Dataset Information

Automatic detection of mind wandering in a simulated driving task with behavioral measures.

ABSTRACT: Mind wandering (MW) is extremely common during driving and is often accompanied by performance losses. This study investigated the use of driving behavior measurements to automatically detect mind wandering state in the driving task. In the experiment, participants (N = 40) performed a car-following task in a driving simulator and reported, upon hearing a tone, whether they were experiencing mind wandering or not. Supervised machine learning techniques were applied to classify MW-absent versus MW-present state, using both driver-independent and driver-dependent modeling methods. In the driver-independent modeling, we separately built models for participants with high or low MW and participants with medium MW. The optimal models can not offer a significant improvement than other models. So building effective driver-independent models with the leave-one-participant-out cross-validation method is challenging. In the driver-dependent modeling, we built models for each participant with medium MW. The best models of some participants were effective. The results indicate the development of mind wandering detecting system should take into account both inter-individual and intra-individual difference. This study provides a step toward minimizing the negative impacts of mindless driving and should benefit other fields of psychological research.

SUBMITTER: Zhang Y

PROVIDER: S-EPMC6231636 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic detection of mind wandering in a simulated driving task with behavioral measures.

Zhang Yuyu Y Kumada Takatsune T

PloS one 20181112 11

Mind wandering (MW) is extremely common during driving and is often accompanied by performance losses. This study investigated the use of driving behavior measurements to automatically detect mind wandering state in the driving task. In the experiment, participants (N = 40) performed a car-following task in a driving simulator and reported, upon hearing a tone, whether they were experiencing mind wandering or not. Supervised machine learning techniques were applied to classify MW-absent versus M ...[more]

PMID: 30419060

Similar Datasets

Project description:A significant body of literature supports the contention that pupil size varies depending on cognitive load, affective state, and level of drowsiness. Here we assessed whether oculometric measures such as gaze position, blink frequency and pupil size were correlated with the occurrence and time course of self-reported mind-wandering episodes. We recorded the pupil size of two subjects engaged in a monotonous breath counting task while keeping their eyes on a fixation cross. This task is conducive to producing mind-wandering episodes. Each subject performed ten 20-min sessions, for total duration of about 4 h. Subjects were instructed to report spontaneous mind-wandering episodes by pressing a button when they lost count of their breath. After each button press, subjects filled in a short questionnaire describing the characteristics of their mind-wandering episode. We observed larger pupil size during the breath-focusing period compared to the mind-wandering period (p < 0.01 for both subjects). Our findings contradict previous research showing a higher baseline pupil size during mind wandering episodes in visual tasks. We discuss possible explanations for this discrepancy. We also analyzed nine other oculometric measures including blink rate, blink duration and gaze position. We built a support vector machine (SVM) classifier and showed that mean pupil size was the most reliable predictor of mind wandering in both subjects. The classification accuracy of mind wandering data segments vs. breath-focusing data segments was 81% for the first subject and 77% for the second subject. Additionally, we analyzed oculometric measures in light of the phenomenological data collected in the questionnaires. We showed that how well subjects remembered their thoughts while mind wandering was positively correlated with pupil size (subject 1, p < 0.001; subject 2, p < 0.05). Feelings of well being were also positively correlated with pupil size (subject 1, p < 0.001; subject 2, p < 0.001). Our results suggest that oculometric data could be used as a neurocognitive marker of mind-wandering episodes.

Dataset Information

Automatic detection of mind wandering in a simulated driving task with behavioral measures.

Publications

Automatic detection of mind wandering in a simulated driving task with behavioral measures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure