SPECIAL SECTION ON DEEP LEARNING FOR INTERNET OF THINGS
Received June 19, 2021, accepted June 27, 2021, date of publication July 2, 2021, date of current version August 20, 2021.
Digital Object Identifier 10.1109/ACCESS.2021.3094243
Internet of Things and Deep Learning Enabled
Elderly Fall Detection Model for Smart Homecare
THAVAVEL VAIYAPURI
VICENTE GARCÍA DÍAZ
1 College
1,
(Member, IEEE), E. LAXMI LYDIA2 , MOHAMED YACIN SIKKANDAR3 ,
4 , IRINA V. PUSTOKHINA 5 , AND DENIS A. PUSTOKHIN 6
of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj 16278, Saudi Arabia
of Computer Science and Engineering, Vignan’s Institute of Information Technology (Autonomous), Visakhapatnam 530049, India
3 Department of Medical Equipment Technology, College of Applied Medical Sciences, Majmaah University, Al Majma’ah 11952, Saudi Arabia
4 Department of Computer Science, School of Computer Science Engineering, University of Oviedo, 33003 Oviedo, Spain
5 Department of Entrepreneurship and Logistics, Plekhanov Russian University of Economics, 117997 Moscow, Russia
6 Department of Logistics, State University of Management, 109542 Moscow, Russia
2 Department
Corresponding author: Thavavel Vaiyapuri (t.thangam@psau.edu.sa)
ABSTRACT Recently, the techniques of Internet of Things (IoT) and mobile communications have been
developed to gather human and environment information data for a variety of intelligent services and
applications. Remote monitoring of elderly and disabled people living in smart homes is highly challenging
due to probable accidents which might occur due to daily activities such as falls. For elderly people, fall
is considered as a major reason for death of post-traumatic complication. So, early identification of elderly
people falls in smart homes is needed to increase the survival rate of the person or offer required support.
Recently, the advent of artificial intelligence (AI), IoT, wearables, smartphones, etc. makes it feasible to
design fall detection systems for smart homecare. In this view, this paper presents an IoT enabled elderly fall
detection model using optimal deep convolutional neural network (IMEFD-ODCNN) for smart homecare.
The goal of the IMEFD-ODCNN model is to enable smartphones and intelligent deep learning (DL)
algorithms to detect the occurrence of falls in the smart home. Primarily, the input video captured by the IoT
devices is pre-processed in different ways like resizing, augmentation, and min-max based normalization.
Besides, SqueezeNet model is employed as a feature extraction technique to derive appropriate feature
vectors for fall detection. In addition, the hyperparameter tuning of the SqueezeNet model takes place using
the salp swarm optimization (SSO) algorithm. Finally, sparrow search optimization algorithm (SSOA) with
variational autoencoder (VAE), called SSOA-VAE based classifier is employed for the classification of fall
and non-fall events. Finally, in case of fall event detected, the smartphone sends an alert to the caretakers
and hospital management. The performance validation of the IMEFD-ODCNN model takes place on UR fall
detection dataset and multiple cameras fall dataset. The experimental outcomes highlighted the promising
performance of the IMEFD-ODCNN model over the recent methods with the maximum accuracy of 99.76%
and 99.57% on the multiple cameras fall and UR fall detection dataset.
INDEX TERMS Smart homecare, smartphone, fall detection, artificial intelligence, elderly people, deep
learning, parameter tuning.
I. INTRODUCTION
In recent years, the Internet of Things (IoT) and mobile communication find useful in healthcare sector. With an enhanced
healthcare system in several countries, average life span has
developed considerably. Plus lower natural increases result
in an elderly population that would need appropriate care
The associate editor coordinating the review of this manuscript and
approving it for publication was Chi-Hua Chen
VOLUME 9, 2021
.
and more interest. But, in several countries, offering appropriate care could be challenging because of several reasons.
The impaired and elderly populations would shortly live in
smart homes [1], [2]. These homes offer a pleasant and safe
place for the elders. Independently, security is considering
the main concern in the smart healthcare model [3]. However, daily emergency incidents will also continue to occur
due to seniors’ human nature. Falling is the most common
problem encountered by elder peoples. For elder adults, a fall
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
113879
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
could be highly risky and might cause serious health issues.
Additionally, lack of balance and fall might be symptoms of
a life-threatening disease. Nevertheless of the cause for a fall,
it can be critical if it happens, the injured people must obtain
quick help. Frequently, the individual might not be able to
rise up with no support and might require immediate medical
consideration.
Unreported cases result in the fall of injury that may
involve earlier treatments. Fear of falling increases the negative post fall effects and may decrease patient confidence [4].
Consequently, it limits the patient’s activities, decreases
social interaction, and finally causes depression [5], [6].
Respectively, it aids to decrease treatment costs and raise the
opportunity of recovery. In [7], researchers have divided fall
detection systems into 3 classes regarding cameras, wearable
devices, and ambiance sensors. The system is depending upon
wearable device seems to be common as they could identify
a fall precisely nevertheless of the patient locations (viz.,
outdoor & indoor) and don’t interrupt the person’s privacy
and day-to-day activities. Because of their asset limitations
(for example storage capacity & limited power), it must
have an innovative scheme that assists to decrease computation heavier loads on wearable sensor nodes, when preserving/enhancing the QoS.
A. NEED OF IoT ENABLED AI TECHNIQUES
FOR FALL DETECTION
The independent life of elder persons could be altered significantly afterward a fall. Based on health state of the elders,
nearly ten percent of the persons fall would endure severe
injuries, or may even pass away straight afterward a fall
when no intermediary aid is presented [8], [9]. For preventing
the serious effects of this fall, consistent fall detection is
required. The most popular method for detecting falls is wrist
worn detection system which measures the acceleration force.
These wrist devices are attaining more interest over the population and become gradually stronger based on computation
efficiency that the utilization of AI is moderate. Generally,
elder person appears to be attentive in utilizing these devices
while they reveal concern on privacy and understand accurately when the device is processing at certain times [10].
Various fall detection methods have been presented in previous years. This method ranges from simple threshold based
techniques, on handcrafted feature based ML technique, and
lastly to DL based automated feature extraction NN.
IoT is the most appropriate candidate for this system
since it contains broad innovative techniques like WSN, CC,
and sensing to interconnect virtual objects using physical
objects. As the gateways could execute difficult fall detection techniques like discrete wavelet transform/data mining.
Additionally, smart gateway helps to enhance QoS by offering innovative services viz. local storage to store temporary
data/push notification to inform anomaly in real world. It is
predictable that IoT could widely assist in reducing power
consumption of wearable devices with the allocation of tasks.
But, IoT could not often assurance a higher level of energy
113880
efficacy in wearable devices. Another main problem is data
transmission and data acquisition cause higher energy utilization in wearable sensor nodes should be considerately
deliberated. If a wearable sensor node is energy ineffective,
it might cause untrustworthiness and decreases QoS.
B. PAPER CONTRIBUTIONS
This paper presents an intelligent IoT enabled elderly fall
detection model using optimal deep convolutional neural
network (IMEFD-ODCNN) for smart homecare. At the initial stage, the input video captured by the IoT devices is
pre-processed in different ways like resizing, augmentation,
and min-max based normalization. Moreover, SqueezeNet
model is used as a feature extractor and its hyperparameters
are tuned by the use of SSO algorithm. Furthermore, sparrow search optimization algorithm (SSOA) with variational
autoencoder (VAE), called SSOA-VAE based classifier is
employed. The SSO algorithm is preferable owing to its high
efficiency, robustness, accuracy, and convergence rate. The
VAE is chosen because of the capability of learning smooth
latent state representations of the input data. Lastly, in case
of fall event detected, the smartphone sends an alert to the
caretakers and hospital management. An extensive set of
simulations is carried out on UR fall detection dataset and
multiple cameras fall dataset. The key contribution of the
paper is given as follows.
•
•
•
•
•
Propose a novel IMEDF-ODCNN model for elderly fall
detection in smart homecare
Develop a hyperparameter tuned SqueezeNet based feature extractor with SSO algorithm to generate useful set
of feature vectors
Design an SSOA-VAE based classification model to
detect the occurrence of fall and non-fall events
Enables the smartphone to generate an alert to the caretakers and hospital authority on the occurrence of fall
event
Validate the fall detection performance of the IMEFDODCNN model on UR fall detection dataset and multiple cameras fall dataset.
C. PAPER ORGANIZATION
The rest of the paper is organized as follows. Section 2
briefs the existing fall detection approaches and section 3
describes the overall system architecture. Then, section 4
explains the different modules involved in the proposed
IMEFD-ODCNN model. Next, section 5 assesses the experimental results and section 6 draws the concluding remarks.
II. LITERATURE REVIEW
Hussain et al. [11] presented a wearable sensor based continuous fall monitoring scheme that can detect falling and
identify fall patterns and the activity related to fall incidents.
The efficiency of the presented system is examined by a
sequence of studies with 3 ML techniques as, RF, KNN, &
SVM. Aziz et al. [12] examined the accuracy of fall detection
VOLUME 9, 2021
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
scheme deepening upon real time fall & non-fall datasets. The
5 younger & nineteen elder persons went on their everyday
works when wearing tri axial accelerometer. Elderly persons suffered ten unexpected falls at the time of collecting
data. Around four hundred hours of ADL have been noted.
They utilized ML, SVM classification for identifying falls
& non-fall activities. Shojaei-Hashemi et al. [13] proposed
DL based method for detecting human fall, with the help of
LSTM-NN. This module isn’t limited to other certain conditions, and efficiency evaluation shows that it exceeds overall
present techniques. Tsinganos and Skodras [14] developed a
smartphone based fall detection scheme that could differentiate among ADL & falls. The usual fall detection scheme contains notification module and sensing component. Android
devices, armed with communication services and sensors, are
optimal candidates for the growth of this technique.
In Liu et al. [15], a sensing module combined energy
efficient sensor was established that could sense and store the
information of human activities from sleep mode, and interrupt driven technique is presented for transmitting the data
to a server combined with Zigbee. Next, an FD-DNN operation on the server is designed carefully for detecting accurate falls. The FD-DNN integrated CNN alongside LSTM
techniques was verified using offline & online datasets. In
Kong et al. [16], a HOG-SVM based fall detection IoT
scheme for elder adults was presented. For ensuring privacy
and strong modifications of the light intensity, deep sensor is
utilized rather than RGB camera for getting binary images of
elder adults. Afterward attaining the denoised binary images,
the features of person are extracted using the histogram of
oriented gradient, and the image classification is executed to
judge the fall condition using linear SVM.
Carletti et al. [17] proposed a new smartphone based fall
detection scheme that considers falls as abnormalities regarding a module of usual events. This technique is related to other
methods and it is demonstrated to be appropriate to operate on
a smartphone located in the trouser pockets. This outcome is
established from the attained accuracy and essential hardware
assets. Mrozek et al. [1] proposed a scalable framework of a
scheme that could observe 1000s of elder persons, identify
falls, and inform the care takers. Scalability test discloses
the need for enabling large scale scheme processes have
been executed. Furthermore, they authenticated various ML
modules for evaluating their appropriateness in the detection
procedure. Amongst the tested modules, Boosted Decision
Tree results in the optimal classification efficiency.
For improving the classification accuracy, the data from
smartphones & smartwatches are integrated into [18]. There
aren’t various publicly available datasets integrating data
from smartphones & smartwatches. Henceforth, the data
would be independently gathering. The DT (J48) classification would be utilized for classifying the falls. Gia et al. [19]
proposed the implementation of lightweight, tiny, energy efficient wearable, and flexible devices. Though several methods
are available in the literature, it is needed to examine distinct
variables (for example transmission protocol, communication
VOLUME 9, 2021
bus interface, transmission rate, and sampling rate) impact on
energy utilization of the wearable device. Additionally, they
give complete analyses of energy utilization of the wearable
in distinct configurations and operating situations. Also, it is
give suggestions (software & hardware) for implementing an
optimum wearable device to IoT based fall detection system
based on higher QoS and energy efficiency.
III. SYSTEM ARCHITECTURE
The overall system architecture of the proposed model is
depicted in Fig. 1. The proposed fall detection model uses
a smartphone for processing. The IMEFD-ODCNN model
allows smartphones and intelligent DL algorithms to detect
the occurrence of falls in the smart home. The proposed
IMEFD-ODCNN model involves distinct stages of operations
like data acquisition, pre-processing, SqueezeNet based feature extraction, SSO based parameter tuning, and SSOA-VAE
based classification. Primarily, the input videos are captured
and are sent to the cloud server for additional processing
where the proposed model gets executed.
FIGURE 1. The working process of IMEFD-ODCNN model.
Then, the video frames are split and are pre-processed
in three major levels such as resizing, augmentation, and
normalization to enhance the quality of the video frames.
Afterward, the features from the video frames are extracted to
derive useful feature vectors using SqueezeNet model. Moreover, the hyperparameter tuning of the SqueezeNet model
takes place using the SSO algorithm. Subsequently, the feature vectors are fed into the SSOA-VAE based classifier
model to detect the occurrence of falls. Based on the classifier
results, the subsequent actions will be performed. According
to the value of classification outcome, the following actions
are taken:
• When an event is detected as a fall and is denoted as
class 1, an alarm is transmitted to the patient device
from where the caretaker can be notified automatically
if the fall was not excluded from the application by the
monitored person.
113881
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
•
When an event is detected as non-fall event and is represented as class 0, no alarm will be transmitted and the
event occurrence is discarded.
By the use of backend systems, the physicians/caretakers
could observe the elderly people in real time from remote
areas. Besides, the backend system aid doctors to treat diseases using the offered data and patient history.
IV. WORKING PROCESS OF IMEFD-ODCNN MODEL
The overall working process of the IMEFD-ODCNN
model involves different subprocesses data acquisition, preprocessing, SqueezeNet based feature extraction, SSO based
parameter tuning, and SSOA-VAE based classification. The
detailed working of these processes is discussed in the succeeding subsections.
A. DATA PRE-PROCESSING
In the beginning stage, the frames were pre-processed for
improving the characteristics of an image, removal the noise
artefacts, and improve specific groups of features. At this
point, the frames were processing from 3 important levels
namely resizing, augmentation and normalization. In order
to decrease the calculation cost, the resizing of frames occur
from 150 × 150. At the same time, the frames are augmented
where the frames are changed at all training epochs. For
augmenting the frames, various models like zooming, horizontal flipping, rotation, width, and height shifting. At last,
normalization technique was implemented to enhanced generalization of the model.
B. SqueezeNet BASED FEATURE EXTRACTION
The CNN generally contains full connection layer, convolutional layer, and pooling layer. Initially, the feature is
extracted with more than one pooling & convolution layer.
Later, entire feature mappings from the latter convolution
layer are converted to 1D vectors for full connection. Lastly,
the output layer categorizes the input images. The network
alters the weight variables using BP and minimizes the square
variance among the classification outcomes and predictable
output. The neurons in every layer are ordered in 3D: depth,
width, and height, where height & width is the size of neuron,
and depth denotes channel amount of the input image/the
amount of input feature mappings. The convolutional layer
has many convolution filters, extract distinct features from
the image using convolution process. The convolution filter
of the present layer convoluted the input feature mappings
for extracting local features and attain the output feature mappings. Later, the nonlinear feature mappings are attained with
activation function. The pooling layer, so called subsampling
layer, is behindhand the convolutional layer. It executes down
sampling process, with a certain value as output in specific
regions. With the removal of insignificant instance points
from the feature map, the size of input feature map of the
following layer is decreased, and the computation complexity
is also reduced. Simultaneously, the flexibility of the network
113882
to the modifications of image rotation & translation was also
raised [20]. The general pooling operation contains average
and maximal pooling. The framework is denuding upon pooling & convolutional layers could enhance the strength of
the network module. The CNN could expand by multilayer
convolutions. By amount of increasing layers, the features
attained via learning becomes global. Eventually, the global
feature map learned is converted to a vector for connecting
full connection layer. All variables in the network module are
in the full connection layer.
Since the number of variables for VGGNet & AlexNet is
increasing, the SqueezeNet network module was presented
that has minimal variables when maintaining accuracy. The
fire model is the fundamental model in SqueezeNet, and
its structure is displayed in Fig. 2. This model is separated
to Expand & Squeeze frameworks. The 1 × 1 convolutional layer has gained more interest in the deliberation of
network structure. The works explain from the perception
of cross channel pooling where MLP is equal to the cascade cross channel parametric pooling layer behindhand the
conventional kernel, therefore attaining a linear integration
of multiple feature maps and data incorporation over the
channels. If the number of output & input channels are
larger, the convolution kernel variable becomes larger. They
include 1 × 1 convolution for all inception modules, decreasing the amount of input channels, and the convolution kernel variables and complexity operation is reduced. Finally,
a 1 × 1 convolution is included for improving the number
of channels and improve feature extraction. If the sampling
reduction process is delayed, a large activation graph is given
to the convolutional layer, whereas the large activation graph
maintains additional data that could give high classification
accuracy [27]–[29].
FIGURE 2. a) SqueezeNet structure (b) Fire module with layers.
C. HYPERPARAMETER OPTIMIZATION USING
SSO ALGORITHM
For tuning the hyperparameters of the SqueezeNet model,
the SSO algorithm is applied to optimally adjust the
VOLUME 9, 2021
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
hyperparameters involved in it. The salps included the set
of Salpidae that comprises a visible barrel shaped body. The
tissues are identical to jellyfishes. As well, the motion is
identical to jelly fish, when the water is inspired by a body
as propulsion and goes in the forward direction. A mathematical depiction of swarming behaviors & population of
salps is determined. In addition, no mathematical method of
salp swarm is utilized for resolving optimization problems
were swarms of fishes, bees, and ants are widely applied
and labeled to solve the enhanced problem. For modeling the
salp chain mathematically, the population is categorized by
two classes such as Follower and Leader. Firstly, leader is
considered to be salp at the front phase of a chain, whereas the
residual salp is so called follower. According to the names,
the salps represents leader guide the swarm where the follower follows each other. Compared with other swarm based
modules, the place of salps is determined as n-dimension
search space where n represents variable amount of the
employed problem. Henceforth, the position of salps is kept
in a two dimensional matrix and so called x. Furthermore,
it consider a food source so called F whereas search space
is the swarm target. For upgrading the leader position, it is
represented by.
(
Fj + c1 ((ubj − lbj )c2 + lbj ) c3 ≥ 0
1
(1)
xj =
Fj − c1 ((ubj − 1bj )c2 + 1bj ) c3 < 0
where as xj1 denotes location of primary salp in jth dimension,
Fj represents position of food source in jth dimension, ubj
indicates maximal bound of jth dimension, lbj denotes minimal bound of jth dimension, c1 , c2 , and c3 denotes random
values [21].
Eq. (1) represents leader is preferred to update the location
regarding food sources. The coefficient c1 is more important
feature in SSA since it deals with the exploitation and exploration as determined by:
41 2
c1 = 2e−( L )
(2)
whereas l denotes current iteration where L indicates high
amount of iteration. The attribute c2 and c3 are determined
as random values which are generated uniformly with zero
and one. The forthcoming location in jth dimension is negative/positive infinity and step size. To upgrade the position of
follower, the given function is employed:
xij =
1 2
at + v0 t
2
(3)
whereas i ≥ 2, xji denotes position of ith follower salp in jth
dimension, t indicates time, v0 represents primary speed, and
ν
x−x0
a = final
ν0 where ν = r . Because the time in optimization
denotes iteration, the difference between iterations is one, and
assume that v0 = 0, whereas the functions are employed by:
1 i
xji =
xj + xji−1
(4)
2
whereas i ≥ 2 and xji denotes location of ith follower salp in
jth dimension. By Eqs. (1) and (4), salp chain can be speeded.
VOLUME 9, 2021
D. FALL DETECTION USING SSOA-VAE MODEL
During the classification stage, the SSOA-VAE model gets
executed to determine the class labels of the input video
frames, i.e. non-fall or fall event. A VAE is a variation of AE
rooted in Bayesian inference. It can module the fundamental
distribution of observation p (z) and generates novel data by
presenting a group of latent arbitrary parameters
z. They
R
could denote the procedure as p (x) =
p (x|z) p (z) dz.
But, the marginalization is computationally intractable as the
search space of z is constant and combinatorically larger.
Instead, they could denote marginal log probability of a separate points log p (x) = DKL (qϕ (z|x)||pθ (z)) + Lvae (ϕ, θ; x)
with representation from [22], whereas DKL denotes Kullback
Leibler divergence from previous pθ (z) to the variation calculation qϕ (z|x) of p (z|x) and Lvae indicates variation lower
bound of the data x with Jensen’s inequality. Noted that ϕ and
θ denote variables of the encoder & decoder, correspondingly.
Fig. 3 demonstrates the structure of VAE.
FIGURE 3. Architecture of VAE.
A VAE enhances the variables, ϕ, and θ, with the maximization of lower bound of the log probability, Lvae ,
Lvae = −DKL (qϕ (z|x)||pθ (z)) + Eqϕ (z|x)[logpθ (x|z)]. (5)
The initial word standardizes the latent parameter z with
the minimization of KL divergence among estimated previous
and posterior of the latent parameter. Next the recreation of
x with the maximization of log probability log pθ (x|z) by
sampling from qϕ (z|x). The selection of distribution kinds
is significant as VAE modules the estimated posterior distribution qϕ (z|x) from previous pθ (z) and probability pθ (x|z).
A usual selection for the posterior is Gaussian distribution,
N (µz , 6z ), whereas a typical standard distribution N (0, 1)
is utilized prior. For the probability, a Bernoulli distribution/multivariate Gaussian distribution is frequently utilized
to continuous/binary data, correspondingly.
In order to determine the parameters involved in the VAE
(ϕ and θ ), the SSOA is applied in such a way that the
fall detection performance gets improved. The sparrows are
usually kindly birds and contain several types. They are distributed worldwide and attentive to survive in areas around
humans. Similarly, they are omnivorous species and mostly
eat seeds and grains. It is usually so called resident in nature.
In comparison with other little birds, it is stronger in memory
power and creativeness. It has two different types of captive
house sparrows such as scrounger and producer. The producers strongly search for the food source, while the scrounger
113883
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
acquires foodstuff from the producer. Furthermore, the proof
exhibits that the bird usually exploits behavioural approach
adaptably, and shift among scrounger & producer. From the
study, it is exposed that the sparrow finds their food by the
approach of producer and the scrounger based on circumstances. It is noteworthy that the birds are placed on the
edge of the population, are possible to be attacked through
predators, and continuously try to attain an optimal location.
The sparrows are located on the central may travel to their
neighbours for reducing the threat.
Initially, the virtual sparrow is employed to identify an
optimum source of food. The residence of sparrow is given
by:
χ1,1 χ1,2 · · · · · · χ1′ d
χ2,1 χ2,2 · · · · · · χ2,d
(6)
X = .
..
..
..
..
..
.
.
.
.
xn,1 xn,2 · · · · · · xn,d
whereas n denotes amount of sparrow and d indicates direction of variable that should be enhanced. Therefore, the fitness score of all sparrows are defined by [23]:
f ([x1,1 χ1,2 · · · · · · χ1,d ])
f ([x2,1 χ2,2 · · · · · · χ2,d ])
FX = .
(7)
..
.. ..
..
..
.
. .
.
f ([xn,1 xn,2 · · · · · · xn,d ])
whereas n denotes amount of sparrow, and calculate of entire
rows in FX represents fitness score of an individual. In SSA,
the producer contains maximal fitness measure that accomplishes an optimum food in search function. Likewise, producer is responsible for exploring food and support the action
of entire populations. Hence, the producer can detect food in
wide range than scroungers. According to rules (6) and (7),
the location of producer is expanded by:
(
t · exp( −i ) if R < ST
Xi,j
2
t+1
α·itermax
(8)
Xj,j =
t +O·L
Xi,j
if R2 ≥ ST
t
whereas t indicates current iteration, j = 1, 2, . . . , d.Xj,j
denotes rate of jt dimension of it sparrow at iteration t.itermax
represents constant with maximal iteration. α ∈ (0, 1]
denotes random value. R2 (R2 ∈ [0, 1]) and ST (ST ∈
[0.5, 1.0]) represents an alarm value and security threshold
respectively. Q denotes arbitrary value that employs simple
distribution and L indicates matrix 1 × d for entire components with one.
While R2 < ST , denotes no predator exists, and producers
get to wide search mode. Once R2 ≥ ST , then some sparrows
have created the predator, and it is important to protect them
by flying to safe region.
For scrounger, it employs rules (9) and (10). Few
scroungers follow the producer obviously. When the producer
finds an optimal food, then it leaves the location for competing to food. When the competitions are effective, then they
could attain the food of producer, or rules (10) is executed.
113884
The position upgrades formal for scrounger is given by:
t
Xt
−X i
0. exp( worstj2 i )
if i > n/2
t+1
Xi,j =
(9)
X t+1 + |X t − X t+1 | · A+ · L otherwise
P
j,j
P
whereas XP denotes optimum location employed with a producer, Xworst indicates current global worst location, A showcase a matrix of 1 × d for a component with one, and A+ =
AT (AAT )−1 . If i > n/2, it recommends that it scrounger with
unsuccessful fitness is highly starving.
Consequently, the sparrows are away from danger will contain further lifespan. The main position of sparrow is created
arbitrarily in the population. Depending upon, the arithmetical technique is given by:
t
t
t
Xbest + β · |Xi,j − Xbest!| if fi > fg
t+1
t −X t
Xi,j
(10)
Xi,j
=
worst
t
if fi = fg
Xi,j + K · (fj −fw )+ε
whereas Xbest denotes current global optimum position. β,
indicate step size control variable that is a standard distribution of random values with mean value of zero and a variance
of one. K ∈ [−1, 1] denotes arbitrary measure. In this
module, fi denotes fitness value of current sparrow. fg and fw
indicates current global optimum and worst fitness measures.
ε indicate minimal constant and remove zero division error.
In event of easiness, when fi > fg determines sparrow
is at edge of a group. Xest indicates location of a centre of
population that is secure. Now, fj = fg indicates sparrow,
is in the center of a population which is attentive from danger
and travels nearer to the border. K denotes direction whereas
sparrow moves and step size control coefficient.
V. PERFORMANCE VALIDATION
The proposed model is validated using Multiple cameras fall
dataset [24] and UR Fall Detection (URFD) dataset [25]. The
first dataset comprises 192 videos where 96 videos come
under fall events and 96 videos come under non-fall events.
The second dataset has frontal sequence of 314 frames, where
74 frames come into fall event and 240 frames come under
non-fall event. The parameter setting of the proposed model
is given as follows: mini batch size: 200, dropout: 0.5, number
of hidden layers:3, and number of hidden units: 1024.
Fig. 4 shows the sample test images from the dataset.
Besides, the depth level of the images from the sample test
images is illustrated in Fig. 5.
The classification results analysis of the IMEFD-ODCNN
model on multiple cameras falls dataset is given in Table 1
under varying training size (TS). On the TS of 40%:60%, the
IMEFD-ODCNN model has gained a specificity of 99.10%,
precision of 99.67%, recall of 99.82%, accuracy of 99.54%,
and F-score of 99.46%. Moreover, on the TS of 60%:40%,
the IMEFD-ODCNN technique has achieved a specificity
of 99.22%, precision of 99.51%, recall of 99.81%, accuracy
of 99.80%, and F-score of 99.53%. Furthermore, on the TS of
80%:20%, the IMEFD-ODCNN methodology has obtained a
VOLUME 9, 2021
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
TABLE 1. Comparative analysis of proposed IMEFD-ODCNN method on multiple cameras fall dataset in terms of different measures.
FIGURE 4. Sample sequences.
FIGURE 5. Depth data of the sequences.
specificity of 99.56%, precision of 100%, recall of 99.83%,
accuracy of 99.94%, and F-score of 99.92%.
Fig. 6 illustrates the ROC analysis of the IMEFD-ODCNN
model on the multiple cameras fall dataset under different
TS. From the figure, it is evident that the IMEFD-ODCNN
model has accomplished effective fall detection performance
with the maximum ROC values under all TS. The classification outcomes analysis of the IMEFD-ODCNN approach
on UR Fall Detection dataset is provided in Table 2 under
varying training size (TS). On the TS of 40%:60%, the
IMEFD-ODCNN method has attained a specificity of
99.09%, precision of 99.93%, recall of 99.47%, accuracy
of 99.49%, and F-score of 99.32%.
Furthermore, on the TS of 60%:40%, the IMEFD-ODCNN
method has reached a specificity of 99.76%, precision
of 99.81%, recall of 99.59%, accuracy of 99.54%, and F-score
of 99.30%. Also, on the TS of 80%:20%, the IMEFDODCNN technique has achieved a specificity of 99.89%,
precision of 99.56%, recall of 99.90%, accuracy of 99.87%,
and F-score of 99.59%.Fig. 7 showcases the ROC analysis
VOLUME 9, 2021
of the IMEFD-ODCNN method on the UR Fall Detection
Dataset in distinct TS. From the figure, it can be stated that
the IMEFD-ODCNN technique has accomplished effective
fall detection performance with the maximal ROC values in
all TS.
A brief comparison study of the IMEFD-ODCNN model
with other existing methods on multiple cameras fall dataset
take place in Table 3. From the figure, it is demonstrated
that the 1D Conv NN and 2D Conv NN models have demonstrated poor results with the accuracy of 94.3% and 95.5%
respectively. In line with that, the ResNet-50 and ResNet101 models have accomplished moderately closer outcomes
with the accuracy of 96.1% and 96.5% respectively. Next
to that, the Depthwise, VGG-16, and VGG-19 models have
accomplished moderately closer outcomes with the accuracy
of 97.8%, 98%, and 98% respectably. Finally, the proposed
IMEFD-ODCNN model has showcased superior results with
an accuracy of 99.76%.
Another comparative study of the IMEFD-ODCNN
methodology with other state-of-art techniques on UR Fall
Detection Dataset takes place in Table 4. From the figure,
it can be outperformed that the 1D Conv NN and 2D Conv
NN techniques have showcased worse outcomes with the
accuracy of 92.7% and 95% correspondingly. Along with
that, the ResNet-50 and ResNet-101 manners have accomplished moderately closer result with the accuracy of 95.4%
and 96.2% correspondingly. Likewise, the VGG-16, Depthwise, and VGG-19 algorithms have accomplished moderately
closer result with the accuracy of 97.6%, 98%, and 98%
correspondingly. Eventually, the projected IMEFD-ODCNN
technique has outperformed maximum outcomes with an
accuracy of 99.57%.
An extensive training time and testing time analysis
of the proposed IMEFD-ODCNN model with other existing techniques on Multiple Cameras Fall dataset is given
in Table 5 and Fig. 8. From the results, it is evident that the
VGG-16 model has required maximum training and testing
time of 3627.48s and 1758.33s respectively. At the same time,
the VGG-19 model has needed a slightly reduced training and
testing time of 3189.03s and 1482.46s respectively. Besides,
the ResNet-101 model has resulted in a moderate training and
testing time of 1274.13s and 932.4s respectively. Meanwhile,
the 2D Conv NN and 1D Conv NN models have showcased
moderate testing and training time. Eventually, the ResNet-50
model has needed a competitively decreased training and
113885
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
FIGURE 6. ROC analysis of proposed IMEFD-ODCNN method on multiple cameras fall dataset.
FIGURE 7. ROC analysis of proposed IMEFD-ODCNN method on UR fall detection dataset.
TABLE 2. Comparative analysis of proposed IMEFD-ODCNN method on UR fall detection dataset in terms of different measures.
testing time of 1163.45s and 946.22s respectively. However,
the proposed IMEFD-ODCNN model has showcased effective outcomes with the training and testing time of 1136.94s
and 735.41s respectively.
113886
An extensive training time and testing time analysis of
the projected IMEFD-ODCNN technique with other existing methods on UR Fall Detection Dataset is provided
in Table 6 and Fig. 9 [26]. From the results, it can be revealed
VOLUME 9, 2021
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
TABLE 3. Comparative analysis of existing with proposed IMEFD-ODCNN
method on multiple cameras fall dataset in terms of accuracy.
TABLE 4. Comparative analysis of existing with proposed IMEFD-ODCNN
method on UR fall detection dataset in terms of accuracy.
FIGURE 8. Comparative analysis of IMEFD-ODCNN model on multiple
cameras fall dataset.
TABLE 6. Comparative analysis of existing with proposed IMEFD-ODCNN
method on UR fall detection dataset in terms of training time and testing
time.
TABLE 5. Comparative analysis of existing with proposed IMEFD-ODCNN
method on multiple cameras fall dataset in terms of training time and
testing time.
that the VGG-16 technique has required higher training and
testing time of 2352.6s and 1108.8s correspondingly. Simultaneously, the VGG-19 approach has needed a somewhat
diminished training and testing time of 2778.6s and 1372.2s
respectively.
Also, the ResNet-101 method has resulted in a moderate training and testing time of 1545.6s and 925.8s correspondingly. In the meantime, the ResNet-50 and 2D Conv
NN models have showcased moderate testing and training time. Finally, the Depthwise model has needed a competitively reduced training and testing time of 1093.2s
and 725.4s respectively. However, the presented IMEFDODCNN methodology has outperformed effective results
with the training and testing time of 1014s and 677.4s correspondingly. The experimental outcomes highlighted the
VOLUME 9, 2021
FIGURE 9. Comparative analysis of IMEFD-ODCNN model on UR fall
detection dataset.
promising performance of the IMEFD-ODCNN model over
the recent methods with the maximum accuracy of 99.76%
and 99.57% on the multiple cameras fall and UR fall detection dataset. The proposed model outperforms the existing
113887
T. Vaiyapuri et al.: IoT and DL Enabled Elderly Fall Detection Model for Smart Homecare
methods due to the inclusion of SqueezeNet model and hyperparameter optimization process using SSOA.
VI. CONCLUSION
This paper has designed a new IMEFD-ODCNN model to
detect fall events in smart homecare of elderly people. The
IMEFD-ODCNN model allows IoT devices and intelligent
DL algorithms to detect the occurrence of falls in the smart
home. The proposed IMEFD-ODCNN model involves different stages of operations such as data acquisition, preprocessing, SqueezeNet based feature extraction, SSO based
parameter tuning, and SSOA-VAE based classification. Once
the fall is identified, an immediate alert is sent to the caretakers and hospital management. The utilization of SSO algorithm to select the hyperparameters of the SqueezeNet model
and SSOA algorithm for parameter adjustments of the VAE
model helps to considerably improve the overall fall detection performance. An extensive set of simulations is carried
out on UR fall detection dataset and multiple cameras fall
dataset. The experimental results highlighted the promising
performance of the IMEFD-ODCNN model over the recent
state of art methods. In future, the fall detection performance
of the IMEFD-ODCNN model can be improved by the use
of advanced DL models for classification process. Besides,
scalable and robust versions of the IMEFD-ODCNN model
can be developed to assist real time fall detection events from
low-quality videos.
CONFLICT OF INTEREST
The authors declare that they have no conflict of interest. The
manuscript was written through contributions of all authors.
All authors have given approval to the final version of the
manuscript.
DATA AVAILABILITY STATEMENT
Data sharing not applicable to this article as no datasets were
generated during the current study.
REFERENCES
[1] D. Mrozek, A. Koczur, and B. Małysiak-Mrozek, ‘‘Fall detection in older
adults with mobile IoT devices and machine learning in the cloud and on
the edge,’’ Inf. Sci., vol. 537, pp. 132–147, Oct. 2020.
[2] C.-H. Chen, F. Song, F.-J. Hwang, and L. Wu, ‘‘A probability density
function generator based on neural networks,’’ Phys. A, Stat. Mech. Appl.,
vol. 541, Mar. 2020, Art. no. 123344.
[3] B. Aguiar, T. Rocha, J. Silva, and I. Sousa, ‘‘Accelerometer-based fall
detection for smartphones,’’ in Proc. IEEE Int. Symp. Med. Meas. Appl.
(MeMeA), Jun. 2014, pp. 1–6.
[4] C. H. Chen, ‘‘A cell probe-based method for vehicle speed estimation,’’
IEICE Trans. Fundam. Electron., Commun. Comput. Sci., vol. 103, no. 1,
pp. 265–267, 2020.
[5] A. C. Scheffer, M. J. Schuurmans, N. van Dijk, T. van der Hooft, and
S. E. D. Rooij, ‘‘Fear of falling: Measurement strategy, prevalence, risk
factors and consequences among older persons,’’ Age Ageing, vol. 37, no. 1,
pp. 19–24, Jan. 2008.
[6] M. Pan, Y. Liu, J. Cao, Y. Li, C. Li, and C.-H. Chen, ‘‘Visual recognition
based on deep learning for navigation mark classification,’’ IEEE Access,
vol. 8, pp. 32767–32775, 2020.
[7] C.-H. Chen, F.-J. Hwang, and H.-Y. Kung, ‘‘Travel time prediction system
based on data clustering for waste collection vehicles,’’ IEICE Trans. Inf.
Syst., vol. E102.D, no. 7, pp. 1374–1383, Jul. 2019.
113888
[8] J. A. Stevens, P. S. Corso, E. A. Finkelstein, and T. R. Miller, ‘‘The costs
of fatal and non-fatal falls among older adults,’’ Injury Prevention, vol. 12,
no. 5, pp. 290–295, 2006.
[9] C.-H. Chen, ‘‘An arrival time prediction method for bus system,’’ IEEE
Internet Things J., vol. 5, no. 5, pp. 4231–4232, Oct. 2018.
[10] S. Chaudhuri, H. Thompson, and G. Demiris, ‘‘Fall detection devices
and their use with older adults: A systematic review,’’ J. Geriatric Phys.
Therapy, vol. 37, no. 4, pp. 178–196, Oct. 2014.
[11] F. Hussain, F. Hussain, M. Ehatisham-ul-Haq, and M. A. Azam, ‘‘Activityaware fall detection and recognition based on wearable sensors,’’ IEEE
Sensors J., vol. 19, no. 12, pp. 4528–4536, Jun. 2019.
[12] O. Aziz, J. Klenk, L. Schwickert, L. Chiari, C. Becker, E. J. Park,
G. Mori, and S. N. Robinovitch, ‘‘Validation of accuracy of SVM-based
fall detection system using real-world fall and non-fall datasets,’’ PLoS
ONE, vol. 12, no. 7, Jul. 2017, Art. no. e0180318.
[13] A. Shojaei-Hashemi, P. Nasiopoulos, J. J. Little, and M. T. Pourazad,
‘‘Video-based human fall detection in smart homes using deep learning,’’
in Proc. IEEE Int. Symp. Circuits Syst. (ISCAS), May 2018, pp. 1–5.
[14] P. Tsinganos and A. Skodras, ‘‘A smartphone-based fall detection system
for the elderly,’’ in Proc. 10th Int. Symp. Image Signal Process. Anal.,
Sep. 2017, pp. 53–58.
[15] L. Liu, Y. Hou, J. He, J. Lungu, and R. Dong, ‘‘An energy-efficient fall
detection method based on FD-DNN for elderly people,’’ Sensors, vol. 20,
no. 15, p. 4192, Jul. 2020.
[16] X. Kong, Z. Meng, N. Nojiri, Y. Iwahori, L. Meng, and H. Tomiyama,
‘‘A HOG-SVM based fall detection IoT system for elderly persons using
deep sensor,’’ Procedia Comput. Sci., vol. 147, pp. 276–282, Jan. 2019.
[17] V. Carletti, A. Greco, A. Saggese, and M. Vento, ‘‘A smartphone-based system for detecting falls using anomaly detection,’’ in Proc. Int. Conf. Image
Anal. Process. Cham, Switzerland: Springer, Sep. 2017, pp. 490–499.
[18] S. Suresh, M. Jain, and R. Ramadoss, ‘‘Fall classification based on sensor
data from smartphone and smartwatch,’’ AIP Conf. Proc., vol. 2112, no. 1,
Jun. 2019, Art. no. 020075.
[19] T. Nguyen Gia, V. K. Sarker, I. Tcarenko, A. M. Rahmani, T. Westerlund,
P. Liljeberg, and H. Tenhunen, ‘‘Energy efficient wearable sensor node
for IoT-based fall detection systems,’’ Microprocessors Microsyst., vol. 56,
pp. 34–46, Feb. 2018.
[20] G. Xu, ‘‘Deep convolutional neural network to detect J-UNIWARD,’’
in Proc. 5th ACM Workshop Inf. Hiding Multimedia Secur., Jun. 2017,
pp. 67–73.
[21] B. S. Ahmed, M. A. Sahib, and M. Y. Potrus, ‘‘Generating combinatorial
test cases using simplified swarm optimization (SSO) algorithm for automated GUI functional testing,’’ Eng. Sci. Technol., Int. J., vol. 17, no. 4,
pp. 218–226, Dec. 2014.
[22] D. Park, Y. Hoshi, and C. C. Kemp, ‘‘A multimodal anomaly detector
for robot-assisted feeding using an LSTM-based variational autoencoder,’’
IEEE Robot. Autom. Lett., vol. 3, no. 3, pp. 1544–1551, Jul. 2018.
[23] W. Tuerxun, X. Chang, G. Hongyu, J. Zhijie, and Z. Huajian, ‘‘Fault
diagnosis of wind turbines based on a support vector machine optimized
by the sparrow search algorithm,’’ IEEE Access, vol. 9, pp. 69307–69315,
2021.
[24] E. Auvinet, C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau, ‘‘Multiple cameras fall dataset,’’ DIRO-Université de Montréal, Montreal, QC,
Canada, Tech. Rep. 1350, Jul. 2010.
[25] [Online]. Available: http://fenix.univ.rzeszow.pl/~mkepski/ds/uf.html
[26] A. Sultana, K. Deb, P. K. Dhar, and T. Koshiba, ‘‘Classification of indoor
human fall events using deep learning,’’ Entropy, vol. 23, no. 3, p. 328,
Mar. 2021.
[27] B. A. Y. Alqaralleh, S. N. Mohanty, D. Gupta, A. Khanna, K. Shankar, and
T. Vaiyapuri, ‘‘Reliable multi-object tracking model using deep learning
and energy efficient wireless multimedia sensor networks,’’ IEEE Access,
vol. 8, pp. 213426–213436, 2020, doi: 10.1109/ACCESS.2020.3039695.
[28] A. Rajagopal, A. Ramachandran, K. Shankar, M. Khari, S. Jha, Y. Lee,
and G. P. Joshi, ‘‘Fine-tuned residual network-based features with latent
variable support vector machine-based optimal scene classification model
for unmanned aerial vehicles,’’ IEEE Access, vol. 8, pp. 118396–118404,
2020, doi: 10.1109/ACCESS.2020.3004233.
[29] V. Porkodi, A. R. Singh, A. R. W. Sait, K. Shankar, E. Yang,
C. Seo, and G. P. Joshi, ‘‘Resource provisioning for cyber–physical–
social system in cloud-fog-edge computing using optimal flower pollination algorithm,’’ IEEE Access, vol. 8, pp. 105311–105319, 2020, doi:
10.1109/ACCESS.2020.2999734.
VOLUME 9, 2021