Sway Risk Analysis Based on Age Group Classification

Abstract

Human postural sway is the horizontal movement, which is generated to control a person's balance while walking or standing. Changes in postural sway patterns are a reflection of changes in brain signals and in physical health affected by a person's aging process. This increases the likelihood of falling. In this paper, we propose a method to estimate the age groups of elderly people based on the extracted sway measurements. These measurements are computed based on learning the postural sway signal from video footage only. Then, we use the person's real age and the estimated age group to define a risk of a fall for the elderly people becoming more likely. This may lead to an early intervention and help them to prevent serious falls or injuries by putting countermeasures in place, e.g. physical exercise regimes. The conducted experiments show the reliability of the proposed method to produce a risk analysis tool for elderly based on their estimated sway signals.