Using animations and visualizations can help students to better understand different concepts in a shorter time than using textual or graphical representations of the same concepts. However, prior researches showed that not every animation and visualization is educationally effective. In the first part of this paper, we summarize, what features an animation should have to be successfully used in education. We briefly mention Mayer's principles of multimedia learning and the importance of interactivity in educational animations. In the next part of the paper, we describe how an interactive web-bases 2D animation can be created. In the past, there were various technologies to create web animations, like Microsoft Silverlight or Adobe Flash. However, after the introduction of HTML5, Silverlight and Flash were gradually replaced by JavaScript, which is nowadays the most used technology for creating web-based interactive content. Even though, that creating interactive animations using the HTML5 and JavaScript languages needs good programming knowledge, there are several external libraries available on the internet to help the developers' work. In the main part of this article, we compare two of these libraries, the Konva and Fabric JS. These two libraries are nowadays probably the most popular libraries for creating 2D interactive web-based animations. To compare these libraries in practice, we created the same educational web-based animation, a simple river crossing puzzle, with both of these libraries. According to our research, both of these libraries can be successfully used for creating educational web-based 2D animations. In the last part of this paper, we summarize the pros and cons of the reviewed JavaScript libraries and we draw our conclusions.

Information about the paper titled "TEACHING AND LEARNING COMPUTER PROGRAMMING BY CREATING 2D GAMES IN UNITY" at IATED Digital Library

Information about the paper titled "CREATION OF 3D MODELS OF REAL OBJECTS IN THE TEACHING OF COMPUTER SCIENCE" at IATED Digital Library

Information about the paper titled "ONLINE GAMES TO INTRODUCING COMPUTER PROGRAMMING TO CHILDREN" at IATED Digital Library

In the last decade, we have observed the usage of artificial intelligence algorithms and machine learning models in industry, education, healthcare, entertainment, and several other areas. In this paper, we focus on using machine learning algorithms in the loan approval process of financial institutions. First, we briefly review some prior research papers that dealt with loan approval predictions using machine learning models. Next, we analyze the loan approval prediction dataset we downloaded from Kaggle, which was used in this paper to compare several machine learning classification models. During this analysis, we observed that credit scores and loan terms are the attributes that probably most affect the result. Next, we divided the dataset into a training set (80%) and a test set (20%). We trained 27 various machine learning models in MATLAB. Three models were optimized with Bayesian optimization to find the best hyperparameters with minimum error. We used 5-fold cross-validation for the validations to prevent overfitting during the training. In the following step, we used the test set on trained models to measure the models’ accuracy on unseen data. The result showed that the best accuracy both on validation and test data, more than 98%, was reached with neural networks and ensemble classification models.