Design of Context Aware Recommendation Engine for Cell Phone using Bayesian Network, Fuzzy Logic, and Rough Set Theory

Design of Context Aware Recommendation Engine for Cell Phone using Bayesian Network, Fuzzy Logic, and Rough Set Theory

Thyagaraju G. S., U. P. Kulkarni
DOI: 10.4018/japuc.2012100105
(Individual Articles)
No Current Special Offers


In this paper the authors have presented design and implementation of context aware service recommendation engine for cell phone. Context aware service recommendation engine for mobile is designed to automatically adopt its behavior to changing environment. To achieve this, an important issue to be addressed is how to effectively select services for adaptation according to the user’s current context. In this paper, the authors propose an intelligent service recommendation model. They formulate the service adaptation process by using artificial intelligence techniques like Bayesian Network, fuzzy logic and rough sets based decision table. Bayesian Network to classify the incoming call (high priority call, low priority call and unknown calls), fuzzy linguistic variables and membership degrees to define the context situations, the decision rules for adopting the policies of implementing a service.
Article Preview

1. Introduction

The users nowadays are mobile dependent. Services provided by the existing mobiles with minimum functionalities are not up to the mark. Context Aware Mobile is in high demand. Mobiles are one of the most popular consumer products all over the world, and have evolved such that they can now provide personalized and adaptive services to users in many ways. The existing technologies allow users to move around with computing power and network resources at hand (say portable computers and wireless communications). Due to their popularity and easy access and varies functionalities, various technologies have been developed that contribute to making the mobile even more context aware. Mobile internet services enable access to information in a more flexible manner. These changes have increasingly enabled people to access their personal information, corporate data, and public resources “anytime, anywhere.” There are already many wireless handheld computers available, running different operating systems such as Palm OS, Microsoft Pocket PC (Windows CE), and Symbian EPOC. Contextual presentation is an emerging technique that has huge commercial possibilities. The theory behind the applications is complex and this makes the implementation non trivial.

With the appearance of mobile devices such as cellphones, PDAs or laptops, context-aware applications are becoming prevalent. Context-aware systems provide relevant information, and services based on information to the user, depends on the users’ situation. Mobile computing imposes new challenges in designing computer hardware and software due to user mobility, the diverse types of devices used, resource constraints, and the dynamic nature in execution context. Context-aware mobile computing middleware provides abstraction and support for application programmers to ease the task of developing mobile applications, ensuring acceptable QoS and allowing for adaptation to changes in the operating environment. An important issue to address in designing a context aware middleware is how to effectively recommend services for adaptation according to the user’s current context. However, this issue has not been adequately addressed in existing work which has been focused either on the software realization of services configuration or on a specific scenario or domain (Capra, Emmerich, & Mascolo, 2003; Li & Nahrstedt, 2003; Jiannong, Na Alvin Chan, & Beihong, 2005). This paper is concerned with the formulization and development of a service recommendation engine for context-aware mobile computing middleware. The presented work is an improvement of our previous work (Thyagaraju & Kulkarni, 2012) where in the service was recommended using an inefficient Rule base. In the present work we have replaced Rule base with Decision table derived using Rough Sets Approach for a set of fuzzy Context attributes .Here decision table is derived based on the study of users mobile usage pattern for a fixed period of time.

We propose the design and implementation of user context aware recommendation for mobile using artificial intelligent tools like Bayesian Network, Fuzzy logic and Rough set based decision rule base.

The recommender makes mobile to adapt to dynamically changing personal, social, environmental and physiological states. To list some of the services (but not limited) provided by recommender are as follows:

  • 1.

    Provide the callers with the ability to communicate the high priority calls irrespective of his situation and location.

  • 2.

    It goes to silent mode in the class room/meeting room automatically.

  • 3.

    It goes to the vibrating mode automatically in the Library and also provides services like book search.

  • 4.

    It provides notifications whenever required.

  • 5.

    It provides Context based desktop applications.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing