scispace - formally typeset

Proceedings ArticleDOI

Internet of things for sleep quality monitoring system: A survey

01 Nov 2016-pp 1-6

TL;DR: The emergence of internet-of-things technology has provided a promising opportunity to build a reliable sleep quality monitoring system by leveraging the rapid improvement of sensor and mobile technology.
Abstract: Sleep quality is an important factor for human physical and mental health, day-time performance, and safety. Sufficient sleep quality can reduce risk of chronic disease and mental depression. Sleep helps brain to work properly that can improve productivity and prevent accident because of falling asleep. In order to analyze the sleep quality, reliable continuous monitoring system is required. The emergence of internet-of-things technology has provided a promising opportunity to build a reliable sleep quality monitoring system by leveraging the rapid improvement of sensor and mobile technology. This paper presents the literature study about internet of things for sleep quality monitoring systems. The study is started from the review of sleep quality problem, the importance of sleep quality monitoring, the enabling internet of things technology, and the open issues in this field. Finally, our future research plan for sleep apnea monitoring is presented.
Topics: Sleep apnea (54%), Sleep (system call) (51%)

Content maybe subject to copyright    Report

Internet of Things for Sleep Quality Monitoring
System: A Survey
Nico Surantha
, Gede Putra Kusuma
, Sani M. Isa
Master in Computer Science
Bina Nusantara University, Jakarta
Email: {nsurantha
,inegara
}@binus.edu
sani.m.isa
@binus.ac.id
Abstract—Sleep quality is an important factor for human
physical and mental health, day-time performance, and safety.
Sufficient sleep qu ality can reduce risk of chronic disease and
mental depression. Sleep helps brain to work properly that can
improve productivity and prevent accident because of falling
asleep. In order to an alyze the sleep quality, reliable continuous
monitoring system is required. The emergence of i nternet-of-
things technology has provided a promising opportunity to
build a reliable sleep quality monitoring system by leveraging
the rapid improvement of sensor and mobile technology. This
paper presents the literature study about internet of things for
sleep quality monitoring systems. The study is started f rom the
review of sleep q uality problem, the importance of sleep quality
monitoring, the enabling internet of things technology, and the
open issues in this field. F inally, our future research plan for
sleep apnea monitoring is presented.
I. INTRODUCTION
In the recent years, internet-of-things (IoT) ha s become a
popular subject in electronics and communication researc h
field. IoT is a technology that interconnec ts people, com-
puter, devices, and anything that is connected to the inter-
net [1]. The emergence of IoT is stimulated by the rapid
growing of wireless sensor network, cloud computing, and
high-th rough put network tech nology [2]-[4]. One of the most
important aspect of IoT is the ability to operate machine-to-
machine (M2M) communication without requirin g human- to-
machine interaction [5]-[6]. The M2M capability of IoT has
become a fundamental aspect to develop a human control-less
and contin uous remote monitoring system. The system based
on the concept of Io T has been developed in many fields,
e.g. industrial automatio n [7]-[8], smart-city [9], smart-farming
[10], many more applications.
Remote monitoring for health care is also a field that can
maximize the capability of IoT technology. The research for
this field has been performed for the last two decades. In
2000, Stephen J. Brown proposed a multi-user remote h ealth
monitoring system [11]. In his proposal, the data acquisition
is performed manually by doctor or car egivers. From ther e, a
smart health monitoring that utilizes wireless sensor network
technology has been introduced [12]. In the recent ye ars, many
researches and developments have been done on smart health
monitoring system based on the concept of IoT [13]-[15].
In this paper, we reviews the current state, open issues, and
future research of remote health monitoring system, especially
Literature Study
Problem Formation
(Sleep Quality & the monitoring)
IoT System Modelling
(Architecture & logic flowchart)
Open Problem & Future Research
Conclusion
Fig. 1. Research Methodology
for sleep quality monitoring. Sleep plays an important role
to maintain health, mental, day-time productivity, and safety
of human being. T he lack of sleep quality can potentially
increase the risk of chronic diseases, dep ression, and the
number of accident because of falling asleep. Therefore, sleep
quality monitoring is imp ortant to maintain the physical and
mental h ealth of human. For this p aper, we perform a r esearch
methodology as described by Fig. 1. Firstly, we gather the
informa tion and r e la te d reference about sleep quality monitor-
ing and IoT tech nology. Secondly, we review the significance
of sleep quality and sleep disorder and the monitoring aspect.
Thirdly, we model the IoT system and the logical flowchart for
sleep quality monitoring. We also review the component of the
IoT architecture. Finally, we review the future research trend
in this field and our research plan on sleep apnea monitoring
system.
This paper is organized as follow. Section II reviews about
the sleep quality, the sleep disorders, and the effect to human
health and well being. Section III reviews about IoT system
architecture , the component of the system, and workflow of
the system. Section IV reviews about the future research trend
on sleep quality monitoring and o ur research plan. Finally, the
conclusion is presented in section V.
2016 11th International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Yogyakarta, Indonesia
978-1-5090-5130-4/16/$31.00 ©2016 IEEE

Stage 1
Very light
sleep
Stage 2
light
sleep
Stage 3
deep
sleep
Stage 4
Very
deep
sleep
Stage 5
Rapid Eye
Movement
Fig. 2. Sleep Cycles
II. SLEEP QUALITY AND THE MONITORING
As defined by William H. Moorcroft in his book, sleep is a
reversible behavioral state when people have low attention to
the environment. It is usually accompanied by an inactivity of
nervouse system, a relaxed posture, minimal movement, the
suspended consciousness.[16, p. 24]. There are ve stages of
sleep, i.e. stages 1, 2, 3, 4, and rapid eye movemen t (REM)
[16, pp. 25-26]. T hese stages progress in cyclic manner, from
stage 1 to REM sleep, then the cycle starts over again with
stage 1. Stage 1 and stage 2 are called light sleep. People
can easily be awaken in these stages. People spend almost
half of their total sleep time in stage 2 sleep, 20% in REM
sleep, the remaining time in other stages. The problem of sleep
disorder is usually associated with the irregularity in sleep
cycles. People need to get the right proportion of every stages
and sufficient number of cycles to obtain a quality sleep.
A. Sleep Disorder
Sleep disorder is a medica l disorder of the sleeping patterns.
Sleep diorder potentially increases the risk of chronic diseases,
mental problem, and number of accident. The most commo n
sleep disorders include sleep ap nea, narcolepsy, insomnia, and
restless legs syndrome. It will be discussed more detail below.
Insomnia refe rs to the deficiency of sleep quality and
quantity. 10-3 0% o f adult population is affected by in-
somnia [17]. This problem can result from jet lag, stress,
diet, and many other factors. The insomnia can affect on
the decrease of life quality, lost of productivity, increasing
number of traffic accidents, and increasing load of general
health care.
Narcolepsy is a medical diorder when a patient has
frequent ”sleep attack moments at different times of the
day, even if they have had a sufficient sleep at the night
before. It is also charac terized by sleep paralysis (the
inability to react, move, or spea k that happens durin g
awakening or when falling asleep), hallucinations, and
some cases episodes o f cataplexy (sud den loss of muscle
tone) [18]. Narcolepsy is usually hereditary [16, p. 330].
It is also linked to brain damage from a he a d injury or
neurological disease.
Restless legs syndrome (RLS) is characterize d by un-
pleasant crawling, tingling sensations from the legs, that
create urgency to move the legs to relieve the painful
feeling [16, p. 332]. It begin s or worsens du ring resting
period and becoming worse a t night. Up to 30% of
the cases are caused by iron deficiency. Therefore, iron
supplementation can be helpful to cure this problem.
Sleep apnea is a breathing disorder that is related to
sleep. It is characterized by a pause in breathing or
shallow breaths during sleep [19]. Due to sleep apnea, the
patient wakes us reqularly throughout the night in order
to breathe. The frequents wake-up moments result in very
poor sleep quality a nd excessive daytime sleepiness. The
breaths of sleep apnea patient is usually accompanied by
loud sn oring.
Sleep apnea occurs bec ause the throat is shrinked during
sleep th at makes the patients get difficulty to breath
during their sleep. The c hest is moving, trying to pump
the air to the lung s, but the a ir could not flow through
the throat completely. Sleep apnea potentially causes
hypertension and hear t problems [16, p. 326-327], due
to a d rop in blood oxygen level and a considerable rise
in blood pressure level during apn e ic moments. Patients
that suffer sleep apnea for many years are in danger of
dying during sleep du e to heart failure.
B. Sleep Quality Mo nitoring
Many physiologica l parameters can be monitored during
sleep in order to gain insight about the sleep quality of the
patient. The monitoring method is performed by placing some
sensor modules close to various body organs of the patient.
The body organs generate few amounts of electrical energy
during their work. T hese sensors can p ic k up some of this
electrical energy, send it to computer, display it as a graphical
representation on monitor, and store it in computer storage.
The physiologica l parameters inc lude heart r ate, respiration
rate and amplitude, central nervous system activity, muscular
activity, etc. The signal re cordings can be utilized for e.g.
detecting sleep staging, detecting various sleep disorders, and
other analysis applications.
Polysomnogr aphy is a comprehensive recording of phys-
iological changes that occur during sleep, which includes
brain activity, he art ryhtm, eye-movement, and skeletal
muscle activation [20]. Despite its extensive c a pabilities,
polysomnograp hy is very troublesome to be implemented
because many sensor modules need to be placed on the
body surface of the patient.
Following are more detail parameter that is recorded by
polysomnograp h.
Brain ac tivity is measured with electroencep halo-
gram (EEG). EEG is a visualization of the waveform
of electrical activities of large groups of brain cells.
2016 11th International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Yogyakarta, Indonesia

Data acquisition system
(sensor & WBAN/WLAN)
Data concentrator/
aggregator
Cloud storage
& processing
Polysomnography
Actigraphy
BCG
sensor
Ballistocardiography
Private Cloud
Public Cloud
Caregivers
Live display
History
Analy
sis
Alert signal
Monitoring
applications
Closest family
Private data
Patient s ID
Location based
services
Hospital ID
Medical
knowledge
sharing
smartphone
cloudlet
Fig. 3. Internet of Things Architecture for Sleep Quality Monitoring
EEG is recorded for the de termination of sleep stages
[21].
Eye movement is measured with electrooculogram
(EOG). Eye movement measurement is possible be-
cause the front of the eye is electrically positive.
Therefore, th e sensor measures the change of its
distance to the positive poles of the eyeball. EOG
is recorded to determine the presence of REM stage
[22].
Muscle activity, e.g. teeth grinding, face twitches,
and leg movements is me asured b y electromy ogram
(EMG) [23]. It he lps to determine if the REM stages
is present during the sleep. Detected fre quent leg
movements may indicate symptoms of restless leg
syndrome (RLS).
Heart activity is recorded by measuring electrical
activity of the h earts at it contracts and expands.
These can be analyzed for any abnormalities that
might be indicative of an underlying heart pathology.
The blood oxygen level is measured with oximetry.
Low oxygen levels may indicate a symptom of sleep
apnea [24].
Actigraphy is a n on-ob trusive method to record sleep-
wake schedule and measure sleep quality from body
movement data [25]. Acceleration sensors a re typically
worn on the wrist, jaw, ankle, calf, or around torso to
determine activity pattern. The weakness of actigraphy is
on its accuracy. Because it is difficult to distinguish if the
patient is sleeping or resting while stay awake. However,
despite its weakness, it has several advantages, i.e. cost
effective and easy to setup for long term monitoring
Ba llistocardiography (BCG) is another unobtrusive
method for measuring heart rate, heart rate variability,
respiration rate, and relative blood stroke volume based
on the body movement induced by heart’s pumping mech-
anism [26]. Recent development in sensor technolo gy and
signal processing h ave made it possible to install BCG
under the bed or ma ttress of the patient for totally un-
obstrusive me asurements. Ther e fore, BCG appears as the
most user-friendly option among the sensor technology.
III. IOT DESIGN MODELLING
This section discusses abou t the IoT architecture, the com-
ponen ts, and the logical flowchart of the sleep quality moni-
toring system. There are some references of IoT architecture
that are introduced in [13]-[15]. In this p aper, we propose
the architecture for sleep monitorin g. We also explain the
mechanism of the proposed architecture by lo gical flowchart.
A. IoT A rchitecture & workflow
Fig. 3 displays our proposed architecture for sleep quality
monitoring. There are four components of the arc hitecture, i.e.
data acquisition system, data concentrator/aggregator, cloud
storage/processing, and monitoring applications. The workflow
of each component in architecture is shown in Fig. 4. The
medical data and real-time location of the patien t is acquired
by data acquisition system through the wireless sensor and
location based detection service. Medical data from sensor is
then transmitted to network through intermediate data con-
centrator/aggregator, which is typically a smart phone that is
located around the patient. Then, data is transmitted to cloud
service for storage and processing. Finally, the me dical data is
displayed in application that can be accessed by caregivers or
closest family. In case of emergency, the system will deliver
2016 11th International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Yogyakarta, Indonesia

warning signal to caregivers and c losest family, therefore a
rescue action can be carried out immediately.
B. Data Acquisition System
Data acquisition system con sists of sleep monitoring sensor
and the conne ction. We have discussed abou t the type of sleep
monitoring sensor in subsection II-B. The connection in data
acquisition system means the wireless connection between
the sensor and data concentr ator/aggr egator. The wireless
connection module is usually integrated into an embedded
system. The type of c onnection used for hea lth monitoring is
usually wireless local area n e twork ( WLAN) or wireless body
area network (WBAN). The WLAN refers to the IEEE 802.11
standard, i.e. WiFi standard [27]. The WBAN was created
to a nswer the challenge of low power consumption issues in
health monitoring sensor [28]. IEEE 802.15.4 or well-known
as ZigBee is a low power consumptio n and low da ta rate
wireless networking protocol for communication between low
power devices that operates around 10 meter space distance
[29]. Bluetooth low enery (BLE) is another low power wireless
communication protoco l suitable for the special applications,
e.g. health monitoring, sports, a nd home enter ta inment. BLE
achieves higher energy efficiency in terms of ratio of energy
per bit transmitted compared to ZigBee [30].
C. Data Concentrator/Aggregator
Data concentrator is used to collect and organize data col-
lected by sensor to be transmitted to cloud service in internet
[31]. The data concentrator usually comes in the form of
mobile phone of the patient that contains application connected
to the w ireless sensor. In case the reso urce in mobile phone
could not support the application, cloudlet can be used as data
aggregator [32]. The cloudlet can be local processing unit and
temporary storage prior communication to cloud service in
internet. The cloudlet can also be used to run time critical
tasks in monitoring a pplication.
D. Cloud Storages & Processing
Mobile cloud computing (MCC) has emerged as a promis-
ing solution for healh remote monitoring system. MCC can
provide powerful, scalable, and flexible high pe rformance
computing, stor age, and sofware services at low cost [3 3]. De-
veloper can develop and deploy numerous mobile applications
for sleep quality monitoring b y accessing larger and faster data
storage service and processing power from the cloud.
For sleep application, we adopt the hybrid MCC architecture
from [33] wh ic h consists of public and private cloud. Sensitive
data, e.g. patient identity, location based services, real-time
monitoring status can be carried out on pr ivate server to
guaran tee the security. On the other hand, o ther insensitive
data, e.g. hospital identity and medical knowledge sharing can
be deployed on public clo ud service .
E. Monitoring Application
The result of data sensing and processing will be reported to
caregivers or relatives of the patient through mobile applica-
tion. The data will be displaye d in form of live data stream ing,
Retrieve medical data from patient
Requires
immediate
treatment?
No
Retrieve location of the patient
Login the cloud and register with
patient`s ID and store data in the cloud
for future reference
Caregivers, families, and patients can
monitor the data through mobile aps.
Send warning signal to caregivers &
families to carry out rescue action.
Yes
Transmit medical data to data
concentrator/aggregator
Fig. 4. Sleep Quality Monitoring System Workflow
data history, data analy sis from the history, and the warning
signal. The data streaming gives a real-time live medical data
of the patient, e.g. heart rate, respir a tion rate, etc. All the
recorde d data is stored by cloud server to keep the history of
the patient. Based on rec orded h istory, application perf orms an
analysis of patient sleep quality. Whenever it is an a lyzed that
there is an irregularity in patient condition then the warning
signal is released to notify caregivers a nd relatives to give an
immediate a ction to the patient.
IV. FUTURE RESEARCH
A. Future Research Trend
There are several open issues and challenges for sleep
quality monitorin g with IoT concepts.
Standardization
In the health remote monitoring system, there are many
vendors that manufacture various products and devices.
We pred ic t, the re ar e more vendors will continue this
trend becau se ther e is still many room for innovation and
improvement in this field. However, there is no default
standard tha t can regulate the interoperability among each
device. Therefore, the standard iz a tion is required to reg-
ulate about communication and protocol, including phy
and media access control (MAC) layer, data aggregatiion ,
device and gateway interfaces, value added services and
many more.
User-friendly data sensing method
In sleep quality monitoring, it is important to do measure-
ment or monitoring that does not disturb the convenience
of the sleeping patient. Polysomnograph appears as the
most comprehensive sensing me thod with extensive ca-
pability and high accuracy [20]. However, since many
electrodes needs to be attach ed to the patients body,
then they disturb the convenience of th e patient. It is
not appropriate for regular m onitoring method at home
2016 11th International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Yogyakarta, Indonesia

Live display
History
Analysis
Alert signal
Embedded system of bed contactless sensor
sensor
microcontroller
WiFi transceiver
heart rate
heart-rate
variability
report & warning
cloud server
Data storage
Data processing
mobile apps
respiration rate
relative stroke
volume
caregivers
Immediate treatment action
Fig. 5. Contactless Sleep Apnea Monitoring System based on Internet of Things
because of the lack of conveninence and troublesome
setup. It is also not appropriate to monitor elderly and
infants that are very sensitive to interfer ence d uring
their sleep. Two unob trusive methods, i.e., Actigraphy
and BCG might appear as the promissing candidate for
this problem. However, the accuracy and the range of
capability of these methods still need to be explored to
obtain the most accurate result.
Reliable a nd low-power communication protocol For
IoT systems, low-power communication has become the
major issues. Reliable MAC and routing protocol must
support multihop commun ications, low end-to-end d e la y,
low packet-delay, and low-power communicatio n. Even-
though, a study reports that the existing routing protocols
can work with minor modifications in IoT scenarios [2],
IETF ROLL workgroup claims that the existing protocol,
e.g. OSPF, AODV, OLSR does not satisfy the lossy
networks specific routing and low p ower requirements in
their present form. The specific ro uting re quirements for
example optimization for energy saving, restricted fra me
sizes, etc. Therefore, there is a need to d efine low energy
communication protocol for the system.
Data security Since there are many sensitive informa-
tions, e.g. patient identity, medical data, patients loc ation
are involved in this system. There fore, data security
becomes one of the main conc ern for th is monitoring
system. Firstly, secure routing protocol is required. The
proper routing and forwarding methods a re vital for real-
time communication in this system. Secondly, the secur ity
of handling IoT big data is also important. The sleep
quality sensor generates huge amounts of medical data
continuously and there is a need to securely store such
data, without compromising privacy, integrity, and con-
fidentiality of the data. Finally, since re source (memory
and power) has become m ain constra int for IoT system ,
therefore the data secu rity system should be designed
to maximize secu rity level while minimizing resource
utilization.
B. Future Research Plan
To a nswer the user-friendly challenge in sleep quality mon-
itoring system as described by subsection IV-A, our future
research plan is to propose a contactless sleep apnea moni-
toring system based on the concept of internet of thin gs. Our
proposed system is dep ic ted by Fig. 5 . There are three main
components of the system, i.e. an embedded system, cloud
server, and mobile apps. An embedded system will be u tilized
for data acquisition. The embedded system consists of some
components as mentioned below
1) contactless ballistoc ardiography sensor
The ”contactless” te rm means the sensor is not be
attached to the body, but it is be a ttached to the be d,
therefore it does not disturb the convenience of the user.
It become possible be cause the emergence of ballisto-
cardiography technology[26]. The ballistocardiography
sensor enable the system to do real-time monitoring of
vital sign of user, e.g. heart-rate, respiration rate, heart-
rate variability, and relative stroke volume.
2) microcontroller
A microcontroller is used to read data from sensor and
send them via a WiFi transceiver unit.
3) WiFi transceiver
A WiFi transceiver is used to transmit the acquired data
from the embedded system to cloud server for storage
and processing
. The result of data processing will be reported to c aregivers
through mobile application. The data will b e displayed in form
of live data streaming, data history, data analysis from the
2016 11th International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Yogyakarta, Indonesia

Citations
More filters

Journal ArticleDOI
14 Apr 2020
TL;DR: A substantial correlation has been observed between the pattern and other related features of longitudinal MRI data that can significantly assist in the diagnosis and determination of AD in older patients.
Abstract: Background: Alzheimer disease (AD) is a degenerative progressive brain disorder where symptoms of dementia and cognitive impairment intensify over time. Numerous factors exist that may or may not be related to the lifestyle of a patient that result in a higher risk for AD. Diagnosing the disorder in its beginning period is important, and several techniques are used to diagnose AD. A number of studies have been conducted on the detection and diagnosis of AD. This paper reports the empirical study performed on the longitudinal-based magnetic resonance imaging (MRI) Open Access Series of Brain Imaging dataset. Furthermore, the study highlights several factors that influence the prediction of AD. Objective: This study aimed to correlate the effect of various factors such as age, gender, education, and socioeconomic background of patients with the development of AD. The effect of patient-related factors on the severity of AD was assessed on the basis of MRI features, Mini-Mental State Examination (MMSE), Clinical Dementia Rating (CDR), estimated total intracranial volume (eTIV), normalized whole brain volume (nWBV), and Atlas Scaling Factor (ASF). Methods: In this study, we attempted to establish the role of longitudinal MRI in an exploratory data analysis (EDA) of AD patients. EDA was performed on the dataset of 150 patients for 343 MRI sessions (mean age 77.01 [SD 7.64] years). The T1-weighted MRI of each subject on a 1.5-Tesla Vision (Siemens) scanner was used for image acquisition. Scores of three features, MMSE, CDR, and ASF, were used to characterize the AD patients included in this study. We assessed the role of various features (ie, age, gender, education, socioeconomic status, MMSE, CDR, eTIV, nWBV, and ASF) on the prognosis of AD. Results: The analysis further establishes the role of gender in the prevalence and development of AD in older people. Moreover, a considerable relationship has been observed between education and socioeconomic position on the progression of AD. Also, outliers and linearity of each feature were determined to rule out the extreme values in measuring the skewness. The differences in nWBV between CDR=0 (nondemented), CDR=0.5 (very mild dementia), and CDR=1 (mild dementia) are significant (ie, P<.01). Conclusions: A substantial correlation has been observed between the pattern and other related features of longitudinal MRI data that can significantly assist in the diagnosis and determination of AD in older patients.

12 citations


Journal ArticleDOI
TL;DR: A literature survey about the intensification of IoT technologies for smart monitoring of sleep quality and OSA diagnosis and a new comprehensive IoIT optimization framework is presented which employing AI for optimizing the performance of intelligent diagnosis of OSA.
Abstract: Obstructive Sleep Apnea (OSA) syndrome is one of the most widespread diseases that difficult to be detected and remedied. In particular, the examination of OSA by using the traditional Polysomnography (PSG) is one of formidable complexity as it requires full observation in a laboratory overnight. Meanwhile, the number of available laboratories and beds is minimal comparing to the number of OSA patients. What's more, the unusual environment and restricted mobility of patients may result in deficient diagnosis results. The Internet of Things (IoT) is the most appropriate solution for the previous diagnosis obstacles by allowing doctors to synchronize patient status. Besides, several studies have been introduced to consolidate the performance of IoT interoperability via the fusion with Artificial Intelligence (AI) resulting in the Internet of Intelligent Things (IoIT). This paper presents a literature survey about the intensification of IoT technologies for smart monitoring of sleep quality and OSA diagnosis. Mainly, the most recent enabling IoT and support technologies such as (smart devices, fog computing, cloud, big data, and machine learning) are covered via the discussion of more recent works of literature published from 2016 to 2019. Also, the roles of AI in optimizing the efficiency of OSA smart diagnosis are presented. Besides, a new comprehensive IoIT optimization framework is presented which employing AI for optimizing the performance of intelligent diagnosis of OSA. Finally, the open issues and challenges in this field are argued. This paper is, therefore, a major contributor to the compilation of all IoT innovative and efficient AI methods that improving the quality of OSA diagnosis.

7 citations


Journal ArticleDOI
Billy Sulistyo1, Nico Surantha1, Sani M. Isa1Institutions (1)
TL;DR: A classification model to identify sleep disorders from the Heart Rate Variability (HRV) features that can be obtained with Electrocardiogram (ECG) signals is built and time domain features shows the most dominant performance among the HRV features.
Abstract: Sleep apnea is a common sleep disorder that interferes with the breathing of a person. During sleep, people can stop breathing for a moment that causes the body lack of oxygen that lasts for several seconds to minutes even until the range of hours. If it happens for a long period, it can result in more serious diseases, e.g. high blood pressure, heart failure, stroke, diabetes, etc. Sleep apnea can be prevented by identifying the indication of sleep apnea itself from ECG, EEG, or other signals to perform early prevention. The purpose of this study is to build a classification model to identify sleep disorders from the Heart Rate Variability (HRV) features that can be obtained with Electrocardiogram (ECG) signals. In this study, HRV features were processed using several classification methods, i.e. ANN, KNN, N-Bayes and SVM linear Methods. The classification is performed using subject-specific scheme and subject-independent scheme. The simulation results show that the SVM method achieves higher accuracy other than three other methods in identifying sleep apnea. While, time domain features shows the most dominant performance among the HRV features.

6 citations


Cites background from "Internet of things for sleep qualit..."

  • ...When a person does not experience normal REM and non-REM cycles, the body will experience various adverse effects such as fatigue, decreasing ability to concentrate, disrupted body metabolism, and so on [2] ....

    [...]


Proceedings ArticleDOI
01 Nov 2017
Abstract: Sleep quality is one of the most important factors for human physical and mental health Sleep disorder may increase the risk of developing chronic physical and mental illnesses such as heart failure, coronary heart disease, depression, and bipolar disorder In addition, sleep disorder also decreases work productivity and increases the risk of traffic accidents The problem of sleep disorder is usually associated with the irregularity in sleep cycles People need to get the right proportion of every stages and sufficient number of cycles to obtain a quality sleep The aim of this study is to examine distinctive features related to sleep stages (wake, light sleep, deep sleep) from heart rate variability (HRV), and evaluate their usefulness to classify sleep stages We utilize support vector machine (SVM) to classify the sleep stages classification and compare the result with conventional methods We also utilize particle swarm optimization (PSO) for feature selection The simulation results show that our proposed sleep classification with SVM and PSO can improve the accuracy of sleep stage classification

4 citations


Additional excerpts

  • ...The improvement of sensor technology and mobile wireless has developed new method to asses sleep structure, e.g. actigraphy and ballistocardiography (BCG)[3]....

    [...]

  • ...actigraphy and ballistocardiography (BCG)[3]....

    [...]

  • ...In order to maximize the emergence of BCG sensor, therefore many research of sleep stage identification using electrocardiogram (ECG) signal have been conducted [4]-[6]....

    [...]

  • ...BCG is an unobtrusive method for measuring heart rate, heart rate variability, respiration rate, and relative blood stroke volume based on the body movement induced by heart pumping mechanism....

    [...]


Journal ArticleDOI
26 Aug 2020
TL;DR: Current research in sleep monitoring is reviewed to serve as a reference for researchers and to provide insights for future work, finding that hotspot techniques such as big data, machine learning, artificial intelligence, and data mining have not been widely applied to the sleep monitoring research area.
Abstract: Background: Sleep is essential for human health. Considerable effort has been put into academic and industrial research and in the development of wireless body area networks for sleep monitoring in terms of nonintrusiveness, portability, and autonomy. With the help of rapid advances in smart sensing and communication technologies, various sleep monitoring systems (hereafter, sleep monitoring systems) have been developed with advantages such as being low cost, accessible, discreet, contactless, unmanned, and suitable for long-term monitoring. Objective: This paper aims to review current research in sleep monitoring to serve as a reference for researchers and to provide insights for future work. Specific selection criteria were chosen to include articles in which sleep monitoring systems or devices are covered. Methods: This review investigates the use of various common sensors in the hardware implementation of current sleep monitoring systems as well as the types of parameters collected, their position in the body, the possible description of sleep phases, and the advantages and drawbacks. In addition, the data processing algorithms and software used in different studies on sleep monitoring systems and their results are presented. This review was not only limited to the study of laboratory research but also investigated the various popular commercial products available for sleep monitoring, presenting their characteristics, advantages, and disadvantages. In particular, we categorized existing research on sleep monitoring systems based on how the sensor is used, including the number and type of sensors, and the preferred position in the body. In addition to focusing on a specific system, issues concerning sleep monitoring systems such as privacy, economic, and social impact are also included. Finally, we presented an original sleep monitoring system solution developed in our laboratory. Results: By retrieving a large number of articles and abstracts, we found that hotspot techniques such as big data, machine learning, artificial intelligence, and data mining have not been widely applied to the sleep monitoring research area. Accelerometers are the most commonly used sensor in sleep monitoring systems. Most commercial sleep monitoring products cannot provide performance evaluation based on gold standard polysomnography. Conclusions: Combining hotspot techniques such as big data, machine learning, artificial intelligence, and data mining with sleep monitoring may be a promising research approach and will attract more researchers in the future. Balancing user acceptance and monitoring performance is the biggest challenge in sleep monitoring system research.

4 citations


Cites background from "Internet of things for sleep qualit..."

  • ...Surantha et al [56] argued that sleep quality monitoring is one of the solutions to maintaining sleep quality and preventing chronic diseases, mental problems, or accidents caused by sleep disorders....

    [...]


References
More filters

Journal ArticleDOI
Abstract: Ubiquitous sensing enabled by Wireless Sensor Network (WSN) technologies cuts across many areas of modern day living. This offers the ability to measure, infer and understand environmental indicators, from delicate ecologies and natural resources to urban environments. The proliferation of these devices in a communicating-actuating network creates the Internet of Things (IoT), wherein sensors and actuators blend seamlessly with the environment around us, and the information is shared across platforms in order to develop a common operating picture (COP). Fueled by the recent adaptation of a variety of enabling wireless technologies such as RFID tags and embedded sensor and actuator nodes, the IoT has stepped out of its infancy and is the next revolutionary technology in transforming the Internet into a fully integrated Future Internet. As we move from www (static pages web) to web2 (social networking web) to web3 (ubiquitous computing web), the need for data-on-demand using sophisticated intuitive queries increases significantly. This paper presents a Cloud centric vision for worldwide implementation of Internet of Things. The key enabling technologies and application domains that are likely to drive IoT research in the near future are discussed. A Cloud implementation using Aneka, which is based on interaction of private and public Clouds is presented. We conclude our IoT vision by expanding on the need for convergence of WSN, the Internet and distributed computing directed at technological research community.

8,564 citations



Journal ArticleDOI
01 Apr 2005-Sleep
TL;DR: These practice parameters are an update of the previously-published recommendations regarding the indications for polysomnography and related procedures in the diagnosis of sleep disorders.
Abstract: These practice parameters are an update of the previously-published recommendations regarding the indications for polysomnography and related procedures in the diagnosis of sleep disorders. Diagnostic categories include the following: sleep related breathing disorders, other respiratory disorders, narcolepsy, parasomnias, sleep related seizure disorders, restless legs syndrome, periodic limb movement sleep disorder, depression with insomnia, and circadian rhythm sleep disorders. Polysomnography is routinely indicated for the diagnosis of sleep related breathing disorders; for continuous positive airway pressure (CPAP) titration in patients with sleep related breathing disorders; for the assessment of treatment results in some cases; with a multiple sleep latency test in the evaluation of suspected narcolepsy; in evaluating sleep related behaviors that are violent or otherwise potentially injurious to the patient or others; and in certain atypical or unusual parasomnias. Polysomnography may be indicated in patients with neuromuscular disorders and sleep related symptoms; to assist in the diagnosis of paroxysmal arousals or other sleep disruptions thought to be seizure related; in a presumed parasomnia or sleep related seizure disorder that does not respond to conventional therapy; or when there is a strong clinical suspicion of periodic limb movement sleep disorder. Polysomnography is not routinely indicated to diagnose chronic lung disease; in cases of typical, uncomplicated, and noninjurious parasomnias when the diagnosis is clearly delineated; for patients with seizures who have no specific complaints consistent with a sleep disorder; to diagnose or treat restless legs syndrome; for the diagnosis of circadian rhythm sleep disorders; or to establish a diagnosis of depression.

1,747 citations


"Internet of things for sleep qualit..." refers background in this paper

  • ...• Polysomnography is a comprehensive recording of physiological changes that occur during sleep, which includes brain activity, heart ryhtm, eye-movement, and skeletal muscle activation [20]....

    [...]

  • ...Polysomnograph appears as the most comprehensive sensing method with extensive capability and high accuracy [20]....

    [...]


Journal ArticleDOI
TL;DR: A framework for the realization of smart cities through the Internet of Things (IoT), which encompasses the complete urban information system, from the sensory level and networking support structure through to data management and Cloud-based integration of respective systems and services, and forms a transformational part of the existing cyber-physical system.
Abstract: Increasing population density in urban centers demands adequate provision of services and infrastructure to meet the needs of city inhabitants, encompassing residents, workers, and visitors. The utilization of information and communications technologies to achieve this objective presents an opportunity for the development of smart cities, where city management and citizens are given access to a wealth of real-time information about the urban environment upon which to base decisions, actions, and future planning. This paper presents a framework for the realization of smart cities through the Internet of Things (IoT). The framework encompasses the complete urban information system, from the sensory level and networking support structure through to data management and Cloud-based integration of respective systems and services, and forms a transformational part of the existing cyber-physical system. This IoT vision for a smart city is applied to a noise mapping case study to illustrate a new method for existing operations that can be adapted for the enhancement and delivery of important city services.

979 citations


"Internet of things for sleep qualit..." refers background in this paper

  • ...industrial automation [7]-[8], smart-city [9], smart-farming [10], many more applications....

    [...]


Journal ArticleDOI
01 Jun 1995-Sleep
TL;DR: The data suggest that actigraphy, despite its limitations, may be a useful, cost-effective method for assessing specific sleep disorders, such as insomnia and schedule disorders, and for monitoring their treatment process.
Abstract: This paper, which has been reviewed and approved by the Board of Directors of the American Sleep Disorders Association, provides the background for the Standards of Practice Committee's parameters for the practice of sleep medicine in North America The growing use of activity-based monitoring (actigraphy) in sleep medicine and sleep research has enriched and challenged traditional sleep-monitoring techniques This review summarizes the empirical data on the validity of actigraphy in assessing sleep-wake patterns and assessing clinical and control groups ranging in age from infancy to elderly An overview of sleep-related actigraphic studies is also included Actigraphy provides useful measures of sleep-wake schedule and sleep quality The data also suggest that actigraphy, despite its limitations, may be a useful, cost-effective method for assessing specific sleep disorders, such as insomnia and schedule disorders, and for monitoring their treatment process Methodological issues such as the proper use of actigraphy and possible artifacts have not been systematically addressed in clinical research and practice

878 citations


"Internet of things for sleep qualit..." refers methods in this paper

  • ...• Actigraphy is a non-obtrusive method to record sleepwake schedule and measure sleep quality from body movement data [25]....

    [...]


Network Information
Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
20215
20207
20192
20182
20171