Internet of Things Smart Healthcare:Technologies, Challenges and Opportunities

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 28

INTERNET OF THINGS SMART

HEALTHCARE:TECHNOLOGIES,CHALLENGES
AND OPPORTUNITIES

SEMINAR REPORT

Submitted in partial fulfillment of the requirements for the award of


B.Tech Degree in Electronics and Communication Engineering of the
A P J Abdul Kalam Technological University

Submitted by
ABHINSYAM M K

Register No. : TVE15EC001

DEPARTMENT OF ELECTRONICS & COMMUNICATION


ENGINEERING

COLLEGE OF ENGINEERING TRIVANDRUM – 695016

2018-2019
Semiar Report

DEPARTMENT OF ELECTRONICS & COMMUNICATION


ENGINEERING
COLLEGE OF ENGINEERING TRIVANDRUM - 695016

CERTIFICATE

This is to certify that this seminar report entitled as “ Internet of


Things for Smart Healthcare:Technologies,Challenges and
Opportunities " is a bonafide record of the work done by
Abhinsyam M K , under our guidance towards partial fulfillment of
the requirements for the award of the degree of Bachelor of
Technology in Electronics and Communication Engineering of the
A P J Abdul Kalam Technological University during the year 2015 -
2019.

Prof. Chandini G S Dr. Ciza Thomas


AssociativeProfessor Professor
Dept. of ECE Dept. of ECE
(Head of the Dept.)

2
Semiar Report

DECLARATION

I undersigned hereby declare that the seminar report Internet of Things Smart
Healthcare:Technologies,Challenges and Opportunities , submitted for partial
fulfillment of the requirements for the award of degree of Bachelor of
Technology of the APJ Abdul Kalam Technological University, Kerala is a
bonafide work done by me . This submission represents my ideas in my own
words and where ideas or words of others have been included, I have
adequately and accurately cited and referenced the original sources. I also
declare that I have adhered to ethics of academic honesty and integrity and
have not misrepresented or fabricated any data or idea or fact or source in my
submission. I understand that any violation of the above will be a cause for
disciplinary action by the institute and/or the University and can also evoke
penal action from the sources which have thus not been properly cited or from
whom proper permission has not been obtained. This report has not been
previously formed the basis for the award of any degree, diploma or similar
title of any other University

Place : Trivandrum Abhinsyam M K


Date : 28 November 2018

ii

3
Semiar Report

ABSTRACT

In recent years Internet of Things(IoT) has attracted very much


attention.Due to aging population and chronic illness demand for Internet of
Things in the field of Healthcare rise.Standardisation of healthcare is a
important issue limiting progress in this area.For future IoT healthcare this
paper proposes a standard model and also evaluates strength,weakness and
suitability for wearable IoT healthcare system.Focus of this paper is placed on
sensors for monitoring health parameters,short range and long range
communication standards and cloud technologies.Also this survey paper
presents challenges that IoT healthcare faces including security, privacy
wearability and low power operations are presented.

iii

4
Semiar Report

ACKNOWLEDGEMENT

I take this opportunity to express my deepest gratitude to those who


have held out their hands in various forms, in successful completion
of my report. First of all, I thank God almighty for his blessings and
helping me to withstand all difficulties faced during seminar
presentation.
I’m grateful to Dr. Ciza Thomas, Professor and Head of the
Department of Electronics and Communication, Prof Ajayan K R and
Prof Chandini G S, associative professors Department of Electronics
and Communication for providing necessary facilities and giving an
opportunity to carry out this seminar..
I would also like to express my heartfelt thanks to all my
classmates for their help and encouragement towards completion of
my seminar report. I’m forever beholden to my parents for their
unfathomable love, personal affection and constant prayers, which
supported me to stay at rough tasks.

Abhinsyam M K

iv

5
Semiar Report

CONTENTS
Certificate . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .i
Declaration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
Acknowledgement. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .iv

1.Introduction 7

2.Healthcare and Internet of Things 8

2.1 The Internet of Things…………………………………………………………….. 8


2.2 Internet of Things Healthcare…………………………………………………. 8
2.3 A Model for Future Internet of Things Healthcare Systems……… 9
2.3.1 Wearable Sensors & Central Nodes……………………………… 11
2.3.2 Short Range Communications………………………………………. 11
2.3.3 Long Range Communications……………………………………….. 11
2.3.4 Secure Cloud Storage Architecture & M L …………………….. 11

3.Wearable Healthcare Systems 12

3.1 Pulse Sensors………………………………………………………………………….. 12


3.2 Respiratory Rate Sensors………………………………………………………… 12
3.3 Body Temperature Sensors…………………………………………………….. 13
3.4 Blood pressure………………………………………………………………………… 13
3.5 Pulse Oximetry Sensors…………………………………………………………… 13

4.Communication Standards 14

4.1 Short Range Communications………………………………………………… 15

4.1.1 Bluetooth Low Energy………………………………………………….. 15


4.1.2 ZigBee………………………………………………………………………….. 16

4.2 Long Range Communications………………………………………………….. 17

4.2.1 Sigfox…………………………………………………………………………… 18
4.2.2 LoRa & LoRaWAN ……………………………………………………….. 19
4.2.3 NB-IoT ………………………………………………………………………… 20

6
Semiar Report

5.Cloud Based IoT Healthcare Systems 21

5.1 Cloud for Healthcare……………………………………………………………. 21

5.1.1 Big Data Management………………………………………………. 21

5.1.2 Data Processing and Analytics………………………………….. 23

5.2 Security and Privacy in the Cloud………………………………………… 24

6.Conclusion 26

7.References 27

7
Semiar Report

1.Introduction

Healthcare is an important part of our daily life.The steadily aging population


and the related rise in chronic illness is placing significant strain on modern
healthcare systems.This results in increase in demand for resources from
hospital beds to doctors and nurses in the field of healthcare.Here comes the
need of IoT Smart Healthcare.As a solution for reducing strain on healthcare
system while providing high quality care to risk patients.
Aiding rehabilitation through constant monitoring of patients
progress,monitoring patients with parkinsons disease,diabetes these all comes
under application of IoT in the field of Smart Healthcare.Also in this paper
Wearable sensor types for monitoring patients conditions are discussed with
some focus on communication. This paper therefore makes a unique
contribution in that it identifies all key components of an end-to-end Internet
of Things healthcare system, and proposes a generic model that could be
applied to all IoT-based healthcare systems.
Focus is placed on sensors for monitoring various health
parameters, short- and long-range communications standards, and cloud
technologies. The remainder of this paper is structured as follows. Section II
investigates the field of Internet of Things, placing focus on the provision of
healthcare using IoT technologies. Section III examines common sensors that
could be used in an IoT healthcare systems, presenting several state-of-the-art
sensors that have been developed in recent research. Section IV reviews
communications standards for both short- and long-term communications,
including a thorough analysis of the new NB-IoT standard for long-range
machine-to-machine (M2M) communications. Section V discusses cloud
technologies and the ways in which they can be used in IoT healthcare systems

8
Semiar Report

SECTION II

2.Healthcare and the Internet of Things

Remote health monitoring could be used to monitor non-critical patients


at home rather than in hospital reducing strain on hospital resources such
as doctors and beds.
2.1)The Internet of Things

The most fundamental level it can be described as a network of


devices interacting with each other via machine to machine (M2M)
communications, enabling collection and exchange of data. Existing systems
in other fields have proven that remote monitoring of objects, with data
collection and reporting, are achievable. This can therefore be expanded
and adapted for monitoring the health of people and reporting it to
relevant parties such as caretakers, doctors, emergency services, and
healthcare centers. This technology enables automation within a large
range of industries, as well as allowing for the collection of big data.

2.2 )Internet of Things Healthcare

Remote health monitoring could be used to monitor non-critical patients at


home rather than in hospital, reducing strain on hospital resources such as
doctors and beds. It could be used to provide better access to healthcare for
those living in rural areas, or to enable elderly people to live independently at
home for longer. Essentially, it can improve access to healthcare resources whilst
reducing strain on healthcare systems, and can give people better control over
their own health at all times. In fact, there are relatively few disadvantages of
remote health monitoring. The most significant disadvantages include the security
risk that comes with having large amounts of sensitive data stored in a single
database, the potential need to regularly have an individual’s sensors recalibrated
to ensure that they’re monitoring accurately, and possible disconnections from
healthcare services if the patient was out of cellular range or their devices ran out
of battery.
In several works, IoT healthcare systems have been developed for specific
purposes, including rehabilitation, diabetes management, assisted ambient living
(AAL) for elderly persons. The aim of this project it to allow older and chronically
9
Semiar Report

ill patients to live in the comfort of their own homes, while their health continues
to be monitored. This allows for intervention by caretakers and doctors if any
issues arise.

2.3) A Model for Future Internet of Things Healthcare Systems

After reviewing this wide range of existing IoT-based healthcare system,


several requirements for the design of such systems become apparent. Each of
these papers emphasize the use of sensors for monitoring patient health. It would
be preferable to implement all essential sensors as small, portable, and externally
wearable nodes. This would provide patients with a non-intrusive and
comfortable solution that is capable of monitoring their health wherever they go.
This would make patients more receptive to using health monitoring technology
than they would be if implantable sensors or cameras were required. Additionally,
repairing or replacing externally wearable nodes would be simple when compared
to implanted sensors or vision-based sensors installed in the home.

short-range communications, such as Bluetooth, are suggested for


transferring sensor data to a smartphone to be processed.

10
Semiar Report

Long-range communications such as LTE can then be used to transfer the


processed information from the patient to the healthcare provider
typically a doctor, through SMS or the Internet.

2.3.1) Wearable Sensor & Central Nodes

Wearable sensor nodes are those that measure physiological conditions.


sensors are those that measure the vital signs - pulse, respiratory rate,
and body temperature The central node receives data from the sensor
nodes.
It processes this information, may implement some decision making, and
then forwards the information to an external location. A dedicated
central node would be preferred to a smartphone

2.3.2) Short-Range Communications

For sensors to communicate with the central node


several important requirements -effects on the human body, security,
and latency.The chosen method should have no negative effects on the
human body. It should also provide strong security mechanisms to
ensure that sensitive patient data cannot be accessed by an attacker.
Finally, low-latency is essential for time-critical systems, such as a system
that monitors critical health and calls for an ambulance if the need
arises.

2.3.3) Long-Range Communications

Data obtained by the central node is not useful unless something


can be done with it. This data should be forwarded to a database where
relevant parties security, error correcting capabilities, robustness against
interference, low-latency, and high availability.

2.3.4) Secure Cloud Storage Architecture & Machine Learning

Medical information obtained from patients must be stored securely


for continued use. Doctors benefit from knowing a patient’s medical
history, and machine learning is not effective unless large databases of
information are available to it.

11
Semiar Report

SECTION III

3.Wearable Healthcare Systems

WBANs have been identified as a key component of a healthcare system


founded on Internet of Things technology. This article focus on sensors that are
non-obtrusive and non-invasive; we exclude sensors such as implantables.
Considered are five fundamental sensors - three for monitoring the vital signs
of pulse, respiratory rate, and body temperature, and a further two for
monitoring blood pressure and blood oxygen, both commonly recorded in a
hospital environment

3.1) Pulse Sensors

pulse can be used to detect a wide range of emergency conditions, such


as cardiac arrest, pulmonary embolisms, and vasovagal syncope
Pulse can be read from the chest, wrist, earlobe, fingertip, and more.

FitBit PurePulse

12
Semiar Report

HRM-Tri by Garmin

photoplethysmographic (PPG), ultrasonic, and radio frequency (RF)


sensors.
PPG sensors operate by an LED transmitting light into the artery

Changes in the amount of light can be recorded and a pulse rate can thus be
determined.

3.1)Respiratory Rate Sensors

The number of breaths a patient takes per minute aid in -dentification of


asthma attacks, hyperventilation, apnea episodes, lung cancer, obstructions of

13
Semiar Report

the airway, tuberculosis….Echocardiogram (ECG) signals can also be used to


obtain respiration rate This is called ECG Derived Respiration (EDR)
Also a microphone to detect respiration(susceptible to noise) Fiber optic
sensor in an elastic substrate, that was sensitive enough to measure vibrations
caused by respiration .A pressure-type sensor (capacitive plates ) A common
method-use a stretch sensor(ferroelectric polymer transducer) .

3.2) Body Temperature Sensors

used to detect hypothermia, heat stroke, fevers….Thermistor-type sensors


negative-temperature-coefficient (NTC) type temperature sensors were used
The accuracy of temperature sensing is limited by how closely the sensor can
be placed to the human body

3.3) Blood Pressure

Hypertension (high BP) is a known risk factor for cardiovascular disease,


including heart attack An accurate estimate of BP through calculation of pulse
transit time (PTT).

3.4) Pulse Oximetry Sensors

Pulse oximeter sensors measures the level of oxygen in the blood


conditions such as hypoxia (low oxygen reaching the body’s tissues).
Usually, two LEDs - one red, one infrared - are directed through the skin
Much of this light is absorbed by the hemoglobin in the blood .The amount of
light not absorbed is measured by receiving photodiodes

absorbance-mode and reflectance-mode PPG sensors

SECTION IV

14
Semiar Report

4.Communications Standards

Communications related to Internet of Things for healthcare can be classified


into two main categories: short-range communications, and long-range
communications. The former is used to communicate between devices within
the WBAN, whilst the latter provides connection between the central node of
the WBAN and a base station (such as a healthcare provider). In this paper,
both types of communications are considered with equal importance.

4.1) Short-Range Communications

In the context of wearable healthcare systems, short-range


communications are often used between nodes, particularly between
sensor nodes and the central node where data processing occurs.
Although short-range communications standards can be used for other
purposes.
Many short-range communications standards exist, but perhaps the
most commonly used ones in IoT are Bluetooth Low Energy (BLE) and
ZigBee

Comparison of Short-Range Communication Standards

4.1.1) Bluetooth Low Energy

BLE was developed by the Bluetooth Special Interest Group (SIG) to provide an
energy-efficient standard that could be used by coin-cell battery operated
devices, including wearables. It also aimed to enable IoT, connecting small
peripheral devices to processing devices such as smartphones.

15
Semiar Report

BLE is used in a star topology, which is suitable for healthcare applications. The
central node would act as the center of the star topology, with sensors linked
to it. The sensors will have no need to communicate with each other directly,
The range for BLE is 150m in an open field. The range is clearly sufficient for
use in a healthcare WBAN where nodes are physically proximal, and the
extremely low latency is ideal for applications such as emergency health.
Power consumption in BLE is extremely low. In [77], it is shown that a 180 mAH
coin cell battery could run a BLE chip for 18 continuous hours, making 21.6
million transactions. However, if the chip was powered off when not needed,
battery would last much longer. If a health sensor transmitted its data every 30
seconds (or 2,880 times per day), then the battery could theoretically run the
BLE chip for around 20.5 years if not for the fact that it would die from self-
depletion well before then. With careful hardware design and low-energy
programming, BLE would clearly be suitable for healthcare applications

4.1.2) ZigBee

The ZigBee standard was designed by the ZigBee Alliance, specifically for
providing low-cost, low-power networks for M2M communications. It builds on
the IEEE 802.15.4 physical standard.
It is commonly known as the standard for mesh networks, but it can also be
used in the star topology required of a WBAN with one central node and many
sensing nodes.
Different ZigBee modules provide different characteristics in terms of
range, data rate, and power consumption. The simplest XBee has a range of up
to 30m in an urban environment, and outputs only 1mW of power for
transmission,
ZigBee can operate at a range of frequencies, including 868MHz, 900MHz, and
2.4GHz bands, depending on the module chosen. Each of these bands faces
interference. The 2.4GHz band is shared by Bluetooth and WiFi, while many
long-range communications systems utilize the unlicensed 868MHz and
900MHz bands in Europe and America respectively. ZigBee uses CSMA-CA to
reduce collisions, and implements re-transmission if messages sent are not
acknowledged.
Several security features are provided by ZigBee, though most are
optional and must be enabled by the network developer. ZigBee’s security
model is largely based on 128-AES encryption, and offers types of security keys
- a link key, a network key, and a master key. The network key is mandatory. It
is shared by all devices on the network, and is a network-layer security
mechanism that cyphers all transmissions within the network. The link key is
optional, and is used to secure communications at the application layer.
Master keys are also optional, and are used to secure the creation and sharing
of link keys.
16
Semiar Report

Overall, ZigBee is reasonably well-suited to healthcare applications. It provides


robustness to interference and several security mechanisms.
The main drawback of using ZigBee is that key exchange can be
compromised unless implemented extremely well by the manufacturer. This
could pose a risk to healthcare systems where sensitive patient data is being
exchanged regularly. Additionally, ZigBee is not commonly implemented in
devices such as smartphones, while BLE typically is. This makes it less
compatible with existing devices, and therefore it is suggested that it would be
better suited to fixed-location, standalone purposes such as home automation
than it is to wearable healthcare systems.

4.2) Long-Range Communications

Low-Power Wide-Area Networks (LPWANs) are a subset of long-range


communications standards with high suitability for IoT applications. The range
of a LPWAN is generally several kilometers, even in an urban environment. This
is significantly longer than the range of traditional IoT communications types
such as WiFi or Bluetooth, whose ranges are in the order of meters and thus
would require extensive and costly mesh networking or similar to be plausible
for healthcare.
This is suitable for a large number of healthcare applications, including
monitoring general health and receiving hourly updates, monitoring critical
health and receiving emergency calls, and rehabilitation where updates may
only be necessary once daily. This design principle also allows for low-power
device design, which in turn ensures that the designed healthcare devices will
operate for longer before human interaction is required to recharge or change
batteries. This reduces the risk of patients being offline, and provides more
convenience to the wearer.
Based on these advantages, it is suggested that LPWANs are the best
solution for transmitting data from the central node to the cloud for storage or
further processing.

The most prominent standards for LPWANs are Sigfox and LoRaWAN. While
these standards are well-established, they face competition from emerging
standards including NB-IoT.

17
Semiar Report

4.2.1) Sigfox

Sigfox uses a star topology, and nodes are designed to be uplink only to
improve battery efficiency. It is possible for a node to receive downlink, but it
must explicitly request it. As acknowledgement of receipt is important for
health data, downlink would have to be requested. Unfortunately, a limitation
of Sigfox is that downlink can only be requested 4 times per day.
In rural areas, Sigfox can reach a range of up to 50km . The high latency of
Sigfox is a drawback for its use in healthcare applications, as it is important for
messages to be delivered quickly in this critical context.
Sigfox operates in the unlicensed bands of 868MHz in Europe and 915MHz in
the US. As with other LPWAN technologies operating in the sub-GHz spectrum,
no globally available band exists for Sigfox’s use. Operating in an unlicensed
band allows Sigfox to occupy a wider bandwidth, but comes with the
disadvantage of increased interference, which may be an issue in healthcare.
To increase resistance to interference, Sigfox sends payloads in three
consecutive frames, each in different pseudo-random sub-carriers and over
different propagation paths. This improves the likelihood that the message will
be received intact, and thus reduces the disadvantages of increased
interference in the unlicensed bands.
Sigfox has a high network capacity and can support approximately 50,000
nodes with a single gateway.
Security is implemented in Sigfox by signing each message with the
device’s private key . This reduces the risk of spoofing attacks or interception,
but does not eliminate it. A sophisticated attack targeting the node hardware
18
Semiar Report

or service provider could still reveal the unique keys, compromising a patient’s
healthcare system.
However, in healthcare, successfully transmitting messages with relative speed
is essential. Any compromise of security could be detrimental for an
individual’s health, or could affect the integrity of medical databases. For this
reason, we recommend that Sigfox not be used for critical healthcare
applications. It is therefore strongly recommended that system designers
instead consider alternative LPWANs for critical healthcare applications.

4.2.2) LoRa & LoRaWAN

LoRa is a physical layer protocol that utilizes chirp spread spectrum techniques
over a wide bandwidth of at least 125kHz. This provides low-power, long-range
communications with high resilience to intentional or environmental
interference.

LoRaWAN is built on top of the LoRa standard, in the network layer. It utilizes a
star topology, and nodes are asynchronous; they only communicate when they
need to, such as after an event or scheduled measurement. Scheduled
messages from nodes would suit long-term monitoring applications, while
event-driven messages from nodes would suit emergency monitoring.

LoRaWAN also has a high network capacity, ensuring many messages can be
passed over the network at the same time. Each gateway can support
approximately 40,000 nodes .

Like Sigfox, LoRaWAN operates in the unlicensed bands of 868MHz in Europe


and 915MHz in the US. This carries the advantage of wider spectrum
availability, but also the disadvantage of increased exposure to potential
interference.

Security is provided by the LoRaWAN standard. A unique key is assigned to


each node on the network; this key is known only to the node and to the
network provider. Theoretically, this would eliminate man-in-the-middle
attacks as intercepted data would be encoded and not decipherable .
19
Semiar Report

Unfortunately, a node’s unique key could become a single point of failure for
the whole system should the key be discovered through sophisticated
hardware hacking of the node, or through an attack on the network server. If a
key was illicitly obtained, then the attacker could use it to decipher all future
messages from the node, or could send false messages to the base station
whilst pretending to be the node.

To be truly secure, proper key management must be implemented by the


developers and service providers so that sensitive healthcare data and
important medical databases are protected from malicious attacks, as
LoRaWAN does not provide a complete security.

4.2.3) NB-IoT

Standardized in the recent 3GPP Release 13, NB-IoT operates in the licensed
bands of GSM or LTE and provides long-range, low-power communications. As
NB-IoT has been developed based on LTE, much of the existing LTE hardware
can be used to deploy it rapidly and effectively NB-IoT utilizes the bandwidth of
an existing LTE carrier’s guard-band. Finally, in stand-alone mode, GSM carriers
can be re-farmed and used for NB-IoT, or NB-IoT can exist in entirely new
bandwidth.
Operating within licensed bands has the significant advantage of reduced risk
of interference. One potential disadvantage is that there will likely be a higher
cost to use NB-IoT than there is for unlicensed standards. Just as mobile phone
users pay a fee to be able to use LTE, NB-IoT device users will likely have to pay
a connection fee for the use of NB-IoT. The exact magnitude of these costs is
not yet known as NB-IoT is yet to be widely deployed. Nonetheless, a decrease
in interference is likely to be worth the additional cost when considering
healthcare systems, as QoS in these applications is critical.

Battery life was a fundamental consideration in the design of NB-IoT. The


power efficiency has some dependence on which mode NB-IoT operates in.
In it was found that the life of 5Wh batteries were 2.6 and 2.4 years in stand-
alone and in-band modes respectively when a 50 byte message was being sent
every 2 hours. When a 50-byte message was only sent once per day, the
battery lifetime increased to 18.0 and 16.8 years respectively.

NB-IoT can also support a minimum of 52,547 nodes per base station. Overall,
NB-IoT is suitable for healthcare applications. It is secure, supports
20
Semiar Report

communications over a long range, has high energy efficiency, and can support
many devices. The most significant drawback is the current lack of deployment,
though this is expected to occur rapidly due to the reusability of existing LTE
infrastructure. This lack of deployment limits the immediate usefulness of NB-
IoT, but the standard will likely be deployed rapidly on a large scale due to the
ability to reuse existing 3G hardware. When this happens, NB-IoT is highly
recommended for use, as it offers many favourable characteristics that make it
the most suitable standard for use in healthcare systems.

SECTION V

5.Cloud-Based IoT Healthcare Systems

Cloud technologies have been widely researched due to their usefulness in big
data management, processing and analytics. Several related works have
surveyed the literature on using cloud technologies for IoT purposes such as
smart grid and mobile cloud computing for smartphones , where complex
computations are offloaded from low-resource mobile devices to the high-
power environment of the cloud, before the result is returned to the mobile
device. These works consider data storage and data processing as key
advantages of cloud technologies.

5.1. Cloud for Healthcare

Much research has been conducted in recent years regarding the benefits of
cloud for healthcare applications. These benefits stem from the three primary
services that can be provided by cloud technologies in healthcare
environments:

 Software as a Service (SaaS) - provides applications to healthcare


providers that will enable them to work with health data or perform
other relevant tasks.

21
Semiar Report

 Platform as a Service (PaaS) - provides tools for virtualization,


networking, database management, and more.

 Infrastructure as a Service (IaaS) - provides the physical infrastructure for


storage, servers, and more.

5.1.1) Big Data Management

Big data is regularly characterized by the so-called 5 V’s - volume, velocity,


variety, veracity and value. Volume refers to the amount of data generated,
while velocity refers to the speed at which it is generated. Variety is the
general variance in data types, while veracity is the uncertainty surrounding
what data types may later be added. Finally, value refers to what information
can be gained from the big data set.

The challenge in big data management lies in designing a system that can
handle the characteristics of a specific big data set. In healthcare, each of the
characteristic 5 V’s are important to consider, as a wide variety of data from

patient name, age and gender to vital sign values as taken at regular intervals
would need to be stored for many systems.
Regularly measured data would create significant velocity, and lead to an
increased volume of total data rapidly. Additionally, new kinds of data may be
added regularly as new sensors are developed to measure previously
unmonitored health signs. Finally, machine learning to perform diagnostics or
provide treatment plans would be extremely valuable in a healthcare context,
so a cloud storage framework for healthcare would need to enable value.

Big data management is crucial in this system, as they aim to draw links
between emotional responses and physiological changes. Large amounts of
physiological data are stored in the cloud module, organized sufficiently to
enable data mining techniques for the extraction of important information. To
maximize storage space, algorithms have been applied to remove redundant or
non-useful data from the database.
The primary focus of cloud storage in this system is not to maintain a health
record, but rather to amass a big data set that machine learning could be
applied to. The authors have placed significant focus on managing all the
characteristic Vs of big data, but there are still some improvements that could
be made. While health data is stored, it appears that patients and doctors
cannot easily access a patient’s complete medical history.
22
Semiar Report

It allows for virtually unlimited storage space, the provision of many useful
services, and enables accessibility for patients and doctors. This gives patients
more control over their own healthcare, and simultaneously enables doctors to
provide more suitable treatments without having to even meet with their
patient in person. Additionally, big data management schemes that are
designed to meet all 5 characteristics of big data will enable data mining,
machine learning, and other forms of detailed analysis. This could lead to new
medical discoveries by identifying previously unknown trends in patient
progression through an illness, finding new links between symptoms and
conditions, determining new treatments that may be suitable for various
conditions, and much more. Big data management is essential for the IoT
healthcare system of the future.

5.1.2)Data Processing and Analytics

There are several types of data processing that can be performed using cloud
technologies, but the most relevant are computational offloading and machine
learning. Computational offloading involves using the cloud to perform
complex data processing beyond the capabilities of low-resource wearable
devices. By sending raw or partially processed sensor data to the cloud, the
computing resources of many machines can be utilized for processing. Using
this high-powered computing environment over processing on the standalone
mobile device offers many advantages; more complex algorithms can be
executed, results can be obtained significantly faster, and battery life will be
extended in mobile devices due to less processing occurring internally.

Complicated sensor nodes such as those measuring ECG data, blood pressure,
or accelerometers for fall detection would benefit greatly from computational
offloading. For example, ECGs have a standard shape, and different deviations
from this shape can indicate several different heart problems including
arrhythmia, heart inflammation, and even cardiac arrest. Machine learning can
also be applied to large datasets so as to obtain meaningful information from
them, including identifying previously unknown links between symptoms and
diseases, determining possible diagnoses based on those given to previous
patients, developing suitable treatment plans for individual patients based on
what has worked for similar patients in the past, and much more. Each of these
applications reduces human uncertainty and thus would help patients receive

23
Semiar Report

Several researchers have identified the usefulness of computational offloading


in healthcare environments. In readings from WBAN sensors are transmitted
to a mobile phone, where some basic processing occurs. The information is
then transmitted forward from smartphone to cloud, where advanced
processing occurs using feature selection and classification techniques. The
meaningful information generated can then be stored or forwarded to
healthcare practitioners. The primary weakness of this is that it is reliant on a
smartphone, which would run out of battery within days at best. It would be
preferable for raw data to be transmitted straight to the cloud for complete
processing, using a low-power communications standard such as the
previously discussed NB-IoT. Additionally, the information obtained through
processing is not analyzed further; instead, it is passed directly to a doctor who
manually observes the result. In many cases, it would be possible to implement
classification algorithms that alert the doctor when an abnormal reading is
detected in a patient’s physiological signs.

Data processing techniques may also aid in the organized storage of health
data, as it can generate meaningful information such as a standard ECG from
many different types of ECG sensors. This is extremely useful in standardizing
health records, and would enable machine learning techniques to be applied to
a big data set with more ease. Due to these benefits, computational offloading
is vital for IoT healthcare systems to ensure that even the most complicated
physiological parameters can be monitored, enabling the highest possible
standard of healthcare for the patient.

5.2) Security and Privacy in the Cloud

Security remains a key issue in cloud-based systems. In a healthcare


environment, it is essential that a patient’s health information is readily
accessible to authorized parties including doctors, nurses, specialists, and
emergency services. It is also essential that the patient’s sensitive health data
is kept private. If malicious attacks revealed the patient’s health data, it could
have many negative ramifications for the patient, including exposing them to
identity theft or making it difficult for them to obtain insurance.
Access control policies and data encryption are two means of securing cloud-
centric healthcare systems. An access control policy specifies who is authorized
access to the patient’s health data, and how much access they are allowed. It
would also implement an authentication mechanism (e.g. password, facial
recognition, etc.) that verifies the identity of the party attempting to access the
data. Meanwhile, data encryption provides security for the data whilst in data
24
Semiar Report

storage. Strong data encryption would prevent an attacker from reading


sensitive health information, even if they did gain access to the database.
Access control is policy-based, where access is given to authorized people. To
ensure that only authorized people can access health records, biometrics are
used to ensure that the person is who they claim to be. Users are asked to
provide a fingerprint, and facial recognition software calculates certain
distances and angles on the face. The user is also asked to blink a random
number of times, so that a photograph cannot be used to “trick” the system.

fully homomorphic encryption (FHE) is considered as a scheme for protecting


the security of the data. FHE allows for public-key encryption to be
implemented before being sent to the cloud. It also allows mathematic
functions to be performed over on the data whilst it is encrypted, enabling
basic machine learning without decrypting data in the cloud.

If data is requested by an authorized user, the key authority system can use a
secure channel to provide them with the secret key required to decrypt the
data. This is a promising approach to combining security with machine
learning, but it is not yet ready to be implemented into IoT-based healthcare
systems. In this work, it is shown that significant computational resources are
required for FHE to be successful. Additionally, only limited arithmetic can be
performed on the encrypted data. Whilst this work shows improvement on
previous FHE schemes, improving the speed and computational capabilities of
FHE schemes remains an active field of research.

We agree that this type of AES-to-FHE scheme is a reasonable means for


securing patient data. However, with the clear advantages of ABE for cloud
security in healthcare, we believe that it would be beneficial to use it for
acquisition and provision of health data. It is therefore suggested that an
optimized ABE-to-FHE conversion scheme that at no point decrypts and re-
encrypts the data would be extremely valuable for securing patient data.

Overall, there is still significant research opportunity in developing a


completely suitable encryption scheme for healthcare systems that rely on
both low-power wearables and big data cloud storage. Increasing speed,
decreasing computational requirements, and enabling high-level machine
learning are all areas for improvement that should be investigated further.

25
Semiar Report

SECTION VI

6.Conclusion
In this work, we have proposed a unique model for future IoT-based
healthcare systems, which can be applied to both general systems and systems
that monitor specific conditions. Several wearable, non-intrusive sensors were
presented and analyzed, with particular focus on those monitoring vital signs,
blood pressure, and blood oxygen levels. Short-range and long-range
communications standards were then compared in terms of suitability for
healthcare applications. BLE and NB-IoT emerged as the most suitable
standards for short-range and long-range communications in healthcare
respectively.

Recent works utilizing cloud technologies for data storage were presented, and
showed that cloud is the best means for storing and organizing big data in
healthcare. It is also shown by several works that significantly better data
processing can be performed in the cloud than can be performed by wearable
devices with their limited resources. The most significant drawback of using
cloud is that it introduces security risks, and as such we presented several
works focused on improving security in the cloud. It was found that access
control policies and encryption can significantly enhance security, but that no
known standard is suitable for immediate application into a wearable, IoT-
based healthcare system.
26
Semiar Report

Based on our analysis of state-of-the-art technologies in the fields of wearable


sensors, communications standards, and cloud technology, we identified
several significant areas for future research. Machine learning and the
development of a secure yet lightweight encryption scheme for cloud storage
were the two areas that provide the most opportunity for researchers seeking
to make significant improvements in the field of IoT-based healthcare.

7.References

1. E. Perrier, Positive Disruption: Healthcare Ageing and Participation


in the Age of Technology, Sydney, NSW, Australia:The McKell
Institute, 2015.
2. P. Gope, T. Hwang, "BSN-care: A secure IoT-based modern
healthcare system using body sensor network", IEEE Sensors J.,
vol. 16, pp. 1368-1376, Mar. 2016.
3. N. Zhu et al., "Bridging e-health and the Internet of Things: The
SPHERE project", IEEE Intell. Syst., vol. 30, no. 4, pp. 39-46,
Jul./Aug. 2015
4. S.-H. Chang, R.-D. Chiang, S.-J. Wu, W.-T. Chang, "A context-aware
interactive M-health system for diabetics", IT Prof., vol. 18, no. 3,
pp. 14-22, May/Jun. 2016
5. C. F. Pasluosta, H. Gassner, J. Winkler, J. Klucken, B. M. Eskofier,
"An emerging era in the management of Parkinson’s disease:
Wearable technologies and the Internet of Things", IEEE J. Biomed.
Health Inform., vol. 19, no. 6, pp. 1873-1881, Nov. 2015.
6. Y. J. Fan, Y. H. Yin, L. D. Xu, Y. Zeng, F. Wu, "IoT-based smart
rehabilitation system", IEEE Trans. Ind. Informat., vol. 10, no. 2,
pp. 1568-1577, May 2014.
7. S. Sarkar, S. Misra, "From micro to nano: The evolution of wireless
sensor-based health care", IEEE Pulse, vol. 7, no. 1, pp. 21-25,
Jan./Feb. 2016
27
Semiar Report

8. S. Milici, J. Lorenzo, A. Lázaro, R. Villarino, D. Girbau, "Wireless


breathing sensor based on wearable modulated frequency
selective surface", IEEE Sensors J., vol. 17, no. 5, pp. 1285-1292,
Mar. 2017.
9. J. Ženko, M. Kos, I. Kramberger, "Pulse rate variability and blood
oxidation content identification using miniature wearable wrist
device", Proc. Int. Conf. Syst. Signals Image Process. (IWSSIP), pp.
1-4, May 2016.
10. D. Wang, D. Zhang, G. Lu, "An optimal pulse system design
by multichannel sensors fusion", IEEE J. Biomed. Health Informat.,
vol. 20, no. 2, pp. 450-459, Mar. 2016.

28

You might also like