Article Preview
Top1. Introduction
The rapid growth in the use of computer technology has facilitated significant changes in the ways we perform our everyday activities. This recent advancement has allowed computational resources to be easily embedded and integrated into services that support users in their everyday life. This effect has cut across different domain areas including the educational system, such that there is a shift from the traditional learning system to e-learning system. In traditional learning system, it is difficult to adapt learning materials prepared by the teachers to each individual learner's learning needs especially those with learning disabilities. Disability is an impairment that may be cognitive, developmental, intellectual, mental, physical, sensory, or some combination of these. With available platforms such as e-mail, chat-rooms, and electronic whiteboards, E-learning has proven to be an effective tool in breaking the barrier created by the traditional learning system. However, the question of how well e-learning system have met the needs of students with different disabilities has not been satisfactory as most e-learning frameworks were either not accessible to students with different ranges of learning impairments or the technologies used were poorly understood (Fichten et al., 2009; Alsobhi et al., 2015). In addition, regular e-learning systems lack the capability for personalization and adaptability. The advances of modern technology and learning on educational focus are shifting gradually from electronic to ubiquitous learning (Boyinbode and Bagula, 2011; Boyinbode and Bagula, 2012). Ubiquitous learning can be defined as an everyday learning environment that is supported by mobile and embedded computers and wireless networks in our everyday life (Ogata et al., 2009). It enables users to interact and learn with sensors and radio frequency identification (RFID) embedded objects in their surroundings (Curtin et al., 2007). U-learning is “any kind of learning in which learners can have access to information almost anywhere and anytime in different contexts”. Context can be said to be the benchmark which brings about ubiquity to the computing environment. “Context” is any information about the circumstances, objects, or conditions by which a user is surrounded that is considered relevant to the interaction between the user and the ubiquitous computing environment (Ranganathan and Campbell, 2003). However, several researches on ubiquitous learning systems still lack adequate contents and algorithms for self-adaptive personalized knowledge output for handicapped learners (Liu and Dai, 2007).
The combination of Artificial neural and Fuzzy Inference System also known as ANFIS have gained much popularity in recent years. Having been applied in several study areas, the hybridized soft computing method has proven to be highly efficient and effective in decision-making and solve problems based on data mining. Middleware is used to describe separate products that serve as the glue between two applications. It is sometimes called plumbing because it connects two sides of an application and passes data between them. It simplifies the tasks of creating and maintaining context aware systems (Hong et al., 2001). Context-toolkit, Gaia, RCSM (Reconfigurable Context-sensitive Middleware) are some of the few existing middleware for ubiquitous computing. However, the aforementioned different middleware does support sensed, combined and inferred context, but not learned context (Boyinbode and Bagula, 2011). Hence, this paper proposes to use ANFIS as a middleware between the learner and the mobile device with the capability to predict instructional materials to support the physical disabilities of learners in a Ubiquitous environment.