Banca de DEFESA: LEDYCNARF JANUÁRIO DE HOLANDA

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
STUDENT : LEDYCNARF JANUÁRIO DE HOLANDA
DATE: 10/02/2023
TIME: 08:30
LOCAL: Remoto
TITLE:

Machine Learning-based Upper Limb Motion Analysis of People with Amyotrophic Lateral Sclerosis.


KEY WORDS:

Machine Learning; Functionality; Motor Function; Amyotrophic Lateral Sclerosis


PAGES: 140
BIG AREA: Ciências da Saúde
AREA: Fisioterapia e Terapia Ocupacional
SUMMARY:

Abstract

Introduction: Amyotrophic Lateral Sclerosis (ALS) leads to progressive motor limitations, which appear differently in each patient, such as impairments related to the upper limb (UL). These impact the performance of activities of daily living and functional independence. Surface electromyography (sEMG) and accelerometer (ACC) are being integrated as additional tools for motor function analysis with technological evolution, thereby enhancing existing assessment tools. These can still be improved with the association of Machine Learning (ML) algorithms that can contribute to the development of more accurate and precise tools for rehabilitation.

Objective: To implement an ML model on sEMG and ACC data to assess the SM motor function of people with ALS.

Methods: This is a cross-sectional study approved by the Ethics Committee of the UFRN Central Campus (CAAE: 25687819.3.0000.5537). 10 healthy people and 7 with ALS were evaluated, using a standardized evaluation form, validated assessment instruments to analyze the health condition of the person with ALS and/or other neurological and/or musculoskeletal disorders, and analysis of the UL movement, from sEMG and ACC. Data processing was performed using Matlab R2022b software and statistical analysis using the Statistical Package for Social Science (SPSS) version 20.0 software.

Results:

Article 1 - Elaborate a scope review in order to describe the characteristics of UL orthoses controlled by ML algorithms, based on information extracted from published articles and patents.

Article 2 - Analyze and compare the degree of stationarity and linearity of ACC data acquired during the UL movement of people with ALS and healthy people.

Article 3 - Analyze and compare the degree of stationarity and linearity of sEMG data acquired during the UL movement of people with ALS and healthy people.

Article 4 - Analyze and compare levels of fatigue and muscle strength in healthy people and people with ALS, based on sEMG and ACC signals.

- To compare the level of muscle activation and the level of movement variation in healthy people and people with ALS, based on EMGs and ACC signals, respectively.

- Classify data from sEMG and ACC of healthy people and those with ALS, based on AM algorithms.

Conclusion: UL orthoses controlled by ML algorithms can offer additional benefits for the motor rehabilitation of people who have movement disorders caused by a disease, such as ALS. These patients depend on illnesses that differ from a healthy person. Our findings showed the difference in statistical properties of the sEMG and ACC signal, level of fatigue, muscle strength, muscle activation, and movement displacement.


COMMITTEE MEMBERS:
Externo à Instituição - DENIS DELISLE RODRÍGUEZ - ISD
Presidente - 2179208 - ANA RAQUEL RODRIGUES LINDQUIST
Externo à Instituição - EMERSON FACHIN MARTINS - UnB
Externo à Instituição - SUELLEN MARY MARINHO DOS SANTOS ANDRADE - UFPB
Interna - 2319151 - TATIANA SOUZA RIBEIRO
Notícia cadastrada em: 21/12/2022 10:04
SIGAA | Superintendência de Tecnologia da Informação - (84) 3342 2210 | Copyright © 2006-2024 - UFRN - sigaa08-producao.info.ufrn.br.sigaa08-producao