Detection and multi-class classification of falling in elderly people by deep belief network algorithms
- PDF / 1,964,764 Bytes
- 21 Pages / 595.276 x 790.866 pts Page_size
- 57 Downloads / 225 Views
ORIGINAL RESEARCH
Detection and multi‑class classification of falling in elderly people by deep belief network algorithms Anice Jahanjoo1 · Marjan Naderan1 · Mohammad Javad Rashti1 Received: 11 September 2019 / Accepted: 3 January 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract According to the reports on aging population, the number of elderly people without a caregiver has increased. These people are always at high risks of adverse incidents such as increased blood pressure, a variety of stroke-leading health issues, as well as other accidents resulting in body instability and eventually hazardous falls. An uncontrolled fall can result in far worse situations than the original cause itself, if the unattended patient is not promptly transmitted to a treatment center. To reduce the adverse consequences of such unfortunate events, the demand for intelligent systems to prevent, detect, and report the incidents has significantly increased during the past decade. So far, many studies have been proposed considering different aspects of the fall detection problem, from simple applied systems to complex ones regarding the detection algorithm and feature extraction methods. In this paper, a framework for smart detection, identification and notification of elderly falls is introduced. Using a personal smartphone, the tri-axial acceleration of the person’s movements is measured, and the related features are extracted following a pre-processing and timing the samples with a predefined window. The deep belief network (DBN) is used next for training and testing the system using two public datasets, with nine classes of fall and one class of daily activity. Simulation results on two generic datasets, TFall and MobiFall, show an accuracy of 97.56% sensitivity and 97.03% specificity, which is promising compared to nine other related studies. Keywords Fall detection · Feature selection · Deep belief network · Smartphone · Elderly people
1 Introduction
* Marjan Naderan [email protected]
Today intelligent systems can take on control and monitoring of daily activities for senior people by gathering and analyzing sensor data using built-in mobile-phone sensors as well as other sensors attached to or around them. One way of monitoring the condition of an elderly person is to identify their motions and continuously determine their physical balance and stability at any given movement. With the advances in mobile communication technology and data analysis methods, it is possible to develop a reliable monitoring system for a human movements to prevent fatal events caused by loss of bodily balance. Figure 1 shows a simple description of a fall detection system. Various methods have been introduced for detecting falls in elderly people based on a variety of categories, depending on the type of sensors and the kind of analysis employed (Makhlouf et al. 2019):
Mohammad Javad Rashti [email protected]
• Vision-based methods: The work in this category is based
Today, more than 900 million people in
Data Loading...
