MultiSense: A Highly Reliable Wearable-free Human Fall Detection Systems

Avishek Mukherjee, Zhenghao Zhang

Abstract

A reliable fall detection system has tremendous value to the well-being of seniors living alone. We design and implement MultiSense, a novel fall detection system, which has the following desirable features. First, it does not require the human to wear any device, therefore it is convenient to seniors. Second, it has been tested in typical settings including living room and bathroom, and has shown very good accuracy. Third, it is built with inexpensive components, with expected hardware cost around $150 to cover a typical room. Therefore, it has a key advantage over the current commercial fall detection systems which all require the human to wear some device, as well as over academic research prototypes which have various limitations such as lower accuracy. The high accuracy is achieved mainly by combining senses from multiple types of sensors that complement each other, which includes a motion sensor, a heat sensor, and a floor vibration sensor. As the activities that are difficult to classify for some sensors are often not difficult for others, combining the strength of multiple types of sensors brings the performance to a level that can meet the requirements in practice.

Download


Paper Citation


in Harvard Style

Mukherjee A. and Zhang Z. (2020). MultiSense: A Highly Reliable Wearable-free Human Fall Detection Systems.In Proceedings of the 9th International Conference on Sensor Networks - Volume 1: SENSORNETS, ISBN 978-989-758-403-9, pages 29-40. DOI: 10.5220/0008957200290040


in Bibtex Style

@conference{sensornets20,
author={Avishek Mukherjee and Zhenghao Zhang},
title={MultiSense: A Highly Reliable Wearable-free Human Fall Detection Systems},
booktitle={Proceedings of the 9th International Conference on Sensor Networks - Volume 1: SENSORNETS,},
year={2020},
pages={29-40},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008957200290040},
isbn={978-989-758-403-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Sensor Networks - Volume 1: SENSORNETS,
TI - MultiSense: A Highly Reliable Wearable-free Human Fall Detection Systems
SN - 978-989-758-403-9
AU - Mukherjee A.
AU - Zhang Z.
PY - 2020
SP - 29
EP - 40
DO - 10.5220/0008957200290040