This paper focuses on enhancing touch-typing skills through state-of-the-art deep learning technologies. It has been demonstrated that writing posture can be assessed using integrated keyboard detection and hand pose estimation in real-time browser environments. A unique dataset was created for training the object detection model to recognize individual keyboards. The object detection models were trained using various architectures and then assessed for both inference time and accuracy. In addition, a hand pose estimation was implemented to precisely recognize 21 knuckle points of the hand and compute their exact positions. In order to implement object detection and hand pose estimation, a stream transmission of the keyboard and hand scene is required. For this purpose, server-client communication via a QR code connection is implemented to transfer the stream between two mobile devices. Based on these deep learning technologies, a mobile web app was developed that offers 170 learning courses for touch-typing training. With the help of the Typing Learning Academy prototype, a study was conducted as part of this paper to evaluate the usability and utility of the learning app. This research demonstrates the potential for enhancing the development of writing skills through touch typing through the utilization of advanced deep learning technologies.
Based on the currently developing trend of so called Massive Open Online Courses it is obvious that learning videos are more in use nowadays. This is some kind of comeback because due to the maxim “TV is easy, book is hard” [1][2] videos were used rarely for teaching. A further reason for this rare usage is that it is widely known that a key factor for human learning is a mechanism called selective attention [3][4]. This suggests that managing this attention is from high importance. Such a management could be achieved by providing different forms of interaction and communication in all directions. It has been shown that interaction and communication is crucial for the learning process [6]. Because of these remarks this research study introduces an algorithm which schedules interactions in learning videos and live broadcastings. The algorithm is implemented by a web application and it is based on the concept of a state machine. Finally, the evaluation of the algorithm points out that it is generally working after the improvement of some drawbacks regarding the distribution of interactions in the video.
Due to the fact that students’ attention is the most crucial resource in a high-quality course it is from high importance to control and analyze it. This could be done by using the interaction and the communication because they are known as valuable influencing factors of the attention. In this publication we introduce a web-based information system which implements an attention-profiling algorithm for learning-videos as well as live-broadcastings of lectures. For that different methods of interaction are offered and analyzed. The evaluation points out that the attention profiling algorithm delivers realistic values.