Presentation
Sampling Frequency Evaluation on Recurrent Neural Networks Architectures for IoT Real-time Fall Detection Devices
Author/s | Luna Perejón, Francisco
Civit Masot, Javier Muñoz Saavedra, Luis Durán López, Lourdes Amaya Rodríguez, Isabel Domínguez Morales, Juan Pedro Vicente Díaz, Saturnino Linares Barranco, Alejandro Civit Balcells, Antón Domínguez Morales, Manuel Jesús |
Department | Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores |
Publication Date | 2019 |
Deposit Date | 2019-12-19 |
Published in |
|
ISBN/ISSN | 978-989-758-384-1 |
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 ... 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. |
Project ID. | TEC2016-77785-P |
Citation | Luna Perejón, F., Civit Masot, J., Muñoz Saavedra, L., Durán López, L., Amaya Rodríguez, I., Domínguez Morales, J.P.,...,Domínguez Morales, M.J. (2019). Sampling Frequency Evaluation on Recurrent Neural Networks Architectures for IoT Real-time Fall Detection Devices. En IJCCI 2019: 11th International Joint Conference on Computational Intelligence (536-541), Vienna, Austria: ScitePress Digital Library. |
Files | Size | Format | View | Description |
---|---|---|---|---|
Sampling Frequency Evaluation ... | 1.827Mb | [PDF] | View/ | |