• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.55.2023.tde-22122023-103153
Document
Author
Full name
Marcela Prince Antunes
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2023
Supervisor
Committee
Rosa, João Luis Garcia (President)
Celeri, Eloisa Helena Rubello Valler
Silva Filho, Antonio Carlos Roque da
Traina, Agma Juci Machado
Title in Portuguese
Detecção precoce do transtorno do espectro autista utilizando EEG
Keywords in Portuguese
Aprendizado de máquina
Classificação
Diagnóstico precoce
EEG
Transtorno do espectro autista
Abstract in Portuguese
O Transtorno do Espectro Autista (TEA) é um transtorno do neurodesenvolvimento que tem sido a cada dia mais diagnosticado em crianças. Os sintomas são comumente percebidos na infância e incluem prejuízos na comunicação e interação social. A antecipação do diagnóstico para antes do aparecimento dos sintomas permitiria que diferentes terapias fossem iniciadas sem que houvesse comprometimento no desenvolvimento da criança. Por isso, diversas pesquisas têm utilizado eletroencefalografia (EEG) para compreender e detectar o TEA, além de sugerir intervenções para indivíduos com TEA. Considerando este cenário, este trabalho executou diversos experimentos utilizando técnicas de aprendizado de máquina para identificar automaticamente o TEA a partir de registros de EEG obtidos de crianças com idades de 3 a 14 meses. Os resultados apontaram acurácia, especificidade e sensitividade acima de 95% com Máquina de Vetores de Suporte (SVM) associada à Eliminação Recursiva de Características com Validação Cruzada (RFECV), mostrando a possibilidade de detecção do TEA já a partir dos 3 meses.
Title in English
Early detection of autism spectrum disorder using EEG
Keywords in English
Autistic spectrum Disorder
Classification
Early diagnosis
EEG
Machine learning
Abstract in English
The Autistic Spectrum Disorder (ASD) is a neurodevelopmental disorder that has been increasingly diagnosed in children. Symptoms are commonly noticed in childhood and include impairments in communication and social interaction. Anticipating the diagnosis to before the onset of symptoms would allow different therapies to be started without compromising the childs development. Hence, several studies have used electroencephalography (EEG) to understand and detect ASD, in addition to suggesting interventions for individuals with ASD. In this scenario, this work performed several experiments using machine learning techniques to automatically identify ASD from EEG recordings obtained from children aged 3 to 14 months. The results showed accuracy, specificity and sensitivity above 95% with Support Vector Machine (SVM) associated with Recursive Feature Elimination with Cross Validation (RFECV), showing the possibility of detecting ASD from 3 months onwards.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2023-12-22
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.