Article
High-Efficiency Multi-Sensor System for Chair Usage Detection
Alessandro Baserga
1
, Federico Grandi
1
, Andrea Masciadri
2
, Sara Comai
2,
* and Fabio Salice
2
Citation: Baserga, A.; Grandi, F.;
Masciadri, A.; Comai, S.; Salice, F.
High-Efficiency Multi-Sensor System
for Chair Usage Detection. Sensors
2021, 21, 7580. https://doi.org/
10.3390/s21227580
Academic Editor: Joaquin Ordieres
Meré
Received: 21 September 2021
Accepted: 5 November 2021
Published: 15 November 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Department of Physics, Politecnico di Milano, 20133 Milan, Italy; alessandro.baserga@mail.polimi.it (A.B.);
federico.grandi@mail.polimi.it (F.G.)
2
Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milano, Italy;
andrea.masciadri@polimi.it (A.M.); fabio.salice@polimi.it (F.S.)
* Correspondence: sara.comai@polimi.it
Abstract:
Recognizing Activities of Daily Living (ADL) or detecting falls in domestic environments
require monitoring the movements and positions of a person. Several approaches use wearable
devices or cameras, especially for fall detection, but they are considered intrusive by many users. To
support such activities in an unobtrusive way, ambient-based solutions are available (e.g., based on
PIRs, contact sensors, etc.). In this paper, we focus on the problem of sitting detection exploiting only
unobtrusive sensors. In fact, sitting detection can be useful to understand the position of the user in
many activities of the daily routines. While identifying sitting/lying on a sofa or bed is reasonably
simple with pressure sensors, detecting whether a person is sitting on a chair is an open problem due
to the natural chair position volatility. This paper proposes a reliable, not invasive and energetically
sustainable system that can be used on chairs already present in the home. In particular, the proposed
solution fuses the data of an accelerometer and a capacitive coupling sensor to understand if a person
is sitting or not, discriminating the case of objects left on the chair. The results obtained in a real
environment setting show an accuracy of 98.6% and a precision of 95%.
Keywords:
fall detection; chair usage; ambient assisted living; capacitive coupling sensor; accelerom-
eter sensor; Activities of Daily Living
1. Introduction
Data collected by the United Nations show a clear trend regarding ageing society: in
2050, the global average age will reach the value of 38 years old, while it was barely 26
in 1990 [
1
]. According to research conducted by the University of Washington, 2.4 billion
people will be 65 years old or older, and only 1.7 billion will be 20 years old or less [
2
]. This
ageing society is a global trend hitting the developed world particularly hard, in which
the population of age over 85 will quadruple by 2050 with respect to today’s figures [
3
].
Healthcare facilities all over the world are faced with the task of taking care of a rising
percentage of the population and a drastic change in paradigm is long due to prevent
the collapse of the system. Technology favours this change, promoting a preventive-
care paradigm of welfare through monitoring tools that allow assessing the individual’s
well-being and anticipating undesirable situations with corrective actions [
4
,
5
], possibly
exploiting artificial intelligence techniques [
6
]. This concept requires the ability to monitor
and assist people in their everyday lives, especially at their own homes as a measure to
reduce healthcare costs in hospitalizations [
7
,
8
]. The goal is to create a “proactive healthcare
system” that tries to keep the patients healthy, encouraging the maintenance of physical
and cognitive abilities through the execution of specific daily activities, thus avoiding the
need for a caregiver in everyday tasks.
Several home care monitoring systems have been proposed where IoT sensors are used
to understand the Activities of Daily Living of the persons, their positions, their routines;
they possibly provide alerts to families or caregivers when anomalies occur (e.g., [
9
–
12
]).
Several solutions monitor daily activities of seniors to prevent critical situations such
Sensors 2021, 21, 7580. https://doi.org/10.3390/s21227580 https://www.mdpi.com/journal/sensors
