to motivate harmless mobility because it is capable of the creation of Crash Prediction Models (CPMs) as well as the investigation of the fundamentals that contribute to the incidence of crashes. Statistical modeling has been utilized in this process in the past, regardless of the fact that they are aware of the limits of this sort of strategy which allows you to experiment with other options, such as using machine learning approaches. Machine learning approaches applied to collision datasets can assist researchers in better knowing the features of motorist behavior, highway surroundings, and meteorological circumstances that are linked to varying mortality risk levels. If we build a reliable predictive model capable of automatically classifying the degree of injury in diverse traffic accidents, we may be able to discover patterns involved in severe wrecks. These patterns of behavior and road accidents can be used to design traffic safety rules.

Language: en

Keywords

Safety; Traffic; Machine learning; Crash prediction models; Patterns; Modeling