Importance of subject‐dependent classification and imbalanced distributions in driver sleepiness detection in realistic conditions. Issue 2 (30th October 2018)

• Record Type: Journal Article
• Authors: Silveira, Cláudia Sofia; Cardoso, Jaime S.; Lourenço, André L.; Ahlström, Christer
• Is Part Of: IET intelligent transport systems. Volume 13:Issue 2(2019)
• Page Start: 347
• Page End: 355
• Publication Date: 2018-10-30
• Subjects: medical signal processing -- medical signal detection -- cardiology -- learning (artificial intelligence) -- electro‐oculography -- eye -- electrocardiography -- feature extraction -- pattern classification -- signal classification; subject‐dependent classification -- imbalanced distributions -- driver sleepiness detection -- realistic conditions -- in‐depth study -- electrocardiogram -- electrooculogram -- driver sleepiness/fatigue -- realistic driving conditions -- sleepiness assessment -- supervised machine learning methods -- 25 eye‐based extracted features -- heart rate variability -- subject dependency -- sleepiness classification -- imbalanced class distributions -- worse performance -- subject‐independent classification -- detection rate; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2018.5284
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : 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.