Towards a Hybrid Modeling

This chapter introduces the reader to Part IV of the book, proposing and discussing a hybrid approach that may serve, not only to synthesize and represent knowledge obtained from the data, but also to explore possible future online learning environment (OLE) states, given different management, policy or environmental scenarios. Pragmatically, this chapter explores the potentiality of the quality of collaboration (QoC) within an Internet-based computer-supported collaborative learning environment and quality of interaction (QoI) with a LMS, both involving fuzzy logic-based modeling, as vehicles to improve the personalization and intelligence of an OLE. Furthermore, QoC and QoI can form the basis for a more pragmatic approach of OLEs under the perspective of semantic Web 3.0, within the context of Higher Education. Finally, a potential case study of the examined hybrid modeling, referring to the “i-TREASURES” European FP7 Programme, is discussed, to explore its applicability and functionality under pragmatic learning scenarios.

Embracing Macro-, Meso-, and Micro-Levels of Analysis of FIS-Based LMS Users' Quality of Interaction

An essential factor in determining the efficiency of the online education is the users' quality of interaction (QoI) with LMSs. In this chapter, the macro-meso-micro structure analysis is adopted, to examine the Fuzzy Inference System (FIS)-based approach of QoI, taking into account the LMS users' (professors' and students') interactions within a b-learning environment, in order to quantitatively estimate a normalized index of their QoI, accordingly. Additionally, for capturing the dynamics of the users interacting with the LMS, the data corresponding to a 51-week LMS Moodle usage time-period of two consequent academic years (2009/2010 and 2010/2011) at a HEI were analyzed. Finally, based on a systemic approach of the derived QoI, user-dependent/independent (group-like) (dis)similarities in LMS interaction trends, correlations, distributions and dependencies with the time-period of the LMS use are analyzed, towards an effort to contribute to a more objective interpretation of the way LMS Moodle-based b-learning functions within the HEIs.

Fuzzy Logic-Based Inference Systems

This chapter presents the mathematical formulation of the fuzzy logic-based inference systems, used as means to infer about the response of ill-conditioned systems, based on the field knowledge representation in the fuzzy world. Particular approaches are explored, e.g., Fuzzy Inference System (FIS), Adaptive Networks-based FIS (ANFIS), Intuitionistic FIS (IFIS) and Fuzzy Cognitive Map (FCM), surfacing their potentialities in modeling applications, such as those in the field of learning, examined in the chapters of Part III that follow.

Personal/Cloud Learning Environment, Semantic Web 3.0, and Ontologies

In the era of digital world that we live in, a new vision for learning is required. Learning is essentially personal, sociocultural, distributed, ubiquitous, flexible, dynamic, and complex in nature. There are multiple challenges, opportunities, and movements in learning that must be considered in the development and implementation of online learning environments. From the emerging computational capacity as a virtualized resource pool available over the network, several benefits can be obtained with regard to the management of computing infrastructures, such as environmental sustainability and improved Personal/Cloud Learning Environment use. In fact, Personal learning environments, Cloud computing, Semantic Web 3.0 and Ontologies are relatively new terms that hold considerable promise for future development and research in higher education contexts. Motivated by the aforementioned perspectives, the purpose of this chapter is to explore and discuss how these terms can be understood towards a more personalized, sociocultural, open, dynamic and encouraging model to support/facilitate teaching and learning processes, fulfilling the integrated view of the educational context presented in Part I of this book.

FIS/IFIS Modeling in Professional and Collaborative Learning

In this chapter, the capability of the fuzzy inference systems (FISs) to model and provide evaluations in the educational context is further explored through the merits of the intuitionistic fuzzy inference systems (IFISs). The Intuitionistic Fuzzy Logic enables the capture and expression of uncertainty and hesitancy with an IFIS model, thus it extends the fuzzy logic capabilities. In this chapter, the purpose and function of the FIS/IFIS modeling, when embedded in an instructional design (ID), is further examined from Boulding's systemic perspective. Elaborations of the latter provide a framework for handling the complexity of the above interplay and clarify the aim and the role of the presented modeling approaches. The ID and FIS/IFIS modeling upon experimental data from their materialization in two educational cases in the area of professional learning and computer supported collaborative learning, respectively, serve as the test-bed for the potentiality of the presented explorations.

ANFIS-Based Collaborative/Metacognitive Data Modeling

Stemming from the approach presented in the previous chapter, this chapter extends the previous modeling concept further, by adopting Adaptive Neuro-Fuzzy Inference System (ANFIS) as the engine to model the collaborative and metacognitive data that are logged during peers' computer-mediated collaboration. The realization of this approach, namely collaboration/metacognition ANFIS (C/M-ANFIS), along with experimental uses and extensions of it, are described in detail. From an overall perspective, the C/M-ANFIS provides innovative opportunities for teaching and learning, on the basis of embedding the fuzzy logic concept within the educational practice, as it equips them with dynamic collaborative performance forecasting capabilities. This reinforces the transitional change of the peers' collaborative and metacognitive skills, gravitating them towards higher quality and more balanced computer-mediated collaboration.

Towards Blending Potentialities within a Learning Management System

The emergence of blended (b-)learning approaches clearly highlights a pressing need for higher education institutions to embrace innovation and change. However, the process of (sociocultural) innovation should be driven by people and pedagogical concepts that are related with new technological developments in a meaningful way for the purpose of adding value to teaching and learning. From this holistic perspective, definitions and issues directly related with b-learning, Information and Communication Technology (ICT) use, pedagogical planning, course management system, Learning Management Systems (LMS) (such as Moodle), usability, accessibility, inclusivity and adaptability are critically discussed in this chapter. In addition, some LMS trends that refer to personalized-, mobile-, systemic-learning conclude the chapter.

Placing the Framework within the Educational Context

This chapter introduces the reader to Part I of the book, describing the educational framework where the core ideas of the book best fit. The appropriate background and fundamental concepts are epitomized, in order to surface the space where the educational needs are placed. In this way, the comprehension of the role of the emerging technologies and the way they could meet such needs, supporting educational innovation, is facilitated.

Concluding Remarks and Probing Further

Arriving to the final destination of the journey started in chapter 1, this concluding chapter represents a brief reflection of the key considerations/contributions of the book and, simultaneously, provides a guidance for future research directions. From an ecological standpoint, the key purpose of this book was to systemically understand the essential issues related to the trends and fuzzy logic-based modeling perspectives of collaborative and blended learning. In addition, the emancipation of collaborative and blended learning environments here is established as a potential contribution to the 21st century learning contexts. In this vein, comprehension of the potentialities of the proposed fuzzy logic-based modeling approaches and the way they could be transferred to tackle real problems in the educational context, contributes to the establishment of a learning ecology for reflection and rethinking upon the intelligence of the online learning environments as current and future constructs.

FCM-Based Modeling of LMS Users' Quality of Interaction

Part III is concluded with this chapter that proposes a Fuzzy Cognitive Map (FCM)-based modeling of the Quality of Interaction (QoI) of the Learning Management System (LMS) users within a blended (b)-learning context, namely FCM-QoI model. Two training/testing scenarios were conducted and explored here, i.e., time-dependent and time-independent, using as pre-validated QoI data the ones presented in chapter 13. Moreover, a FCM-Viewer application that facilitates the visualization of the FCM-QoI model structure is also presented. The experimental results show that the proposed FCM-QoI model can provide concepts interconnection and causal dependencies representation of LMS users' interaction behavior. With this chapter, the circle around the basic fuzzy logic topics discussed in Part II, i.e., FIS, ANFIS, IFIS and FCM, injected into the educational context is fulfilled. Based on the models discussed so far, prospective hybrid modeling approaches are envisioned in the final section of the book (Part IV) that follows.