Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with Dyslexia

Electroencephalogram (EEG) recordings of children are often used to study the underlying neural basis of causal factors of reading disorders and dyslexia. However, the inter-subject variability in EEG and the unconstrained nature of reading experiments used to elicit these factors made it challengin...

Full description

Saved in:
Bibliographic Details
Main Authors: Christoforos Christoforou, Jacqueline Torres M., Timothy Papadopoulos C., Maria Theodorou
Format: Article
Language:English
Published: LibraryPress@UF 2024-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Online Access:https://journals.flvc.org/FLAIRS/article/view/135385
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271166607917056
author Christoforos Christoforou
Jacqueline Torres M.
Timothy Papadopoulos C.
Maria Theodorou
author_facet Christoforos Christoforou
Jacqueline Torres M.
Timothy Papadopoulos C.
Maria Theodorou
author_sort Christoforos Christoforou
collection DOAJ
description Electroencephalogram (EEG) recordings of children are often used to study the underlying neural basis of causal factors of reading disorders and dyslexia. However, the inter-subject variability in EEG and the unconstrained nature of reading experiments used to elicit these factors made it challenging for traditional EEG analysis methods to extract neural components of these factors. In this work, we aim to explore the use of novel deep neural network architectures and contrastive learning methods to overcome the methodological limitations of traditional techniques and enhance the extraction process of neural components during reading tasks. Notably, we formulate a neural network architecture to extract EEG embedding using contrastive loss that maximizes the neural congruency in non-dyslexic children compared to children with dyslexia. We plan to evaluate our approach on three EEG datasets involving children with dyslexia performing Rapid Automatized Naming (RAN) and Phonological Processing (PA) tasks. The proposed contrastive learning framework will provide an enhanced tool to facilitate studying the neural underpinnings of naming speed and their association with reading performance and related difficulties.
format Article
id doaj-art-c3099cd72e9b417ab6bd28a9848f09d9
institution OA Journals
issn 2334-0754
2334-0762
language English
publishDate 2024-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-c3099cd72e9b417ab6bd28a9848f09d92025-08-20T01:52:19ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622024-05-013710.32473/flairs.37.1.13538571758Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with DyslexiaChristoforos Christoforou0https://orcid.org/0000-0003-1864-5862Jacqueline Torres M.Timothy Papadopoulos C.Maria TheodorouSt. John's UniversityElectroencephalogram (EEG) recordings of children are often used to study the underlying neural basis of causal factors of reading disorders and dyslexia. However, the inter-subject variability in EEG and the unconstrained nature of reading experiments used to elicit these factors made it challenging for traditional EEG analysis methods to extract neural components of these factors. In this work, we aim to explore the use of novel deep neural network architectures and contrastive learning methods to overcome the methodological limitations of traditional techniques and enhance the extraction process of neural components during reading tasks. Notably, we formulate a neural network architecture to extract EEG embedding using contrastive loss that maximizes the neural congruency in non-dyslexic children compared to children with dyslexia. We plan to evaluate our approach on three EEG datasets involving children with dyslexia performing Rapid Automatized Naming (RAN) and Phonological Processing (PA) tasks. The proposed contrastive learning framework will provide an enhanced tool to facilitate studying the neural underpinnings of naming speed and their association with reading performance and related difficulties.https://journals.flvc.org/FLAIRS/article/view/135385
spellingShingle Christoforos Christoforou
Jacqueline Torres M.
Timothy Papadopoulos C.
Maria Theodorou
Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with Dyslexia
Proceedings of the International Florida Artificial Intelligence Research Society Conference
title Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with Dyslexia
title_full Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with Dyslexia
title_fullStr Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with Dyslexia
title_full_unstemmed Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with Dyslexia
title_short Exploring Contrastive Learning Neural-Congruency on EEG Recording of Children with Dyslexia
title_sort exploring contrastive learning neural congruency on eeg recording of children with dyslexia
url https://journals.flvc.org/FLAIRS/article/view/135385
work_keys_str_mv AT christoforoschristoforou exploringcontrastivelearningneuralcongruencyoneegrecordingofchildrenwithdyslexia
AT jacquelinetorresm exploringcontrastivelearningneuralcongruencyoneegrecordingofchildrenwithdyslexia
AT timothypapadopoulosc exploringcontrastivelearningneuralcongruencyoneegrecordingofchildrenwithdyslexia
AT mariatheodorou exploringcontrastivelearningneuralcongruencyoneegrecordingofchildrenwithdyslexia