Texas A&M University-San Antonio Texas A&M University-San Antonio
Digital Commons @ Texas A&M University- San Antonio Digital Commons @ Texas A&M University- San Antonio
Computer Science Faculty Publications College of Business
2016
Mobile Cloud Computing Model and Big Data Analysis for Mobile Cloud Computing Model and Big Data Analysis for
Healthcare Applications Healthcare Applications
Lo'ai A. Tawalbeh
Texas A&M University-San Antonio
, ltawalbeh@tamusa.edu
R. Mehmood
E. Benkhlifa
H. Song
Follow this and additional works at: https://digitalcommons.tamusa.edu/computer_faculty
Part of the Computer Sciences Commons
Repository Citation Repository Citation
Tawalbeh, Lo'ai A.; Mehmood, R.; Benkhlifa, E.; and Song, H., "Mobile Cloud Computing Model and Big Data
Analysis for Healthcare Applications" (2016).
Computer Science Faculty Publications
. 19.
https://digitalcommons.tamusa.edu/computer_faculty/19
This Article is brought to you for free and open access by the College of Business at Digital Commons @ Texas
A&M University- San Antonio. It has been accepted for inclusion in Computer Science Faculty Publications by an
authorized administrator of Digital Commons @ Texas A&M University- San Antonio. For more information, please
contact
deirdre.mcdonald@tamusa.edu.
SPECIAL SECTION ON HEALTHCARE BIG DATA
Received August 16, 2016, accepted September 11, 2016, date of publication September 26, 2016,
date of current version October 15, 2016.
Digital Object Identifier 10.1109/ACCESS.2016.2613278
Mobile Cloud Computing Model and Big Data
Analysis for Healthcare Applications
LO’AI A. TAWALBEH
1,2
, (Senior Member, IEEE), RASHID MEHMOOD
3
, (Senior Member, IEEE),
ELHADJ BENKHLIFA
4
, AND HOUBING SONG
5
, (Member, IEEE)
1
Department of Computer Engineering, Jordan University of science and Technology, Irbid 22110, Jordan
2
Department of Computer Engineering, Umm Al-Qura University, Mecca 21955, Saudi Arabia
3
High Performance Computing Centre, King Abdulaziz University, Jeddah 21589, Saudi Arabia
4
Staffordshire University, Stoke-on-Trent ST4 2DE, U.K.
5
Department of Electrical and Computer Engineering, West Virginia University, Morgantown, WV 26506, USA
Corresponding author: L. A. Tawalbeh (latawalbeh@uqu.edu.sa)
This work was supported by the Long-Term National Science Technology and Innovation Plan (LT-NSTIP) under Grant 13-ELE2527-10
and in part by the King Abdulaziz City for Science and Technology (KACST), Saudi Arabia.
ABSTRACT Mobile devices are increasingly becoming an indispensable part of people’s daily life,
facilitating to perform a variety of useful tasks. Mobile cloud computing integrates mobile and cloud
computing to expand their capabilities and benefits and overcomes their limitations, such as limited memory,
CPU power, and battery life. Big data analytics technologies enable extracting value from data having four
Vs: volume, variety, velocity, and veracity. This paper discusses networked healthcare and the role of mobile
cloud computing and big data analytics in its enablement. The motivation and development of networked
healthcare applications and systems is presented along with the adoption of cloud computing in healthcare.
A cloudlet-based mobile cloud-computing infrastructure to be used for healthcare big data applications
is described. The techniques, tools, and applications of big data analytics are reviewed. Conclusions are
drawn concerning the design of networked healthcare systems using big data and mobile cloud-computing
technologies. An outlook on networked healthcare is given.
INDEX TERMS Healthcare systems, big data analytics, mobile cloud computing, cloudlet infrastructure,
health applications.
I. INTRODUCTION
Recently, there have been many advances in information and
communication technologies that have been transforming the
world; the world is increasingly becoming a small neighbor-
hood. Among these technologies are the cloud computing, the
wireless communications (3G/4G/5G), and the competitive
mobile devices industry. The mobile devices can provide
variety of services to facilitate our living style [1]. They are
integrated in our daily routine to help performing variety
of tasks such as location determination, time management,
image processing, booking hotels, selling and buying online,
and staying connected with others. Also, there are mobile
applications to help you measure and manage your health
through applications for blood pressure, exercises, and weight
loss [2].
The mobility feature of mobile devices (Figure 1) changed
the way that people use different technologies all over the
world. There is no need any more to stay at your office to
do your job or daily activities. The users can move to many
FIGURE 1. Mobility features.
locations based on many parameters for easier life such as
efficiency, stable and fast internet connection and data privacy
concerns to impose the need to protect the users’ data from
unauthorized disclosure especially over non-secure wireless
channels [3]. All these features of mobile devices and inte-
grating them in our life speed up the transition towards
greener and smarter cities [4].
VOLUME 4, 2016
2169-3536 2016 IEEE. Translations and content mining are permitted for academic research only.
Personal use is also permitted, but republication/redistribution requires IEEE permission.
See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
6171
L. A. Tawalbeh et al.: Mobile Cloud Computing Model and Big Data Analysis for Healthcare Applications
FIGURE 2. Cloud computing concept.
Another recent technology is cloud computing
(see Figure 2) which allows access to the stored information
from anywhere at any time, and can be used in different
organizations or by individuals to enhance productivity and
increase performance and reduce the cost and complexity [5].
Cloud computing is defined by NIST as ‘‘a model for
enabling ubiquitous, convenient, on-demand network access
to a shared pool of configurable computing resources
(e.g., networks, servers, storage, applications, and services)
that can be rapidly provisioned and released with minimal
management effort or service provider interaction’’ [6].
Moreover, integrating the mobile devices with cloud com-
puting to utilize the unlimited service provided by the cloud
through the mobile device results in what is known as Mobile
Cloud Computing [7]. The Cloud Computing relies on a set
of network-connected resources shared to maximize their
utilization resulting in reduced management and capital costs.
Mobile Cloud Computing (MCC) is set to benefit many sec-
tors including the cloud-healthcare systems. As an example,
MCC healthcare system was built to capture and analyze real
time biomedical signals (such as ECG and Blood pressure)
from users in different locations. On the mobile device, a per-
sonalized healthcare application is installed and health data
are being synchronized into the healthcare cloud computing
service for storage and analysis [8].
MCC expands the capabilities and benefits of the mobile
devices, and overcomes their limitations, so the users will not
be worried about the memory size and required CPU power
to run intensive tasks that consume considerable amount of
energy [9] and require extra memory. For example, multi-
media applications which are known to be among the most
common applications in today’s mobile devices involve shar-
ing and creating images and video files. These applications
require high computing capabilities, big space to be stored,
and maybe more security protection [10] which are chal-
lenges for mobile devices. Mobile cloud computing resolves
these issues by storing the large multimedia file on the cloud,
and it will be available to the mobile users when requested
resulting in better performance. And since the energy drain
is an important issue in mobile devices and sometimes limits
the optimum utilization of these devices, the researchers are
motivated to find optimization methods to reduce the con-
sumed energy by mobile devices in the cloud and mobile
computing environments [11].
Besides all the great benefits of using the mobile cloud
computing, there are still some limitations such as the delays
encountered when the mobile devices access the cloud ser-
vices from far distance which are mainly due to/from the
mobile devices. It is believed that using the cloudlet concept
between the enterprise cloud and the mobile device has a
good impact in reducing connection latencies and power
consumption [12].
On the other side, there are many challenges associated
with storing data on cloud, and mainly is to protect the
privacy of the users’ data from unauthorized access and from
malicious attacks. Also, availability of the owners’ data at any
time request is an issue. The integrity is also a concern in
which the data should not be altered or modified by intrud-
ers. Many cryptographic techniques can be used to provide
solution to these information security concerns [13], [14].
It is well-known that healthcare applications require large
amounts of computational and communication resources, and
involve dynamic access to large amounts of data within
and outside the heath organization leading to the need for
networked healthcare [15]. Mobile cloud computing could
provide the necessary computational resources at the right
place and right time through cloudlet and fog computing
based architectures. Moreover, big data and relevant tech-
nologies could provide the data management and analytics
solutions that are necessary to reduce healthcare costs and
improve system and clinical inefficiencies. Big data refers to
the emerging technologies that are designed to extract value
from data having four Vs characteristics; volume, variety,
velocity and veracity. Big data is set to affect the future
network traffic and hence the network architectures [15].
See [16] for a survey on big data.
This paper discusses the concept of networked healthcare
and its enablement through the mobile cloud computing and
big data analytics technologies. The motivation and devel-
opment of networked healthcare applications and systems
is presented along with the adoption of cloud computing in
healthcare. A cloudlet–based mobile cloud computing infras-
tructure to be used for healthcare big data applications is
described. The techniques, tools, and applications of big data
analytics are reviewed. Conclusions are drawn concerning the
design of networked healthcare systems using big data and
mobile cloud computing technologies.
The rest of the paper is organized as follows. Section II
presents the literature review, and Section III discusses the
healthcare applications and systems. Section IV presents the
cloudlet based mobile cloud computing infrastructure for
healthcare use. Section V presents big data analytics, fol-
lowed by a review of data analytics tools in Section VI.
Section VII concludes the paper and provides an outlook for
networked healthcare.
6172 VOLUME 4, 2016
L. A. Tawalbeh et al.: Mobile Cloud Computing Model and Big Data Analysis for Healthcare Applications
II. RELATED WORK
There are many related work in the literature about cloud and
mobile cloud computing and their useful applications in many
life aspects including health and financial transactions. Not
neglecting the important issue of securing users sensitive data
on the cloud, a secure framework for cloud computing based
on data classification is proposed in [17]. This framework
categorizes the data based on its confidentiality, and selects
the suitable encryption mechanism to provide the appropriate
protection for each data category.
The authors in [18] presented a prototype implementation
of cloudlet architecture. They pointed out the advantages of
such architecture in real-time applications. In the straight
forward approach, the cloudlet is fixed near a wireless access
points. But in this prototype, a cloudlet can be chosen dynam-
ically from the resources inside the network to manage the
running applications on the component model.
In [19], a large scale Cloudlet MCC model was deployed
for the purpose of reducing network delay and power dis-
sipation especially for intensive jobs such as multimedia
applications. Also, the large scale deployment covering large
areas allows the mobile users to stay connected with the cloud
services remotely while they are moving within this area with
less broadband communication needs while satisfying high
quality service requirements.
The impact of using cloudlet along with mobile cloud
computing on some interactive applications (including video
streaming) was analyzed in [20]. The authors compared the
two models in terms of system throughput and data transfer
delay. Their results indicated that in most cases, the use of the
cloudlet-based model outperformed the cloud-based model.
A framework to provide personalized emotion-aware services
by mobile cloud computing is proposed in [21].
Energy conservation is a major concern in cloud computing
systems with huge number of operating data centers that
consume large amounts of power. Moreover, the prediction
of how much this consumption will increase depends on
the dynamic expansion of their infrastructures to meet the
increasing demand for huge computation and massive com-
munication. The authors in [22] proposed resources man-
agement and optimization policies in the Cloud such as
using virtualization, VM live migration, and server consoli-
dation. They presented an energy efficient network resources
management approach, and proposed a practical multi-level
Cloud Resource-Network Management (CRNM) algorithm,
which is implemented in a virtual Cloud environment using
Snooze framework as the Cloud energy efficiency manager.
The results showed saving of more than 70% of power con-
sumption in Cloud data centers compared to other non-power
aware algorithms.
III. NETWORKED HEALTHCARE: MOTIVATIONS
AND STATE-OF-THE-ART
This section provides the motivation for networked health-
care followed by a review of literature on the state-of-the-
art of networked healthcare architectural and performance
studies including those implemented on cloud computing
platforms.
Healthcare, like many other sectors, has grown rapidly
with the massive growth in ICT. The increasing role and
benefits of ICT in healthcare are becoming visible in the
health informatics, bioengineering and Healthcare Informa-
tion Systems (HIS). We can now imagine a near future
where healthcare providers can port powerful analytics and
decision support tools to mobile computing devices aiding
clinicians at the point of care helping them with synthesis
of data from multiple sources, and context-aware decision
making [23]. Major drivers for ICT-based healthcare include
demands for increased access to and quality of healthcare,
rising healthcare costs, system inefficiencies, variations in
quality of care, high prevalence of medical errors, greater
public analysis of government spending, ageing population,
and the fact that patients and the public want a greater say
in decisions about their health and healthcare. The scientific
developments that are yet to reach their required potential for
providing personalized healthcare include genetic and molec-
ular research, translation of knowledge into clinical practice,
new processes and relationships in product development and
knowledge management [24]. However, we believe that the
major hurdles for the healthcare industry in realizing the full
potential of ICT include the social reasons including privacy
of health data and public trust [25].
The key management strategies that healthcare executives
should focus on over the coming years include Collabora-
tion, Open Systems, and Innovation [26]. The key health
information technologies (HIT), according to them to be
deployed over the next decade include Electronic Health
Record (EHR), Personal Health Record (PHR), and Health
Information Exchange (HIE) systems. They projected that
by 2020, 80% of health care provider organizations will
have implemented EHR systems in the US, and 80% of the
general population will have started using PHR systems in
the US. A vision of Medical Informatics in 2040 is presented
in [27]. The authors believe that transformation of healthcare
will be enabled through the implementation of technologies
including genomic information systems & bio-repositories
integrated with EHR systems; nanotechnology, advanced user
interface solutions, e.g. wearable systems, health apps, health
information exchange (HIE) with other industries/sectors
such as pharma and manufacturing, Home-based TeleHealth
solutions interconnecting patients with health care providers,
and medical robotic devices interfaced to health IT (HIT)
systems.
The United States Department of Health and Human Ser-
vices [24] envisions personalized health care and gives a
perspective on how far and how quickly we have come in
treatment strategies of dangerous diseases including cancer,
diabetes and heart attacks. In 2014, Apple introduced the
mobile health platform HealthKit [28], a cloud API made
available for iOS 8 [29]. HealthKit benefits by the Apple’s
partnership on this enterprise with Mayo Clinic and soft-
ware company Epic Systems. The HealthKit API provides
VOLUME 4, 2016 6173
L. A. Tawalbeh et al.: Mobile Cloud Computing Model and Big Data Analysis for Healthcare Applications
the users with an interface for accessing and sharing their
PHRs. The information collected through the Apple Health
App could be integrated with, for example, the Epic’s EHR
systems allowing the use of Epic’s software tools. The Apple
Health app provides a convenient entry point to personal-
ized health services. Apple has also provided information
for developers and extended an invitation to discuss the
possibilities for interaction of various devices with the sys-
tem [30]. The ‘‘S’’ Health app from Samsung for Android
platform is also being used by many people on their smart
phones [31]. These are important milestones in the move
towards personalized healthcare. We believe that the major
innovations in personalized healthcare will begin when open
Source community will start contributing in the healthcare
applications space.
Having discussed the motivation for networked healthcare,
we now review literature on the architectural and performance
studies in healthcare.
There have been many studies on performance modeling
and analyses of healthcare applications over communication
networks [15], and distributed systems [32], including cloud
computing systems [15], [33]. A quantitative modeling study
to demonstrate the potential of computational grids for its use
in healthcare organizations to deploy diverse medical appli-
cations was presented in [32]. The study considered multiple
organizational and application scenarios for grid deployment
in networked healthcare including four different classes of
healthcare applications and 3 different types of healthcare
organizations. The computational requirements of key health-
care applications were identified and a Markov model of a
networked healthcare system was built. For each scenario,
steady state probability distributions of the respective Markov
models were computed in order to analyze the system per-
formance. Various performance measures of interest such
as blocking probability and throughput could be computed
from these state probability distributions. The paper provides
an interesting insight into computational requirements of
healthcare applications, as well as provides a platform to
explore communication requirements of healthcare applica-
tions. These requirements are important because the traffics
on future networks connecting healthcare systems are likely
to be dominated by the analytics applications that require fre-
quent, low-latency, communications. These individual com-
munications though may not be heavy in terms of data,
however will create significant traffic due to the large number
of individual communications. This is also very typical of
high performance computing applications. A healthcare mon-
itoring system based on wireless sensor networks is proposed
in [34]. Specifically, the monitoring system monitors phys-
iological parameters from multiple patient bodies through
a coordinator node attached to the patient’s body that col-
lects the signals from the wireless sensors and sends them
to the base station. Continuous monitoring of physiological
parameters is an important application area of healthcare and
has major implication on the design of network that con-
nects sensors, analysis applications, physicians, healthcare
systems and providers. For example, as exemplified in this
paper, monitoring of blood pressure and heart rate of a preg-
nant woman, and the heart rate/movement of the fetus, is
a vital requirement for managing her health. The sensors
attached to a patient’s body form a wireless body sensor
network (WBSN) and provide information related to heart
rate, blood pressure and other health related parameters.
A framework for a unified middleware based on Session
Initiation Protocol (SIP) to enable mobile healthcare appli-
cations over heterogeneous networks is proposed in [35].
Their motivation is the need for anytime anywhere delivery
of healthcare services that will in turn require operation over
heterogeneous networks. Their approach is to use the pro-
posed unified middleware to isolate applications from mobil-
ity management and other transport/discovery related tasks.
A survey of wireless sensor networks (WSNs) for healthcare
is provided in [36]. An overview of the design issues for
healthcare monitoring systems using WSNs is provided along
with a discussion of the benefits of these systems. Several
applications and prototypes of WSN healthcare monitoring
systems are reviewed from the literature, as well as challenges
and open research problems for the design of these systems.
A study of end-to-end network performance within and
between three hospitals in the Central-West region of Ontario
with the aim to examine the healthcare applications require-
ments was presented in [37]. The OPNET modeler is used to
study the network performance. Results of four applications
used in this study; database, HTTP, FTP, email, were pre-
sented and discussed for throughput and queuing delays for
servers and the main router. A comparative study on mobile
computing to get a better solution for mobile healthcare appli-
cations was presented in [38]. A mobile cloud architecture
relevant to healthcare applications that stores and manages
personal healthcare data was proposed. A number of other
works have discussed cloud computing adoption in healthcare
and the expected advantages and limitations, see e.g. [39].
In the context of networked healthcare we should men-
tion the Health Level Seven International standard. HL7 is
a not-for-profit organization that was formed in 1987. It is
accredited by ANSI (American National Standards Institute)
and it is ‘‘dedicated to providing a comprehensive framework
and related standards for the exchange, integration, sharing,
and retrieval of electronic health information that supports
clinical practice and the management, delivery and evaluation
of health services’’ [40]. ‘‘Level Seven’’ refers to the seventh
layer (the application layer) of the International Organiza-
tion for Standardization (ISO) seven-layer communications
model for Open Systems Interconnection (OSI).
Many studies have explored the networked systems and
QoS in transferring data over different networks, which is
very important in many applications especially in healthcare.
Service modeling of multimedia over Wi-Fi networks was
explored in [41]. End to end Service Modeling of multimedia
(video, voice and text) over VoIP networks within metropoli-
tan area network environments was explored in [42] with
a focus on VoIP. The study also presented a novel analysis
6174 VOLUME 4, 2016