Aplicação de Inteligência Computacional como Ferramenta de Apoio para Análise de Risco de Queda em Idosos

Luan M. M. Pereira; Daniele Alves da Silva; Laiana S. de A. Mesquita; Nayra F. L. C. Branco; Hermes M. G. C. Branco; Guilherme Alencar Barreto

doi:10.20906/sbai.v1i1.2825

Luan M. M. Pereira Universidade Estadual do Piauí
Daniele Alves da Silva Universidade Federal do Piauí
Laiana S. de A. Mesquita Universidade Estadual do Piauí
Nayra F. L. C. Branco Centro Universitário do Piauí
Hermes M. G. C. Branco Universidade Federal do Piauí
Guilherme Alencar Barreto Universidade Federal do Ceará´

DOI: https://doi.org/10.20906/sbai.v1i1.2825

Keywords: Fall Risk, Elderly, Neural Netword, PMC, SVM, TUG Test, Berg Test

Abstract

Fall is a serious public health problem, especially in the elderly, and several approaches based on sensors and the use of computational intelligence to classify the risk of falling in the elderly have been proposed in the literature. This work used inertial sensors (accelerometer and gyroscope), signal processing techniques and computational intelligence to estimate the score that elderly people would obtain with the application of the Timed Up and Go (TUG) and Berg balance scales. The results of the proposed approach proved to be promising, with a correlation between the real and estimated scores near to 1 for the best models.