Miloš Milovanović

Using data mining on student behavior and cognitive style data for improving e-learning systems: a case study

Abstract In this research we applied classification models for prediction of students’ performance, and cluster models for grouping students based on their cognitive styles in e-learning environment. Classification models described in this paper should help: teachers, students and business people, for early engaging with students who are likely to become excellent on a selected topic. Clustering students based on cognitive styles and their overall performance should enable better adaption of the learning materials with respect to their learning styles. The approach is tested using well-established data mining algorithms, and evaluated by several evaluation measures. Model building process included data preprocessing, parameter optimization and attribute selection steps, which enhanced the overall performance. Additionally we propose a Moodle module that allows automatic extraction of data needed for educational data mining analysis and deploys models developed in this study.

Walking in Colors: Human Gait Recognition Using Kinect and CBIR

This article proposes a new method of recognizing human gait. The proposed method is based on the idea that the problem of human gait recognition can be transformed from a spatio-temporal problem into the spatial domain, specifically the 2D image domain. This is done by representing a sample of a human gait as a still image. By doing so, all the recorded information is kept while enabling the use of proven content-based image retrieval (CBIR) techniques for recognition. The proposed method uses Microsoft Kinect human-computer interaction technology for data acquisition. To prove the validity of the proposed approach, the authors conducted a study with 50 participants.

Motivational aspects of different learning contexts: “My mom won't let me play this game...”

Learning motivation should describe mechanisms that direct toward the learning goals, initiate learning activity and hold ones learning ability on a level that enables person to attain new information and more complex knowledge. Educational games are emerging as a new form of learning that should improve students desire for knowledge. Idea that educational games can be used as an effective teaching tool is what inspires our work in this field. In our study we attempted to explore the connection between motivational effects and application of educational game design as a learning tool. Additionally, we took into consideration effects of this approach on improving final exam results. Our results indicate that designing computer programs can raise enough curiosity and can be seen as a relevant learning tool for students.

Visualisation of student learning model in serious games

Game-based learning environment requires concrete real-time analytical tool.We propose a new tool for visualisation of student learning model during gameplay session.Tool can be used by educators and by students to track the game progress.Evaluation of the proposed approach was done through an empirical study.Initial quantitative results and recorded opinions of the participants speak in favour of the proposed approach. Application of serious games in distance learning can raise quality of education and student satisfaction on a higher level. However, when student learns through game, his focus is moved from learning domain to different context of the game. This actually enables to achieve fun and learn at the same time. But this approach also makes harder for educators to track and analyse students learning progress during game session, which is crucial in order to provide immediate feedback and to help students reach established learning goals. Such a specific learning environment requires concrete real-time analytical tool that will adequately match the dynamic game environment. This paper proposes a new tool for visualisation of student learning model during gameplay session. Tool can be used by educators and by students to track the game progress. Using this tool educators are provided with real-time tracking of students learning and it enables them to react and influence the overall learning process. Evaluation of the proposed approach was done through an empirical study, conducted on educators group monitoring an educational game session, using the combination of traditional analytic tool and the newly proposed visualisation approach. Initial quantitative results and recorded opinions of the participants speak in favour of the proposed approach and justify further investment in development of this specific learning analytics method.

Adventure Game Learning Platform

Educational games display great potential as an active form of knowledge transfer. This research field is young, but some patterns in educational game development can be recognized. In this paper, the authors present a new approach to educational game development that overcomes some downsides of more traditional systems. The paper provides the opportunity to create an educational adventure game by using specialized software tool as well as integrating knowledge in that specific game instance. As a result of that process, game definition is created as a form of XML document. On the other side, a web-based interpreter is used to present the adventure game to user in runtime. XML format provides us with platform independency. By use of this tool, the educator gains the ability to create an educational game without programming knowledge, and to reuse some previously created knowledge.

Real-time learning analytics in educational games

Learning analytics is a research area that targets the problem of tracking and evaluating students learning progress. In case of educational games, traditional analytic tools can prove insufficient. Electronic games are dynamic, packed with action and learning is integral part of gameplay. Such a specific learning environment requires a specific real-time analytical tool that will adequately match the dynamic game environment. This paper presents a new form of specific visualization tool for educators to track students learning progress in real-time, while in gameplay session. The tool is based on the specially designed students learning model. Same tool can be used by students to track the game progress. Use of this tool provides educators with real-time tracking of students learning and enables them to react and influence the overall learning process.

New gait recognition method using Kinect stick figure and CBIR

This paper presents a new approach in human gait recognition. We use new Human Interaction Device Microsoft Kinect for acquisition of data from human walk. Data retrieved is then used to create a still image that will represent one sequence of human walk. Finally, Content Based Image Retrieval technologies are used for image comparison in order to complete the recognition process. Evaluation study is conducted in order to prove the concept and it provided some promising results.

Effectiveness of Game-Based Learning: Influence of Cognitive Style

Today students have grown up using devices like computers, mobile phones, and video consoles for almost any activity; from studies and work to entertainment or communication. Motivating them with traditional teaching methods such as lectures and written materials becomes more difficult daily. That is why digital games are becoming more and more considered to have a promising role in education process. We decided to conduct a study among university students. Purpose of that study was to try to find some empirical evidence to support the claim that educational games can be used as an effective form of teaching. We also invested an effort to measure effects of different teaching approaches with the respect of individual differences in cognitive styles. Initial results provide a good argument for use of educational games in teaching. In addition, we reported some influence of cognitive style on effectiveness of using educational games.

Cloud based metalearning system for predictive modeling of biomedical data.

Rapid growth and storage of biomedical data enabled many opportunities for predictive modeling and improvement of healthcare processes. On the other side analysis of such large amounts of data is a difficult and computationally intensive task for most existing data mining algorithms. This problem is addressed by proposing a cloud based system that integrates metalearning framework for ranking and selection of best predictive algorithms for data at hand and open source big data technologies for analysis of biomedical data.

Learning objects in educational games

In this paper we will focus on the problem of using learning objects (LO) in educational games. The purpose of this paper is to propose a model that will attempt to establish the balance between knowledge integration into game on one side, and its reusability on the other. Our model driven approach is relying on use of LOs as constructing pieces of knowledge resources which are specialised for educational game design purpose. Presented models contribute to methodology of educational games development in a way that they embrace principles of learning and knowledge management early in design process. We demonstrated applicability of our models in design case study, where we developed an educational game editor where educators can easily define new educational game utilising existing knowledge, assessment and multimedia from repository.