Application of machine learning techniques in vehicle collision detection

Application of machine learning techniques in vehicle collision detection

Vehicle accidents are still happening daily even with the existing technological support provided. This can be due to limitations of the technology and/or human error. Using a newer technology, the vehicle-to-everything communication, the aim is to use machine learning techniques to make predi...

Full description

Saved in:
Bibliographic Details
Main Author: Low, Xian Hao
Other Authors: Guan Yong Liang
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Online Access:https://hdl.handle.net/10356/158253
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Vehicle accidents are still happening daily even with the existing technological support provided. This can be due to limitations of the technology and/or human error. Using a newer technology, the vehicle-to-everything communication, the aim is to use machine learning techniques to make predictions on GPS data, in order to provide an early collision warning system. With such a system in place, drivers would be alerted if a collision might happen several seconds prior and be mentally prepared for the potential threat. The algorithms explored in this study is the multi-layered perceptron classifier, random forest and Tabnet.

Similar Items