Many approaches to automated epileptic seizure detection share a common challenge — the trade-off between recall and precision. This study aims to develop a novel approach for reducing false positive predictions in seizure detection tasks applied to real-world EEG recordings. We propose a multi-stage modeling framework, for which the novelty lies in combination of traditional machine learning outlier detection with state-of-the-art convolutional neural networks. Our dataset includes raw epileptic EEG data directly from the hospital. Continuous wavelet analysis is employed for EEG preprocessing and feature extraction. We evaluated the performance of the proposed two-stage algorithm, and it demonstrated a slight decrease in recall but a significant improvement in precision in comparison to machine-learning-only or neural-network-only algorithms. We hypothesize that this finding aligns well with our previous research and relates to the fundamental properties of epileptic EEG, including the extreme behavior of seizures. Finally, we propose a potential practical application of the developed approach within a clinical decision support system.

Neuroeducation seeks to implement knowledge about neural mechanisms of learning into educational practice and to understand the impact of learning itself. The crucial tasks in this field are to evaluate and to enhance cognitive abilities, that are used in monitoring educational performance, but also known to greatly impact learning process. Contemporary neuroscience achieved significant progress in measuring brain cognitive abilities through mental state assessment. Popular approach to this task based on brain-computer interface can be difficult to implement in the context of education, but general concept of neuroadaptation is still plausible. In this study, we propose open-loop neuroadaptive system for enhancing student’s cognitive abilities in learning. Assessment of cognitive abilities is based on the concept of executive functions. We design EEG study with special tests and use combined analysis of behavioral and brain activity to assess the level of development of cognitive abilities. Feedback in this system is implemented in the form of recommendations aimed to develop and enhance underdeveloped cognitive abilities and skills. Recommendations have form of various types of extracurricular activities and are based on extensive literature search. This is the system with open-loop adaptation, as it can assess cognitive abilities, provide feedback aimed to enhance these abilities and then after a period of time it can assess cognitive abilities again as a part of the next loop. We believe that developed neuroadaptive system has a potential to be used in educational institutes.

Extreme events are rare and sudden abnormal deviations of the system's behavior from a typical state. Statistical analysis reveals that if the time series contains extreme events, its distribution has a heavy tail. In dynamical systems, extreme events often occur due to developing instability preceded by noise amplification. Here, we apply this theory to analyze generalized epileptic seizures in the human brain. First, we demonstrate that the time series of electroencephalogram (EEG) spectral power in a frequency band of 1–5 Hz obeys a heavy-tailed distribution, confirming the presence of extreme events. Second, we report that noise on EEG signals gradually increases before the seizure onset. Thus, we hypothesize that generalized epileptic seizures in humans are the extreme events emerging from instability accompanied by preictal noise amplification similar to other dynamical systems.

The problem of insufficient cognitive development in schoolchildren can be solved through the organization of personalized extracurricular activities with the help of a recommendation service based on neuroscientific research and modern knowledge of brain function. The basis for compiling a personalized list of extracurricular activities is data obtained through neuroimaging technology in the process of testing the cognitive and personality characteristics of the student combined with information about their interests and preferences. Regular testing, conducted every three to six months, helps to determine the effectiveness of the chosen activities and to adjust the educational route. It is assumed that regular use of the recommendation service will stimulate the development of child’s cognitive functions, thus contributing to the improvement of his/her academic performance. The article presents the scheme and principles of the service as a whole, as well as its evaluation and recommendation modules. The possibilities of the recommendation service application in the educational process are defined. A description of the practical realization of the recommendation service is given. The proposed service can be useful for individual participants of the educational process: class teachers, methodologists, tutors, parents, and students. Teachers will be able to individualize the approach to each student using the service as an additional source of information about the structural and functional development of the child. For parents, the service will help to better understand the strengths and weaknesses of their children as well as to track the effectiveness of including a particular activity in their educational route. Students will have access to personalized recommendations for developing extracurricular activities.