This work has been carried out to support the investigation of the electroencephalogram (EEG) Fourier power spectral, coherence, and detrended fluctuation characteristics during performance of mental tasks. To this aim, the presented dataset contains International 10/20 system EEG recordings from subjects under mental cognitive workload (performing mental serial subtraction) and the corresponding reference background EEGs. Based on the subtraction task performance (number of subtractions and accuracy of the result), the subjects were divided into good counters and bad counters (for whom the mental task required excessive efforts). The data was recorded from 36 healthy volunteers of matched age, all of whom are students of Educational and Scientific Centre “Institute of Biology and Medicine”, National Taras Shevchenko University of Kyiv (Ukraine); the recordings are available through Physiobank platform. The dataset can be used by the neuroscience research community studying brain dynamics during cognitive workload.

In the study of human cognitive activity using electroencephalogram (EEG), the brain dynamics parameters and characteristics play a crucial role. They allow to investigate the changes in functionality depending on the environment and task performance process, and also to access the intensity of the brain activity in various locations of the cortex and its dependencies. Usually, the dynamics of activation of different brain areas during the cognitive tasks are being studied by spectral analysis based on power spectral density (PSD) estimation, and coherence analysis, which are de facto standard tools in quantitative characterization of brain activity. PSD and coherence reflect the strength of oscillations and similarity of the emergence of these oscillations in the brain, respectively, while the concept of stability of brain activity over time is not well defined and less formalized. We propose to employ the detrended fluctuation analysis (DFA) as a measure of the EEG persistence over time, and use the DFA scaling exponent as its quantitative characteristics. We applied DFA to the study of the changes in activation in brain dynamics during mental calculations and united it with PSD and coherence estimation. In the experiment, EEGs during resting state and mental serial subtraction from 36 subjects were recorded and analyzed in four frequency ranges: θ1 (4.1–5.8 Hz), θ2 (5.9–7.4 Hz), β1 (13–19.9 Hz), and β2 (20–25 Hz). PSD maps to access the intensity of cortex activation and coherence to quantify the connections between different brain areas were calculated, the distribution of DFA scaling exponent over the head surface was exploited to measure the time characteristics of the dynamics of brain activity. Obtained arrangements of DFA scaling exponent suggest that normal functioning of the brain is characterized by long-term temporal correlations in the cortex. Topographical distribution of the DFA scaling exponent was comparable for θ and β frequency bands, demonstrating the largest values of DFA scaling exponent during cognitive activation. The study shows that the long-term temporal correlations evaluated by DFA can be of great interest for diagnosis of the variety of brain dysfunctions of different etiology in the future.

Deep learning is a relatively new computational technique for the description of the musculoskeletal dynamics. The experimental relationships of muscle geometry in different postures are the high-dimensional spatial transformations that can be approximated by relatively simple functions, which opens the opportunity for machine learning (ML) applications. In this study, we challenged general ML algorithms with the problem of approximating the posture-dependent moment arm and muscle length relationships of the human arm and hand muscles. We used two types of algorithms, light gradient boosting machine (LGB) and fully connected artificial neural network (ANN) solving the wrapping kinematics of 33 muscles spanning up to six degrees of freedom (DOF) each for the arm and hand model with 18 DOFs. The input-output training and testing datasets, where joint angles were the input and the muscle length and moment arms were the output, were generated by our previous phenomenological model based on the autogenerated polynomial structures. Both models achieved a similar level of errors: ANN model errors were 0.08 ± 0.05% for muscle lengths and 0.53 ± 0.29% for moment arms, and LGB model made similar errors—0.18 ± 0.06% and 0.13 ± 0.07%, respectively. LGB model reached the training goal with only 10³samples, while ANN required 10⁶samples; however, LGB models were about 39 times slower than ANN models in the evaluation. The sufficient performance of developed models demonstrates the future applicability of ML for musculoskeletal transformations in a variety of applications, such as in advanced powered prosthetics.

Objective : In this work we explore the potential of combining standard time and frequency domain indexes with novel information measures, to characterize pre- and post-ictal heart rate variability (HRV) in epileptic children, with the aim of differentiating focal and generalized epilepsy regarding the autonomic control mechanisms. Approach : We analyze short-term HRV in 37 children suffering from generalized or focal epilepsy, monitored 10 s, 300 s, 600 s and 1800 s both before and after seizure episodes. Nine indexes are computed in time (mean, standard deviation of normal-to-normal intervals, root mean square of the successive differences (RMSSD)), frequency (low-to-high frequency power ratio LF/HF, normalized LF and HF power) and information (entropy, conditional entropy and self-entropy) domains. Focal and generalized epilepsy are compared through statistical analysis of the indexes and using linear discriminant analysis (LDA). Main results : In children with focal epilepsy, early post-ictal phase is characterized by significant tachycardia, depressed HRV, increased LF power and LF/HF, and decreased complexity, progressively recovered across time windows after the episodes. Children with generalized seizures instead show significant tachycardia, lower RMSSD, higher LF power and LF/HF ratio before the seizure. These different behaviors are exploited by LDA analysis to separate focal and generalized epilepsy up to an accuracy of 75%. Results suggest a shift of the sympatho-vagal balance towards sympathetic dominance and vagal withdrawal, noticeable just after the termination of seizure episodes and then reverted in focal epilepsy, and persistent during inter-ictal and pre-ictal periods in generalized epilepsy. Significance : Our analysis helps in elucidating the pathophysiology of inter-ictal HRV autonomic control and the differential diagnosis of generalized and focal epilepsy. These findings may have clinical relevance since altered sympatho-vagal control can be related to a higher danger of morbidity and mortality, may reduce thresholds for life-threatening arrhythmias, and could be a biomarker of risk for sudden unexpected death in epilepsy.

Objective: This article shows the interest in deep learning techniques to detect motor imagery (MI) from raw electroencephalographic (EEG) signals when a functional electrical stimulation is added or not. Impacts of electrode montages and bandwidth are also reported. The perspective of this work is to improve the detection of intraoperative awareness during general anesthesia. Methods: Various architectures of EEGNet were investigated to optimize MI detection. They have been compared to the state-of-the-art classifiers in Brain-Computer Interfaces (based on Riemannian geometry, linear discriminant analysis), and other deep learning architectures (deep convolution network, shallow convolutional network). EEG data were measured from 22 participants performing motor imagery with and without median nerve stimulation. Results: The proposed architecture of EEGNet reaches the best classification accuracy (83.2%) and false-positive rate (FPR 19.0%) for a setup with only six electrodes over the motor cortex and frontal lobe and for an extended 4-38 Hz EEG frequency range while the subject is being stimulated via a median nerve. Configurations with a larger number of electrodes result in higher accuracy (94.5%) and FPR (6.1%) for 128 electrodes (and respectively 88.0% and 12.9% for 13 electrodes). Conclusion: The present work demonstrates that using an extended EEG frequency band and a modified EEGNet deep neural network increases the accuracy of MI detection when used with as few as 6 electrodes which include frontal channels. Significance: The proposed method contributes to the development of Brain-Computer Interface systems based on MI detection from EEG.

Understanding brain reactions to facial expressions can help in explaining emotion-processing and memory mechanisms. The purpose of this research is to examine the dynamics of electrical brain activity caused by visual emotional stimuli. The focus is on detecting changes in cognitive mechanisms produced by negative, positive, and neutral expressions on human faces. Three methods were used to study brain reactions: power spectral density, detrending moving average (DMA), and coherence analysis. Using electroencephalogram (EEG) recordings from 48 subjects while presenting facial image stimuli from the International Affective Picture System, the topographic representation of the evoked responses was acquired and evaluated to disclose the specific EEG-based activity patterns in the cortex. The theta and beta systems are two key cognitive systems of the brain that are activated differently on the basis of gender. The obtained results also demonstrate that the DMA method can provide information about the cortical networks’ functioning stability, so it can be coupled with more prevalent methods of EEG analysis.