Development of an applied intelligent system based on neurophysiological data to support decision-making on the organization of the educational process

In modern science, one of the urgent problems is the search for ways to improve the effectiveness of learning. The study of neurophysiological patterns in the formation of individual variations of cognitive activity of students at different stages of ontogenesis is an important condition for developing innovative technologies to improve the quality of the educational process. The article presents the development of an applied intelligent system that allows considering individual differences in cognitive activity of students and schoolchildren using neuroscience technologies.The use of teaching methods and techniques is largely due to individual typological features, which can be analyzed using neurobiological indicators. Express analysis of the individual neurophysiological profile characterizes behavioral aspects of cognitive activity. With the help of an intelligent system, a set of neuro-physiological indicators of groups of students was processed to identify the influence of learning conditions on these indicators. Based on the test data sets, the system assigns learners to pairs, groups, or project teams and recommends learning tasks based on the learners’ neurophysiological profiles.When developing the system, the basic principles of the development and use of artificial intelligence are taken into account, such as transparency of the program’s choice of the process of forming pairs and groups of learners and the criteria for selecting tasks, so the so-called weak artificial intelligence — machine learning with a teacher is used.