Content uploaded by Sheikh Nooruddin
Author content
All content in this area was uploaded by Sheikh Nooruddin on Jun 21, 2021
Content may be subject to copyright.
Vol.:(0123456789)
1 3
Journal of Ambient Intelligence and Humanized Computing
https://doi.org/10.1007/s12652-021-03248-z
ORIGINAL RESEARCH
Sensor‑based fall detection systems: areview
SheikhNooruddin1 · Md.MilonIslam1 · FalguniAhmedSharna1· HusamAlhetari2·
MuhammadNomaniKabir2,3
Received: 1 February 2020 / Accepted: 29 March 2021
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2021
Abstract
Accidental fallis one of the most prevalent causes of loss of autonomy, deaths and injuries among the elderly people. Fall
detection and rescue systems with the advancement of technology help reduce the loss of lives and injuries, as well as the
cost of healthcare systems by providing immediate emergency services to the victims of accidental falls. The aim of this
paper is to perform a systematic review of the existing sensor-based fall detection and rescue systems and to facilitate further
research in this field. The systems are reviewed based on their architecture, used sensors, performance metrics, limitations,
etc. This review also provides a taxonomy for classifying the fall detection systems. The systems have been divided into
two main categories: single sensor-based fall detection systems, and multiple sensor-based fall detection systems. Although
single sensor-based systems are very accurate in detecting falls, multiple sensor-based systems are more efficient. The low
power consumption of most single sensor-based systems especially those which are based on the accelerometer is perfect
for wearable solutions, while most multiple sensor-based systems are perfect for indoor monitoring.
Keywords Fall detection· Single sensor· Multiple sensors
1 Introduction
Accidental fall is one of the predominant causes of injury
and death for the general population, particularly the elderly.
The elderly people make up a significant part of the world
population. In 2017, 13% of the world population (962 mil-
lion people) were aged 60 or above, according to a United
Nations prediction (Sugawara and Nikaido 2014). This is
expected to about double to 2.1 billion by 2050, and about
triple to 3.1 billion by 2100 (Sugawara and Nikaido 2014).
According to the World Health Organization (WHO) (Verma
etal. 2016), accidental falls are the second leading cause
of premature death from injury. Every year, an estimated
646,000 falls result in fatalities over the world and 37.3 mil-
lion falls require immediate medical attention (Verma etal.
2016). Adults over 60years of age have the highest fall-
related death rates and adults over 65years of age suffer
the highest number of fatal falls (Verma etal. 2016). These
fall events result in a loss of 17 million disability-adjusted
life years. Disability-adjusted life years denote the potential
years of “healthy” life lost due to premature death or dis-
abilities caused by unfortunate events. Fall events also result
in significant monetary loss for both the individual and the
state. The average cost of the health care system per fall
injury for people over 65years of age is US$ 1049 and US$
3611 in Australia and the Republic of Finland, respectively
(Verma etal. 2016).
In general, most fall events occur at home due to an abun-
dance of potential fall hazards (Hamm etal. 2016). Common
* Muhammad Nomani Kabir
dr.nomankabir@gmail.com
Sheikh Nooruddin
nooruddinimad@gmail.com
Md. Milon Islam
milonislam@cse.kuet.ac.bd
Falguni Ahmed Sharna
falguniahmed114@gmail.com
Husam Alhetari
husamalhetari@gmail.com
1 Department ofComputer Science andEngineering, Khulna
University ofEngineering & Technology, Khulna9203,
Bangladesh
2 Faculty ofComputing, Universiti Malaysia Pahang,
Gambang, 26300Kuantan, Pahang, Malaysia
3 Department ofComputer Science & Engineering, Trust
University, Ruiya, Nobogram Road, Barishal8200,
Bangladesh
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
hazards include but not limited to slippery floors, obstructed
ways, clutter, pets, unstable furniture, and poor lighting con-
ditions (Lord etal. 2006). The average elderly population is
less prone to falls than older people suffering from severe
neurological diseases, e.g., dementia and epilepsy (Homann
etal. 2013), (Wang etal. 2016), (Rawashdeh etal. 2012),
(Rahaman etal. 2019). Risk of falls also increases due to sol-
itary living arrangements (Bergen etal. 2016), (O’Loughlin
etal. 1993). However, in most cases, the falls do not result
in loss of lives. Life-threatening complications arise when
the affected person does not get the necessary treatment in
time and remains on the floor for a prolonged period without
others’ notice (Vallabh and Malekian 2018), (Sterling etal.
2001), (Islam etal. 2020), (Parkkari etal. 1999), (Jager etal.
2000), (Florence etal. 2018).
Making the entire home environment fall-proof is not a
feasible solution (Pynoos etal. 2010), (Pynoos etal. 2012).
However, the advancement of fall detection technologies
enables automated systems to detect falls in an environment
and minimizes both the damage and the response time by
notifying the emergency services and caregivers of the fall
event (Doulamis 2010), (Mukhopadhyay 2015), (Delahoz
and Labrador 2014), (Chaudhuri etal. 2014), (Noury etal.
2007), (Igual etal. 2013), (Mubashir etal. 2013).
Modern fall detection systems involve the following
stages: data collection stage, feature extraction stage, detec-
tion stage or learning stage (Noury etal. 2007), (Igual etal.
2013), (Mubashir etal. 2013), (Nooruddin etal. 2020). Rel-
evant fall and Activities of Daily Living (ADL) motion data
of users are collected via sensors in the data collection stage.
Many types of sensors can be used to acquire the motion
data. Meaningful features are extracted from the raw sensor
data in the feature extraction stage. The systems that use
machine learning algorithms to classify the motion data use
the extracted features to train the model. The trained model
is then deployed and used to classify future motion data. The
threshold-based systems compare the extracted features with
predetermined values to classify the motion data (Rahman
etal. 2020, Islam etal. 2019, Buke etal. 2015, Bagalà etal.
2012.
Many monitoring and fall detection systems were
reviewed in (Mukhopadhyay 2015), (Delahoz and Labra-
dor 2014), (Chaudhuri etal. 2014), (Noury etal. 2007),
(Igual etal. 2013), (Mubashir etal. 2013), (Bet etal. 2019).
Mubashir etal. (2013) classified fall detection systems into
three types: wearable, vision-based, and ambient/fusion.
Typically, the sensors that are used to develop wearable fall
detection systems comprise accelerometer, gyroscope, depth
sensor, infrared sensor, acoustic sensor and vibration sensor.
Video surveillance and Doppler radars are used for real-time
monitoring-based fall detection systems (Mubashir etal.
2013), (Islam etal. 2019). A combination of monitoring
systems and wearable sensors are used in ambient/fusion
based systems.
Mukhopadhyay etal. (2015) reviewed the wearable solu-
tions used in fall detection and rescue systems. The types
of sensors, the wireless protocols used in the applications,
the monitored activities, design challenges of the solutions
and energy consumption of the sensors, as well as current
market situation and future trends were reviewed. Delahoz
and Labrador (2014) reviewed machine learning based fall
detection and fall prevention systems. The general structure
of fall detection systems was presented as a collection of
three modules: data collection module, feature extraction
module and learning module. The design issues such as
occlusion, multiple people, obtrusion, privacy, aging, com-
putational cost, energy consumption, noise and difficulty
in choosing thresholds were considered. The fall detection
systems were reviewed based on the overall position of the
sensors. The reviewed sensors were divided into two types:
external sensors and wearable sensors. The external sensors
were divided into camera-based sensors and ambient sen-
sors. The authors also discussed the various environmental,
psychological, and physical factors of falls. Chaudhuri etal.
(2014) reviewed fall detection systems systematically and
provided quality scoring based on a condensed version of
the Statement of Reporting of Evaluation Studies in Health
Informatics (STARE-HI). The reviewed fall detection sys-
tems were divided into two main categories: wearable and
non-wearable systems. The categorization was based on the
position of the detecting sensor. If the sensors were worn by
the monitored person, the respective system was categorized
as a wearable system. If the sensors were mounted on a sta-
tionary platform, the respective system was categorized as
a non-wearable system. The used sensors were grouped into
general types such as motion sensors, floor sensors, cameras,
etc. The systems that used a combination of multiple systems
for accurate fall detection were also reviewed.
Noury etal. (2007) reviewed the fall detection systems
and grouped them into two main categories: analytical meth-
ods and machine learning methods. Analytical methods
mainly detect the lying position from various sensors, such
as horizontal inclination sensors and floor sensors. Machine
learning methods leverage large datasets and machine learn-
ing classifier models detect falls from sensor data. Igual
etal. (2013) categorized the reviewed fall detection systems
into two main types: context-aware systems and wearable
devices. In context-aware systems, the sensors are deployed
in the environment. In this case, the sensors are stationary
and overlook a fixed environment. On the other hand, in
wearable systems, the sensors are placed on different posi-
tions, e.g., chest, waist, and wrist of the monitored person.
The methods of the context-aware systems can be broadly
categorized into three main stages: data collection and pro-
cessing, feature extraction, and inference stage. Smartphone
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
based fall detection systems were also reviewed. The cur-
rent and future trends of computer vision-based detectors
and machine learning based approaches were discussed.
Various design challenges such as performance of usabil-
ity, acceptance, and social stigma related to such devices
were discussed. Various issues related to fall detection tech-
nology such as smartphone limitations, privacy concerns,
availability of public datasets, and real-life falls were also
considered in the review. Bet etal. (2019) reviewed wearable
sensor-based fall detection systems and explored the types
of commonly used sensors, their sampling rate, the type of
the signal acquisition and data processing method used, the
functional tests performed on the system, and the types of
application. Four main types of sensors, namely: accelerom-
eter, gyroscope, magnetometer, and barometer were mostly
used in the reviewed systems. The systems developed in
(Safi etal. 2015), (Hu etal. 2018), (Buke etal. 2015) also
reviewed inertial wearable sensors. Some computer vision-
based fall detection systems were reviewed in (Zhang etal.
2015), (Erden etal. 2016). Various available public fall
detection datasets and the performance of various systems
on those datasets were discussed in (Khan and Hoey 2017),
(Igual etal. 2015), and (Casilari etal. 2017).
It is evident from the current review works that in cur-
rent literature, fall detection systems are divided into two
broad categories: wearable systems and non-wearable sys-
tems based on the “wearability” perspective. The categoriza-
tion of the systems in existing literature into two groups—
context-aware and wearable systems—is also based on a
similar perspective. The categorization of the systems into
two types—analytical methods and machine learning meth-
ods—is based on the “classification methodology” perspec-
tive. The categorization of the systems by existing literature
into three categories—wearable, vision-based and ambient
or fusion—is based on the “used sensor type” perspective.
In this case, the non-wearable systems are further divided
into the vision-based and ambient-based categories. Many
other reviews are conducted on a specific sub-category of
fall-detection systems, such as inertial sensors-based wear-
able systems, computer vision-based systems, etc. Most of
the review works till now have categorized fall detection
systems based on whether the system is wearable or not.
However, the number of sensors used and their type is a
major specification of any fall detection system. While some
systems only employ a single sensor for data collection pur-
poses, other systems use multiple sensors. Both kinds of
systems have achieved state-of-the-art results.
The purpose of this review work is the systematic assess-
ment of recent fall detection systems. We provide a tax-
onomy categorizing the developed fall detection systems
based on the number of used sensors. We reviewed the sys-
tems considering the following issues: system type (single/
multiple sensors), system technologies, system working
principles, and the merits and demerits of the system. The
research was limited to peer reviewed articles which were
written in English and published between the years 2014 and
early 2019 in scientific journals or magazines or presented
in conferences. The research was restricted to a number
of sources, namely: Google Scholar, PubMed, EMBASE,
CINAHL, and NCBI. Additionally, to acquire fall statistics,
a manual search was carried out on books and publications
by organizations that focus on statistics of accidental falls
and their consequences, such as the World Health Organiza-
tion (WHO). The keywords used, for searching the databases
or for manual web searches, were the following: “fall detec-
tion”, “fall detection and rescue systems”, “fall statistics”,
“fall prevention”, “sensor-based fall detection”, and “fall
monitoring”. The titles and abstracts from the search results
were analyzed to eliminate duplicates and publications that
were beyond the scope of this review work. After thoroughly
reading and evaluating the remaining publications, specific
topics of interest in the review articles were identified and
quantified. Our main focus was on fall detection systems
that employ some kind of sensors for data acquisition and
detection.
The remaining part of the paper is organized as follows:
Sect.2 describes the fall detection systems with two catego-
ries: single sensor-based and multiple sensor-based systems.
The results and detailed discussion of the review are pre-
sented in Sect.3. Section4 concludes the review.
2 Literature review onfall detection
systems
Many organizations have been working for a long time to
make cost-effective and well-organized fall detection sys-
tems for the elderly. The work associated with this field is
reviewed as follows.
All the systems that are reviewed in this paper are cat-
egorized into two groups: single sensor-based systems and
multiple sensor-based systems. The categorization is done
based on how many sensors for the system have been used to
capture the real-world scenario. Single sensor-based systems
use the data from only one sensor for feature extraction and
classification. Multiple sensor-based systems use data from
multiple sensors for feature extraction and classification. The
sensors such as Wi-Fi or Bluetooth modules (communica-
tion purpose) which are not used for feature extraction or
classification purposes are not considered during categoriza-
tion. The taxonomy of the reviewed fall detection systems is
depicted in Fig.1.
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
2.1 Single sensor‑based fall detection systems
Single sensor-based systems rely on a single sensor or a sin-
gle module for data collection. Single sensor-based systems
use one of the sensors or modules, e.g., accelerometer, gyro-
scope or depth camera for data collection. The collected data
is then processed and passed to a detection technique, e.g.,
threshold-based algorithm (Chen etal. 2019), (Mehmood
etal. 2019), machine learning model or statistical model
(Sanchez and Muñoz 2019), (Yhdego etal. 2019), (Yac-
chirema etal. 2019). Systems that employ a threshold-based
algorithm test the collected data against preset data for
detection. Systems that employ machine learning or statis-
tical models pass the collected data to a pre-trained model
that was trained on a similar dataset. Various open-access
datasets are available for single sensor-based ADL and fall
detection (Igual etal. 2015), (Casilari etal. 2017), (Khan
and Hoey 2017).
2.1.1 Fall detection using accelerometer
Anaccelerometeris a device that measures theacceleration
or rate of change of velocity of a body in its instantaneous
rest frame. Single-axis and multi-axis models of the accel-
erometer are available to detect the magnitude and direction
of the proper acceleration, as a vector quantity. Sense orien-
tation, vibration, shock, falling in a resistive environment,
etc. are popular applications of accelerometers (Rand etal.
2009), (Ward etal. 2005). Almost all of the modern portable
devices contain Microelectromechanicalsystems(MEMS)
accelerometers. These accelerometers are used for detecting
screen orientation, position, etc. However, they are perfectly
capable of detecting fall events (Lee and Tseng 2019), (San-
tos etal. 2019), (Thanh etal. 2019), (Ranakoti etal. 2019).
Data from accelerometers can be used in machine learning,
statistical models (Santos etal. 2019) or threshold-based
algorithms (Lee and Tseng 2019) for fall detection.
Chen etal. (2019) proposed a wrist-worn accelerator-
based fall detection system by combining ensemble stacked
auto-encoders (ESAEs) and one class classification based
on the convex hull (OCCCH). ESAEs were used to over-
come the disadvantages of ANNs and unsupervised feature
extraction was done. The pattern recognition task was per-
formed by the OCCCH. The strategies such as majority vot-
ing and weight adaptive adjustment were used to improve
the overall performance of the system. Two experiments
were performed to validate the overall performance of the
system. Experiment I involved fall and ADL data from 6
volunteers. Experiment II involved fall and ADL data from
11 volunteers from a different group. All fall data was reg-
istered while falling on a yoga mat, whereas, all ADL data
are real-world data. In experiment I, the system achieved
accuracy, sensitivity, and specificity of 97.45, 96.09, and
98.92%, respectively. The system achieved accuracy, sensi-
tivity, and specificity of 97.82, 99.30, and 96.36%, respec-
tively in experiment II. Mehmood etal. (2019) proposed a
tri-axial accelerometer based fall detection system that uses
Mahalanobis distance for detecting falls in real-time data.
Mahalanobis distance is used to calculate distances between
two points. However, Mahalanobis distance does not require
the points to be of the same data group, thus enabling cal-
culating distance between points of groups of different
sizes. Three types of ADLs: walking, standing posture, get-
ting up, and sitting on chair were recorder. Four volunteers
recorded the fall motions in a laboratory environment. The
calculated Mahalanobis distance was compared against a
threshold value for determining whether a fall occurred or
not. However, the prototype used Bluetooth technology to
communicate with the main computer which processes the
data, constraining the versatility of the device. The devel-
oped system achieved 96% accuracy from the experiment.
Yhdego et al. (2019) developed an accelerometer-
based fall detection system that used transfer learning with
AlexNet and continuous wavelet transform for fall detection.
The URFD public dataset was used as the main data source.
Fig. 1 Taxonomy of the
reviewed fall detection systems Reviewable Fall Detection Systems
Single Sensor-Based Systems
Accelerometer
Depth Camera
Infrared Sensor
Radar
802.11n NIC
Multiple Sensor-Based Systems
Accelerometer and Camera
Accelerometer and Gyroscope
Accelerometer, Gyroscope, and Depth
Accelerometer, Cardiotachometer, and Smart
Accelerometer, Gyroscope, and UWB Location Tags
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
A continuous wavelet transform was performed on the data
in the data processing stage. AlexNet was trained on the data
using transfer learning. ImageNet weights were used in the
pre-trained model. The deep convolutional neural network
based system achieved 96.43% accuracy, 95.83% sensitivity,
and 96.875% specificity. Yacchirema etal. (2019) proposed a
tri-axial accelerometer based wearable fall detection system
that used a random forest algorithm to properly distinguish
between ADL and fall events. The system is waist-mounted.
The system also has a rescue component to monitor the
persons. The random forest algorithm outperformed other
logistic regression and convolutional neural network based
models. The system achieved 98.72% accuracy, 94.60%
specificity, and 96.22% sensitivity.
Cao etal. (2016) proposed a fall detection system that
collects acceleration data of the human chest using a weara-
ble device containing a triaxial accelerometer. The collected
data from the sensor is used for fall detection using Hid-
den Markov Model (HMM). The Feature Sequences (FSs)
extracted from the accelerometer are used to train the HMM.
The framework achieved the accuracy, sensitivity, and speci-
ficity of 97.2, 91.7, and 100%, respectively. The parameters
of HMM in this literature might not be optimal as the train-
ing samples used are collected from the simulated motion
process, not from real practice falls. Aguiar etal. (2014)
developed an unobtrusive smartphone-based fall detection
system. The accelerometer data of the smartphone placed in
the user’s belt or pocket is continuously monitored. 14 differ-
ent signal components are computed from the acceleration
vectors and passed through a Butterworth digital filter. The
computed signal components are x, y, z projections, angles
and magnitude value along the three axes of the phone. A
decision tree is used to select the most significant features
and calculate the thresholds. These thresholds are then used
in a state machine to classify fall events. The system also
incorporates a rescue system. In case of a fall scenario,
it sends the location info of the patient to the emergency
services and caregivers, thus ensuring immediate medical
assistance. The system was tested in two positions: belt and
pocket. The specificity and sensitivity of the system are
close to 99% and 97%, respectively, for both usage positions.
Power consumption is a major concern for the system as it
continuously monitors the accelerometer data of the device.
Lim etal. (2014) proposed a highly efficient activity
monitoring system. To filter possible fall events, the system
uses simple thresholds from fall-feature parameters calcu-
lated from a single triaxial accelerometer. A Hidden Markov
Model (HMM) is then used on the possible fall events to dis-
tinguish between actual fall events and fall-like events. Thus,
this system conserves computational cost and resources by
using the Hidden Markov Model (HMM) only for classi-
fying possible fall events. The system is chest-mounted as
the chest is the closest to the body’s center of gravity. The
best results were obtained when the threshold parameters
were set as ASVM = 2.5g and θ = 55°. The system achieved
99.5% accuracy, 99.69% specificity, and 99.17% sensitivity,
respectively.
2.1.2 Fall detection using depth camera
Depth cameras are used to produce a 2D image represent-
ing the distance to points in a scene from a specific point.
The pixel values of the resultant image correspond to the
depth or distance of the points. Images from generated
from RGB cameras do not contain depth information.
Pixels in normal images correspond to intensities of the
corresponding points. Depth cameras and their generated
depth images can be used to properly determine the posi-
tion of an object or a person in an environment (Xu etal.
2019). Depth images can be used for detecting fall events
(Xu etal. 2019), (Kong etal. 2019). Depth camera-based
systems almost exclusively employ machine learning mod-
els for detection and classification of fall and ADL events.
Ding etal. (2017) introduced a detection algorithm
employing depth images collected from a Kinect sensor
using wavelet moment. At first, the algorithm normal-
izes the depth image according to each pixel in the image
relative to the distance from the centroid and polar coor-
dinates. The feature vectors are extracted after perform-
ing Fast Fourier Transform (FFT) of the image. Wavelet
transform is used in the extraction process. Finally, Sup-
port Vector Machine (SVM) classification methods and
the minimum distance are used to detect the fall. The algo-
rithm was tested on 100 images (non-fall 58 images and
42 fall images). The accuracy of detecting fall images is
about 88% and the accuracy of detecting non-fall images
is about 90%. The algorithm currently monitors only one
user. The effectiveness of the algorithm on multiple users
can be checked in the future. Kong etal. (2017) proposed
an algorithm for fall detection. The system relies on a
depth camera. The RGB-D camera is placed at 2m from
the ground. The binary images found through the depth
camera are passed through a canny filter for getting the
outline of the images. Then 15° groups were created by
dividing the calculated tangent vector angles of all the
white angles in the outline image. The value of the tangent
angles (in most of the cases) below 45° considered a fall.
The system appraised the accuracy, sensitivity, specific-
ity of 97.1, 94.9, and 100%, respectively. As the system
uses an RGB-D camera, it can work perfectly even in dark
conditions. The system also works on environments where
more than one person is present. Tran etal. (2014) pro-
posed a novel approach that defines and computes three
distinct features (angle, distance, velocity) of 8 upper body
joints (Head, Shoulder_Right, Shoulder_Center, Shoul-
der_Left, Spine, Hip_Right, Hip_center, Hip_Left). The
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
activities are represented as a set of three values (angle,
distance, velocity) of several joints of the human skeleton
that are known as feature vectors in the prototype. These
feature vectors are provided as inputs for training or test-
ing SVM classifiers. Using a combination oftwo joints:
head and spine with two features: distance and velocity
provided the best results. The transition time should also
be taken into account for reducing the number of fall posi-
tives of the proposed system in the future.
2.1.3 Fall detection using infrared sensor
An infrared sensor is an electronic sensor that measures
infrared light radiating from the objects in the field of view.
IR sensors can detect general movement but cannot provide
information on the moving subject itself. As humans mostly
give off infrared radiation, IR sensors can be used to monitor
human movement (Martínez-Villaseñor etal. 2019), (Mou-
lik and Majumdar 2019). Infrared based systems are also
mostly surveillance oriented. IR sensor-generated data are
normally used to create 3D images or blocks representing
environmental infrared radiation information (Mastorakis
and Makris 2014). After feature extraction, various machine
learning or statistical models are used to detect the fall and
ADL events (Martínez-Villaseñor etal. 2019), (Moulik and
Majumdar 2019), (Mastorakis and Makris 2014).
Chen and Ma (2015) adopted an infrared sensor array
composed of a 16 × 4 thermopile array with corresponding
60° × 16.4° field of view. Two sensors attached to different
places in the wall that capture the three-dimensional image
information. The temperature difference characteristic is
then used to subtract the image from the background model
to determine the foreground of the human body. The Angle
of Arrival (AOA) from each sensor is obtained by using the
foreground temperature. An AOA based positioning algo-
rithm is used to estimate the location and the location is
then passed to a regression model to reduce the positioning
error. As the two sensors capture any action simultaneously,
the fall detection algorithm extracts feature from the sensor
with the larger foreground region. The extracted features
are then applied to the k-Nearest Neighbor (k-NN) classi-
fication model which classifies them into fall and non-fall
events. This system managed to distinguish fall event with
93% total accuracy, 95.25% sensitivity, and 90.75% specific-
ity. Jankowski etal. (2015) proposed a system based on IR
depth sensor measurements. A feature selection block by
Gram-Schmidt orthogonalization and a Nonlinear Principal
Component Analysis (NPCA) block is used to improve the
effectiveness of discriminative statistical classifiers (multi-
layer perceptron). The feature selection block determines the
ranking of the features. NPCA block transforms the raw data
into a nonlinear manifold, thus reducing the dimensional-
ity of the data to two dimensions. The system obtained an
accuracy of 93% and a sensitivity of 92%. The deep learn-
ing classifier structure used 5 hidden neurons, whereas, the
neural networks used 15 hidden neurons.
2.1.4 Fall detection using radar
Radars are devices for tracking objects using radio waves
to determine their position, size and velocity. A radar sys-
tem normally consists of a transmitter capable of generating
electromagnetic waves in the radio and microwave spectrum,
a receiving antenna, a receiver, a transmitting antenna and
a processor to determine the characteristics of the objects.
The transmitter transmits radio waves. These waves reflect
off the objects. The object’s location and speed can be cal-
culated from the reflected waves (Rana etal. 2019). Doppler
radars have been extensively used in fall detection systems
(Yoshino etal. 2019), (Su etal. 2015). Doppler radars are
specialized radars that employ the Doppler effect. Doppler
radars emit microwave signals and analyze how the objects
alter the frequencies of the returned signal. Various signal
processing techniques are generally used to detect falls from
radar data (Yoshino etal. 2019), (Sadreazami etal. 2019),
(Sadreazami etal. 2020), (Ding etal. 2019), (Erol and Amin
2019).
Jokanovic etal. (2016) used a monostatic Continuous
Wave (CW) Radar for fall detection. In the proposed system,
radar returns nonstationary-natured signals corresponding
to normal human motions. Thus, constant and higher-order
velocity components of various parts of the human body
under motion can be revealed using time–frequency (TF)
analysis can be used to extract the higher-order and con-
stant velocity components of various parts of the human
body. This system uses a TF-based deep learning approach
for detecting fall events. The proposed approach in the sys-
tem captures the TF signature properties automatically and
applies the features to the softmax regression classifier.
The system uses stacked auto-encoders for feature extrac-
tion. The system achieved 87% success rate in detection
fall events. Su etal. (2015) developed a detection system
that employed a Doppler range control radar. The radar is
ceiling mounted. The radar senses the falls and non-falls
from the Doppler Effect. The Wavelet Transform is used to
distinguish among the activity events. The system at first
uses the coefficients of wavelet decomposition at a given
scale for identifying the time locations of the possible fall
events. Then the time–frequency content is extracted from
the wave coefficients at many scales and a feature vector is
formed for classification. Out of the different wavelet func-
tions tested in the system, higher detection accuracy was
reached using “bior2.2”, “db3”, “rbio1.3”, “rbio3.3”, and
“sym3,” for the prescreening stage and “bior2.6”, “coif4”,
“db10”, “db11”, and “rbio3.3” for the classification stage.
This system can be used in any indoor scenarios including
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
bathrooms as this system does not compromise the privacy
of the user. With the use of the WT pre-screener and clas-
sifier, the system achieved 93% accuracy, 97.1% sensitivity,
and 92.2% specificity.
2.1.5 Fall detection using 802.11n NIC
The wireless medium consists of electromagnetic signals
in the radio or microwave spectrum. These signals contain
binary data. The channel data resulting from humans affect-
ing the wireless medium can be used in machine learning
or statistical models for fall detection (Fung etal. 2019),
(Wang etal. 2017).
Wang etal. (2017) developed a system named WiFall.
Human activities affect the wireless medium. WiFall takes
the time variability and special diversity of Channel State
Information (CSI) as an indication of human activities. As
CSI is available in almost all of the current wireless infra-
structure, WiFall does not require any hardware modifi-
cation or wearable devices or any kind of environmental
modifications. The system used WiFall on laptops equipped
with commercial 802.11n NICs. The channel properties of a
communication link can be estimated by CSI. It can also be
used to detect human motion because human motion affects
wireless propagation space, creating different patterns in the
received signal. A one-class SVM was used to distinguish
human fall based on the features extracted from the anomaly
patterns. WiFall achieved 87% positive detection rate and
18% false detection rate in laboratory experiments.
It can be observed from the reviewed single sensor-based
works that there are three major distinct stages in single sen-
sor-based fall detection systems. The first distinct stage is the
data collection stage. In this stage, single sensor modalities
are used to collect raw data. The reviewed systems used vari-
ous sensing modalities, e.g., tri-axial accelerometer, depth
camera, infrared sensor, radar, 802.11n NIC, etc. to collect
data from the patients. The second major distinct stage is the
feature extraction stage. In this stage, various methods are
used to extract meaningful information and features from
the data collected in the previous stage. The majority of
the reviewed works used various feature extraction methods,
such as ESAE, FFT, wavelet transform and stacked auto-
encoders to extract features from the collected data. The
third distinct stage is the classification stage. The extracted
features from the previous stage are classified using vari-
ous methods in this stage. The reviewed single sensor-based
fall detection systems used various threshold and artificial
intelligence-based methods to classify the extracted features.
Considering these three stages, a general architecture of sin-
gle sensor-based fall detection systems which are found from
the reviewed works is presented in Fig.2.
Table1 summarizes the above described single sensor-
based systems considering the following issues: sensor
type, location of the used sensor, portability of the system,
indoor-outdoor use, user privacy, accuracy, sensitivity, and
specificity.
2.2 Multiple sensor‑based fall detection systems
Multiple sensor-based systems depend on multiple sensors
for capturing the real-world scenario. The systems normally
rely on a fusion of sensors, such as gyroscope, accelerometer
and depth camera for data collection purposes. The data col-
lected from multiple sensors are processed differently and
then used in threshold-based algorithms (Cillis etal. 2015)
or machine learning models for detection (Boutellaa etal.
2019), (Wu etal. 2019).
2.2.1 Fall detection using accelerometer andcamera
Accelerometers are used to determine the acceleration of a
body along several axes. Cameras provide information about
the movement of the patient, as well as the environment
around the patient. Both still images and video sequences
can be used for fall detection. Still images are normally
multidimensional matrices where an entry implying a pixel
Fig. 2 General architecture of
single sensor-based fall detec-
tion systems
Accelerometer
Gyroscope
Depth Camera
RGB Camera
Infrared Sensor
Single Sensor
Motion Data
Pretrained
Models
Predefined
Thresholds
Feature
Extraction
Raw Sensor
Data
Results
Detection StageData Collection Stage
Feature Extraction Stage
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
represents the intensity of the light on that location. Vid-
eos are sequences of still images. Various image processing
techniques employing shape information and segmentation
techniques can be used on video sequences for fall detection
(Ozcan and Velipasalar 2016), (Zerrouki etal. 2016).
Zerrouki etal. (2016) used the Exponentially Weighted
Moving Average (EWMA) monitoring scheme on the accel-
erometric data to detect potential falls. Only the features
corresponding to detected falls were then classified using
SVM into true falls and fall like events. A background sub-
traction technique was used to extract the body silhouette
from the input image sequence. Thus, unchanged pixels in
the frame sequence were eliminated by using the background
image as a reference. This EWMA-SVM classification sys-
tem outperformed Neural Network, k-NN, andNaive Bayes
classifiers (AUCNN = 0.94, AUCKNN = 0.93, AUCNaive-
Bayes = 0.95 and AUCEWMA-SVM = 0.97). The system
achieved an overall accuracy of 96.77%. But the system has
still some shortcomings. The RGB camera used in this sys-
tem is not capable of extracting the human silhouette in dark
conditions. The dataset used in the system is collected from
the University of Rzeszow named as fall detection dataset
(URFD) (Kwolek and Kepski 2014) to test the system. The
dataset contained the fall events and ADL from volunteers
who are normally over the age of 26. The volunteers used in
the dataset do not reflect the elderly community.
Ozcan and Velipasalar (2016) proposed a system employ-
ing camera and accelerometer sensors of smartphones to
assist the elderly. The system uses histograms of edge orients
with gradient local binary patterns as the main features. For
the accelerometer-based part of fall detection, the system
checks if the magnitude of the 3-axis vector is greater than
the empirically determined threshold. The 3-axis vector is
obtained by observing the magnitude of linear acceleration
with the gravity component extracted from the correspond-
ing direction. This system performed better than other sys-
tems which used Histograms of Oriented Gradients (HOG)
and its variants for feature extraction. The system achieved
96.36% sensitivity and 92.45% specificity in detecting falls
from standing and 90.91% sensitivity and 66.04% specificity
in detecting falls from sitting.
Table 1 Summary of the single sensor-based fall detection systems
*N/A not appropriately defined, I indoor use only, B both indoor and outdoor use
Authors Used Sensor Location of
Sensor
Portability Indoor/
Outdoor
Use
User Privacy Accuracy (%) Sensitivity (%) Specificity (%)
Chen etal.
(2019)
Accelerometer Wrist 2 B 2 97.82 99.30 96.36
Mehmood etal.
(2019)
Accelerometer Waist 2 B 2 96.00 N/A N/A
Yhdego etal.
(2019)
Accelerometer N/A 2 B 2 96.43 95.83 96.87
Yacchirema etal.
(2019)
Accelerometer Waist 2 B 2 98.72 96.22 94.60
Cao etal. (2016) Accelerometer Chest 1 B 2 97.20 91.70 100
Aguiar etal.
(2014)
Accelerometer Belt/pocket 2 B 2 N/A 97.00 99.00
Lim etal. (2014) Accelerometer Chest 1 B 2 99.50 99.17 99.69
Ding etal. (2017) Depth camera N/A 0 I 1 89.00 N/A N/A
Kong etal.
(2017)
RGB-D camera 2m from ground 0 I 1 97.10 94.90 100
Tran etal. (2014) Depth camera N/A 0 I 1 N/A N/A N/A
Chen and Ma
(2015)
Infrared sensor
array
Wall 0 I 1 93.00 95.25 90.75
Jankowski etal.
(2015)
Infrared depth
sensor
N/A 0 I 1 93.00 92.00 N/A
Jokanovic etal.
(2016)
Monostatic CW
radar
N/A 0 I 1 87.00 N/A N/A
Su etal. (2015) Doppler radar Ceiling 0 I 1 93.00 97.10 92.20
Wang etal.
(2017)
802.11n NIC N/A 0 I 2 87.00 N/A N/A
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
2.2.2 Fall detection using accelerometer andgyroscope
While accelerometers provide an overall motion of a body
along several axes, gyroscopes provide information about
the orientation and angular velocity of the body. Acceler-
ometers and gyroscopes can be combined to create highly
accurate fall detection systems (Bet etal. 2019), (Kwon etal.
2019).
Wu etal. (2019) proposed a multiple sensor-based fall
detection system that used a novel threshold derived from
a multivariate control chart to detect falls in motion data.
Two types of sensors namely: accelerometer and gyroscope
are used in the system. The sensors are fixed on the waist,
arm, and thigh location of the monitored person. In the data
processing stage, the Autoregressive Integrated Moving
Average (ARIMA) technique is used to remove autocorre-
lation, and PCA is used to reduce dimensionality from the
multidimensional data. In the classification stage, falls and
ADLs are differentiated by using a multivariate statistical
process control chart. The system is person-specific as the
threshold value is calculated from individual historical data.
The developed system achieved 95.2% specificity and 94.8%
sensitivity.
Cillis etal. (2015) introduced a smartphone-based fall
detection that used accelerometer and gyroscope to collect
the data from the real-time environment (Inertial Measure-
ment Units and/or Smartphones). The system combined the
user’s heading with the instantaneous acceleration magni-
tude vector in a Threshold Based Algorithm (TBA). The
best performance was achieved using a threshold-based
algorithm combining gyroscope and accelerometer informa-
tion. The system achieved 100% accuracy in discriminating
between falls and ADLs using this approach. Huynh etal.
(2015) developed an approach using a combination of accel-
erometer and gyroscope sensors for robust fall detection.
The system implemented an optimization schema using the
Receiver Operating Characteristic (ROC) curve and itera-
tive analysis of sensitivity and specificity and determined
critical thresholds for LFTacc, UFTacc, and UFTgyro to be
0.30g–0.35g, 2.4g, and 240°/s, respectively. The system
achieved 96.3% sensitivity and 96.2% specificity, respec-
tively, using an accelerometer, gyroscope, and a ROC opti-
mization strategy. While the system is very effective for
detecting falls, it might be less effective in determining near
fall detection scenarios. For testing, the sensors were worn
in the chest.
2.2.3 Fall detection using accelerometer, gyroscope
anddepth camera
Still images generated from RGB cameras do not contain
any depth information about the subject or the environ-
ment. Depth cameras generate images that contain the depth
information of the environment. This depth information can
be used to accurately track a subject’s location in the envi-
ronment (Xu etal. 2019), (Kong etal. 2019), (Kwolek and
Kepski 2014).
Kwolek and Kepski (2014) used a tri-axial accelerom-
eter and a gyroscope to observe and detect potential falls
as well as the motion of the user. If the calculated accelera-
tion passes a set threshold, the person is extracted from the
depth images taken from the Kinect, features are calculated
and finally, SVM classifier is used to classify the action
and initialize the fall alarm. The system achieved accu-
racy, sensitivity, and specificity of 98.33, 100, and 96.67%
when SVM was used to classify based on depth images
and accelerometer data. The dataset developed and used in
this system is named University of Rzeszow Fall Detection
dataset (URFD) (Kwolek and Kepski 2014) and is publicly
available. However, as this system relies heavily on depth
images from the Kinect sensor, this system is most suitable
for indoor uses as the sunlight interferes with the depth esti-
mation of the Kinect device in an outdoor scenario.
2.2.4 Fall detection using accelerometer, cardiotachometer
andsmart sensors
Cardiotachometer is a device that is used for a prolonged
graphical recording of the heartbeat. Fall events result in
accelerated heart rates. Thus, cardiotachometer readings are
useful in detecting fall events (Gia etal. 2018).
A multi-functional data acquisition board was proposed
by Wang etal. (2014) which incorporated temperature and
humidity sensors, a low power 3-axis accelerometer, a GPS
module, a cardiotachometer, and a wireless communication
module. The threshold-based algorithm used in this system
relies on three features for accurate fall detection such as
impact magnitude, trunk angle, and after-event heart rate.
The system achieved 97.5% total accuracy, 96.8% sensitivity,
and 98.1% specificity.
2.2.5 Fall detection using accelerometer, gyroscope
andUWB location tags
UWB location tags provide continuous location informa-
tion to the receiver. This location information can be used
to determine the real-time location of a patient in a closed
environment. Several other sensors can be combined with
the location information to detect fall events (Gjoreski etal.
2014).
A system named CoFDILS using body-worn inertial and
location sensors proposed by Gjoreski etal. (2014). Three
context components such as the user’s activity, body accel-
erations, and location information are used to determine the
occurrence of a fall. A context-based reasoning schema is
used in the system. Each of the three components uses the
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
information from the other two components as context and
determines the user’s situation. Each component is assigned
a context variable. The context variable contains the value
of the component at each point in time. A total of six iner-
tial sensors were placed on the user body. The positions of
the inertial sensors were: chest, waist, left thigh, left ankle,
right thigh, and right ankle. Only the sensors in the user’s
legs and waist were studied. A total of four location tags
were placed on the user’s body. The positions of the location
tags were: chest, waist, left and right ankle. Their detected
UWB (Ultra-Wide Band) radio signals were tracked by sen-
sors fixed in the corners of the room. After processing the
acquired data, various machine learning classification meth-
ods (Decision trees, k-NN, Naive Bayes, Random Forest and
SVM) were used to classify the data. A single sensor enclo-
sure including one inertial sensor and one location sensor
placed on the chest achieved 96.6% success in fall detection
and 93.3% success in activity recognition. The Random For-
est technique also provided the best classification results.
2.2.6 Fall detection using accelerometer, gyroscope
andmagnetometer
Sanchez and Muñoz (2019) introduced a multiple sensor-
based wrist-worn fall detection system that used an artifi-
cial neural network (ANNs) for differentiating between falls
and ADLs. Three types of sensors namely: accelerometer,
gyroscope, and magnetometer were used in the prototype.
The used neural network was very simple having only 1 hid-
den layer with 8 neurons. The system achieved accuracy,
sensitivity, and specificity of 98.10%, 98.10%, and 98.10%,
respectively. All the tests were performed in laboratory con-
ditions. The prototype was also bulky in size. Boutellaa etal.
(2019) proposed a multiple wearable sensor-based fall detec-
tion system that used the covariance matrix as a means to
fuse signals from sensors and the nearest neighbor classifier
to differentiate between falls and ADLs. In the data collec-
tion stage, three sensors, namely: accelerometer, gyroscope,
and magnetometer are used. In the feature extraction stage,
the covariance matrix is used to fuse the multiple signals.
In the detection stage, Riemannian metrics and K-NN are
used to classify activities into three types: falls, risk-falls,
and ADLs. Two available public datasets were used as main
data sources, no prototypes were made. The system achieved
92.5% accuracy.
A similar observation to the single sensor-based fall
detection systems is made for the reviewed multiple sen-
sor-based works. Three major distinct stages are involved
with multiple sensor-based fall detection systems. The first
distinct stage is the data collection stage, where a combi-
nation of sensing modalities is used to collect raw data
from patients. The reviewed works used various combina-
tions of sensing modalities, such as tri-axial accelerom-
eter, gyroscope, magnetometer, UWB location tag, etc. to
collect data from the patients. The second major distinct
stage comprises the feature extraction stage, where vari-
ous methods are used to extract meaningful information
from raw sensor data. The majority of the reviewed mul-
tiple sensor-based works used various feature extraction
methods, such as EWMA, context-based reasoning, his-
togram of oriented gradients, etc. to extract features from
the collected data. The third major distinct stage consists
of the classification, where extracted features are classified
into various classes. The reviewed multiple sensor-based
fall detection systems used threshold and artificial intel-
ligence-based methods for classification. Thus, a general
architecture as illustrated in Fig.3 is derived from the
reviewed multiple sensor-based fall detection systems.
Table2 summarizes the above-described multiple sen-
sor-based systems considering the following issues: sensor
type, location of the used sensor, portability of the system,
indoor-outdoor use, user privacy, accuracy, sensitivity, and
specificity.
Fig. 3 General architecture of
multiple sensor-based fall detec-
tion systems Accelerometer
Gyroscope
Depth Camera
RGB Camera
Infrared
Multiple
Sensors
Motion Data
Pretrained
Models
Predefined
Thresholds
Feature
Extraction
Raw Sensor
Data
Results
Detection Stage
Data Collection StageFeature Extraction Stage
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
3 Results anddiscussion
Several performance metrics are used for comparing the
effectiveness of systems. Accuracy, specificity, and sensi-
tivity are such metrics used for evaluating and differentiat-
ing different systems. In the context of fall detection, True
Positives (TP) are correctly identified “fall” instances. False
Positives (FP) are incorrectly classified “non-fall” instances.
True Negatives (TN) are correctly identified “non-fall”
instances. False Negatives (FN) are incorrectly classified
“fall” instances. A reliable system should strive for a low
False Positive and False Negative rate.
Accuracy can be described as the proportion of accurate
instances to total number of instances. Accuracy can be cal-
culated as follows.
Sensitivity also termed as Recall or True Positive Rate
(TPR) can be expressed as the ratio of actual positives that
have been correctly classified as positives. Sensitivity can
be calculated as follows.
Specificity also termed as Selectivity or True Negative
Rate (TNR) can be expressed as the ratio of actual negatives
that have been correctly classified as negatives. Specificity
can be calculated as follows.
(1)
Accuracy
=
TP
+
TN
TP +TN +FP +FN
(2)
Sensitivity
=
TP
TP +FN
Table 2 Summary of the multiple sensor-based fall detection systems
*N/A not appropriately defined, I indoor use only, B both indoor and outdoor use
Authors Used sensors Location of Sensors Portability Indoor/
Outdoor
Use
User Privacy Accuracy (%) Sensitivity (%) Specificity (%)
Zerrouki etal.
(2016)
Accelerom-
eter + Camera
N/A 0 I 0 96.77 N/A N/A
Ozcan and
Velipasalar
(2016)
Accelerom-
eter + Camera
Pocket 0 I 0 N/A 96.36 92.45
Wu etal.
(2019)
Accelerom-
eter + Gyro-
scope
Waist + Arm + Thigh 1 B 2 N/A 94.80 95.20
Cillis etal.
(2015)
Accelerom-
eter + Gyro-
scope
Pocket 2 B 2 100 N/A N/A
Huynh etal.
(2015)
Accelerom-
eter + Gyro-
scope
Chest 1 B 2 N/A 96.30 96.20
Kwolek and
Kepski
(2014)
Accelerom-
eter + Gyro-
scope + Depth
Camera
N/A 0 I 1 98.33 100 96.67
Wang etal.
(2014)
Accelerom-
eter + Car-
diotachom-
eter + Smart
sensors
N/A 0 I 2 97.50 96.80 98.10
Gjoreski etal.
(2014)
Accelerom-
eter + Gyro-
scope + UWB
location tags
Chest 1 I 1 96.60 N/A N/A
Sanchez and
Muñoz
(2019)
Accelerom-
eter + Gyro-
scope + Mag-
netometer
Wrist 2 B 2 98.10 98.10 98.10
Boutellaa etal.
(2019)
Accelerom-
eter + Gyro-
scope + Mag-
netometer
N/A N/A N/A 2 92.50 N/A N/A
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
Accuracy of all the reviewed systems is presented in
Fig.4. Single sensor-based systems and multiple sensor-
based systems have been separated by using two different
colors. Among single sensor-based systems, the accelerom-
eter-based system proposed in (Lim etal. 2014) achieved
the highest accuracy of 99.50%. The waist mounted accel-
erometer based system proposed in (Yacchirema etal. 2019)
achieved 98.72% accuracy. The accelerometer-based system
introduced in (Cao etal. 2016) and RGB-D camera-based
system introduced in (Kong etal. 2017) achieved accuracy
(3)
Specificity
=
TN
TN +FP
of 97.20% and 97.10%, respectively. The monostatic CW
radar-based system developed in (Jokanovic etal. 2016)
and 802.11n NIC based system developed in (Wang etal.
2017) both achieved 87.0% accuracy, which is the lowest in
all the reviewed systems. Among the multiple sensor-based
systems, the system employing both accelerometer and gyro-
scope in (De Cillis etal. 2015) achieved the highest accu-
racy of 100.0%. The system employing an accelerometer,
gyroscope, and depth camera in (Kwolek and Kepski 2014)
achieved an accuracy of 98.33%. Among all the reviewed
systems, the multiple sensor-based system proposed in (De
Cillis etal. 2015) achieved the highest accuracy (100.0%).
The second highest accuracy (99.50%) was achieved by the
Fig. 4 The accuracy of the
reviewed systems
97.82
96.00
96.43
98.72
97.20
99.50
89.00
97.10
93.00
93.00
87.00
93.00
87.00
96.77
100.00
98.33
97.50
96.60
98.10
92.50
80
85
90
95
100
Chen et al. (2019)
Mehmood et al. (2019)
Yhdego et al. (2019)
Yacchire et al. (2019)
Cao et al. (2016)
Lim et al. (2014)
Ding et al. (2017)
Kong et al. (2017)
Chen and Ma (2015)
Jankowski et al. (2015)
Jokanovic et al. (2016)
Su et al. (2015)
Wang et al. (2017)
Zerrouki et al. (2016)
Cillis et al. (2015)
Kwolek and Kepski (2014)
Wang et al. (2014)
Gjoreski et al. (2014)
Sanchez and
Muñoz (2019)
Boutella et al. (2019)
Accuracy (%)
Single Sensor based Systems
Multiple Sensor based Systems
Fig. 5 The sensitivity of the
reviewed systems
99.30
95.83
96.22
91.70
97.00
99.17
94.90
95.25
92.00
97.10
96.36
94.80
96.30
100.00
96.80
98.10
80
85
90
95
100
Chen et al. (2019)
Yhdego et al. (2019)
Yacchirema et al. (2019)
Cao et al. (2016)
Aguiar et al. (2014)
Lim et al. (2014)
Kong et al. (2017)
Chen and Ma (2015)
Jankowski et al. (2015)
Su et al. (2015)
Ozcan and Velipasalar (2016)
Wu et al. (2019)
Huynh et al. (2015)
Kwolek and Kepski (2014)
Jin Wang et al. (2014)
Sanchez and Muñoz (2019)
Sensitivity (%)
Single Sensor based Sytems
Multiple Sensor based Systems
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
single sensor-based system developed in (Lim etal. 2014).
The lowest accuracy (87.0%) was achieved by the systems
described in (Jokanovic etal. 2016) and (Wang etal. 2017)
where both are single sensor-based systems. The systems
developed in (Aguiar etal. 2014), (Tran etal. 2014), (Ozcan
and Velipasalar 2016), (Huynh etal. 2015) did not provide
accuracy metrics, making their systems harder to compare
to other systems.
Sensitivity of all the reviewed systems is presented in
Fig.5. Single sensor-based systems and multiple sensor-
based systems have been separated by using two differ-
ent colors. Among the single sensor-based systems, the
accelerometer-based system proposed in (Chen etal. 2019)
achieved the highest sensitivity of 99.30%. The accelerom-
eter based systems designed in (Lim etal. 2014) achieved
99.7% sensitivity. The Doppler radar-based system intro-
duced in (Su etal. 2015) and the accelerometer-based system
introduced in (Aguiar etal. 2014) achieved the sensitivity of
97.1% and 97.0%, respectively. Among the reviewed mul-
tiple sensor-based systems, the accelerometer, gyroscope,
and depth camera-based system developed in (Kwolek and
Kepski 2014) achieved the highest sensitivity of 100.0%.
The accelerometer, gyroscope and magnetometer based
system proposed by (Sanchez and Muñoz 2019) achieved
98.10% sensitivity. The accelerometer and camera-based
system proposed in (Ozcan and Velipasalar 2016), accel-
erometer and gyroscope-based system described in (Huynh
etal. 2015), and the accelerometer, cardiotachometer, smart
sensors-based system introduced in (Jin Wang etal. 2014)
achieved sensitivity scores as 96.36%, 96.30%, and 96.80%,
respectively. Among all the reviewed systems, the multi-
ple sensor-based systems proposed in (Kwolek and Kepski
2014) achieved the highest sensitivity (100.0%). The system
introduced in (Chen etal. 2019) achieved the second-highest
sensitivity (99.30%). The systems proposed in (Ding etal.
2017), ( Tran etal. 2014), (Jokanovic etal. 2016), (Wang
etal. 2017), (Zerrouki etal. 2016), (De Cillis etal. 2015),
(Gjoreski etal. 2014) did not provide any sensitivity metric.
The specificity of all the reviewed systems is presented in
Fig.6. Two colors were used to differentiate between single
sensor-based systems and multiple sensor-based systems.
Among the reviewed single sensor-based systems, the accel-
erometer-based system proposed in (Cao etal. 2016) and
the RGB-D camera-based system introduced in (Kong etal.
2017) achieved the highest specificity (100%). The accel-
erometer-based systems proposed in (Aguiar etal. 2014)
and (Lim etal. 2014) achieved almost similar specificity
of 99.0%, and 99.69%, respectively. Among the reviewed
multiple sensor-based systems, the accelerometer, cardiota-
chometer, and smart sensor-based system proposed in (Jin
Wang etal. 2014) and the accelerometer, gyroscope, mag-
netometer based system proposed in (Sanchez and Muñoz
2019) achieved the highest specificity of 98.1%. The accel-
erometer and gyroscope-based system introduced in (Huynh
etal. 2015), and the accelerometer, gyroscope, and depth
camera-based system introduced in (Kwolek and Kepski
2014) achieved 96.2% and 96.67% specificity scores, respec-
tively. Among all the reviewed systems, the systems pro-
posed in (Cao etal. 2016) and (Kong etal. 2017) achieved
the highest specificity, and they are both single sensor-based
Fig. 6 The specificity of the
reviewed systems
96.36
96.88
94.60
100.00
99.00
99.69
100.00
90.75
92.20
92.45
95.2
96.2
96.67
98.1
98.1
80
85
90
95
100
Chen et al. (2019)
Yhdego et al. (2019)
Yacchirema et al. (2019)
Cao et al. (2016)
Aguiar et al. (2014)
Lim et al. (2014)
Kong et al. (2017)
Chen and Ma (2015)
Su et al. (2015)
Ozcan and Velipasalar (2016)
Wu et al. (2019)
Huynh et al. (2015)
Kwolek and Kepski (2014)
Jin Wang et al. (2014)
Sanchez and Muñoz (2019)
Specificity (%)
Single Sensor based Systems
Multiple Sensor based Systems
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
systems. The system described in (Lim etal. 2014) achieved
the second-highest specificity as 99.69%. The systems pro-
posed in (Ding etal. 2017), (Tran etal. 2014), (Jankowski
etal. 2015), (Jokanovic etal. 2016), (Wang etal. 2017),
(Zerrouki etal. 2016), (De Cillis etal. 2015), (Gjoreski etal.
2014) did not provide any specificity metrics.
In most of the developed systems, the researchers only
measured one or two out of the three performance metrics.
In single sensor-based systems, only the systems proposed
in (Chen etal. 2019), (Yhdego etal. 2019), and (Lim etal.
2014) have scored greater than 95% in all three perfor-
mance metrics. Out of the three, the system developed in
(Lim etal. 2014) achieved the highest accuracy, sensitivity,
and specificity values of 99.5, 99.17, 99.69%, respectively.
In multiple sensor-based systems, only the systems devel-
oped in (Kwolek and Kepski 2014), (Jin Wang etal. 2014),
and (Sanchez and Muñoz 2019) achieved greater than 95%
scores in all three performance metrics.
Both single sensor and multiple sensors-based fall detec-
tion systems achieve higher accuracy, sensitivity, and speci-
ficity. The multiple sensors, however, increase the overall
accuracy, sensitivity, and specificity, but not by leaps and
bounds. Accelerometers are the most used sensors in our
review. Gyroscopes are a close second.
We evaluated the systems based on three criteria: port-
ability, indoor/outdoor use and user’s privacy. The portabil-
ity score represents the ease of carrying the system with
the monitored person. The portability score is provided on
a scale of 0–2. A score of 0 meaning the relevant system is
not portable; 1 meaning, somewhat portable; and 2 meaning,
highly portable.
The attribute—indoor/outdoor use—represents the adapt-
ability of the system with the environment where the sys-
tem can be used. This attribute can have a character symbol
from I, O, and B. “I” represents that the relevant system can
only be used indoors, “O” represents the relevant system
can only be used outdoors, while “B” represents that the
relevant system can be used both indoors and outdoors. The
privacy score represents the degree of privacy violation of
the monitored person through the system. While all data
leaks are harmful in one way or another, leaks of raw data
from one type of sensor might be relatively less harmful than
leaks from another type of sensor, depending on the capacity
of data access by a third party. The privacy score is provided
on a scale of 0–2. A score of 0 represents that the relevant
system does not protect the user’s privacy i.e., it poses a high
risk to the user’s privacy. A score of 1 represents that the
relevant system moderately protects the user’s privacy, while
a score of 2 represents that the relevant system protects the
user’s privacy.
Out of the reviewed systems, single or multiple sensor-
based wrist-mounted solutions such as smart watches are the
most versatile. They can be used both indoor and outdoor
environments. However, power efficiency and network con-
nectivity are big issues for such devices. The network con-
nectivity issues for the devices make them difficult to embed
fall rescue services. Other waist-mounted, thigh-mounted
or chest-mounted solutions might be uncomfortable for the
users. But a combination of these mounts increases the over-
all effectiveness of the fall detection system.
Smartphone based fall detection and rescue systems are
good alternatives to embedded-system-based solutions.
Availability of all types of motion sensors in smartphones,
easy to use APIs, network connectivity, good battery life,
the widespread availability and affordability of smartphones
makes them a very good choice for developing fall detection
systems. Most multiple sensors-based wearable fall detection
systems are chest or waist mounted. Multiple sensors-based
solutions combining wearable sensors and stationary sensors
can only be used indoor but might be more applicable for
mass monitoring in nursing homes, hospitals, care centers,
etc. Fall detection systems employing floor sensors, Dop-
pler radars, different types of cameras, etc. can only be used
indoors and are applicable for use in the aforementioned
scenarios. No such system is found that could only be used
outdoors.
User privacy is also a huge concern for fall detection sys-
tems. Fall detection systems employing various cameras do
not protect the users’ privacy. Accelerometer, gyroscope,
magnetometer, and cardiotachometer based solutions pro-
tect the privacy of the users relatively better. Portability is a
huge consideration for fall detection systems. Fall detection
systems that use different types of cameras, IR sensors, floor
sensors, and radars are not portable at all. On the other hand,
body-mounted systems employing various motion sensors,
such as accelerometers, gyroscopes, barometers, and mag-
netometers are highly portable and adaptable.
4 Conclusion
The paper reviews the various automatic fall detection sys-
tems which use various types of sensors to capture the real-
world environment. The reviewed fall detection systems
use either single or multiple sensors for data acquisition
related to falls. The number of sensors used does not nor-
mally dictate the system’s accuracy. However, accuracy is
more dependent on the features used for classification in the
system. Accelerometer based single sensor systems are the
best for wearable solutions. Kinect sensor-based fall detec-
tion systems cannot be used for outdoor monitoring as the
sunlight affects the accuracy of the depth estimation. Most
of the monitoring systems do not protect the users’ privacy.
Depth camera, Wi-Fi Channel State Information (CSI), Dop-
pler radar, Infrared Sensor Array based monitoring systems
are great for maintaining the users’ privacy. They can even
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
be deployed in bathrooms. But most of these systems are
limited by their range and need multiple sensors deployed
throughout the environment for providing accurate fall moni-
toring. Most of the network-reliant systems are also suscepti-
ble to hackers. The overall security of the patients should be
considered while developing fall detection systems. As most
of the fall detection systems are tested on their custom data-
sets, it becomes difficult to compare different fall detection
systems based on their performance metrics. Therefore, fall
detection systems should be tested on similar open-access
datasets for future comparison. Similar open-access data-
sets can be merged to generate larger benchmark datasets.
Computer vision or surveillance-based fall detection sys-
tems need huge amounts of processing power. They also stop
working when a power failure occurs. Hence, failsafe sys-
tems should be proposed that would work when the primary
systems cease to work for some reason. Most fall detection
systems face problems in differentiating the activity of lying
down and falling. Depth image and radar-based fall detection
systems face problems when furniture is present in the sys-
tem and the user falls behind furniture. The most important
aspects while designing fall detection systems are compu-
tational cost, classifiers, energy consumption, environment,
the presence of multiple people, privacy, threshold values,
etc. We hope that this review will aid the researchers to
design better sensor-based fall detection systems.
Acknowledgements This research is supported by Universiti Malaysia
Pahang (UMP) through University Research Grant RDU192206.
References
Aguiar B, Rocha T, Silva J, Sousa I (2014) Accelerometer-based fall
detection for smartphones. In: 2014 IEEE International Sympo-
sium on Medical Measurements and Applications (MeMeA).
IEEE, pp 1–6
Bagalà F, Becker C, Cappello A etal (2012) Evaluation of accelerome-
ter-based fall detection algorithms on real-world falls. PLoS ONE
7:e37062. https:// doi. org/ 10. 1371/ journ al. pone. 00370 62
Bergen G, Stevens MR, Burns ER (2016) Falls and fall injuries among
adults aged ≥65 years—United States, 2014. MMWR Morb
Mortal Wkly Rep 65:993–998. https:// doi. org/ 10. 15585/ mmwr.
mm653 7a2
Bet P, Castro PC, Ponti MA (2019) Fall detection and fall risk assess-
ment in older person using wearable sensors: a systematic review.
Int J Med Inform 130:103946. https:// doi. org/ 10. 1016/j. ijmed inf.
2019. 08. 006
Bin KS, Park J-H, Kwon C etal (2019) An energy-efficient algorithm
for classification of fall types using a wearable sensor. IEEE
Access 7:31321–31329. https:// doi. org/ 10. 1109/ ACCESS. 2019.
29027 18
Boutellaa E, Kerdjidj O, Ghanem K (2019) Covariance matrix based
fall detection from multiple wearable sensors. J Biomed Inform
94:103189. https:// doi. org/ 10. 1016/j. jbi. 2019. 103189
Buke A, Gaoli F, Yongcai W etal (2015) Healthcare algorithms by
wearable inertial sensors: a survey. China Commun 12:1–12.
https:// doi. org/ 10. 1109/ CC. 2015. 71140 54
Cao H, Wu S, Zhou Z, etal (2016) A fall detection method based
on acceleration data and hidden Markov model. In: 2016 IEEE
International Conference on Signal and Image Processing (ICSIP).
IEEE, pp 684–689
Casilari E, Santoyo-Ramón J-A, Cano-García J-M (2017) Analysis
of public datasets for wearable fall detection systems. Sensors
17:1513. https:// doi. org/ 10. 3390/ s1707 1513
Chaudhuri S, Thompson H, Demiris G (2014) Fall detection devices
and their use with older adults. J Geriatr Phys Ther 37:178–196.
https:// doi. org/ 10. 1519/ JPT. 0b013 e3182 abe779
Chen WH, Ma HP (2015) A fall detection system based on infrared
array sensors with tracking capability for the elderly at home.
In: 2015 17th International Conference on E-health Networking,
Application & Services (HealthCom). IEEE, pp 428–434
Chen L, Li R, Zhang H etal (2019) Intelligent fall detection method
based on accelerometer data from a wrist-worn smart watch.
Measurement 140:215–226. https:// doi. org/ 10. 1016/j. measu
rement. 2019. 03. 079
De Cillis F, De Simio F, Guido F, etal (2015) Fall-detection solution
for mobile platforms using accelerometer and gyroscope data.
In: 2015 37th Annual International Conference of the IEEE
Engineering in Medicine and Biology Society (EMBC). IEEE,
pp 3727–3730
Debes C, Merentitis A, Sukhanov S etal (2016) Monitoring activities
of daily living in smart homes: understanding human behavior.
IEEE Signal Process Mag 33:81–94. https:// doi. org/ 10. 1109/
MSP. 2015. 25038 81
Delahoz Y, Labrador M (2014) Survey on fall detection and fall pre-
vention using wearable and external sensors. Sensors 14:19806–
19842. https:// doi. org/ 10. 3390/ s1410 19806
Ding Y, Li H, Li C, etal (2017) Fall detection based on depth images
via wavelet moment. In: 2017 10th International Congress on
Image and Signal Processing, BioMedical Engineering and
Informatics (CISP-BMEI). IEEE, pp 1–5
Ding C, Zou Y, Sun L, etal (2019) Fall detection with multi-domain
features by a portable FMCW radar. In: 2019 IEEE MTT-S
International Wireless Symposium (IWS). IEEE, pp 1–3
Doulamis N (2010) Viusal fall alert service in low computational
power device to assist persons’ with dementia. In: 2010 3rd
International Symposium on Applied Sciences in Biomedical
and Communication Technologies (ISABEL 2010). IEEE, pp
1–5
Erden F, Velipasalar S, Alkar AZ, Cetin AE (2016) Sensors in assisted
living: a survey of signal and image processing methods. IEEE
Signal Process Mag 33:36–44. https:// doi. org/ 10. 1109/ MSP. 2015.
24899 78
Erol B, Amin MG (2019) Radar data cube processing for human activ-
ity recognition using multisubspace learning. IEEE Trans Aerosp
Electron Syst 55:3617–3628. https:// doi. org/ 10. 1109/ T AES. 2019.
29109 80
Florence CS, Bergen G, Atherly A etal (2018) Medical costs of fatal
and nonfatal falls in older adults. J Am Geriatr Soc 66:693–698.
https:// doi. org/ 10. 1111/ jgs. 15304
Fung NM, Wong Sing Ann J, Tung YH, etal (2019) Elderly Fall Detec-
tion and Location Tracking System Using Heterogeneous Wireless
Networks. In: 2019 IEEE 9th Symposium on Computer Applica-
tions & Industrial Electronics (ISCAIE). IEEE, pp 44–49
Gjoreski H, Gams M, Luštrek M (2014) Context-based fall detec-
tion and activity recognition using inertial and location sensors.
J Ambient Intell Smart Environ 6:419–433. https:// doi. org/ 10.
3233/ AIS- 140268
Hamm J, Money AG, Atwal A, Paraskevopoulos I (2016) Fall preven-
tion intervention technologies: a conceptual framework and survey
of the state of the art. J Biomed Inform 59:319–345. https:// doi.
org/ 10. 1016/j. jbi. 2015. 12. 013
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
S.Nooruddin et al.
1 3
Homann B, Plaschg A, Grundner M etal (2013) The impact of neuro-
logical disorders on the risk for falls in the community dwelling
elderly: a case-controlled study. BMJ Open 3:e003367. https:// doi.
org/ 10. 1136/ bmjop en- 2013- 003367
Hu L, Wang S, Chen Y, etal (2018) Fall detection algorithms based on
wearable device: a review. zjujournals.com
Huynh QT, Nguyen UD, Irazabal LB etal (2015) Optimization of
an accelerometer and gyroscope-based fall detection algorithm. J
Sensors 2015:1–8. https:// doi. org/ 10. 1155/ 2015/ 452078
Igual R, Medrano C, Plaza I (2013) Challenges, issues and trends in
fall detection systems. Biomed Eng Online 12:66. https:// doi. org/
10. 1186/ 1475- 925X- 12- 66
Igual R, Medrano C, Plaza I (2015) A comparison of public datasets
for acceleration-based fall detection. Med Eng Phys 37:870–878.
https:// doi. org/ 10. 1016/j. meden gphy. 2015. 06. 009
Islam MM, Neom NH, Imtiaz MS etal (2019) A review on fall detec-
tion systems using data from smartphone sensors. Ing des Syst
d’Inform 24:569–576. https:// doi. org/ 10. 18280/ isi. 240602
Islam MM, Rahaman A, Islam MR (2020) Development of smart
healthcare monitoring system in IoT environment. SN Comput
Sci 1:185. https:// doi. org/ 10. 1007/ s42979- 020- 00195-y
Jager TE, Weiss HB, Coben JH, Pepe PE (2000) Traumatic brain inju-
ries evaluated in U.S. emergency departments, 1992–1994. Acad
Emerg Med 7:134–140. https:// doi. org/ 10. 1111/j. 1553- 2712. 2000.
tb005 15.x
Jankowski S, Szymanski Z, Dziomin U, etal (2015) Deep learning clas-
sifier for fall detection based on IR distance sensor data. In: 2015
IEEE 8th International Conference on Intelligent Data Acquisition
and Advanced Computing Systems: Technology and Applications
(IDAACS). IEEE, pp 723–727
Jokanovic B, Amin M, Ahmad F (2016) Radar fall motion detection
using deep learning. In: 2016 IEEE Radar Conference (Radar-
Conf). IEEE, pp 1–6
Khan SS, Hoey J (2017) Review of fall detection techniques: a data
availability perspective. Med Eng Phys 39:12–22. https:// doi. org/
10. 1016/j. meden gphy. 2016. 10. 014
Kong X, Meng L, Tomiyama H (2017) Fall detection for elderly per-
sons using a depth camera. In: 2017 International Conference on
Advanced Mechatronic Systems (ICAMechS). IEEE, pp 269–273
Kong X, Meng Z, Meng L, Tomiyama H (2019) Three-states-transition
method for fall detection algorithm using depth image. J Robot
Mechatronics 31:88–94. https:// doi. org/ 10. 20965/ jrm. 2019. p0088
Kwolek B, Kepski M (2014) Human fall detection on embedded plat-
form using depth maps and wireless accelerometer. Comput Meth-
ods Programs Biomed 117:489–501. https:// doi. org/ 10. 1016/j.
cmpb. 2014. 09. 005
Lee J-S, Tseng H-H (2019) Development of an enhanced threshold-
based fall detection system using smartphones with built-in accel-
erometers. IEEE Sens J 19:8293–8302. https:// doi. org/ 10. 1109/
JSEN. 2019. 29186 90
Lim D, Park C, Kim NH etal (2014) Fall-detection algorithm using
3-axis acceleration: combination with simple threshold and hidden
Markov model. J Appl Math 2014:1–8. https:// doi. org/ 10. 1155/
2014/ 896030
Lord SR, Menz HB, Sherrington C (2006) Home environment risk
factors for falls in older people and the efficacy of home modifica-
tions. Age Ageing 35:ii55–ii59. https:// doi. org/ 10. 1093/ ageing/
afl088
Martínez-Villaseñor L, Ponce H, Brieva J etal (2019) UP-fall detection
dataset: a multimodal approach. Sensors 19:1988. https:// doi. org/
10. 3390/ s1909 1988
Mastorakis G, Makris D (2014) Fall detection system using Kinect’s
infrared sensor. J Real-Time Image Process 9:635–646. https://
doi. org/ 10. 1007/ s11554- 012- 0246-9
Mehmood A, Nadeem A, Ashraf M etal (2019) A novel fall detec-
tion algorithm for elderly using SHIMMER wearable sensors.
Health Technol (Berl) 9:631–646. https:// doi. org/ 10. 1007/
s12553- 019- 00298-4
Moulik S, Majumdar S (2019) FallSense : an automatic fall detection
and alarm generation system in IoT-enabled environment. IEEE
Sens J 19:8452–8459. https:// doi. org/ 10. 1109/ JSEN. 2018. 28807
39
Mubashir M, Shao L, Seed L (2013) A survey on fall detection: princi-
ples and approaches. Neurocomputing 100:144–152. https:// doi.
org/ 10. 1016/j. neucom. 2011. 09. 037
Mukhopadhyay SC (2015) Wearable sensors for human activity moni-
toring: a review. IEEE Sens J 15:1321–1330. https:// doi. org/ 10.
1109/ JSEN. 2014. 23709 45
Nguyen Gia T, Sarker VK, Tcarenko I etal (2018) Energy efficient
wearable sensor node for IoT-based fall detection systems. Micro-
process Microsyst 56:34–46. https:// doi. org/ 10. 1016/j. micpro.
2017. 10. 014
Nooruddin S, Islam M, Sharna FA (2020) Internet of things an IoT
based device-type invariant fall detection system. Internet Things
9:100130. https:// doi. org/ 10. 1016/j. iot. 2019. 100130
Noury N, Fleury A, Rumeau P, etal (2007) Fall detection—principles
and methods. In: 2007 29th Annual International Conference of
the IEEE Engineering in Medicine and Biology Society. IEEE,
pp 1663–1666
O’Loughlin JL, Robitaille Y, Boivin J-F, Suissa S (1993) Incidence of
and risk factors for falls and injurious falls among the community-
dwelling elderly. Am J Epidemiol 137:342–354. https:// doi. org/
10. 1093/ oxfor djour nals. aje. a1166 81
Ozcan K, Velipasalar S (2016) Wearable camera- and accelerometer-
based fall detection on portable devices. IEEE Embed Syst Lett
8:6–9. https:// doi. org/ 10. 1109/ LES. 2015. 24872 41
Parkkari J, Kannus P, Palvanen M etal (1999) Majority of hip fractures
occur as a result of a fall and impact on the greater trochanter of
the femur: a prospective controlled hip fracture study with 206
consecutive patients. Calcif Tissue Int 65:183–187. https:// doi.
org/ 10. 1007/ s0022 39900 679
Pynoos J, Steinman BA, Nguyen AQD (2010) Environmental assess-
ment and modification as fall-prevention strategies for older
adults. Clin Geriatr Med 26:633–644. https:// doi. org/ 10. 1016/j.
cger. 2010. 07. 001
Pynoos J, Steinman BA, Do Nguyen AQ, Bressette M (2012) Assessing
and adapting the home environment to reduce falls and meet the
changing capacity of older adults. J Hous Elderly 26:137–155.
https:// doi. org/ 10. 1080/ 02763 893. 2012. 673382
Rahaman A, Islam M, Islam M etal (2019) Developing IoT based
smart health monitoring systems: a review. Rev d’Intell Artif
33:435–440. https:// doi. org/ 10. 18280/ ria. 330605
Rahman MM, Islam MM, Ahmmed S, Khan SA (2020) Obstacle and
fall detection to guide the visually impaired people with real
time monitoring. SN Comput Sci 1:231. https:// doi. org/ 10. 1007/
s42979- 020- 00231-x
Rana S, Dey M, Ghavami M, Dudley S (2019) Signature inspired home
environments monitoring system using IR-UWB technology. Sen-
sors 19:385. https:// doi. org/ 10. 3390/ s1902 0385
Ranakoti S, Arora S, Chaudhary S, etal (2019) Human Fall detec-
tion system over IMU sensors using triaxial accelerometer. In:
Advances in Intelligent Systems and Computing. pp 495–507
Rand D, Eng JJ, Tang P-F etal (2009) How active are people with
stroke? Stroke 40:163–168. https:// doi. org/ 10. 1161/ STROK
EAHA. 108. 523621
Rawashdeh O, Sa’deh W, Rawashdeh M, etal (2012) Development
of a low-cost fall intervention system for hospitalized dementia
patients. In: 2012 IEEE International Conference on Electro/Infor-
mation Technology. IEEE, pp 1–7
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Sensor-based fall detection systems: areview
1 3
Sadreazami H, Bolic M, Rajan S (2019) CapsFall: fall detection using
ultra-wideband radar and capsule network. IEEE Access 7:55336–
55343. https:// doi. org/ 10. 1109/ ACCESS. 2019. 29079 25
Sadreazami H, Bolic M, Rajan S (2020) Fall detection using standoff
radar-based sensing and deep convolutional neural network. IEEE
Trans Circuits Syst II Express Briefs 67:197–201. https:// doi. org/
10. 1109/ TCSII. 2019. 29044 98
Safi K, Attal F, Mohammed S, etal (2015) Physical activity recognition
using inertial wearable sensors—a review of supervised classifica-
tion algorithms. In: 2015 International Conference on Advances
in Biomedical Engineering, ICABME 2015
Sanchez JAU, Muñoz DM (2019) Fall detection using accelerometer
on the user’s wrist and artificial neural networks. In: IFMBE Pro-
ceedings. pp 641–647
Santos GL, Endo PT, de Monteiro KH, C, etal (2019) Accelerometer-
based human fall detection using convolutional neural networks.
Sensors (Switzerland) 19:1–12. https:// doi. org/ 10. 3390/ s1907
1644
Sterling DA, O’Connor JA, Bonadies J (2001) Geriatric falls: injury
severity is high and disproportionate to mechanism. J Trauma
Inj Infect Crit Care 50:116–119. https:// doi. org/ 10. 1097/ 00005
373- 20010 1000- 00021
Su BY, Ho KC, Rantz MJ, Skubic M (2015) Doppler radar fall activity
detection using the wavelet transform. IEEE Trans Biomed Eng
62:865–875. https:// doi. org/ 10. 1109/ TBME. 2014. 23670 38
Sugawara E, Nikaido H (2014) Properties of AdeABC and AdeIJK
efflux systems of Acinetobacter baumannii compared with those
of the AcrAB-TolC system of Escherichia coli. Antimicrob
Agents Chemother 58:7250–7257. https:// doi. org/ 10. 1128/ AAC.
03728- 14
Tran T-T-H, Le T-L, Morel J (2014) An analysis on human fall detec-
tion using skeleton from Microsoft kinect. In: 2014 IEEE Fifth
International Conference on Communications and Electronics
(ICCE). IEEE, pp 484–489
Vallabh P, Malekian R (2018) Fall detection monitoring systems:
a comprehensive review. J Ambient Intell Humaniz Comput
9:1809–1833. https:// doi. org/ 10. 1007/ s12652- 017- 0592-3
Van Thanh P, Tran D-T, Nguyen D-C etal (2019) Development of
a real-time, simple and high-accuracy fall detection system for
elderly using 3-DOF accelerometers. Arab J Sci Eng 44:3329–
3342. https:// doi. org/ 10. 1007/ s13369- 018- 3496-4
Verma SK, Willetts JL, Corns HL etal (2016) Falls and fall-related
injuries among community-dwelling adults in the United States.
PLoS ONE 11:e0150939. https:// doi. org/ 10. 1371/ journ al. pone.
01509 39
Wang J, Zhang Z, Li B etal (2014) An enhanced fall detection system
for elderly person monitoring using consumer home networks.
IEEE Trans Consum Electron 60:23–29. https:// doi. org/ 10. 1109/
TCE. 2014. 67809 21
Wang P, Chen C-S, Chuan C-C (2016) Location-aware fall detection
system for dementia care on nursing service in evergreen inn of
Jianan Hospital. In: 2016 IEEE 16th International Conference on
Bioinformatics and Bioengineering (BIBE). IEEE, pp 309–315
Wang Y, Wu K, Ni LM (2017) WiFall: device-free fall detection by
wireless networks. IEEE Trans Mob Comput 16:581–594. https://
doi. org/ 10. 1109/ TMC. 2016. 25577 92
Ward DS, Everson KR, Vaughn A, Rodgers AB, Troiano RP (2005)
Accelerometer use in physical activity: best practices and research
recommendations. Med Sci Sport Exerc 37:S582–S588. https://
doi. org/ 10. 1249/ 01. mss. 00001 85292. 71933. 91
Wu Y, Su Y, Hu Y etal (2019) A multi-sensor fall detection system
based on multivariate statistical process analysis. J Med Biol Eng
39:336–351. https:// doi. org/ 10. 1007/ s40846- 018- 0404-z
Xu Y, Chen J, Yang Q, Guo Q (2019) Human posture recognition and
fall detection using kinect V2 camera. In: 2019 Chinese Control
Conference (CCC). IEEE, pp 8488–8493
Yacchirema D, de Puga JS, Palau C, Esteve M (2019) Fall detection
system for elderly people using IoT and ensemble machine learn-
ing algorithm. Pers Ubiquitous Comput 23:801–817. https:// doi.
org/ 10. 1007/ s00779- 018- 01196-8
Yhdego H, Li J, Morrison S, etal (2019) towards musculoskeletal
simulation-aware fall injury mitigation: transfer learning with
deep CNN for fall detection. In: 2019 Spring Simulation Confer-
ence (SpringSim). IEEE, pp 1–12
Yoshino H, Moshnyaga VG, Hashimoto K (2019) Fall detection on
a single doppler radar sensor by using convolutional neural net-
works. In: 2019 IEEE International Conference on Systems, Man
and Cybernetics (SMC). IEEE, pp 2889–2892
Yu X (2008) Approaches and principles of fall detection for elderly and
patient. In: 2008 10th IEEE Intl. Conf. on e-Health Networking,
Applications and Service, HEALTHCOM 2008
Zerrouki N, Harrou F, Sun Y, Houacine A (2016) Accelerometer and
camera-based strategy for improved human fall detection. J Med
Syst 40:284. https:// doi. org/ 10. 1007/ s10916- 016- 0639-6
Zhang Z, Conly C, Athitsos V (2015) A survey on vision-based fall
detection. In: Proceedings of the 8th ACM International Confer-
ence on PErvasive Technologies Related to Assistive Environ-
ments—PETRA’15. ACM Press, New York, pp 1–7
Publisher’s Note Springer Nature remains neutral with regard to
jurisdictional claims in published maps and institutional affiliations.
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
1.
2.
3.
4.
5.
6.
Terms and Conditions
Springer Nature journal content, brought to you courtesy of Springer Nature Customer Service Center GmbH (“Springer Nature”).
Springer Nature supports a reasonable amount of sharing of research papers by authors, subscribers and authorised users (“Users”), for small-
scale personal, non-commercial use provided that all copyright, trade and service marks and other proprietary notices are maintained. By
accessing, sharing, receiving or otherwise using the Springer Nature journal content you agree to these terms of use (“Terms”). For these
purposes, Springer Nature considers academic use (by researchers and students) to be non-commercial.
These Terms are supplementary and will apply in addition to any applicable website terms and conditions, a relevant site licence or a personal
subscription. These Terms will prevail over any conflict or ambiguity with regards to the relevant terms, a site licence or a personal subscription
(to the extent of the conflict or ambiguity only). For Creative Commons-licensed articles, the terms of the Creative Commons license used will
apply.
We collect and use personal data to provide access to the Springer Nature journal content. We may also use these personal data internally within
ResearchGate and Springer Nature and as agreed share it, in an anonymised way, for purposes of tracking, analysis and reporting. We will not
otherwise disclose your personal data outside the ResearchGate or the Springer Nature group of companies unless we have your permission as
detailed in the Privacy Policy.
While Users may use the Springer Nature journal content for small scale, personal non-commercial use, it is important to note that Users may
not:
use such content for the purpose of providing other users with access on a regular or large scale basis or as a means to circumvent access
control;
use such content where to do so would be considered a criminal or statutory offence in any jurisdiction, or gives rise to civil liability, or is
otherwise unlawful;
falsely or misleadingly imply or suggest endorsement, approval , sponsorship, or association unless explicitly agreed to by Springer Nature in
writing;
use bots or other automated methods to access the content or redirect messages
override any security feature or exclusionary protocol; or
share the content in order to create substitute for Springer Nature products or services or a systematic database of Springer Nature journal
content.
In line with the restriction against commercial use, Springer Nature does not permit the creation of a product or service that creates revenue,
royalties, rent or income from our content or its inclusion as part of a paid for service or for other commercial gain. Springer Nature journal
content cannot be used for inter-library loans and librarians may not upload Springer Nature journal content on a large scale into their, or any
other, institutional repository.
These terms of use are reviewed regularly and may be amended at any time. Springer Nature is not obligated to publish any information or
content on this website and may remove it or features or functionality at our sole discretion, at any time with or without notice. Springer Nature
may revoke this licence to you at any time and remove access to any copies of the Springer Nature journal content which have been saved.
To the fullest extent permitted by law, Springer Nature makes no warranties, representations or guarantees to Users, either express or implied
with respect to the Springer nature journal content and all parties disclaim and waive any implied warranties or warranties imposed by law,
including merchantability or fitness for any particular purpose.
Please note that these rights do not automatically extend to content, data or other material published by Springer Nature that may be licensed
from third parties.
If you would like to use or distribute our Springer Nature journal content to a wider audience or on a regular basis or in any other manner not
expressly permitted by these Terms, please contact Springer Nature at
onlineservice@springernature.com
A preview of this full-text is provided by Springer Nature.
Content available from Journal of Ambient Intelligence and Humanized Computing
This content is subject to copyright. Terms and conditions apply.