The effects of applying filters on EEG signals for classifying developers’ code comprehension

EEG signals are a relevant indicator for measuring aspects related to human factors in Software Engineering. EEG is used in software engineering to train machine learning techniques for a wide range of applications, including classifying task difficulty, and developers’ level of experience. The EEG...

ver descrição completa

Detalhes bibliográficos
Autores: Gonçales, Lucian Jose, Farias, Kleinner, Kupssinskü, Lucas, Segalotto, Matheus
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2021
País:México
Recursos:UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO
Repositório:Journal of Applied Research and Technology
Idioma:inglês
OAI Identifier:oai:ojs2.localhost:article/1299
Acesso em linha:https://jart.icat.unam.mx/index.php/jart/article/view/1299
Access Level:Acceso aberto
Palavra-chave:Software Engineering
Program Comprehension
Machine Learning
EEG
id MX_c1d96d94d0a5c759d749842eaf8d0840
oai_identifier_str oai:ojs2.localhost:article/1299
network_acronym_str MX
network_name_str México
repository_id_str
spelling The effects of applying filters on EEG signals for classifying developers’ code comprehensionGonçales, Lucian JoseFarias, KleinnerKupssinskü, LucasSegalotto, MatheusSoftware EngineeringProgram ComprehensionMachine LearningEEGEEG signals are a relevant indicator for measuring aspects related to human factors in Software Engineering. EEG is used in software engineering to train machine learning techniques for a wide range of applications, including classifying task difficulty, and developers’ level of experience. The EEG signal contains noise such as abnormal readings, electrical interference, and eye movements, which are usually not of interest to the analysis, and therefore contribute to the lack of precision of the machine learning techniques. However, research in software engineering has not evidenced the effectiveness when applying these filters on EEG signals. The objective of this work is to analyze the effectiveness of filters on EEG signals in the software engineering context. As literature did not focus on the classification of developers’ code comprehension, this study focuses on the analysis of the effectiveness of applying EEG filters for training a machine learning technique to classify developers' code comprehension. A Random Forest (RF) machine learning technique was trained with filtered EEG signals to classify the developers' code comprehension. This study also trained another random forest classifier with unfiltered EEG data. Both models were trained using 10-fold cross-validation. This work measures the classifiers' effectiveness using the f-measure metric. This work used the t-test, Wilcoxon, and U Mann Whitney to analyze the difference in the effectiveness measures (f-measure) between the classifier trained with filtered EEG and the classifier trained with unfiltered EEG. The tests pointed out that there is a significant difference after applying EEG filters to classify developers' code comprehension with the random forest classifier. The conclusion is that the use of EEG filters significantly improves the effectivity to classify code comprehension using the random forest technique.Universidad Nacional Autónoma de México2021-12-31info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionPeer-reviewed Articleapplication/pdfhttps://jart.icat.unam.mx/index.php/jart/article/view/129910.22201/icat.24486736e.2021.19.6.1299Journal of Applied Research and Technology; Vol. 19 No. 6 (2021); 584-602Journal of Applied Research and Technology; Vol. 19 Núm. 6 (2021); 584-6022448-67361665-642310.22201/icat.24486736e.2021.19.6reponame:Journal of Applied Research and Technologyinstname:UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICOinstacron:UNAMenghttps://jart.icat.unam.mx/index.php/jart/article/view/1299/870Copyright (c) 2021 Universidad Nacional Autónoma de Méxicoinfo:eu-repo/semantics/openAccessoai:ojs2.localhost:article/12992024-08-16T17:54:19Z
dc.title.none.fl_str_mv The effects of applying filters on EEG signals for classifying developers’ code comprehension
title The effects of applying filters on EEG signals for classifying developers’ code comprehension
spellingShingle The effects of applying filters on EEG signals for classifying developers’ code comprehension
Gonçales, Lucian Jose
Software Engineering
Program Comprehension
Machine Learning
EEG
title_short The effects of applying filters on EEG signals for classifying developers’ code comprehension
title_full The effects of applying filters on EEG signals for classifying developers’ code comprehension
title_fullStr The effects of applying filters on EEG signals for classifying developers’ code comprehension
title_full_unstemmed The effects of applying filters on EEG signals for classifying developers’ code comprehension
title_sort The effects of applying filters on EEG signals for classifying developers’ code comprehension
dc.creator.none.fl_str_mv Gonçales, Lucian Jose
Farias, Kleinner
Kupssinskü, Lucas
Segalotto, Matheus
author Gonçales, Lucian Jose
author_facet Gonçales, Lucian Jose
Farias, Kleinner
Kupssinskü, Lucas
Segalotto, Matheus
author_role author
author2 Farias, Kleinner
Kupssinskü, Lucas
Segalotto, Matheus
author2_role author
author
author
dc.subject.none.fl_str_mv Software Engineering
Program Comprehension
Machine Learning
EEG
topic Software Engineering
Program Comprehension
Machine Learning
EEG
description EEG signals are a relevant indicator for measuring aspects related to human factors in Software Engineering. EEG is used in software engineering to train machine learning techniques for a wide range of applications, including classifying task difficulty, and developers’ level of experience. The EEG signal contains noise such as abnormal readings, electrical interference, and eye movements, which are usually not of interest to the analysis, and therefore contribute to the lack of precision of the machine learning techniques. However, research in software engineering has not evidenced the effectiveness when applying these filters on EEG signals. The objective of this work is to analyze the effectiveness of filters on EEG signals in the software engineering context. As literature did not focus on the classification of developers’ code comprehension, this study focuses on the analysis of the effectiveness of applying EEG filters for training a machine learning technique to classify developers' code comprehension. A Random Forest (RF) machine learning technique was trained with filtered EEG signals to classify the developers' code comprehension. This study also trained another random forest classifier with unfiltered EEG data. Both models were trained using 10-fold cross-validation. This work measures the classifiers' effectiveness using the f-measure metric. This work used the t-test, Wilcoxon, and U Mann Whitney to analyze the difference in the effectiveness measures (f-measure) between the classifier trained with filtered EEG and the classifier trained with unfiltered EEG. The tests pointed out that there is a significant difference after applying EEG filters to classify developers' code comprehension with the random forest classifier. The conclusion is that the use of EEG filters significantly improves the effectivity to classify code comprehension using the random forest technique.
publishDate 2021
dc.date.none.fl_str_mv 2021-12-31
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://jart.icat.unam.mx/index.php/jart/article/view/1299
10.22201/icat.24486736e.2021.19.6.1299
url https://jart.icat.unam.mx/index.php/jart/article/view/1299
identifier_str_mv 10.22201/icat.24486736e.2021.19.6.1299
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://jart.icat.unam.mx/index.php/jart/article/view/1299/870
dc.rights.none.fl_str_mv Copyright (c) 2021 Universidad Nacional Autónoma de México
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2021 Universidad Nacional Autónoma de México
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidad Nacional Autónoma de México
publisher.none.fl_str_mv Universidad Nacional Autónoma de México
dc.source.none.fl_str_mv Journal of Applied Research and Technology; Vol. 19 No. 6 (2021); 584-602
Journal of Applied Research and Technology; Vol. 19 Núm. 6 (2021); 584-602
2448-6736
1665-6423
10.22201/icat.24486736e.2021.19.6
reponame:Journal of Applied Research and Technology
instname:UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO
instacron:UNAM
instname_str UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO
instacron_str UNAM
institution UNAM
reponame_str Journal of Applied Research and Technology
collection Journal of Applied Research and Technology
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1858176842391879680
score 15,811543

Registros relacionados