Publicação

Fall detection system for elderly people

Ver documento

Detalhes bibliográficos
Resumo:accelerometer and a 3-axis gyroscope to measure linear acceleration and angular velocities, respectively. Information from both sensors is used to characterize movements through selected features extracted from raw data. A classification system based on a Feedforward Backpropagation Neural Network is then trained, based on the extracted features. The performed tests present low false positives and low false negatives rates with good specificity and sensitivity values.
Autores principais:Igrejas, Getúlio
Outros Autores:Amaral, Joana S.; Rodrigues, Pedro João
Assunto:Fall detection Neural network Inertial sensors Features selection Embedded devices
Ano:2012
País:Portugal
Tipo de documento:comunicação em conferência
Tipo de acesso:acesso restrito
Instituição associada:Instituto Politécnico de Bragança
Idioma:inglês
Origem:Biblioteca Digital do IPB
Descrição
Resumo:accelerometer and a 3-axis gyroscope to measure linear acceleration and angular velocities, respectively. Information from both sensors is used to characterize movements through selected features extracted from raw data. A classification system based on a Feedforward Backpropagation Neural Network is then trained, based on the extracted features. The performed tests present low false positives and low false negatives rates with good specificity and sensitivity values.