Machine Learning Insights on Driving Behaviour Dynamics among Germany, Belgium, and UK Drivers

Aug 4, 2026

Upload by Riley

The i-DREAMS project aims to create a context-aware “Safety Tolerance Zone” (STZ) that keeps drivers within safe operational boundaries. This research compares two machine learning methods—long short-term memory networks and shallow neural networks—to assess safety levels during natural driving in i-DREAMS on-road field trials. Data comprise trips from 30 German drivers, 43 Belgian drivers, and 26 UK drivers, enabling stage-wise identification of factors linked to unsafe driving behaviour. Results show i-DREAMS real-time interventions and post-trip assessments improve driving behaviour, and neural networks outperform other algorithms in this setting.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Project objective and STZ framework

Comparative methods: LSTM vs shallow neural networks

Naturalistic trials and dataset by country

sustainability Article Machine Learning Insights on Driving Behaviour Dynamics among Germany, Belgium, and UK Drivers Stella Roussou 1, *, Thodoris Garefalakis 1, Eva Michelaraki 1, Tom Brijs 2 and George Yannis 1 Citation: Roussou, S.; Garefalakis, T.; Michelaraki, E.; Brijs, T.; Yannis, G. Machine Learning Insights on Driving Behaviour Dynamics among Germany, Belgium, and UK Drivers. Sustainability 2024, 16, 518 . [https://doi.org/10.3390/su16020518](https://doi.org/10.3390/su16020518) Academic Editors: Evangelos Bekiarisand Maria Gkemou Received: 9 November 2023 Revised: 28 December 2023 Accepted: 4 January 2024 Published: 7 January 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Transportation Planning and Engineering, National Technical University of Athens, 5 Iroon Polytechniou Str., 15773 Athens, Greece; [tgarefalakis@mail.ntua.gr](tgarefalakis@mail.ntua.gr) (T.G.); [evamich@mail.ntua.gr](evamich@mail.ntua.gr) (E.M.); [geyannis@central.ntua.gr](geyannis@central.ntua.gr) (G.Y.) 2 Transportation Research Institute (IMOB), School of Transportation Sciences, UHasselt–Hasselt University, 3500 Hasselt, Belgium; [tom.brijs@uhasselt.be](tom.brijs@uhasselt.be) * Correspondence: [s_roussou@mail.ntua.gr](s_roussou@mail.ntua.gr) Abstract: The i-DREAMS project has a core objective: to establish a comprehensive framework that defines, develops, and validates a context-aware ‘Safety Tolerance Zone’(STZ) . This zone is crucial for maintaining drivers within safe operational boundaries. The primary focus of this research is to conduct a detailed comparison between two machine learning approaches: long short-term memory networks and shallow neural networks. The goal is to evaluate the safety levels of participants as they engage in natural driving experiences within the i-DREAMS on-road field trials. To accomplish this objective, the study gathered a series of trips from a sample group consisting of 30 German drivers, 43 Belgian drivers, and 26 drivers from the United Kingdom. These trips were then input into the aforementioned machine learning methods to reveal the factors contributing to unsafe driving behaviour across various experiment stages. The results obtained highlight the significant positive impact of i-DREAMS’real-time interventions and post-trip assessments on enhancing driving behaviour. Furthermore, it is worth noting that neural networks demonstrated superior performance compared to other algorithms considered within this research context. Keywords: driving behaviour; road safety; long short-term memory network; neural network; machine learning techniques 1. Introduction Road safety stands as a critical worldwide concern, with an alarming annual toll resulting in around 1.3 million lives lost and numerous injuries due to road crashes [1] . These occurrences are shaped by a variety of elements, including human conduct, road layout, safety attributes of vehicles, environmental circumstances, and socioeconomic differences [1] . Emphasising the crucial contribution of drivers to the happening and intensity of road accidents is essential. A considerable part of these incidents can be linked to driving behaviour, underscoring the pivotal role of drivers in research on traffic safety [2] . Acknowledging the seriousness of this concern, the European Union and the World Health Organization have established ambitious objectives to halve fatal traffic accidents from 2021 to 2030 . Emerging technology is anticipated to play a crucial role in realising these advancements in road safety [3] . Road safety is influenced by a range of risk factors, encompassing the driver’s

FAQs

What is the core objective of the i-DREAMS project in this study?

To establish a context-aware “Safety Tolerance Zone” (STZ) that maintains drivers within safe operational boundaries during driving.

Which two machine learning approaches are compared, and what is the evaluation goal?

Long short-term memory networks and shallow neural networks are compared to evaluate participants’ safety levels during naturalistic on-road field trials and to identify factors behind unsafe behaviour.

How was the driving data collected, and from which driver groups?

The study collected driving trips from naturalistic field trials involving 30 German drivers, 43 Belgian drivers, and 26 drivers from the United Kingdom.

Aug 4, 2026

Upload by Riley