Sampling Frequency Evaluation on Recurrent Neural Networks Architectures for IoT Real-time Fall Detection Devices

F. Luna-Perejon, J. P. Dominguez-Morales, L. Muñoz-Saavedra, L. Duran-Lopez, I. Amaya-Rodriguez, J. P. Dominguez-Morales, S. Vicente-Diaz, A. Linares-Barranco, A. Civit-Balcells, M. J. Dominguez-Morales

2019

Abstract

Falls are one of the most frequent causes of injuries in elderly people. Wearable Fall Detection Systems provided a ubiquitous tool for monitoring and alert when these events happen. Recurrent Neural Networks (RNN) are algorithms that demonstrates a great accuracy in some problems analyzing sequential inputs, such as temporal signal values. However, their computational complexity are an obstacle for the implementation in IoT devices. This work shows a performance analysis of a set of RNN architectures when trained with data obtained using different sampling frequencies. These architectures were trained to detect both fall and fall hazards by using accelerometers and were tested with 10-fold cross validation, using the F1-score metric. The results obtained show that sampling with a frequency of 25Hz does not affect the effectiveness, based on the F1-score, which implies a substantial increase in the performance in terms of computational cost. The architectures with two RNN layers and without a first dense layer had slightly better results than the smallest architectures. In future works, the best architectures obtained will be integrated in an IoT solution to determine the effectiveness empirically.

Paper Citation

in Harvard Style

Luna-Perejon F., Civit-Masot J., Muñoz-Saavedra L., Duran-Lopez L., Amaya-Rodriguez I., Dominguez-Morales J., Vicente-Diaz S., Linares-Barranco A., Civit-Balcells A. and Dominguez-Morales M. (2019). Sampling Frequency Evaluation on Recurrent Neural Networks Architectures for IoT Real-time Fall Detection Devices. In Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - Volume 1: NCTA; ISBN 978-989-758-384-1, SciTePress, pages 536-541. DOI: 10.5220/0008494805360541

in Bibtex Style

@conference{ncta19,
author={F. Luna-Perejon and J. P. Civit-Masot and L. Muñoz-Saavedra and L. Duran-Lopez and I. Amaya-Rodriguez and J. P. Dominguez-Morales and S. Vicente-Diaz and A. Linares-Barranco and A. Civit-Balcells and M. J. Dominguez-Morales},
title={Sampling Frequency Evaluation on Recurrent Neural Networks Architectures for IoT Real-time Fall Detection Devices},
booktitle={Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - Volume 1: NCTA},
year={2019},
pages={536-541},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008494805360541},
isbn={978-989-758-384-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - Volume 1: NCTA
TI - Sampling Frequency Evaluation on Recurrent Neural Networks Architectures for IoT Real-time Fall Detection Devices
SN - 978-989-758-384-1
AU - Luna-Perejon F.
AU - Civit-Masot J.
AU - Muñoz-Saavedra L.
AU - Duran-Lopez L.
AU - Amaya-Rodriguez I.
AU - Dominguez-Morales J.
AU - Vicente-Diaz S.
AU - Linares-Barranco A.
AU - Civit-Balcells A.
AU - Dominguez-Morales M.
PY - 2019
SP - 536
EP - 541
DO - 10.5220/0008494805360541
PB - SciTePress