EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis

This paper proposes two novel methods to classify semantic vigilance levels by utilizing EEG directed connectivity patterns with their corresponding graphical network measures. We estimate the directed connectivity using relative wavelet transform entropy (RWTE) and partial directed coherence (PDC)...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Yahya, Fares (author)
مؤلفون آخرون: Hassanin, Omnia (author), Tariq, Usman (author), Al-Nashash, Hasan (author)
التنسيق: article
منشور في: 2020
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/21414
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513440703315968
author Yahya, Fares
author2 Hassanin, Omnia
Tariq, Usman
Al-Nashash, Hasan
author2_role author
author
author
author_facet Yahya, Fares
Hassanin, Omnia
Tariq, Usman
Al-Nashash, Hasan
author_role author
dc.creator.none.fl_str_mv Yahya, Fares
Hassanin, Omnia
Tariq, Usman
Al-Nashash, Hasan
dc.date.none.fl_str_mv 2020
2021-04-15T09:29:57Z
2021-04-15T09:29:57Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv F. M. Al-Shargie, O. Hassanin, U. Tariq and H. Al-Nashash, "EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis," in IEEE Access, vol. 8, pp. 115941-115956, 2020, doi: 10.1109/ACCESS.2020.3004504.
2169-3536
http://hdl.handle.net/11073/21414
10.1109/ACCESS.2020.3004504
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv IEEE
dc.relation.none.fl_str_mv https://doi.org/10.1109/ACCESS.2020.3004504
dc.subject.none.fl_str_mv Vigilance decrement
Electroencephalogram
Relative wavelet transform entropy
Partial directed coherence
Graph theory analysis
Machine Learning
dc.title.none.fl_str_mv EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This paper proposes two novel methods to classify semantic vigilance levels by utilizing EEG directed connectivity patterns with their corresponding graphical network measures. We estimate the directed connectivity using relative wavelet transform entropy (RWTE) and partial directed coherence (PDC) and the graphical network measures by graph theory analysis (GTA) at four frequency bands. The RWTE and PDC quantify the strength and directionality of information flow between EEG nodes. On the other hand, the GTA of the complex network measures summarizes the topological structure of the network. We then evaluate the proposed methods using machine learning classifiers. We carried out an experiment on nine subjects performing semantic vigilance task (Stroop color word test (SCWT)) for approximately 45 minutes. Behaviorally, all subjects demonstrated vigilance decrement as reflected by the significant increase in response time and reduced accuracy. The strength and directionality of information flow in the connectivity network by RWTE/PDC and the GTA measures significantly decrease with vigilance decrement, p<0.05. The classification results show that the proposed methods outperform other related and competitive methods available in the literature and achieve 100% accuracy in subject-dependent and above 89% in subject-independent level in each of the four frequency bands. The overall results indicate that the proposed methods of directed connectivity patterns and GTA provide a complementary aspect of functional connectivity. Our study suggests directed functional connectivity with GTA as informative features and highlight Support Vector Machine as the suitable classifier for classifying semantic vigilance levels.
format article
id aus_d523359b5baf8f6db5aca7a6aa1356b9
identifier_str_mv F. M. Al-Shargie, O. Hassanin, U. Tariq and H. Al-Nashash, "EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis," in IEEE Access, vol. 8, pp. 115941-115956, 2020, doi: 10.1109/ACCESS.2020.3004504.
2169-3536
10.1109/ACCESS.2020.3004504
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/21414
publishDate 2020
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory AnalysisYahya, FaresHassanin, OmniaTariq, UsmanAl-Nashash, HasanVigilance decrementElectroencephalogramRelative wavelet transform entropyPartial directed coherenceGraph theory analysisMachine LearningThis paper proposes two novel methods to classify semantic vigilance levels by utilizing EEG directed connectivity patterns with their corresponding graphical network measures. We estimate the directed connectivity using relative wavelet transform entropy (RWTE) and partial directed coherence (PDC) and the graphical network measures by graph theory analysis (GTA) at four frequency bands. The RWTE and PDC quantify the strength and directionality of information flow between EEG nodes. On the other hand, the GTA of the complex network measures summarizes the topological structure of the network. We then evaluate the proposed methods using machine learning classifiers. We carried out an experiment on nine subjects performing semantic vigilance task (Stroop color word test (SCWT)) for approximately 45 minutes. Behaviorally, all subjects demonstrated vigilance decrement as reflected by the significant increase in response time and reduced accuracy. The strength and directionality of information flow in the connectivity network by RWTE/PDC and the GTA measures significantly decrease with vigilance decrement, p<0.05. The classification results show that the proposed methods outperform other related and competitive methods available in the literature and achieve 100% accuracy in subject-dependent and above 89% in subject-independent level in each of the four frequency bands. The overall results indicate that the proposed methods of directed connectivity patterns and GTA provide a complementary aspect of functional connectivity. Our study suggests directed functional connectivity with GTA as informative features and highlight Support Vector Machine as the suitable classifier for classifying semantic vigilance levels.American University of SharjahIEEE2021-04-15T09:29:57Z2021-04-15T09:29:57Z2020Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfF. M. Al-Shargie, O. Hassanin, U. Tariq and H. Al-Nashash, "EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis," in IEEE Access, vol. 8, pp. 115941-115956, 2020, doi: 10.1109/ACCESS.2020.3004504.2169-3536http://hdl.handle.net/11073/2141410.1109/ACCESS.2020.3004504en_UShttps://doi.org/10.1109/ACCESS.2020.3004504oai:repository.aus.edu:11073/214142024-08-22T12:08:17Z
spellingShingle EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
Yahya, Fares
Vigilance decrement
Electroencephalogram
Relative wavelet transform entropy
Partial directed coherence
Graph theory analysis
Machine Learning
status_str publishedVersion
title EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
title_full EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
title_fullStr EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
title_full_unstemmed EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
title_short EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
title_sort EEG-Based Semantic Vigilance Level Classification Using Directed Connectivity Patterns and Graph Theory Analysis
topic Vigilance decrement
Electroencephalogram
Relative wavelet transform entropy
Partial directed coherence
Graph theory analysis
Machine Learning
url http://hdl.handle.net/11073/21414