EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach

<p dir="ltr">Electrooculography, also known as EOG, is a technique that is used to calculate the corneo-retinal standing potential, which is located between the cornea and the retina of the human eye. Applications of EOG include eye disease diagnosis and eye movement tracking. There...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Sriman Bidhan Baray (15302398) (author)
مؤلفون آخرون: Mosabber Uddin Ahmed (17773200) (author), Muhammad E. H. Chowdhury (14150526) (author), Koichi Kise (5896985) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513527409016832
author Sriman Bidhan Baray (15302398)
author2 Mosabber Uddin Ahmed (17773200)
Muhammad E. H. Chowdhury (14150526)
Koichi Kise (5896985)
author2_role author
author
author
author_facet Sriman Bidhan Baray (15302398)
Mosabber Uddin Ahmed (17773200)
Muhammad E. H. Chowdhury (14150526)
Koichi Kise (5896985)
author_role author
dc.creator.none.fl_str_mv Sriman Bidhan Baray (15302398)
Mosabber Uddin Ahmed (17773200)
Muhammad E. H. Chowdhury (14150526)
Koichi Kise (5896985)
dc.date.none.fl_str_mv 2023-09-15T06:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2023.3316032
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/EOG-Based_Reading_Detection_in_the_Wild_Using_Spectrograms_and_Nested_Classification_Approach/25239520
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Electrooculography
Deep learning
Feature extraction
Sensors
Tracking
Spectrogram
Task analysis
Machine learning
Pattern classification
Smart glasses
signal classification
dc.title.none.fl_str_mv EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Electrooculography, also known as EOG, is a technique that is used to calculate the corneo-retinal standing potential, which is located between the cornea and the retina of the human eye. Applications of EOG include eye disease diagnosis and eye movement tracking. There has been various research on reading activity detection from EOG signals in controlled laboratory settings. However, determining reading behaviours from data collected from real-world environments remains a challenging problem. Detecting reading in practical scenarios can lead us to track our daily reading activity, thereby improving our learning experience and even workplace productivity. Tracking regular reading behaviour can also lead to further research in cognitive psychology, literacy development, reading motivation, and reading comprehension. In this study, we investigated an electrooculogram dataset that was collected on the field from 10 users who were engaged in their daily activities on two separate days. We propose a pipeline combining the statistical features with deep learning features from pre-trained ImageNet models. To detect the fine-grained reading activities, we adopted a nested classification approach. Initially, we differentiate between reading and not reading and then we employ an additional classification step to discriminate among three distinct types of reading activities. With our pipeline, we could achieve 66.56% accuracy in detecting the reading activities whereas the original dataset publication showed a baseline performance of only 32%.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3316032" target="_blank">https://dx.doi.org/10.1109/access.2023.3316032</a></p>
eu_rights_str_mv openAccess
id Manara2_82bfb075b6eb78c59451d86d7dd73b8a
identifier_str_mv 10.1109/access.2023.3316032
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25239520
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification ApproachSriman Bidhan Baray (15302398)Mosabber Uddin Ahmed (17773200)Muhammad E. H. Chowdhury (14150526)Koichi Kise (5896985)EngineeringElectrical engineeringElectronics, sensors and digital hardwareMaterials engineeringElectrooculographyDeep learningFeature extractionSensorsTrackingSpectrogramTask analysisMachine learningPattern classificationSmart glassessignal classification<p dir="ltr">Electrooculography, also known as EOG, is a technique that is used to calculate the corneo-retinal standing potential, which is located between the cornea and the retina of the human eye. Applications of EOG include eye disease diagnosis and eye movement tracking. There has been various research on reading activity detection from EOG signals in controlled laboratory settings. However, determining reading behaviours from data collected from real-world environments remains a challenging problem. Detecting reading in practical scenarios can lead us to track our daily reading activity, thereby improving our learning experience and even workplace productivity. Tracking regular reading behaviour can also lead to further research in cognitive psychology, literacy development, reading motivation, and reading comprehension. In this study, we investigated an electrooculogram dataset that was collected on the field from 10 users who were engaged in their daily activities on two separate days. We propose a pipeline combining the statistical features with deep learning features from pre-trained ImageNet models. To detect the fine-grained reading activities, we adopted a nested classification approach. Initially, we differentiate between reading and not reading and then we employ an additional classification step to discriminate among three distinct types of reading activities. With our pipeline, we could achieve 66.56% accuracy in detecting the reading activities whereas the original dataset publication showed a baseline performance of only 32%.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3316032" target="_blank">https://dx.doi.org/10.1109/access.2023.3316032</a></p>2023-09-15T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2023.3316032https://figshare.com/articles/journal_contribution/EOG-Based_Reading_Detection_in_the_Wild_Using_Spectrograms_and_Nested_Classification_Approach/25239520CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/252395202023-09-15T06:00:00Z
spellingShingle EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
Sriman Bidhan Baray (15302398)
Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Electrooculography
Deep learning
Feature extraction
Sensors
Tracking
Spectrogram
Task analysis
Machine learning
Pattern classification
Smart glasses
signal classification
status_str publishedVersion
title EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
title_full EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
title_fullStr EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
title_full_unstemmed EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
title_short EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
title_sort EOG-Based Reading Detection in the Wild Using Spectrograms and Nested Classification Approach
topic Engineering
Electrical engineering
Electronics, sensors and digital hardware
Materials engineering
Electrooculography
Deep learning
Feature extraction
Sensors
Tracking
Spectrogram
Task analysis
Machine learning
Pattern classification
Smart glasses
signal classification