December 2022
Volume 22, Issue 14
Open Access
Vision Sciences Society Annual Meeting Abstract  |   December 2022
Seeing the Forrest through the trees: Random forests predict heart rate based on oculomotor features during film viewing
Author Affiliations & Notes
  • Alex Hoogerbrugge
    Department of Experimental Psychology, Helmholtz Institute, Utrecht University, Netherlands
  • Christoph Strauch
    Department of Experimental Psychology, Helmholtz Institute, Utrecht University, Netherlands
  • Zoril A Oláh
    Department of Experimental Psychology, Helmholtz Institute, Utrecht University, Netherlands
  • Edwin S Dalmaijer
    School of Psychological Science, University of Bristol, United Kingdom
  • Tanja CW Nijboer
    Department of Experimental Psychology, Helmholtz Institute, Utrecht University, Netherlands
    Center of Excellence for Rehabilitation Medicine, UMC Utrecht Brain Center, University Medical Center Utrecht, De Hoogstraat Rehabilitation, Netherlands
    Department of Rehabilitation, Physical Therapy Science & Sports, UMC Utrecht Brain Center, University Medical Center Utrecht, Netherlands
  • Stefan Van der Stigchel
    Department of Experimental Psychology, Helmholtz Institute, Utrecht University, Netherlands
  • Footnotes
    Acknowledgements  This work was supported by ERC under Grant [ERC-CoG-863732]
Journal of Vision December 2022, Vol.22, 3486. doi:https://doi.org/10.1167/jov.22.14.3486
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Alex Hoogerbrugge, Christoph Strauch, Zoril A Oláh, Edwin S Dalmaijer, Tanja CW Nijboer, Stefan Van der Stigchel; Seeing the Forrest through the trees: Random forests predict heart rate based on oculomotor features during film viewing. Journal of Vision 2022;22(14):3486. https://doi.org/10.1167/jov.22.14.3486.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

The degree of a person’s arousal, such as excitedness, anxiousness, or mental effort, impacts their ability to execute tasks correctly and safely, and can influence their mental health. Fluctuations in arousal can be detected from various sources such as fMRI, EEG, or skin conductance, but these methods require physical interaction between the device and the participant, which can be obtrusive and time-consuming to set up. Eye tracking can be performed remotely and unobtrusively, and there is evidence that oculomotor features such as fixations, smooth pursuit events, and saccades can be indicative of mental effort, motivation, or task type. In the current study we propose that a wide range of oculomotor features can provide sufficient information to accurately predict fluctuations in one of the most robust central indicators of arousal: heart rate. Using the studyforrest dataset, we demonstrate that traditional regression models cannot sufficiently predict heart rate as a continuous variable from oculomotor features, but that a Random Forest binary classifier could predict high versus low heart rates at well above chance level. The current study provides a first step towards a novel method of remotely and unobtrusively predicting fluctuations in heart rate, which can have implications for human-computer interaction, psychophysics, and other fields of research.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×