A machine learning approach to predict perceptual decisions: an insight into face pareidolia

Rhiannon Jones, Kasturi Barik, Syed Daimi, Goutam Saha, Joydeep Bhattacharya

Research output: Contribution to journalArticleResearchpeer-review

Abstract

The perception of an external stimulus not only depends upon the characteristics of the stimulus but is also influenced by the ongoing brain activity prior to its presentation. In this work, we directly tested whether spontaneous electrical brain activities in prestimulus period could predict perceptual outcome in face pareidolia (visualizing face in noise images) on a trial-by-trial basis. Participants were presented with only noise images but with the prior information that some faces would be hidden in these images, while their electrical brain activities were recorded; participants reported their perceptual decision, face or no-face, on each trial. Using differential hemispheric asymmetry features based on large-scale neural oscillations in a machine learning classifier, we demonstrated that prestimulus brain activities could achieve a classification accuracy, discriminating face from no-face perception, of 75% across trials. The time–frequency features representing hemispheric asymmetry yielded the best classification performance, and prestimulus alpha oscillations were found to be mostly involved in predicting perceptual decision. These findings suggest a mechanism of how prior expectations in the prestimulus period may affect post-stimulus decision making.
LanguageEnglish
Article number2
Number of pages16
JournalBrain Informatics
Volume6
Issue number2
DOIs
Publication statusPublished - 5 Feb 2019

Keywords

  • Artificial neural network
  • EEG
  • Face pareidolia
  • Prior expectation
  • Single-trial classification

Cite this

Jones, Rhiannon ; Barik, Kasturi ; Daimi, Syed ; Saha, Goutam ; Bhattacharya, Joydeep. / A machine learning approach to predict perceptual decisions: an insight into face pareidolia. In: Brain Informatics. 2019 ; Vol. 6, No. 2.
@article{a16ba914180f479aa3f73eccdc8e0af2,
title = "A machine learning approach to predict perceptual decisions: an insight into face pareidolia",
abstract = "The perception of an external stimulus not only depends upon the characteristics of the stimulus but is also influenced by the ongoing brain activity prior to its presentation. In this work, we directly tested whether spontaneous electrical brain activities in prestimulus period could predict perceptual outcome in face pareidolia (visualizing face in noise images) on a trial-by-trial basis. Participants were presented with only noise images but with the prior information that some faces would be hidden in these images, while their electrical brain activities were recorded; participants reported their perceptual decision, face or no-face, on each trial. Using differential hemispheric asymmetry features based on large-scale neural oscillations in a machine learning classifier, we demonstrated that prestimulus brain activities could achieve a classification accuracy, discriminating face from no-face perception, of 75{\%} across trials. The time–frequency features representing hemispheric asymmetry yielded the best classification performance, and prestimulus alpha oscillations were found to be mostly involved in predicting perceptual decision. These findings suggest a mechanism of how prior expectations in the prestimulus period may affect post-stimulus decision making.",
keywords = "Artificial neural network, EEG, Face pareidolia, Prior expectation, Single-trial classification",
author = "Rhiannon Jones and Kasturi Barik and Syed Daimi and Goutam Saha and Joydeep Bhattacharya",
year = "2019",
month = "2",
day = "5",
doi = "10.1186/s40708-019-0094-5",
language = "English",
volume = "6",
journal = "Brain Informatics",
issn = "2198-4018",
publisher = "Springer Berlin",
number = "2",

}

A machine learning approach to predict perceptual decisions: an insight into face pareidolia. / Jones, Rhiannon; Barik, Kasturi; Daimi, Syed; Saha, Goutam; Bhattacharya, Joydeep.

In: Brain Informatics, Vol. 6, No. 2, 2, 05.02.2019.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A machine learning approach to predict perceptual decisions: an insight into face pareidolia

AU - Jones, Rhiannon

AU - Barik, Kasturi

AU - Daimi, Syed

AU - Saha, Goutam

AU - Bhattacharya, Joydeep

PY - 2019/2/5

Y1 - 2019/2/5

N2 - The perception of an external stimulus not only depends upon the characteristics of the stimulus but is also influenced by the ongoing brain activity prior to its presentation. In this work, we directly tested whether spontaneous electrical brain activities in prestimulus period could predict perceptual outcome in face pareidolia (visualizing face in noise images) on a trial-by-trial basis. Participants were presented with only noise images but with the prior information that some faces would be hidden in these images, while their electrical brain activities were recorded; participants reported their perceptual decision, face or no-face, on each trial. Using differential hemispheric asymmetry features based on large-scale neural oscillations in a machine learning classifier, we demonstrated that prestimulus brain activities could achieve a classification accuracy, discriminating face from no-face perception, of 75% across trials. The time–frequency features representing hemispheric asymmetry yielded the best classification performance, and prestimulus alpha oscillations were found to be mostly involved in predicting perceptual decision. These findings suggest a mechanism of how prior expectations in the prestimulus period may affect post-stimulus decision making.

AB - The perception of an external stimulus not only depends upon the characteristics of the stimulus but is also influenced by the ongoing brain activity prior to its presentation. In this work, we directly tested whether spontaneous electrical brain activities in prestimulus period could predict perceptual outcome in face pareidolia (visualizing face in noise images) on a trial-by-trial basis. Participants were presented with only noise images but with the prior information that some faces would be hidden in these images, while their electrical brain activities were recorded; participants reported their perceptual decision, face or no-face, on each trial. Using differential hemispheric asymmetry features based on large-scale neural oscillations in a machine learning classifier, we demonstrated that prestimulus brain activities could achieve a classification accuracy, discriminating face from no-face perception, of 75% across trials. The time–frequency features representing hemispheric asymmetry yielded the best classification performance, and prestimulus alpha oscillations were found to be mostly involved in predicting perceptual decision. These findings suggest a mechanism of how prior expectations in the prestimulus period may affect post-stimulus decision making.

KW - Artificial neural network

KW - EEG

KW - Face pareidolia

KW - Prior expectation

KW - Single-trial classification

U2 - 10.1186/s40708-019-0094-5

DO - 10.1186/s40708-019-0094-5

M3 - Article

VL - 6

JO - Brain Informatics

T2 - Brain Informatics

JF - Brain Informatics

SN - 2198-4018

IS - 2

M1 - 2

ER -