Evaluation of Clustering Methods for Adaptive Learning Systems

Clustering student data is a central task in the educational data mining and design of intelligent learning tools. The problem is that there are thousands of clustering algorithms but no general guidelines about which method to choose. The optimal choice is of course problem- and data-dependent and can seldom be found without trying several methods. Still, the purposes of clustering students and the typical features of educational data make certain clustering methods more suitable or attractive. In this chapter, the authors evaluate the main clustering methods from this perspective. Based on the analysis, the authors suggest the most promising clustering methods for different situations.

Ideas on the Future of Intelligent Web-Based E-Learning

With the outstanding improvements in technology, the number of e-learning applications has increased greatly. This increment is associated with awareness levels of educational institutions on the related improvements and the power of communication and computer technologies to ensure effective and efficient teaching and learning experiences for teachers and students. Consequently, there is a technological flow that changes the standards of e-learning processes and provides better ways to obtain desired educational objectives. When we consider today's widely used technological factors, Web-based e-learning approaches have a special role in directing the educational standards. Improvements among m-learning applications and the popularity of the Artificial Intelligence usage for educational works have given great momentum to this orientation. In this sense, this chapter provides some ideas on the future of intelligent Web-based e-learning applications by thinking on the current status of the literature. As it is known, current trends in developing Artificial Intelligence-supported e-learning tools continue to shape the future of e-learning. Therefore, it is an important approach to focus on the future. The author thinks that the chapter will be a brief but effective enough reference for similar works, which focus on the future of Artificial Intelligence-supported distance education and e-learning.

Design and Development of an Expert System Shell Program and Evaluation of Its Effectiveness

In recent years, the amount of software developed to be used in the fields of computer-assisted teaching, e-learning, and distance education, and their quality levels have greatly varied. In order to meet the increasing demand for effective and suitable coursewares at an optimum level, the most convenient method is believed to be that these coursewares should be developed by teachers themselves, and a considerable number of quality studies focusing on these coursewares should be conducted to improve educational processes in general. At this point, the studies and projects benefitting from the advantages of artificial intelligence-based approaches are becoming frequently available in the related literature as an innovative trend. The current chapter deals with the design and development of an “expert system shell program” on the basis of certain specific goals and needs mentioned in the literature. The main objective of the study is to assist teachers in developing their own courseware by using this particular program. The shell program developed within the scope of this study was tested on a group of people that consists of teachers from different fields of teaching and education levels, and its effectiveness was evaluated through certain methods.

A Web-Based Intelligent Educational Laboratory System for Forecasting Chaotic Time Series

In the context of Chaos Theory and its applications, forecasting time series of a chaotic system is an attractive work area for the current literature. Many different approaches and the related scientific studies have been introduced and done by researchers since the inception of this working area. Newer studies are also performed in order to provide more effective and efficient approaches and improve the related literature in this way. On the other hand, it is another important research point to ensure effective educational approaches for teaching Chaos Theory and chaotic systems within the associated courses. In this sense, this chapter introduces a Web-based, intelligent, educational laboratory system for forecasting chaotic time series. Briefly, the system aims to enable students to experience their own learning process over the Web by using a simple interface. The laboratory system employs an Artificial Intelligence-based approach including a Single Multiplicative Neuron System trained by Intelligent Water Drops Algorithm in order to forecast time series of chaotic systems. It is possible to adjust parameters of the related Artificial Intelligence techniques, so it may possible for students to have some knowledge about Artificial Intelligence and intelligent systems.

Review and Proposal for Intelligent Distance Education

Information and communication technologies have led to new developments in education. Time and place independent education has emerged. Furthermore, different characteristics and huge numbers of individuals have made the use of new technological methods inevitable. In this context, distance education has become a popular education method to meet the emerging needs, increasing satisfaction, and learning performance of students. Mobile technology, intelligent systems, and Three Dimensional (3D) animations also provide enhancements in this field. In addition, distance education systems should be selected and developed properly for target students and environments. For this purpose, the assessment of prominent studies provides a road map for new research. In this sense, this chapter evaluates intelligent distance education studies in literature. Furthermore, it proposes a novel Artificial Neural Network (ANN)-based distance education system for Mehmet Akif Ersoy University. This ANN-based system can be implemented on Mehmet Akif Ersoy University infrastructure with agent. The proposed system consists of a learning management system, Web conferencing system, and an ANN agent. The agent's inputs that are already stored in Mehmet Akif Ersoy University's distance education databases can be easily retrieved. This agent provides reusability of course content and Web conferencing records.

On the Intersection of Artificial Intelligence and Distance Education

In today's world, intelligent systems play an important role in improving humankind's life standards and providing effective solutions for real-world-based problems. In this sense, such intelligent systems are the research outputs of the Artificial Intelligence field in Computer Science. Today, in many fields intelligent systems are widely used to obtain effective and accurate results for the problems encountered. At this point, education is one of the most remarkable fields in which lots of Artificial Intelligence-oriented research works are performed. When we consider the education field in terms of the latest technological developments, we can also see that the e-learning technique and more generally distance education approach are highly associated with the applications of Artificial Intelligence. Therefore, in this chapter the author explores the trends within the interaction between Artificial Intelligence and Distance Education. The chapter is a brief report on current trends of applications of “intelligent distance education” solutions. It also provides a short focus on the future possibilities of the relation of Artificial Intelligence and Distance Education.

Evolutionary Approach for Automatic and Dynamic Modeling of Students' Learning Styles

Most of the distance educational systems consider only little, or no, adaptivity. Personalization according to specific requirements of an individual student is one of the most important features in adaptive educational systems. Considering learning and how to improve a student's performance, these systems must know the way in which an individual student learns best. In this context, this chapter depicts an application of evolutionary algorithms to discover students' learning styles. The approach is mainly based on the non-deterministic and non-stationary aspects of learning styles, which may change during the learning process in an unexpected and unpredictable way. Because of the stochastic and dynamic aspects enclosed in learning process, it is important to gradually and constantly update the student model. In this way, the student model stochastically evolves towards the real student's learning style, considering its fine-tuned strengths. This approach has been tested through computer simulation of students, and promising results have been obtained. Some of them are presented in this chapter.

Agent-Based Distributed Intelligent Tutoring System Using Case-Based Reasoning

Intelligent Tutoring Systems have proven their worth in multiple ways and in multiple domains in education. In this chapter, the proposed Agent-Based Distributed ITS using CBR for enhancing the intelligent learning environment is introduced. The general architecture of the ABDITS is formed by the three components that generally characterize an ITS: the Student Model, the Domain Model, and the Pedagogical Model. In addition, a Tutor Model has been added to the ITS, which provides the functionality that the teacher of the system needs. Pedagogical strategies are stored in cases, each dictating, given a specific situation, which tutoring action to make next. Reinforcement learning is used to improve various aspects of the CBR module: cases are learned and retrieval and adaptation are improved, thus modifying the pedagogical strategies based on empirical feedback on each tutoring session. The student modeling is a core component in the development of proposed ITS. In this chapter, the authors describe how a Multi-Agent Intelligent system can provide effective learning using Case-Based Student Modeling.

Resolving the Paradox of Overconfident Students with Intelligent Methods

The chapter presents a case study of using data mining tools to solve the puzzle of inconsistency between students' in-class performance and the results of the final tests. Classical test theory cannot explain such inconsistency, while the classification tree generated by one of the well-known data mining algorithms has provided reasonable explanation, which was confirmed by course exit interviews. The experimental results could be used as a case study of implementing Artificial Intelligence-based methods to analyze course results. Such analyses equip educators with an additional tool that allows closing the loop between assessment results and course content and arrangements.

Expert Systems in Distance Education

Computers have been used in educational environments to carry out applications that need expertise, such as compiling, storing, presentation, and evaluation of information. In some teaching environments that need expert knowledge, capturing and imitating the knowledge of the expert in an artificial environment and utilizing computer systems that have the ability to communicate with people using natural language might reduce the need for the expert and provide fast results. Expert systems are a study area of artificial intelligence and can be defined as computer systems that can approach a problem for which an answer is being sought like an expert and present solution recommendations. In this chapter, the definition of expert systems and their characteristics, information about the expert systems in teaching environments, and especially their utilization in distance education are given.