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

• Published in: IET intelligent transport systems Vol. 13; no. 2; pp. 347 - 355
• Main Authors: Silveira, Cláudia Sofia, Cardoso, Jaime S, Lourenço, André L, Ahlström, Christer
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.02.2019
• Subjects: 25 eye‐based extracted features; 84 Road: Road users; cardiology; Classification; detection rate; Driver; driver sleepiness detection; driver sleepiness/fatigue; Driving (veh); electrocardiogram; Electrocardiography; electrooculogram; electro‐oculography; eye; Eye movement; Fatigue (human); feature extraction; heart rate variability; imbalanced class distributions; imbalanced distributions; In situ; in‐depth study; learning (artificial intelligence); medical signal detection; medical signal processing; pattern classification; realistic conditions; realistic driving conditions; Research Article; signal classification; sleepiness assessment; sleepiness classification; subject dependency; subject‐dependent classification; subject‐independent classification; supervised machine learning methods; worse performance; supervised machine learning methods; electro-oculography; 25 eye-based extracted features; detection rate; worse performance; electrocardiography; sleepiness classification; electrocardiogram; feature extraction; heart rate variability; realistic driving conditions; imbalanced class distributions; subject-independent classification; learning (artificial intelligence); pattern classification; imbalanced distributions; electrooculogram; subject-dependent classification; medical signal detection; driver sleepiness detection; cardiology; signal classification; eye; medical signal processing; in-depth study; subject dependency; driver sleepiness/fatigue; sleepiness assessment; realistic conditions; driver sleepiness; fatigue
• ISSN: 1751-956X; 1751-9578; 1751-9578
• DOI: 10.1049/iet-its.2018.5284

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 ∼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.