NORMA eResearch @NCI Library

Navigation System To Avoid Accident Prone Areas Using Machine Learning Techniques

Murali, Saikrishnan (2022) Navigation System To Avoid Accident Prone Areas Using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (3MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


One of the most common ways in which individuals are affected is by road traffic accidents, which are more likely to occur in areas with excessive traffic or poor roadway management. The best way to avoid accidents is to avoid these regions and travel along a safer route. The aim of this research is to develop a navigation system using machine learning that avoids accident-prone areas. The research data comprises of daily accident reports with location details acquired from the City of Chicago website, which is an open repository. By using classification models such as Logistic Regression, Decision Trees, and Random Forests, the severity of the accident can be determined. The optimal model determined is Random Forest which has a accuracy, precision, and recall, scores of 94%, 94% and 91% respectively. Once the severity is determined, the parameters that have the greatest effect on severity will be identified. The risk score for each location will be determined on the basis of those parameters, using multiple linear regression. Using the KNN clustering technique, distinct areas or clusters will be identified on the basis of the co-ordinates and the risk score of the location. The machine learning model’s outputs will be fed into the open route service (ORS), and depending on the mode of transportation, the route map, instructions, and time required for each stage of the journey will be provided. The model developed in this research project can be implemented in real time to ensure people travel safely and minimize traffic accidents.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Accidents; Logistic Regression; Decision Tree Classifier; Random Forest Classifier; Severity; Multiple Linear Regression; Risk Score; K-Means Clustering; Accident Prone Area; Navigation System
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > TE Highway engineering. Roads and pavements
T Technology > TL Motor vehicles. Aeronautics. Astronautics
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 23 Feb 2023 16:29
Last Modified: 02 Mar 2023 08:39

Actions (login required)

View Item View Item