Fall Detection Using Multiple Bioradars and Convolutional Neural Networks.

Lesya Anishchenko,Margarita Chizh,Andrey Zhuravlev

doi:10.3390/s19245569

Lesya Anishchenko, Margarita Chizh + Show 1 more

Open Access

https://doi.org/10.3390/s19245569

Copy DOI

Abstract

A lack of effective non-contact methods for automatic fall detection, which may result in the development of health and life-threatening conditions, is a great problem of modern medicine, and in particular, geriatrics. The purpose of the present work was to investigate the advantages of utilizing a multi-bioradar system in the accuracy of remote fall detection. The proposed concept combined usage of wavelet transform and deep learning to detect fall episodes. The continuous wavelet transform was used to get a time-frequency representation of the bio-radar signal and use it as input data for a pre-trained convolutional neural network AlexNet adapted to solve the problem of detecting falls. Processing of the experimental results showed that the designed multi-bioradar system can be used as a simple and view-independent approach implementing a non-contact fall detection method with an accuracy and F1-score of 99%.

Highlights

According to the UN [1], in 2019, 9% of the world’s population was aged 65 years or older; in Europe and Northern America, which have the most aged populations, the division was even more significant (18% of citizens were over 65) [1]
Training was carried out using the scalograms of data recorded by bioradars No 1 and No 2 independently
The CNNs trained on bioradar No 1 and bioradar No 2 data were named as CNN1 and CNN2, respectively

Summary

Introduction

According to the UN [1], in 2019, 9% of the world’s population was aged 65 years or older; in Europe and Northern America, which have the most aged populations, the division was even more significant (18% of citizens were over 65) [1]. Every year the population over 65 is growing and by 2050 it will reach 15.9% for the World and 26.1% for Europe and Northern America regions, respectively [1] It is a well-known phenomenon of global population aging, which is a result of increasing longevity and fertility decline. The aging process is accompanied by negative changes in many systems and organs of the body, which may cause impaired coordination, loss of balance while changing the body position, a tendency towards fainting and dizziness, and others. These changes increase the risk of falls.

Objectives

Methods

Results

Conclusion