Cargando…
An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data
In recent years, affective computing has been actively researched to provide a higher level of emotion-awareness. Numerous studies have been conducted to detect the user’s emotions from physiological data. Among a myriad of target emotions, boredom, in particular, has been suggested to cause not onl...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6832442/ https://www.ncbi.nlm.nih.gov/pubmed/31635194 http://dx.doi.org/10.3390/s19204561 |
_version_ | 1783466173336125440 |
---|---|
author | Seo, Jungryul Laine, Teemu H. Sohn, Kyung-Ah |
author_facet | Seo, Jungryul Laine, Teemu H. Sohn, Kyung-Ah |
author_sort | Seo, Jungryul |
collection | PubMed |
description | In recent years, affective computing has been actively researched to provide a higher level of emotion-awareness. Numerous studies have been conducted to detect the user’s emotions from physiological data. Among a myriad of target emotions, boredom, in particular, has been suggested to cause not only medical issues but also challenges in various facets of daily life. However, to the best of our knowledge, no previous studies have used electroencephalography (EEG) and galvanic skin response (GSR) together for boredom classification, although these data have potential features for emotion classification. To investigate the combined effect of these features on boredom classification, we collected EEG and GSR data from 28 participants using off-the-shelf sensors. During data acquisition, we used a set of stimuli comprising a video clip designed to elicit boredom and two other video clips of entertaining content. The collected samples were labeled based on the participants’ questionnaire-based testimonies on experienced boredom levels. Using the collected data, we initially trained 30 models with 19 machine learning algorithms and selected the top three candidate classifiers. After tuning the hyperparameters, we validated the final models through 1000 iterations of 10-fold cross validation to increase the robustness of the test results. Our results indicated that a Multilayer Perceptron model performed the best with a mean accuracy of 79.98% (AUC: 0.781). It also revealed the correlation between boredom and the combined features of EEG and GSR. These results can be useful for building accurate affective computing systems and understanding the physiological properties of boredom. |
format | Online Article Text |
id | pubmed-6832442 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-68324422019-11-25 An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data Seo, Jungryul Laine, Teemu H. Sohn, Kyung-Ah Sensors (Basel) Article In recent years, affective computing has been actively researched to provide a higher level of emotion-awareness. Numerous studies have been conducted to detect the user’s emotions from physiological data. Among a myriad of target emotions, boredom, in particular, has been suggested to cause not only medical issues but also challenges in various facets of daily life. However, to the best of our knowledge, no previous studies have used electroencephalography (EEG) and galvanic skin response (GSR) together for boredom classification, although these data have potential features for emotion classification. To investigate the combined effect of these features on boredom classification, we collected EEG and GSR data from 28 participants using off-the-shelf sensors. During data acquisition, we used a set of stimuli comprising a video clip designed to elicit boredom and two other video clips of entertaining content. The collected samples were labeled based on the participants’ questionnaire-based testimonies on experienced boredom levels. Using the collected data, we initially trained 30 models with 19 machine learning algorithms and selected the top three candidate classifiers. After tuning the hyperparameters, we validated the final models through 1000 iterations of 10-fold cross validation to increase the robustness of the test results. Our results indicated that a Multilayer Perceptron model performed the best with a mean accuracy of 79.98% (AUC: 0.781). It also revealed the correlation between boredom and the combined features of EEG and GSR. These results can be useful for building accurate affective computing systems and understanding the physiological properties of boredom. MDPI 2019-10-20 /pmc/articles/PMC6832442/ /pubmed/31635194 http://dx.doi.org/10.3390/s19204561 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Seo, Jungryul Laine, Teemu H. Sohn, Kyung-Ah An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data |
title | An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data |
title_full | An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data |
title_fullStr | An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data |
title_full_unstemmed | An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data |
title_short | An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data |
title_sort | exploration of machine learning methods for robust boredom classification using eeg and gsr data |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6832442/ https://www.ncbi.nlm.nih.gov/pubmed/31635194 http://dx.doi.org/10.3390/s19204561 |
work_keys_str_mv | AT seojungryul anexplorationofmachinelearningmethodsforrobustboredomclassificationusingeegandgsrdata AT laineteemuh anexplorationofmachinelearningmethodsforrobustboredomclassificationusingeegandgsrdata AT sohnkyungah anexplorationofmachinelearningmethodsforrobustboredomclassificationusingeegandgsrdata AT seojungryul explorationofmachinelearningmethodsforrobustboredomclassificationusingeegandgsrdata AT laineteemuh explorationofmachinelearningmethodsforrobustboredomclassificationusingeegandgsrdata AT sohnkyungah explorationofmachinelearningmethodsforrobustboredomclassificationusingeegandgsrdata |