G. Yannis

Temporal Modeling of Heart Rate Variability for Driver Drowsiness Detection with LSTM Networks

A Systematic Review of Traffic Safety Culture in Relation to New Mobility Modes, Technology and Policy Developments

Road safety progress in Europe has slowed as the transport landscape has grown more complex through new mobility modes, advancing vehicle technologies and changing patterns of road use. Traffic Safety Culture (TSC), the shared values, beliefs, attitudes, norms, and patterns of behaviour that shape how traffic safety is...

Road users' safety attitudes towards speeding across 39 countries.

Speeding remains a major contributor to road traffic crash risk and injury severity, yet its behavioural, attitudinal, and cultural determinants vary across populations and contexts. This study analyses speeding-related behaviours and safety attitudes using the ESRA3 survey, a harmonised international questionnaire adm...

Improving risky driving behavior classification via conditional GAN-augmented hybrid machine learning models: a two-country naturalistic driving study

A hybrid machine learning pipeline that combines Conditional Generative Adversarial Networks (cGANs) for creating realistic synthetic samples with robust classifiers, including an XGBoost-Random Forest ensemble, a Recurrent Neural Network boosted by AdaBoost, and dedicated GAN-driven models is introduced.

Evaluating Risky Driving Behavior Using a Naturalistic Driving Dataset: A Hybrid Modelling Approach

Three hybrid machine learning models are developed and evaluated to classify risky driving behavior into three safety levels using naturalistic driving data from Belgium and the UK, supporting the potential of hybrid deep learning models in improving road safety by accurately detecting risky driving behaviors.