Classifying, Understanding, and Mimicking Driver Behaviour from Sensor Data Using LSTM-Based Models for Autonomous Driving

Dilekmen, Metehan (2025) Classifying, Understanding, and Mimicking Driver Behaviour from Sensor Data Using LSTM-Based Models for Autonomous Driving. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (800kB) | Preview

Abstract

The automatic detection of vehicle driving behaviour is an important step towards driver assistance systems and autonomous vehicle technologies. In this project, a model has been developed that uses physical data generated during driving to determine the driver's behaviour pattern.

The primary driving behaviours targeted are classified as aggressive, drowsy, and normal. The model aims to identify these behaviours and establish a system capable of making human-like decisions. In addition to classical methods, deep learning models that work on time series data were also used in the study. The system was tested using data obtained from real driving and achieved various classification successes. The model was tested in different driving scenarios and made incorrect predictions in some cases due to external factors. This showed that systems based solely on physical data may be limited.

This project demonstrates the potential of artificial intelligence-based classification systems to mimic human behaviour, while also pointing to future needs for the development of such systems.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Vamadevan, Arundev UNSPECIFIED
Uncontrolled Keywords:	Driver Behaviour Classification; LSTM-Based Deep Learning; Driving Pattern Recognition; Aggressive and Calm Driving Detection; Explainable AI in Autonomous Vehicles
Subjects:	T Technology > TL Motor vehicles. Aeronautics. Astronautics Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	12 Aug 2026 08:50
Last Modified:	12 Aug 2026 08:50
URI:	https://norma.ncirl.ie/id/eprint/9504

Actions (login required)

View Item