NeuroNet and NeuroEducation One of the key NTI markets is NeuroNet - a market for human-machine communications based on advanced developments in neurotechnology and increasing the productivity of human-machine systems and the performance of mental and thought processes. NeuroEducation services and products are developing in such segments as distance learning, massive open online courses (MOOCs), blended learning, as well as innovative models of additional education. Modern MOOC platforms allow the collection of complete records of students' online course activity on the Internet, which makes it possible to more closely study student behavior while mastering the course than was previously possible. Students with different motivations for learning MOOCs have very different learning behaviors, and online learning may also differ from the traditional learning process. Therefore, there is a clear need to understand user behavior in MOOCs and, more importantly, to develop effective mechanisms for increased participation in both learning and social interaction. The development of online platforms and other educational services determines the new potential of big data produced by participants in such courses and poses a new range of tasks for researchers, which are mainly focused on two aspects:
|
A student’s behavior model is a set of features (patterns) that can be extracted by analyzing the student’s behavior with educational content - videos, electronic documents (text data), chats between students on the portal, etc.
We studied the key patterns of MOOC students that influence the effectiveness of the educational process, and also developed a model for predicting final results based on Bayesian probabilistic inference networks.
Key patterns include: student activity on forums (the number of questions to forum participants regarding the course content was taken into account), video viewing time (the number of stops in the video lecture was taken into account), the presence of certificates of completion of other online courses, gender, age, etc.
During the exam, broadcasting and recording are carried out from a webcam or desktop, and violations are automatically monitored. The student's face is photographed, and the student is authenticated. Throughout the exam, a continuous verification of the person’s identity on the computer is carried out. This process is based on methods for automatic face detection, keyboard signature registration, and the application and pre-training of Bayesian networks. After completing the exam, an assessment of the degree of confidence in the exam results is made as a percentage.