The time students spend in a learning management system (LMS) is an important measurement in learning analytics (LA). One of the most common data sources is log files from LMS, which do not directly reveal the online time, the duration of which needs to be estimated. As this measurement has a great impact on the results of statistical models in LA, its estimation is crucial. In the literature, there are many strategies for estimating the duration, which do not represent the actual online time of the students. In this article, we combine LMS log files of our students with parallel screen recordings and automatically analyze for how long the LMS is present in the video. We visualize the results and show that common online time estimation strategies do not represent the online time for our students accurately. By using modified online time estimation methods, we find estimations that fit the data of our students better on an individual basis.
Logging mobile application usage on smartphones is limited to rather general system events unless one has access to the operating system's or applications' source code. In this paper, we present a method for analyzing mobile application usage in detail by generating log files based on mobile screen output. We are combining long-term log file analysis and short-term screen recording analysis by utilizing existing computer vision and machine learning methods. To validate the log results of our approach and implementation we collect 118 sample screen recordings of phone usage sessions and evaluate the resulting log file manually. Besides that, we explore the performance of our approach with different video quality parameters: frame rate and bit rate. We show that our method provides detailed data about application use and can work with low-quality video under certain circumstances.
Abstract. Controlling virtual characters in AR games for modern smartphones is even more challenging than controls for 'pure' VR games because the player has to keep the AR world in view. We propose six interaction concepts based on combinations of both physical and virtual buttons and sensor input and suggest an evaluation according to game experience criteria.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.