A PARADIGM FOR THE APPLICATION OF CLOUD
COMPUTING IN MOBILE INTELLIGENT TUTORING
Hossein Movafegh Ghadirli1 and Maryam Rastgarpour2
1 Graduate student in Computer Engineering, Young Researchers Club, Islamshahr
Branch, Islamic Azad University, Islamshahr, Iran
2 Faculty of Computer Engineering, Department of Computer, Saveh
Branch, Islamic Azad University, Saveh, Iran
Nowadays, with the rapid growth of cloud computing, many industries are going to move their computing
activities to clouds. Researchers of virtual learning are also looking for the ways to use clouds through
mobile platforms. This paper offers a model to accompany the benefits of “Mobile Intelligent Learning”
technology and “Cloud Computing”. The architecture of purposed system is based on multi-layer
architecture of Mobile Cloud Computing. Despite the existing challenges, the system has increased the
life of mobile device battery. It will raise working memory capacity and processing capacity of the
educational system in addition to the greater advantage of the educational system. The proposed system
allows the users to enjoy an intelligent learning every-time and every-where, reduces training costs and
hardware dependency, and increases consistency, efficiency, and data reliability.
Mobile Services, Cloud Computing, Mobile Intelligent Learning, Expert System
Nowadays growth of technology is fast and unpredictable in the economy, industry and personal
issues . One of the aspects of social life is the process of learning in universities, schools and
other educational institutions. Extensive researches and huge investments have been carried out
to develop technological learning in recent years. Now the word “Learning” is accompanied
with the concepts such as Electronic, Cognitive, Intelligent, Distance and Web based. Since one
of the attractive, efficient and widely used technologies is the use of mobile devices to do the
tasks, researchers have tried to replace the previous notions with mobile learning. They develop
educational softwares that can be implemented on mobile devices.
Mobile learning means the use of learning applications on mobile devices such as smart phones,
PDA and tablets (unlike mobile devices which are small, portable, compact and pocket sized,
Laptops are not considered as mobile systems, since they are expensive and heavy and they
consume much energy) . Recent researches indicate that the variety of learners, the training
and learning process and infrastructure changes to subscribers, in addition to significant impact
on learning quality, is more motivating learners. It causes wider interest of investors toward
At the present, mobile devices are increasing rapidly, since they are the easiest and the most
effective communication tools. In addition, their crucial role in human life, when and where to
use them are not restricted (called ETEW1) , , . Mobile users can use different
applications on their devices or receive even different kinds of services through wireless
With increasing propagation of mobile devices technology, the popularity of this device has also
increased. Some features such as mobility, optimized and easy to use are of the benefits of
mobile devices. Nevertheless, the challenges of the resources of mobile devices (such as short
battery life, small memory capacity and low bandwidth) and also of communication (such as
mobility and data security) are the reasons for the decrease of service quality.
Cloud computing has been known as the Infrastructure of the next generation . Cloud
computing provides users with a way to share distributed resources and services of
organizations in a cloud, and a platform and software is provided as a service in that
infrastructure . Cloud computing can present benefits for the users in the use of the
infrastructures (such as servers, networks and storages), platform (such as firm-wares and
operating systems), and softwares (such as applications) with a little cost. In addition, cloud
computing providers (such as Google, Amazon, IBM, Sun Microsystems, Microsoft, IBM, and
Sales-force) can use their resources flexibly, depending on the demands of the users .
Many educational institutions such as universities and schools would like to use software that
can be hosted on the cloud; since it allows the final user (such as the softwares on his/her PC)
needs no License, installation and maintenance of the softwares , . In this regard, some
cloud providers like Amazon, Google, Yahoo, Microsoft, etc. also support free hosting of e-
learning systems . Thus, this paper tries to present a paradigm for the application of cloud
computing in mobile intelligent tutoring systems.
1.1. Related Works
In 2009 a system was introduced that provided private and virtual education for learners with
regard to pedagogical rules . But researchers were to transfer the complicate educational
systems from PCs to mobile devices. The benefits of cloud computing and mobile learning
integration have been pointed out in , one of which is increasing the quality of
communication between the learner and the teacher. But they are mentioned in detail in section
Some mobile applications already extract and aggregate information from multiple phones.
Tweetie Atebits for the iPhone uses locations from other phones running the application to
allow users to see recent Twitter posts by nearby users . Video and photo publishing
applications such as YouTube and Flickr allow users to upload multimedia data to share online.
The Ocarina application Smule for the iPhone allows users to listen to songs played by other
users of the application, displaying the location of each user on a globe. Such smartphone
applications are “push”-based and centralized, meaning that users push their information to a
remote server where it is processed and shared .
Cornucopia is one of the implemented examples of the proposed system, designed for the
research affairs of undergraduate Genetic learners, and Plantations Pathfinder which was also
designed to provide information for them, qua farms and gardens information were shown on
mobile devices for visitors .
Another example of the system was presented in  that teaches some courses on image/video
processing; using a mobile phone, learners are able to compare a variety of algorithms such as
deblurring, denoising, face detection and image enhancement used in mobile applications.
The rest of this paper is organized as follows. Section 2 investigates mobile intelligent learning
systems and its challenges. It also explains cloud computing and its derivative namely mobile
1 Every Time and Every Where
cloud computing. Section 3 presents the proposed system in this paper and discusses its
architecture. System evaluation is carried out in detail in section 5. Finally, the paper concludes
in section 5.
2. MATERIALS AND METHODS
Cloud computing is not only related to personal computers, it also affects and heavily impact
the mobile technology. In Mobile Cloud Computing both the data storage and the data
processing happen outside of the mobile device i.e. when we combined concept of cloud
computing in mobile environment. In Mobile Cloud Computing scenario all the computing
power and data storage move into the mobile cloud. In fact Cloud has generated many
resources which can be used by various educational institutions and streams where their
existing/proposed web based learning systems can be implemented at low cost.
2.1 Mobile Intelligent Learning System
Since 1980 that the use of computers began in learning process , the researchers have so far
tried to make the educational systems more effective and easier. With the emergence of the
phenomenon of AI now few systems can be found that does not use the minimum intelligence;
In this context, the idea of integrating "intelligence" feature and static e-learning systems was
also formed that resulted in the increased effectiveness of these systems in users' speed, quality
and amount of learning.
Another aspect of e-learning systems is learning easiness. Users are often interested in being
trained in anytime and anyplace they wish.
Not very long lifetime passes from the e-learning web-based systems; nevertheless one of the
main factors that led to the use of "mobile learning" instead of “web-based learning” is the
learners' lack of access to a computer (connected to internet). Reports show that in 2005, in
many schools, there is one computer for every learner and the lowest rate of “computers to
learners” is about 1 to 3 . Though these factors do not represent the majority of the school’s
situations, but a 9% increase is observed in the use of handheld computers since 2003 .
These factors show a positive trend in the use of handheld computers at schools and it allows
learners to balance their use of technology at home and school.
Applying mobile devices, universities, schools and other educational establishments can provide
conditions for the use of intelligent learning systems without financial resources and
construction of computer labs . Learner can easily have educational system on their mobile
devices and transport them between home and school. Mobility lets these systems also be used
outside of computer labs and classrooms. As a result, opportunities can also occur for learners to
learn at home and in other locations. SO, universities, schools, and shopping centers'
administrators can share a number of mobile devices for learners instead of computer labs and
Generally, the benefits of cloud computing in e-learning can be divided into four groups :
reducing the costs of using resources
flexibility in the use of infrastructure
the client is the end user
Intelligent Tutoring System will make a specific model of learner’s knowledge and
characteristics and this model will get perfect during the interaction between the system and the
learner. This model is compared with the domain model in the system to determine an
appropriate strategy for tutoring learner . It should be noted that users are not always in a
fixed location or it is not possible for them to have free access to the internet all the time.
Therefore, researchers have taken advantage of the potential of mobile devices to enable data
transfers on intelligent learning application systems  and create “mobile intelligent tutoring
The main characteristics of a mobile intelligent tutoring system are portability and intelligence;
however, these systems also have disadvantages compared to desktop-based systems. Mobile
intelligent tutoring systems face some challenges such as “implementation difficulty”, which are
discussed in Table 1.
Table 1. Challenges of a Mobile Intelligent Tutoring System .
Description of challenge
- Small monitor (2-5 inch)
- Difficult design as a single window
- Limited data entry with a small keyboard
- Using for a short time, from few seconds to few minutes
- Having the role of the client with no content of itself
- Low memory capacity
- Needing a cellular network or wireless internet
2.2 Cloud Computing
The NIST2 defines Cloud Computing as follows :
It is 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. Cloud computing is a new computational method in which the
infrastructure, platform and software is provided as a service. Using different computing
resources, members of cloud computing can easily solve their problems by a cloud, and it gives
users a lot of flexibility.
In fact, cloud computing can remove the limitations of the network and its hardware
components and attract a lot of attention through its services to many components (Figure 1).
Figure 1. Cloud Computing Clients
2 National Institute of Standards and Technology (NIST)
The great popularity of cloud computing is because of “computing” transfer; Instead of the local
machine, the data center, located on the clouds, is responsible for computing task. So any device
such as mobile phones, rather than doing difficult and complex calculations, will be able to send
equation parameter to a service in a cloud and receive a quick response to it .
Cloud computing is generally a large-scale distributed network, which is implemented based on
a number of servers (within the data center). This cloud model promotes availability and is
composed of five essential characteristics, three service models, and four deployment models
2.2.1 Essential Characteristics
1) On-demand self-service. A consumer can unilaterally provision computing capabilities,
such as server time and network storage, as needed automatically without requiring
human interaction with each service’s provider.
2) Broad network access. Capabilities are available over the network and accessed through
standard mechanisms that promote use by heterogeneous thin or thick client platforms
(e.g., mobile phones, laptops, and PDAs).
3) Resource pooling. The provider’s computing resources are pooled to serve multiple
consumers using a multi-tenant model, with different physical and virtual resources
dynamically assigned and reassigned according to consumer demand. There is a sense
of location independence in that the customer generally has no control or knowledge
over the exact location of the provided resources but may be able to specify location at a
higher level of virtuality (e.g., country, state, or data center). Examples of resources
include storage, processing, memory, network bandwidth, and virtual machines.
4) Rapid elasticity. Capabilities can be rapidly and elastically provisioned, in some cases
automatically, to quickly scale out, and rapidly released to quickly scale in. To the
consumer, the capabilities available for provisioning often appear to be unlimited and
can be purchased in any quantity at any time.
5) Measured Service. Cloud systems automatically control and optimize resource use by
leveraging a metering capability at some level of abstraction appropriate to the type of
service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage
can be monitored, controlled, and reported, providing transparency for both the provider
and consumer of the utilized service.
2.2.2 Service Models
Cloud services, illustrated in Figure 2, are usually based on three layers :
1) Data Center layer provides the required hardware and infrastructure of the clouds. In
this layer, there are a number of servers connected to high-speed networks. Data centers
are often located in places with the ability of high voltage power supply and away from
2) Infrastructure as a Service (IAAS) is located on the data center which provides
hardware, storage, servers and network components and the use these resources is based
on users' needs; some examples of this layer are Amazon Elastic Cloud Computing and
Simple Storage Service(S3).
3) Platform as a Service (PAAS) is proposed as a developed environment for traditional
software's building, testing and developing. Some examples of this layer are Google
App Engine، Microsoft Azure, and Amazon Map Reduce/Simple Storage Service.
4) Software as a Service (SAAS) provides an application distribution with special needs. In