Adaptive Structure Strategy for Designing Nonparametric Models Based on Differential Neural Networks Using Functional Projection.

Differential neural networks (DiNNs) encounter a trade-off between the approximation quality and structural complexity. One promising approach to address this trade-off is incorporating dynamic complexity adjustment as an integral part of the learning process. Taking inspiration from the Fourier approximation theory, this study introduces a novel method for adapting the architecture of DiNNs, when they serve as nonparametric identifiers for dynamic systems with uncertain mathematical models. The structural adaptation process is executed through a recursive algorithm based on a modification structure strategy, which dynamically adjusts the number of neurons within the network's structure. By applying a projection operator to the set of neurons, this method identifies the most relevant sequence of sigmoidal functions, intending to minimize the mean square error in approximating the trajectories of uncertain systems. This simultaneous reduction in overall complexity enhances the quality of the approximations. Moreover, the proposed method can implement a coarse-to-fine approach, wherein selecting necessary neurons occurs in multiple steps. These steps are determined by an adaptive structure strategy that alters the topology of the DiNN. The resulting framework's effectiveness is demonstrated by evaluating the proposed identifier's performance in approximating the evolution of real-life data associated with the ocular response during controlled motions or virtual reality engagement. In both experimental cases, there was a noticeable improvement in the accuracy of eye motion approximation by the DiNN, thanks to the variable structure approximation basis determined by the adaptive structure strategy. Overall, this study presents a formal method to automatically determine a feasible DiNN topology.

Heart rate response to cognitive load as a marker of depression and increased anxiety.

Introduction: Understanding the interplay between cardiovascular parameters, cognitive stress induced by increasing load, and mental well-being is vital for the development of integrated health strategies today. By monitoring physiological signals like electrocardiogram (ECG) and photoplethysmogram (PPG) in real time, researchers can discover how cognitive tasks influence both cardiovascular and mental health. Cardiac biomarkers resulting from cognitive strain act as indicators of autonomic nervous system function, potentially reflecting conditions related to heart and mental health, including depression and anxiety. The purpose of this study is to investigate how cognitive load affects ECG and PPG measurements and whether these can signal early cardiovascular changes during depression and anxiety disorders. Methods: Ninety participants aged 18 to 45 years, ranging from symptom-free individuals to those with diverse psychological conditions, were assessed using psychological questionnaires and anamnesis. ECG and PPG monitoring were conducted as volunteers engaged in a cognitive 1-back task consisting of two separate blocks, each with six progressively challenging levels. The participants' responses were analyzed to correlate physiological and psychological data with cognitive stressors and outcomes. Results: The study confirmed a notable interdependence between anxiety and depression, and cardiovascular responses. Task accuracy decreased with increased task difficulty. A strong relationship between PPG-measured heart rate and markers of depression and trait anxiety was observed. Increasing task difficulty corresponded to an increase in heart rate, linked with elevated levels of depression and trait anxiety. A strong relationship between ECG-measured heart rate and anxiety attacks was observed. Increasing task difficulty corresponded to an increase in heart rate, linked with elevated levels of anxiety attacks, although this association decreased under more challenging conditions. Discussion: The findings underscore the predictive importance of ECG and PPG heart rate parameters in mental health assessment, particularly depression and anxiety under cognitive stress induced by increasing load. We discuss mechanisms of sympathetic activation explaining these differences. Our research outcomes have implications for clinical assessments and wearable device algorithms for more precise, personalized mental health diagnostics.

Is Frequency of Practice of Different Types of Physical Activity Associated with Health and a Healthy Lifestyle at Different Ages?

Physical activity (PA) has been shown to be related to physical and mental health. Yet there are few studies on how the frequency of PA relates to health and a healthy lifestyle. We aimed to investigate how the frequency of different PAs is associated with the following health indicators: body mass index (BMI), substance consumption, physical health, and mental health. We focused on three types of PA: (1) medium- to high-intensity aerobic exercise; (2) low- to medium-intensity relaxing exercise; and (3) outdoor leisure PA. A total of 9617 volunteers, aged 19 to 81, participated in the study. The relationships between the frequencies of the three types of PA and health-related and sociodemographic factors were analyzed using multinomial logistic regression. We found that women more frequently engaged in PA type 2, and men in types 1 and 3. A higher frequency of PA was associated with lower BMI and less or no smoking behavior; higher education (PAs 1 and 3); higher age (PAs 2 and 3); better physical health (PAs 1 and 3); and better mental health (PA 3). In conclusion, higher frequency of different PAs was significantly associated with better physical and mental health, less smoking, higher age, and a higher level of education.

What Differences Exist in Professional Ice Hockey Performance Using Virtual Reality (VR) Technology between Professional Hockey Players and Freestyle Wrestlers? (a Pilot Study).

There is little research on the study of specific characteristics that contribute to the faster adaptation of athletes during the transition from one sport to another. We used virtual reality (VR) to study the differences between professional ice hockey players and other sport professionals (freestyle wrestlers), who were novices in hockey in terms of motor responses and efficiency performance, on different levels of difficulty. In the VR environment, four levels of difficulty (four blocks) were simulated, depended on the speed of the puck and the distance to it (Bl1-60-80 km/h and 18 m; Bl2-60-100 km/h, distances 12 and 18 m; Bl3-speeds up to 170 km/h and 6, 12, and 18 m; Bl4-the pucks are presented in a series of two (in sequence with a 1 s interval)). The results of the study showed that the hockey professionals proved to have more stable movement patterns of the knee and hip joints. They also made fewer head movements as a response to stimuli during all runs (0.66 vs. 1.25, p = 0.043). Thus, working out on these parameters can contribute to the faster adaptation of wrestlers in developing professional ice hockey skills.

A Toolbox and Crowdsourcing Platform for Automatic Labeling of Independent Components in Electroencephalography.

Independent Component Analysis (ICA) is a conventional approach to exclude non-brain signals such as eye movements and muscle artifacts from electroencephalography (EEG). A rejection of independent components (ICs) is usually performed in semiautomatic mode and requires experts' involvement. As also revealed by our study, experts' opinions about the nature of a component often disagree, highlighting the need to develop a robust and sustainable automatic system for EEG ICs classification. The current article presents a toolbox and crowdsourcing platform for Automatic Labeling of Independent Components in Electroencephalography (ALICE) available via link http://alice.adase.org/. The ALICE toolbox aims to build a sustainable algorithm to remove artifacts and find specific patterns in EEG signals using ICA decomposition based on accumulated experts' knowledge. The difference from previous toolboxes is that the ALICE project will accumulate different benchmarks based on crowdsourced visual labeling of ICs collected from publicly available and in-house EEG recordings. The choice of labeling is based on the estimation of IC time-series, IC amplitude topography, and spectral power distribution. The platform allows supervised machine learning (ML) model training and re-training on available data subsamples for better performance in specific tasks (i.e., movement artifact detection in healthy or autistic children). Also, current research implements the novel strategy for consentient labeling of ICs by several experts. The provided baseline model could detect noisy IC and components related to the functional brain oscillations such as alpha and mu rhythm. The ALICE project implies the creation and constant replenishment of the IC database, which will improve ML algorithms for automatic labeling and extraction of non-brain signals from EEG. The toolbox and current dataset are open-source and freely available to the researcher community.

Individual Features in the Typology of the Nervous System and the Brain Activity Dynamics of Freestyle Wrestlers Exposed to a Strong Physical Activity (A Pilot Study).

Nowadays, knowledge of psychophysiological features, particularly on the nervous system's characteristics, is essential in the sporting context, particularly for freestyle wrestling. The study aimed to investigate the peculiarities of the wrestlers' nervous system-on the individual and electrophysiological levels in two functional states-in calm wakefulness and during intense physical fatigue. Psychological (Well-being, Activity, Mood; Spielberger-Hanin; Leonhard's questionnaires), as well as electrophysiological techniques (dynamics of the dominant and average frequencies of the main electroencephalogram (EEG) spectra-theta, alpha, low and high-frequency beta rhythms), were used in the study. It was shown that athletes were mainly characterized by the hyperthymic type of character accentuation and a low frequency of theta rhythm in a calm wakefulness state. After the acute physical load, wrestlers with high hyperthymia showed a moderate increase in theta, whereas other athletes showed a decrease in this parameter. Regardless of the level of hyperthymic accentuation, all wrestlers were characterized by an increase in the frequency of alpha rhythm after exercises in the left hemisphere. These results suggest the existence of a particular functional system in freestyle wrestlers, which allows the body's regulatory systems to be adapted for the effective implementation of sports activity.

Physical exercise speeds up motor timing.

THIS STUDY AIMED TO EXAMINE EFFECT OF PHYSICAL EXERCISE ON MOTOR TIMING: personal, maximum and "once per second" tapping. The acute effect was examined by comparing the baseline tapping with that after acute exercise in 9 amateur athletes, 8 elite synchronous swimmers and 9 elite biathletes. Then the baseline tapping was compared among athletes of different sports and professional levels (15 elite biathletes, 27 elite cross-country skiers, 15 elite synchronous swimmers and 9 amateur wrestlers) with a control group (44 non-athletes) not involved in regular exercise to examine the sport-specific or long-term effects. Maximum and "once per second" tapping speed increased after acute physical exercise and were also faster in elite athletes compared to controls during the baseline condition. However, personal tapping tempo was not affected by exercise. In addition, physical exercise had no effects on the variability of the intertap interval. The accuracy of "once per second" tapping differentiates controls and amateur wrestlers from elite synchronous swimmers and skiers suggesting sport-specific adaptations to play a role. It is concluded that acute physical exercise selectively speeds up motor timing but does not affect its variability and accuracy, and this speeding-up is suggested to transfer into a long-term effect in elite athletes.