Stationary gaze entropy predicts lane departure events in sleep-deprived drivers

Abstract

Performance decrement associated with sleep deprivation is a leading contributor to traffic accidents and fatalities. While current research has focused on eye blink parameters as physiological indicators of driver drowsiness, little is understood of how gaze behaviour alters as a result of sleep deprivation. In particular, the effect of sleep deprivation on gaze entropy has not been previously examined. In this randomised, repeated measures study, 9 (4 male, 5 female) healthy participants completed two driving sessions in a fully instrumented vehicle (1 after a night of sleep deprivation and 1 after normal sleep) on a closed track, during which eye movement activity and lane departure events were recorded. Following sleep deprivation, the rate of fixations reduced while blink rate and duration as well as saccade amplitude increased. In addition, stationary and transition entropy of gaze also increased following sleep deprivation as well as with amount of time driven. An increase in stationary gaze entropy in particular was associated with higher odds of a lane departure event occurrence. These results highlight how fatigue induced by sleep deprivation and time-on-task effects can impair drivers’ visual awareness through disruption of gaze distribution and scanning patterns.

New Measures of Visual Scanning Efficiency and Cognitive Effort

“…As a matter of fact, our idea resides in that the visual scanning is a behavior directed by the driving task, as a combination of top-down and bottom-up influences; this has been widely accepted in literature [3]. As discussed above and, as commonly known in relevant research [1], the visual scanning behavior plays a very important role in performing a sensorimotor task (such as driving), this paper calculates how much correlation there exists between visual scanning efficiency and driving performance, as an evaluation of the proposed VSE .…”

“…Indeed, the entropy based measures express the concept of complexity, which is essentially different from our proposed VSE . Concretely, GTE is a powerful estimator of the complexity for transition pattern [1] [2], but not of the efficiency for the whole visual scanning procedure. Similarly, SGE [13] and EoFS [12] give the complexity for spatial patterns of fixations and of fixation sequences, respectively.…”

“…EoFS has not been indicated to have correlation with the task performance. It has been reported that GTE [1] could not predict the performance of sensorimotor tasks. As for SGE , it relates to the complexity of visual content, but can not indicate the performance of task directed sensorimotor activities [3].…”

Quantifying the Predictability of Visual Scanpaths Using Active Information Storage

“…The analysis of scanpaths has gained renewed interest in recent years, for example, to study cognitive function [ 7 , 8 ], personality traits [ 9 , 10 ], or as marker in gaze-based applications [ 11 ]. In particular, information-theoretic measures have become a popular tool for studying cognitive function through the analysis of human gaze behavior [ 5 , 8 , 12 , 13 , 14 , 15 , 16 , 17 ]. A commonly used measure is the (gaze) transition entropy (GTE) [ 17 ], which uses a conditional Shannon Entropy [ 18 ] to describe the regularity of transitions between fixations of pre-defined areas of interest (AOI) [ 5 ].…”

“…Low GTE—and thus a low remaining uncertainty about the location of the next fixation given the previous one—thereby is interpreted as a high predictability of the next fixation [ 5 ]. GTE has been applied in various studies (see [ 5 ] for a review), which have shown that changes in GTE are associated with higher task demand [ 13 , 19 , 20 ], increased anxiety [ 21 , 22 , 23 ], or sleep deprivation [ 14 ].…”