Notícias

Banca de QUALIFICAÇÃO: DANIELE ALVES DA SILVA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
DISCENTE: DANIELE ALVES DA SILVA
DATA: 22/04/2022
HORA: 15:00
LOCAL: meet.google.com/wsj-bhcs-ppg
TÍTULO: Electromyography and Dynamometry in the Prediction of Risk of Falls in the Elderly Using Machine Learning Tools
PALAVRAS-CHAVES: Fall risk, machine learning, Berg Balance Scale, elderly, feature selection.
PÁGINAS: 13
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
RESUMO:

The aging process affects mechanisms for maintaining physical integrity. The assessment of the risk of falls is routine in the services of assistance to the elderly, but subjective and time-consuming, so that the automation of the process is valid. The aim of this study is to use machine learning (ML) tools as an instrument to predict the final Berg Balance Scale (BBS) score, using different sets of electromyographic and dynamometric data collected during a voluntary isometric contraction and to compare the performance of various tools. Thirty participants were evaluated with the BBS and with electromyography and dynamometry of the vastus lateralis, biceps femoris, lateral gastrocnemius and tibialis anterior muscles during maximal isometric voluntary contractions. After pre-processing the dataset, the attributes were selected through principal components analysis (PCA), correlation-based function select (CFS) and relief-F to then be applied to the multilayer perceptron (MLP), random forest (RF), random tree (RT), k-nearest neighbors (KNN) and least squares support vector regression (LS-SVR). The myoelectric signals proved to be more effective for use in predicting the risk of falls in the elderly in relation to the force signal. The LS-SVR and MLP tools proved to be acceptable alternatives in most cases and the RF algorithm with attributes calculated from the electromyography signals and selected by CFS was the best model for predicting the final BBS score.


MEMBROS DA BANCA:
Externo à Instituição - FABIANA TEIXEIRA DE CARVALHO PORTELA - UESPI
Interno - 328.414.503-68 - GUILHERME DE ALENCAR BARRETO - UFC
Presidente - 3095957 - HERMES MANOEL GALVÃO CASTELO BRANCO
Externo à Instituição - RENATO TINOS - USP
Notícia cadastrada em: 06/04/2022 12:38
SIGAA | Superintendência de Tecnologia da Informação - STI/UFPI - (86) 3215-1124 | © UFRN | sigjb03.ufpi.br.sigaa 03/03/2024 10:08