Feasibility of Using Floor Vibration to Detect Human Falls

Abstract

With the increasing aging population in modern society, falls as well as fall-induced injuries in elderly people become one of the major public health problems. This study proposes a classification framework that uses floor vibrations to detect fall events as well as distinguish different fall postures. A scaled 3D-printed model with twelve fully adjustable joints that can simulate human body movement was built to generate human fall data. The mass proportion of a human body takes was carefully studied and was reflected in the model. Object drops, human falling tests were carried out and the vibration signature generated in the floor was recorded for analyses. Machine learning algorithms including K-means algorithm and K nearest neighbor algorithm were introduced in the classification process. Three classifiers (human walking versus human fall, human fall versus object drop, human falls from different postures) were developed in this study. Results showed that the three proposed classifiers can achieve the accuracy of 100, 85, and 91%. This paper developed a framework of using floor vibration to build the pattern recognition system in detecting human falls based on a machine learning approach.

Acceptability of Remote Monitoring in Assisted Living/Smart Homes in the United Kingdom and Associated Use of Sounds and Vibrations—A Systematic Review

“…In answering RQ2, the searches and screening process resulted in thirteen articles to be critically appraised. Twelve [46][47][48][49][50][51][52][53][54][55][56][57] of the thirteen studies demonstrated medium to high quality, as the twelve studies had information to answer all criteria in the MMAT, with the thirteenth [56] study falling short of answering S2 and the rest of the criteria. The research hypothesis of these twelve studies was clear and relevant, focusing on vibration and/or acoustic sensing technologies in monitoring human activities.…”

“…All showed reliable data collection methods, using experiments or mixed methods to ensure the sampling strategy was appropriate and relevant to the population. Experimental studies [46][47][48][50][51][52][53][54][55][56][57] involving model development considered relevant parameters to simulate human activity. Those involving sensor development used dummy models, dolls, or human actors for sampling.…”

“…The twelve articles selected for the review comprised eleven experiments [46][47][48][50][51][52][53][54][55][56][57] and one mixed method [49]. Unlike RQ1, RQ2 resulted in three conference papers [46,52,57] as well as nine published journals [47][48][49][50][51][52][53][54][55][56].…”

An Ambient Intelligence-Based Human Behavior Monitoring Framework for Ubiquitous Environments

“…The algorithm tracked the distance between the neck of the user and the ground, and if the distance was found to decrease with a situation lasting greater than a minute, then the algorithm interpreted the situation as a fall. Shao et al [25] proposed an approach that analyzed the characteristics of floor vibrations to detect falls. The authors performed experiments with objects and humans falling on the ground to study the characteristics of floor vibrations.…”

“…Several fall detection systems are dependent on external parameters that cannot be controlled and could affect the performance characteristics. For instance, Shao et al [25] proposed a fall detection methodology based on measuring the vibrations of the floor. Several factors such as the weight of the user, the material of the floor, the condition of the floor, and other objects placed on the floor can impact the intensity of vibrations that could affect the performance of the system.…”