Analysis of goal, feedback and rewards on sustained attention via machine learning

IntroductionSustaining attention is a notoriously difficult task as shown in a recent experiment where reaction times (RTs) and pupillometry data were recorded from 350 subjects in a 30-min vigilance task. Subjects were also presented with different types of goal, feedback, and reward.MethodsIn this...

Full description

Saved in:
Bibliographic Details
Main Authors: Nethali Fernando, Matthew Robison, Pedro D. Maia
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Behavioral Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnbeh.2024.1386723/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134863528591360
author Nethali Fernando
Nethali Fernando
Matthew Robison
Matthew Robison
Pedro D. Maia
Pedro D. Maia
author_facet Nethali Fernando
Nethali Fernando
Matthew Robison
Matthew Robison
Pedro D. Maia
Pedro D. Maia
author_sort Nethali Fernando
collection DOAJ
description IntroductionSustaining attention is a notoriously difficult task as shown in a recent experiment where reaction times (RTs) and pupillometry data were recorded from 350 subjects in a 30-min vigilance task. Subjects were also presented with different types of goal, feedback, and reward.MethodsIn this study, we revisit this experimental data and solve three families of machine learning problems: (i) RT-regression problems, to predict subjects' RTs using all available data, (ii) RT-classification problems, to classify responses more broadly as attentive, semi-attentive, and inattentive, and (iii) to predict the subjects' experimental conditions from physiological data.ResultsAfter establishing that regressing RTs is in general a difficult task, we achieve better results classifying them in broader categories. We also successfully disambiguate subjects who received goals and rewards from those who did not. Finally, we quantify changes in accuracy when coarser features (averaged throughout multiple trials) are used. Interestingly, the machine learning pipeline selects different features depending on their resolution, suggesting that predictive physiological features are also resolution-specific.DiscussionThese findings highlight the potential of machine learning to advance research on sustained attention and behavior, particularly in studies incorporating pupillometry or other physiological measurements, offering new avenues for understanding and analysis.
format Article
id doaj-art-f3c67faedf71493bbacdbb6ffd781372
institution OA Journals
issn 1662-5153
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Behavioral Neuroscience
spelling doaj-art-f3c67faedf71493bbacdbb6ffd7813722025-08-20T02:31:37ZengFrontiers Media S.A.Frontiers in Behavioral Neuroscience1662-51532024-12-011810.3389/fnbeh.2024.13867231386723Analysis of goal, feedback and rewards on sustained attention via machine learningNethali Fernando0Nethali Fernando1Matthew Robison2Matthew Robison3Pedro D. Maia4Pedro D. Maia5Department of Mathematics, University of Texas at Arlington, Arlington, TX, United StatesDivision of Data Science, College of Science, University of Texas at Arlington, Arlington, TX, United StatesDepartment of Psychology, University of Notre Dame, Notre Dame, IN, United StatesDepartment of Psychology, University of Texas at Arlington, Arlington, TX, United StatesDepartment of Mathematics, University of Texas at Arlington, Arlington, TX, United StatesDivision of Data Science, College of Science, University of Texas at Arlington, Arlington, TX, United StatesIntroductionSustaining attention is a notoriously difficult task as shown in a recent experiment where reaction times (RTs) and pupillometry data were recorded from 350 subjects in a 30-min vigilance task. Subjects were also presented with different types of goal, feedback, and reward.MethodsIn this study, we revisit this experimental data and solve three families of machine learning problems: (i) RT-regression problems, to predict subjects' RTs using all available data, (ii) RT-classification problems, to classify responses more broadly as attentive, semi-attentive, and inattentive, and (iii) to predict the subjects' experimental conditions from physiological data.ResultsAfter establishing that regressing RTs is in general a difficult task, we achieve better results classifying them in broader categories. We also successfully disambiguate subjects who received goals and rewards from those who did not. Finally, we quantify changes in accuracy when coarser features (averaged throughout multiple trials) are used. Interestingly, the machine learning pipeline selects different features depending on their resolution, suggesting that predictive physiological features are also resolution-specific.DiscussionThese findings highlight the potential of machine learning to advance research on sustained attention and behavior, particularly in studies incorporating pupillometry or other physiological measurements, offering new avenues for understanding and analysis.https://www.frontiersin.org/articles/10.3389/fnbeh.2024.1386723/fullsustained attentionpupillometry datarewardreaction timemachine learningclassification
spellingShingle Nethali Fernando
Nethali Fernando
Matthew Robison
Matthew Robison
Pedro D. Maia
Pedro D. Maia
Analysis of goal, feedback and rewards on sustained attention via machine learning
Frontiers in Behavioral Neuroscience
sustained attention
pupillometry data
reward
reaction time
machine learning
classification
title Analysis of goal, feedback and rewards on sustained attention via machine learning
title_full Analysis of goal, feedback and rewards on sustained attention via machine learning
title_fullStr Analysis of goal, feedback and rewards on sustained attention via machine learning
title_full_unstemmed Analysis of goal, feedback and rewards on sustained attention via machine learning
title_short Analysis of goal, feedback and rewards on sustained attention via machine learning
title_sort analysis of goal feedback and rewards on sustained attention via machine learning
topic sustained attention
pupillometry data
reward
reaction time
machine learning
classification
url https://www.frontiersin.org/articles/10.3389/fnbeh.2024.1386723/full
work_keys_str_mv AT nethalifernando analysisofgoalfeedbackandrewardsonsustainedattentionviamachinelearning
AT nethalifernando analysisofgoalfeedbackandrewardsonsustainedattentionviamachinelearning
AT matthewrobison analysisofgoalfeedbackandrewardsonsustainedattentionviamachinelearning
AT matthewrobison analysisofgoalfeedbackandrewardsonsustainedattentionviamachinelearning
AT pedrodmaia analysisofgoalfeedbackandrewardsonsustainedattentionviamachinelearning
AT pedrodmaia analysisofgoalfeedbackandrewardsonsustainedattentionviamachinelearning