Autor(es)

Garcia, Felipe Aparecido ; Ranieri, Caetano Mazzoni ; Romero, Roseli A. F. ; Colombini, EL ; Junior, PLJD ; Garcia, LTD ; Goncalves, LMG ; Sa, STD ; Estrada, EDD ; Botelho, SSD

• Tipo de documento: Artigo Científico
• Fonte: 2019 LATIN AMERICAN ROBOTICS SYMPOSIUM, 2019 BRAZILIAN SYMPOSIUM ON ROBOTICS (SBR) AND 2019 WORKSHOP ON ROBOTICS IN EDUCATION (LARS-SBR-WRE 2019); v. N/A, p. 5-pg., 2019-01-01.

Resumo

Human Activity Recognition (HAR) involves classifying one person's activity based on sensor data. In this work, inertial data, collected mainly from wearable sensors, are used to recognize HAR by using Convolutional Neural Networks (CNN) to extract features from the raw sensor data. Additionally, Temporal Convolutional Networks (TCN) are applied to classify the extracted features, comparing the overall performance of those layers with Long Short-Term Memory (LSTM) recurrent neural network layers. Several experiments are performed and the results show that TCN based architectures are able to outperform LSTM based architectures in sequence modeling. (AU)

• Processo FAPESP: 14/50851-0 - Inct 2014 - instituto nacional de ciencia e tecnologia para sistemas autonomos cooperativos aplicados em seguranca e meio ambiente.
• Beneficiário: Marco Henrique Terra
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 17/01687-0 - Arquitetura e aplicações para robótica em ambientes inteligentes
• Beneficiário: Roseli Aparecida Francelin Romero
• Modalidade de apoio: Auxílio à Pesquisa - Regular