Importance of subject-dependent classification and imbalanced distributions in driver sleepiness detection in realistic conditions

Publisher's full text
Claudia Sofia Silveira
Jaime S. Cardoso
Andre L. Lourenco

The first in-depth study on the use of electrocardiogram and electrooculogram for subject-dependent classification in driver sleepiness/fatigue under realistic driving conditions is presented in this work. Since acquisitions in simulated environments may be misleading for sleepiness assessment, performing studies on road are required. For that purpose, the authors present a database resulting from a field driving study performed in the SleepEye project. Based on previous research, supervised machine learning methods are implemented and applied to 16 heart- and 25 eye-based extracted features, mostly related to heart rate variability and blink events, respectively, in order to study the influence of subject dependency in sleepiness classification, using different classifiers and dealing with imbalanced class distributions. Results showed a significantly worse performance in subject-independent classification: a decrease of similar to 40 and 20% in the detection rate of the 'sleepy' class for two and three classes, respectively. Since physiological signals are the ones that present the most individual characteristics, a subject-independent classification can be even harder to perform. Transfer learning techniques and methods for imbalanced distributions are promising approaches and need further investigation.



Social sustainability and just mobility

Welcome to a research workshop on Social sustainability and just mobility, 8–9 October 2019 in Linköping, Sweden

European Road Profile User's Group, ERPUG

Welcome to the sixth ERPUG meeting in Vilnius, Lithuania. 

Vision Zero for Sustainable Road Safety in the Baltic Sea Region

The second Vision Zero for Sustainable Road Safety in the Baltic Sea Region conference will be held in Tallinn, Estonia. VTI is part of the programme committee. 



Knowledge in the fight against microplastics from road traffic

The Government has commissioned VTI to develop and disseminate knowledge regarding the emission of microplastics from road traffic.


How to make autonomous vehicles coexist with other traffic

The road infrastructure must be prepared for self-driving vehicles – especially in the beginning when the concepts are still new. Researchers are contributing to this through CoEXist, an EU-funded research project in which VTI participates as the largest...


Electric roads: ‘Standardisation is an important factor for a future European transport system’

VTI employees recently arranged a workshop in Brussels on the standardisation of Electric Road Systems (ERS). ERS has become increasingly relevant as a possible method for reducing the transport sector's environmental impacts, especially in terms of climate...


Research on passenger and freight transport research

Shift2Rail is a European railway project that works actively to create innovations within the railway sector. IMPACT-2 is a project within Shift2Rail that follows and evaluates the innovation projects. How are the innovations coming along? Are they beneficial...


How vehicles can avoid accidents on newly paved roads

Friction is an important property for road safety. VTI has investigated how roads change in the first few weeks after surfacing work has been completed. Researchers recommend posting warning signs when the road is opened and waiting at least three weeks to...


VTI contributes to study on older drivers and accidents

On behalf of and in collaboration with the Swedish Transport Agency, VTI has carried out a study of older drivers and the link between illness and traffic accidents. The Transport Agency has now published the results.