
With the increasing popularity of e-learning in higher education institutions, there is a need to develop data analytics tools to analyze e-learning data, student learning behavior and student performance. In recent years, there has been growing interest in educational data mining, which can provide useful insights into student learning behavior, providing holistic analysis. This paper presents an online data analytics tool called Studentlyzer, which applies data mining to analyze student data. It can cluster student datasets using K-means clustering, and visualize the graphical results through a web browser. Two real-world student e-learning datasets, the Open University Learning Analytics Dataset (OULAD) and Educational Processing Mining (EPM) dataset, were used to demonstrate Studentlyzer’s usefulness. The results provide valuable insights about students. In general, Studentlyzer can help identify students who are similar (e.g., with similar study behavior) and provide useful information about student performance and student behavior (e.g., their correlation).
With the advent of cloud computing, there is a potential need for the interconnection of clouds (i.e., Intercloud). Intercloud seeks to connect heterogeneous clouds together to form a network of clouds. As an extension to our previous work, this paper gives an overview of an Intercloud system with a focus on the Intercloud Gateways and Intercloud communications protocol. To analyze the performance of the Intercloud systems, we have conducted experiments under different settings and scenarios. Furthermore, we have evaluated the Intercloud system to support a mobile Intercloud application.