March 2009 Index
Home Page

Editor’s Note: Social networking and related Web 2.0 technologies create new opportunities for learning from computers and a wide range of mobile communication devices. This article extends our concept of flexible and open learning in the anywhere-anytime environment.

Learning Agents Framework Utilizing Ambient Awareness and Enterprise Mashup

Jinan Fiaidhi  and  Sabah Mohammed



For a learning agent to support a human in learning it is important to be aware of the progress made in a given enterprise and build on it. This article introduces a framework to obtain such an awareness of the human’s learning progress for an enterprise by using ambient awareness and ambient intelligence models along with mashup services.

Keywords: ambient learning, social networks, web 2.0, ami, ambient awareness, enterprise mashup, collaborative learning.


The common understanding of e-learning shifted over the last decades from the traditional learning objects portals to learning paradigms that enforces constructivism, discovery learning and social collaboration.  Today most educational institutions are equipped with at least some kind of tools (mostly web-based) that bring together people and content artifacts in learning activities to support their learning activities in constructing and processing information and knowledge. Moreover, web-based learning is becoming common learning ground as the Web is representing a delivery medium, as well as a provider of content and subject matters. With the advent of the Web 2.0 technologies, web-based learning is shifting more to a new learning community driven environment. While the success of web-based learning (still) requires a careful selection of appropriate communication/collaboration tools, the underlying software methodology is shifting from (passive) content consumption towards (active) content creation (Spaniol, Klamma and Cao, 2008).

Web 2.0 technologies are offering very attractive capabilities for learners to collaborate and share learning contents (e.g. learning objects, drawings, animations, pictures, digital videos, texts etc.). Although the advantages of Web 2.0 related to learning are obvious (Ullrich et al. 2008), Web 2.0 technologies keep advancing with new challenges that we need to understand and solve. Recently Web 2.0 technologies are embracing Enterprise Mashup as a mean for collaboratively creating new contents and some researchers like Eisenstaedt (2007) praises its importance for learning. Indeed, the promise of remixing existing online services and data into entirely new online application and content has captured the software industry’s attention. Many notable software vendors produced several environments and frameworks for Enterprise Mashup (e.g. Oracle Fusion Middleware, Mainsoft Microsoft SharePoint Federator and IBM WebShere Portal, Adobe Flex) which have offered the potential to finally make widespread software reuse a reality. However, though anecdotal evidence seem to abound — there are a good number of stories about businesses creating isolated mashups here and there, we’re clearly still not yet seeing the flood of mashup-based apps inside of the educational institutions despite their consistent and steadfast growth on the web. Dion Hinchcliffe (2007) described some major challenges facing Enterprise Mashup programming and technology that requires effective remedies. However, this article introduces a new learning perspective and framework for adopting Enterprise Mashup for Enterprise Learning based ambient awareness and learning agent’s technologies.

Enterprise Mashup for Ambient Learning

Ambient Learning and Ambient Intelligence are promising concepts for new methods of learning and in particular for adapted, comprehensive and personalized learning environments. These concepts help learners and institutions to keep up with the rapidly changing knowledge-based economy. Ambient learning is designed to facilitate access to high quality e-learning material tailored to the needs of an individual learner. These needs are determined by the time, place, pace and context that best suits the individual learner. Ambient learning through the provision of content integration and composition allows access to, new e-learning material as well as existing catalogues/e-learning resources (Paraskakis 2006). Although ambient learning is based on Ambient Intelligence Technologies (AmI) its use is not only limited to rooms and buildings. Ambient learning is taking new dimensions as it can be realized by technologies that combines both Ambient Intelligence and Web 2.0  AmI involves the convergence of several computing areas. The first is ubiquitous or pervasive computing where its major contribution is on the development of various ad hoc networking capabilities that exploit highly portable and very-low cost computing devices. The second key area is intelligent systems research, which provides learning algorithms and pattern matchers as well as other classification, interpretation and situation assessment capabilities. A third element is on context awareness (e.g. track and position objects). 

The basic advantage of using AmI in any application is to enhance interactions between objects. However, the social focus/perspective of the AmI research is largely neglected (Bohn et al 2005). Instead of enhancing interactions with technological objects, there is a need for possible AmI applications that can enhance interactions with other people (Cassens 2008). Enhancing the interactions among people contributes to what is currently termed as the Social Ambient Intelligence or Ambient Awareness (Rizopoulous 2007). Central to the social ambient intelligence research is the use of Web 2.0 techniques within AmI applications. In fact, the Web 2.0 approach has revolutionized the way we use the web and certainly, it can have major positive impact on the AmI research. On one hand, Web 2.0 enables the active participation of users with new contents such as wiki pages, blogs or online multimedia tagged. On the other hand, Web 2.0 transforms the Web into an application-enabling platform. Enterprise Mashups, one of the hottest Web 2.0 technologies today, could affect your ambient learning in a very positive way. Before the enterprise mashup, that same business user had to sign in to several applications and go to different Web sites to manually collect the information and then try to make sense of it. The enterprise mashup web application overcomes this hassle in an elegant way and allows the user to harness more of the collective intelligence in the enterprise to make better decisions. Mashups have the opportunity to increases the strategic value of learning—by delivering enriched information to users—and reduce time cycles spent on custom development. However, mashups have been around for years and the concept of the end-user being able to easily ‘drag-drop’ and put together a hacked up application within minutes hasn’t - and this is what is causing a major obstacle. For mashups to really take off, we need to be able to capture the context of information. Information becomes relevant, and more useful when it is placed in the right context. If a Mashup can leverage of some form of social context, it would then be able to provide the relevant information to the user. In this direction, social mashups are a new trend that takes the traditional mashup one-step further. Ultimately, in an enterprise, social interaction is a key part of how information is tied together and increasingly more relevant to how individuals want to visualize information. Hence, linking people, processes and information through mashing can creates a real social enterprise mashup.

The Learning Agents Framework

There are many historical attempts to develop a framework for e-learning including Learning Objects, Learning portals, Web-Based Learning (WBL), Web-Based Instruction (WBI), Web-Based Training (WBT), Internet-Based Training (IBT), Distributed Learning (DL), Advanced Distributed Learning (ADL), Distance Learning, Online Learning (OL),  m-Learning, Remote Learning, Off-site Learning, a-Learning (anytime, anyplace, anywhere learning).  However, a learning environment consists of a dynamic mix of many different types of resources and facilities, which should be aware of, and adapt to, the learner in his/her current context. This multiplicity of technologies including the recent waves of Web 2.0 and Web 3.0 demands sort of service-oriented approach, and this in turn leads us to ambient learning when learning goals are focused on collaboration, contextualization, ubiquity and accessibility (See Figure1).

Figure 1:  Towards Service Oriented Learning (L Declan Dagger et al (2007)).

Collaboration and contextualization can only be supported through services, which can be created and modified dynamically to suit the current needs and situations of learners. Ubiquity and accessibility, however,  requires services which can adapt to the capabilities of the infrastructure (Allison et al   2004; Dagger et al 2007).  Therefore, Service Oriented Architecture (SOA) and in particular those that are based on lightweight RESFul Web Services have become active areas of research and development in learning. Enterprise Mashup and ambient learning represent excellent examples of applications that utilizes such the RESTful web services technologies (Kölmel and Kicin 2005). Based on Ambient learning and the Enterprise mashup, the learners participate and co-operate in, for example, syndicating, re-mixing, or creating learning materials and environments. On one hand, mashups, by their very definition, involve a man-in-the-middle and rely on RESTful communication protocols (e.g. RSS, ATOM). While Web Services based on SOAP as a transport can provide only end-to-end services. As a result, the practice of mashup services has become increasingly popular in the Web development community compared to the traditional Web Services composition and integration. In fact, mashup services bring flexibility and speed in delivering new valuable easy-to-use eLearning service, which allows any time, any where and any how access to personalized, high quality learning content. With the rediscovery of AJAX (Asynchronous JavaScript and XML) technology, we now have the ability to create RESTful mashups that quickly solve learning problems.  On the other hand, ambient learning aims at seamless delivery of ubiquitous services, continuous communications and intelligent user interfaces and context-awareness.  In this sense, ambient learning systems needs to provide autonomy, distribution, adaptation, pro-activeness and responsiveness as the key characteristics, which are similar to the characteristics learning agents (Hagras et al 2004). Learning Agents are computer programs capable of flexible autonomous actions in a dynamic environment and are apparently a suitable choice for implementing ambient intelligence systems  (Tapia et al 2008). In fact, learning agents inside the Enterprise provide an ecosystem for creating and sharing learning knowledge (Vuor 2005). Based on learning agent’s solutions, learners are empowered with personalized software assistants or learning agents to uncover high-value data, resulting in cost reduction and higher productivity. Using Learning Agents "trained" to do anything a human can to monitor, harvest, extract, process, deliver and integrate dynamic content from the internet, intranets, extranets and Enterprise applications – Learners can access the data that are normally inaccessible. Not only can information be accessed, it can be shared and mashups can be created and made available to key learners. Empowering learners in this way can produce enormous educational returns.

Figure 2: The Learning Framework based on AmI and Enterprise Mashup.

Figure 2 illustrates our vision to the new learning agents framework that employs both Ambient Intelligence and Enterprise Mashup. The learning agents have the ability to obtain automatic and real-time information about the learner’s context using a set of technologies.  The framework utilizes learning agents where users can interact on a level that best suits their needs and capabilities, leaving tedious chores to the learning agents. Intelligence and ambient awareness enables the learning agents to learn about their user and adept the environment.

The framework provides tools to quickly capture and share knowledge among users in an enterprise. Hence, search engines are part of both the creation and deployment of knowledge content and knowledge integration can be achieved through mashups. These technologies allow the information to be linked with the other learning processes more easily where it allows more rapid content creation, dissemination, and more importantly, contextualization.


This article provides a framework for the migration of legacy web learning to a service-oriented learning paradigm by means of ambient awareness and mashup services. The authors are engaged currently in developing a prototype for implementing the proposed framework. Some early references to the progress in implementing various aspects of this framework for a biomedical learning enterprise can be found in (Mohammed, Fiaidhi and Mohammed, 2008, 2008a).


The first author NSERC Discovery Grant supports this research.


Allison, C.   Bateman, M.   Nicoll, R.   Ruddle, A. (2004),   Adaptive QoS for collaborative service-oriented learning environments, In CCGrid 2004 Proceedings. IEEE International Symposium on Cluster Computing and the Grid, 2004, 19-22 April 2004

Bohn, J, et al. (2005) , Social, Economic, and Ethical Implications of Ambient Intelligence and Ubiquitous Computing, In Ambient Intelligence, Editors Werner Weber, Jan M. Rabaey and Emile Aarts,Springer Berlin Heidelberg, 2005

Cassens, Jörg (2008), Explanation Awareness and Ambient Intelligence as Social Technologies, PhD Thesis, 2008, Norwegian University of Science and Technology, Faculty of Information Technology, Mathematics and Electrical Engineering, Department of Computer and Information Science.

Dagger, D. et al. (2007), "Service-Oriented E-Learning Platforms: From Monolithic Systems to Flexible Services," IEEE Internet Computing, vol. 11, no. 3, pp. 28-35, May/June 2007,

Dante I. Tapia, D. et al. (2008),  An Ambient Intelligence Based Multi-Agent Architecture, Springer Paris, 2008

Dion Hinchcliffe (2007) The 10 top challenges facing enterprise mashups, ZDNet Online Journal, October 16th, 2007

Eisenstadt, M. (2007), Does Elearning Have To Be So Awful? (Time to Mashup or Shutup),  ICALT 2007. Seventh IEEE International Conference on Advanced Learning Technologies, 18-20 July 2007 Page(s):6 – 10

Hagras, H. et. al.  (2004), Creating an Ambient-Intelligence Environment Using Embedded Agents, IEEE Intelligent Systems,  Volume 19 ,  Issue 6  (November 2004), Pages: 12 - 20  

Kölmel, B.  and Kicin, S. (2005), Ambient Learning: The experience of ambient technologies in eLearning, IFIP International Federation for Information Processing, Springer, Volume 171/2005

Mohammed, S.  Fiaidhi, J.  and Mohammed, O (2008)Sharing Biomedical Learning Knowledge for Social Ambient Intelligence, Presented for Publication, Journal of Computers, Academy Publisher-Finland, December 2008.

Mohammed, S.  Fiaidhi, J.  and Mohammed, O. (2008 a),  Developing an Ontology Extraction Agent for a Biomedical Learning Social Network, NASTEC 2008 Int. Conference, August 13-15, 2008, McGill University, Montreal, Canada.

Paraskakis, I. (2006), Ambient Learning: Rationale and its use in Supporting Blend Learning for Executive Education, 2006. Sixth International Conference on Advanced Learning Technologies, 5-7 July 2006 Page(s):144 – 146

Spaniol, M, Klamma, R. and  Cao, Y. (2008), Learning as a Service: A Web-Based Learning Framework for Communities of Professionals on the Web 2.0Advances in Web Based Learning – ICWL 2007 (2008), pp. 160-173.

Rizopoulos, C (2007), An activity-based perspective of interacting with ambient intelligence systems, 2007. IE 07. 3rd IET International Conference on Intelligent Environments, 24-25 Sept. 2007 Page(s):81 – 88

Ullrich, C. el. Al (2008),  Why web 2.0 is good for learning and for research: principles and prototypes. WWW 2008: 705-714

Vuori, E.K. (2005),  Knowledge-intensive service organizations as agents in a business ecosystem 2005. Proceedings of ICSSSM apos;05. 2005 International Conference on Services Systems and Services Management, Volume 2, Issue , 13-15 June 2005 Page(s): 908 - 912 Vol. 2.

About the Authors

Jinan Fiaidhi is a Professor of Computer Science at Lakehead, University, Ontario, Canada. Her current research focuses on ubiquitous learning.


Sabah Mohammed  is Professor of Computer Science at Lakehead, University, Ontario, Canada. His current research is in Web Intelligence.


go top
March 2009 Index
Home Page