Prediction of mind-wandering with electroencephalogram and non-linear regression modeling

Issaku Kawashima, Hiroaki Kumano

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Mind-wandering (MW), task-unrelated thought, has been examined by researchers in an increasing number of articles using models to predict whether subjects are in MW, using numerous physiological variables. However, these models are not applicable in general situations. Moreover, they output only binary classification. The current study suggests that the combination of electroencephalogram (EEG) variables and non-linear regression modeling can be a good indicator of MW intensity. We recorded EEGs of 50 subjects during the performance of a Sustained Attention to Response Task, including a thought sampling probe that inquired the focus of attention. We calculated the power and coherence value and prepared 35 patterns of variable combinations and applied Support Vector machine Regression (SVR) to them. Finally, we chose four SVR models: two of them non-linear models and the others linear models; two of the four models are composed of a limited number of electrodes to satisfy model usefulness. Examination using the held-out data indicated that all models had robust predictive precision and provided significantly better estimations than a linear regression model using single electrode EEG variables. Furthermore, in limited electrode condition, non-linear SVR model showed significantly better precision than linear SVR model. The method proposed in this study helps investigations into MW in various little-examined situations. Further, by measuring MW with a high temporal resolution EEG, unclear aspects of MW, such as time series variation, are expected to be revealed. Furthermore, our suggestion that a few electrodes can also predict MW contributes to the development of neuro-feedback studies.

Original languageEnglish
Article number365
JournalFrontiers in Human Neuroscience
Volume11
DOIs
Publication statusPublished - 2017 Jul 12

Fingerprint

Electroencephalography
Electrodes
Linear Models
Nonlinear Dynamics
Research Personnel
Support Vector Machine

Keywords

  • Electroencephalogram
  • Machine learning
  • Mind-wandering
  • Neuro-feedback
  • Support vector machine regression

ASJC Scopus subject areas

  • Neuropsychology and Physiological Psychology
  • Neurology
  • Psychiatry and Mental health
  • Biological Psychiatry
  • Behavioral Neuroscience

Cite this

Prediction of mind-wandering with electroencephalogram and non-linear regression modeling. / Kawashima, Issaku; Kumano, Hiroaki.

In: Frontiers in Human Neuroscience, Vol. 11, 365, 12.07.2017.

Research output: Contribution to journalArticle

@article{6c44d8f9797e49918f9a97f2bad823d9,
title = "Prediction of mind-wandering with electroencephalogram and non-linear regression modeling",
abstract = "Mind-wandering (MW), task-unrelated thought, has been examined by researchers in an increasing number of articles using models to predict whether subjects are in MW, using numerous physiological variables. However, these models are not applicable in general situations. Moreover, they output only binary classification. The current study suggests that the combination of electroencephalogram (EEG) variables and non-linear regression modeling can be a good indicator of MW intensity. We recorded EEGs of 50 subjects during the performance of a Sustained Attention to Response Task, including a thought sampling probe that inquired the focus of attention. We calculated the power and coherence value and prepared 35 patterns of variable combinations and applied Support Vector machine Regression (SVR) to them. Finally, we chose four SVR models: two of them non-linear models and the others linear models; two of the four models are composed of a limited number of electrodes to satisfy model usefulness. Examination using the held-out data indicated that all models had robust predictive precision and provided significantly better estimations than a linear regression model using single electrode EEG variables. Furthermore, in limited electrode condition, non-linear SVR model showed significantly better precision than linear SVR model. The method proposed in this study helps investigations into MW in various little-examined situations. Further, by measuring MW with a high temporal resolution EEG, unclear aspects of MW, such as time series variation, are expected to be revealed. Furthermore, our suggestion that a few electrodes can also predict MW contributes to the development of neuro-feedback studies.",
keywords = "Electroencephalogram, Machine learning, Mind-wandering, Neuro-feedback, Support vector machine regression",
author = "Issaku Kawashima and Hiroaki Kumano",
year = "2017",
month = "7",
day = "12",
doi = "10.3389/fnhum.2017.00365",
language = "English",
volume = "11",
journal = "Frontiers in Human Neuroscience",
issn = "1662-5161",
publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - Prediction of mind-wandering with electroencephalogram and non-linear regression modeling

AU - Kawashima, Issaku

AU - Kumano, Hiroaki

PY - 2017/7/12

Y1 - 2017/7/12

N2 - Mind-wandering (MW), task-unrelated thought, has been examined by researchers in an increasing number of articles using models to predict whether subjects are in MW, using numerous physiological variables. However, these models are not applicable in general situations. Moreover, they output only binary classification. The current study suggests that the combination of electroencephalogram (EEG) variables and non-linear regression modeling can be a good indicator of MW intensity. We recorded EEGs of 50 subjects during the performance of a Sustained Attention to Response Task, including a thought sampling probe that inquired the focus of attention. We calculated the power and coherence value and prepared 35 patterns of variable combinations and applied Support Vector machine Regression (SVR) to them. Finally, we chose four SVR models: two of them non-linear models and the others linear models; two of the four models are composed of a limited number of electrodes to satisfy model usefulness. Examination using the held-out data indicated that all models had robust predictive precision and provided significantly better estimations than a linear regression model using single electrode EEG variables. Furthermore, in limited electrode condition, non-linear SVR model showed significantly better precision than linear SVR model. The method proposed in this study helps investigations into MW in various little-examined situations. Further, by measuring MW with a high temporal resolution EEG, unclear aspects of MW, such as time series variation, are expected to be revealed. Furthermore, our suggestion that a few electrodes can also predict MW contributes to the development of neuro-feedback studies.

AB - Mind-wandering (MW), task-unrelated thought, has been examined by researchers in an increasing number of articles using models to predict whether subjects are in MW, using numerous physiological variables. However, these models are not applicable in general situations. Moreover, they output only binary classification. The current study suggests that the combination of electroencephalogram (EEG) variables and non-linear regression modeling can be a good indicator of MW intensity. We recorded EEGs of 50 subjects during the performance of a Sustained Attention to Response Task, including a thought sampling probe that inquired the focus of attention. We calculated the power and coherence value and prepared 35 patterns of variable combinations and applied Support Vector machine Regression (SVR) to them. Finally, we chose four SVR models: two of them non-linear models and the others linear models; two of the four models are composed of a limited number of electrodes to satisfy model usefulness. Examination using the held-out data indicated that all models had robust predictive precision and provided significantly better estimations than a linear regression model using single electrode EEG variables. Furthermore, in limited electrode condition, non-linear SVR model showed significantly better precision than linear SVR model. The method proposed in this study helps investigations into MW in various little-examined situations. Further, by measuring MW with a high temporal resolution EEG, unclear aspects of MW, such as time series variation, are expected to be revealed. Furthermore, our suggestion that a few electrodes can also predict MW contributes to the development of neuro-feedback studies.

KW - Electroencephalogram

KW - Machine learning

KW - Mind-wandering

KW - Neuro-feedback

KW - Support vector machine regression

UR - http://www.scopus.com/inward/record.url?scp=85027888718&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027888718&partnerID=8YFLogxK

U2 - 10.3389/fnhum.2017.00365

DO - 10.3389/fnhum.2017.00365

M3 - Article

AN - SCOPUS:85027888718

VL - 11

JO - Frontiers in Human Neuroscience

JF - Frontiers in Human Neuroscience

SN - 1662-5161

M1 - 365

ER -