Hidden data recovery using reservoir computing: Adaptive network model and experimental brain signals.

The problem of hidden data recovery is crucial in various scientific and technological fields, particularly in neurophysiology, where experimental data can often be incomplete or corrupted. We investigate the application of reservoir computing (RC) to recover hidden data from both model Kuramoto network system and real neurophysiological signals (EEG). Using an adaptive network of Kuramoto phase oscillators, we generated and analyzed macroscopic signals to understand the efficiency of RC in hidden signal recovery compared to linear regression (LR). Our findings indicate that RC significantly outperforms LR, especially in scenarios with reduced signal information. Furthermore, when applied to real EEG data, RC achieved more accurate signal reconstruction than traditional spline interpolation methods. These results underscore RC's potential for enhancing data recovery in neurophysiological studies, offering a robust solution to improve data integrity and reliability, which is essential for accurate scientific analysis and interpretation.

Toward interpretability of machine learning methods for the classification of patients with major depressive disorder based on functional network measures.

We address the interpretability of the machine learning algorithm in the context of the relevant problem of discriminating between patients with major depressive disorder (MDD) and healthy controls using functional networks derived from resting-state functional magnetic resonance imaging data. We applied linear discriminant analysis (LDA) to the data from 35 MDD patients and 50 healthy controls to discriminate between the two groups utilizing functional networks' global measures as the features. We proposed the combined approach for feature selection based on statistical methods and the wrapper-type algorithm. This approach revealed that the groups are indistinguishable in the univariate feature space but become distinguishable in a three-dimensional feature space formed by the identified most important features: mean node strength, clustering coefficient, and the number of edges. LDA achieves the highest accuracy when considering the network with all connections or only the strongest ones. Our approach allowed us to analyze the separability of classes in the multidimensional feature space, which is critical for interpreting the results of machine learning models. We demonstrated that the parametric planes of the control and MDD groups rotate in the feature space with increasing the thresholding parameter and that their intersection increases with approaching the threshold of 0.45, for which classification accuracy is minimal. Overall, the combined approach for feature selection provides an effective and interpretable scenario for discriminating between MDD patients and healthy controls using measures of functional connectivity networks. This approach can be applied to other machine learning tasks to achieve high accuracy while ensuring the interpretability of the results.

Topology switching during window thresholding fMRI-based functional networks of patients with major depressive disorder: Consensus network approach.

We present a novel method for analyzing brain functional networks using functional magnetic resonance imaging data, which involves utilizing consensus networks. In this study, we compare our approach to a standard group-based method for patients diagnosed with major depressive disorder (MDD) and a healthy control group, taking into account different levels of connectivity. Our findings demonstrate that the consensus network approach uncovers distinct characteristics in network measures and degree distributions when considering connection strengths. In the healthy control group, as connection strengths increase, we observe a transition in the network topology from a combination of scale-free and random topologies to a small-world topology. Conversely, the MDD group exhibits uncertainty in weak connections, while strong connections display small-world properties. In contrast, the group-based approach does not exhibit significant differences in behavior between the two groups. However, it does indicate a transition in topology from a scale-free-like structure to a combination of small-world and scale-free topologies. The use of the consensus network approach also holds immense potential for the classification of MDD patients, as it unveils substantial distinctions between the two groups.

Transcranial Magnetic Stimulation of the Dorsolateral Prefrontal Cortex Increases Posterior Theta Rhythm and Reduces Latency of Motor Imagery.

Experiments show activation of the left dorsolateral prefrontal cortex (DLPFC) in motor imagery (MI) tasks, but its functional role requires further investigation. Here, we address this issue by applying repetitive transcranial magnetic stimulation (rTMS) to the left DLPFC and evaluating its effect on brain activity and the latency of MI response. This is a randomized, sham-controlled EEG study. Participants were randomly assigned to receive sham (15 subjects) or real high-frequency rTMS (15 subjects). We performed EEG sensor-level, source-level, and connectivity analyses to evaluate the rTMS effects. We revealed that excitatory stimulation of the left DLPFC increases theta-band power in the right precuneus (PrecuneusR) via the functional connectivity between them. The precuneus theta-band power negatively correlates with the latency of the MI response, so the rTMS speeds up the responses in 50% of participants. We suppose that posterior theta-band power reflects attention modulation of sensory processing; therefore, high power may indicate attentive processing and cause faster responses.

Forecasting macroscopic dynamics in adaptive Kuramoto network using reservoir computing.

Forecasting a system's behavior is an essential task encountering the complex systems theory. Machine learning offers supervised algorithms, e.g., recurrent neural networks and reservoir computers that predict the behavior of model systems whose states consist of multidimensional time series. In real life, we often have limited information about the behavior of complex systems. The brightest example is the brain neural network described by the electroencephalogram. Forecasting the behavior of these systems is a more challenging task but provides a potential for real-life application. Here, we trained reservoir computer to predict the macroscopic signal produced by the network of phase oscillators. The Lyapunov analysis revealed the chaotic nature of the signal and reservoir computer failed to forecast it. Augmenting the feature space using Takkens' theorem improved the quality of forecasting. RC achieved the best prediction score when the number of signals coincided with the embedding dimension estimated via the nearest false neighbors method. We found that short-time prediction required a large number of features, while long-time prediction utilizes a limited number of features. These results refer to the bias-variance trade-off, an important concept in machine learning.

Central pattern generator based on self-sustained oscillator coupled to a chain of oscillatory circuits.

We have proposed and studied both numerically and experimentally a multistable system based on a self-sustained Van der Pol oscillator coupled to passive oscillatory circuits. The number of passive oscillators determines the number of multistable oscillatory regimes coexisting in the proposed system. It is shown that our system can be used in robotics applications as a simple model for a central pattern generator (CPG). In this case, the amplitude and phase relations between the active and passive oscillators control a gait, which can be adjusted by changing the system control parameters. Variation of the active oscillator's natural frequency leads to hard switching between the regimes characterized by different phase shifts between the oscillators. In contrast, the external forcing can change the frequency and amplitudes of oscillations, preserving the phase shifts. Therefore, the frequency of the external signal can serve as a control parameter of the model regime and realize a feedback in the proposed CPG depending on the environmental conditions. In particular, it allows one to switch the regime and change the velocity of the robot's gate and tune the gait to the environment. We have also shown that the studied oscillatory regimes in the proposed system are robust and not affected by external noise or fluctuations of the system parameters. Moreover, using the proposed scheme, we simulated the type of bipedal locomotion, including walking and running.

Age-Related Changes in Functional Connectivity during the Sensorimotor Integration Detected by Artificial Neural Network.

Large-scale functional connectivity is an important indicator of the brain's normal functioning. The abnormalities in the connectivity pattern can be used as a diagnostic tool to detect various neurological disorders. The present paper describes the functional connectivity assessment based on artificial intelligence to reveal age-related changes in neural response in a simple motor execution task. Twenty subjects of two age groups performed repetitive motor tasks on command, while the whole-scalp EEG was recorded. We applied the model based on the feed-forward multilayer perceptron to detect functional relationships between five groups of sensors located over the frontal, parietal, left, right, and middle motor cortex. Functional dependence was evaluated with the predicted and original time series coefficient of determination. Then, we applied statistical analysis to highlight the significant features of the functional connectivity network assessed by our model. Our findings revealed the connectivity pattern is consistent with modern ideas of the healthy aging effect on neural activation. Elderly adults demonstrate a pronounced activation of the whole-brain theta-band network and decreased activation of frontal-parietal and motor areas of the mu-band. Between-subject analysis revealed a strengthening of inter-areal task-relevant links in elderly adults. These findings can be interpreted as an increased cognitive demand in elderly adults to perform simple motor tasks with the dominant hand, induced by age-related working memory decline.

Sensor-Level Wavelet Analysis Reveals EEG Biomarkers of Perceptual Decision-Making.

Perceptual decision-making requires transforming sensory information into decisions. An ambiguity of sensory input affects perceptual decisions inducing specific time-frequency patterns on EEG (electroencephalogram) signals. This paper uses a wavelet-based method to analyze how ambiguity affects EEG features during a perceptual decision-making task. We observe that parietal and temporal beta-band wavelet power monotonically increases throughout the perceptual process. Ambiguity induces high frontal beta-band power at 0.3-0.6 s post-stimulus onset. It may reflect the increasing reliance on the top-down mechanisms to facilitate accumulating decision-relevant sensory features. Finally, this study analyzes the perceptual process using mixed within-trial and within-subject design. First, we found significant percept-related changes in each subject and then test their significance at the group level. Thus, observed beta-band biomarkers are pronounced in single EEG trials and may serve as control commands for brain-computer interface (BCI).

Monitoring the Cortical Activity of Children and Adults during Cognitive Task Completion.

In this paper, we used an EEG system to monitor and analyze the cortical activity of children and adults at a sensor level during cognitive tasks in the form of a Schulte table. This complex cognitive task simultaneously involves several cognitive processes and systems: visual search, working memory, and mental arithmetic. We revealed that adults found numbers on average two times faster than children in the beginning. However, this difference diminished at the end of table completion to 1.8 times. In children, the EEG analysis revealed high parietal alpha-band power at the end of the task. This indicates the shift from procedural strategy to less demanding fact-retrieval. In adults, the frontal beta-band power increased at the end of the task. It reflects enhanced reliance on the top-down mechanisms, cognitive control, or attentional modulation rather than a change in arithmetic strategy. Finally, the alpha-band power of adults exceeded one of the children in the left hemisphere, providing potential evidence for the fact-retrieval strategy. Since the completion of the Schulte table involves a whole set of elementary cognitive functions, the obtained results were essential for developing passive brain-computer interfaces for monitoring and adjusting a human state in the process of learning and solving cognitive tasks of various types.

Slow-wave activity preceding the onset of 10-15-Hz sleep spindles and 5-9-Hz oscillations in electroencephalograms in rats with and without absence seizures.

Cortico-thalamocortical networks generate sleep spindles and slow waves during non-rapid eye movement sleep, as well as paroxysmal spike-wave discharges (i.e. electroencephalogram manifestation of absence epilepsy) and 5-9-Hz oscillations in genetic rat models (i.e. pro-epileptic activity). Absence epilepsy is a disorder of the thalamocortical network. We tested a hypothesis that absence epilepsy associates with changes in the slow-wave activity before the onset of sleep spindles and pro-epileptic 5-9-Hz oscillations. The study was performed in the WAG/Rij genetic rat model of absence epilepsy and Wistar rats at the age of 9-12 months. Electroencephalograms were recorded with epidural electrodes from the anterior cortex. Sleep spindles (10-15 Hz), 5-9-Hz oscillations and their slow-wave (2-7 Hz) precursors were automatically detected and analysed using continuous wavelet transform. Subjects with electroencephalogram seizures (the "epileptic" phenotype) and without seizure activity (the "non-epileptic" phenotype) were identified in both strains. It was found that time-amplitude features of sleep spindles and 5-9-Hz oscillations were similar in both rat strains and in both phenotypes. Sleep spindles in "epileptic" rats were more often preceded by the slow-wave (~4 Hz) activity than in "non-epileptic" rats. The intrinsic frequency of slow-wave precursors of sleep spindles and 5-9-Hz oscillations in "epileptic" rats was 1-1.5 Hz higher than in "non-epileptic" rats. In general, our results indicated that absence epilepsy associated with: (a) the reinforcement of slow waves immediately prior to normal sleep spindles; and (b) weakening of amplitude growth in transition "slow wave → spindle/5-9-Hz oscillation".

Functional Near-Infrared Spectroscopy for the Classification of Motor-Related Brain Activity on the Sensor-Level.

Sensor-level human brain activity is studied during real and imaginary motor execution using functional near-infrared spectroscopy (fNIRS). Blood oxygenation and deoxygenation spatial dynamics exhibit pronounced hemispheric lateralization when performing motor tasks with the left and right hands. This fact allowed us to reveal biomarkers of hemodynamical response of the motor cortex on the motor execution, and use them for designing a sensing method for classification of the type of movement. The recognition accuracy of real movements is close to 100%, while the classification accuracy of imaginary movements is lower but quite high (at the level of 90%). The advantage of the proposed method is its ability to classify real and imaginary movements with sufficiently high efficiency without the need for recalculating parameters. The proposed system can serve as a sensor of motor activity to be used for neurorehabilitation after severe brain injuries, including traumas and strokes.

Age-Related Distinctions in EEG Signals during Execution of Motor Tasks Characterized in Terms of Long-Range Correlations.

The problem of revealing age-related distinctions in multichannel electroencephalograms (EEGs) during the execution of motor tasks in young and elderly adults is addressed herein. Based on the detrended fluctuation analysis (DFA), differences in long-range correlations are considered, emphasizing changes in the scaling exponent α. Stronger responses in elderly subjects are confirmed, including the range and rate of increase in α. Unlike elderly subjects, young adults demonstrated about 2.5 times more pronounced differences between motor task responses with the dominant and non-dominant hand. Knowledge of age-related changes in brain electrical activity is important for understanding consequences of healthy aging and distinguishing them from pathological changes associated with brain diseases. Besides diagnosing age-related effects, the potential of DFA can also be used in the field of brain-computer interfaces.

Percept-related EEG classification using machine learning approach and features of functional brain connectivity.

Machine learning is a promising approach for electroencephalographic (EEG) trials classification. Its efficiency is largely determined by the feature extraction and selection techniques reducing the dimensionality of input data. Dimensionality reduction is usually implemented via the mathematical approaches (e.g., principal component analysis, linear discriminant analysis, etc.) regardless of the origin of analyzed data. We hypothesize that since EEG features are determined by certain neurophysiological processes, they should have distinctive characteristics in spatiotemporal domain. If so, it is possible to specify the set of EEG principal features based on the prior knowledge about underlying neurophysiological processes. To test this hypothesis, we consider the classification of EEG trials related to the perception of ambiguous visual stimuli. We observe that EEG features, underlying the different ambiguous stimuli interpretations, are defined by the network properties of neuronal activity. Having analyzed functional neural interactions, we specify the brain area in which neural network architecture exhibits differences for different classes of EEG trials. We optimize the feedforward multilayer perceptron and develop a strategy for the training set selection to maximize the classification accuracy, being 85% when all channels are used. The revealed localization of the percept-related features allows about 95% accuracy, when the number of channels is reduced up to 90%. Obtained results can be used for classification of EEG trials associated with more complex cognitive tasks. Taking into account that cognitive activity is subserved by a distributed functional cortical network, its topological properties have to be considered when selecting optimal features for EEG trial classification.

Artificial neural network detects human uncertainty.

Artificial neural networks (ANNs) are known to be a powerful tool for data analysis. They are used in social science, robotics, and neurophysiology for solving tasks of classification, forecasting, pattern recognition, etc. In neuroscience, ANNs allow the recognition of specific forms of brain activity from multichannel EEG or MEG data. This makes the ANN an efficient computational core for brain-machine systems. However, despite significant achievements of artificial intelligence in recognition and classification of well-reproducible patterns of neural activity, the use of ANNs for recognition and classification of patterns in neural networks still requires additional attention, especially in ambiguous situations. According to this, in this research, we demonstrate the efficiency of application of the ANN for classification of human MEG trials corresponding to the perception of bistable visual stimuli with different degrees of ambiguity. We show that along with classification of brain states associated with multistable image interpretations, in the case of significant ambiguity, the ANN can detect an uncertain state when the observer doubts about the image interpretation. With the obtained results, we describe the possible application of ANNs for detection of bistable brain activity associated with difficulties in the decision-making process.

Amplification through chaotic synchronization in spatially extended beam-plasma systems.

In this paper, we have studied the relationship between chaotic synchronization and microwave signal amplification in coupled beam-plasma systems. We have considered a 1D particle-in-cell numerical model of unidirectionally coupled beam-plasma oscillatory media being in the regime of electron pattern formation. We have shown the significant gain of microwave oscillation power in coupled beam-plasma media being in the different regimes of generation. The discovered effect has a close connection with the chaotic synchronization phenomenon, so we have observed that amplification appears after the onset of the complete time scale synchronization regime in the analyzed coupled spatially extended systems. We have also provided the numerical study of physical processes in the chain of beam-plasma systems leading to the chaotic synchronization and the amplification of microwave oscillations power, respectively.

Self-organized bistability on globally coupled higher-order networks.

Self-organized bistability (SOB) stands as a critical behavior for the systems delicately adjusting themselves to the brink of bistability, characterized by a first-order transition. Its essence lies in the inherent ability of the system to undergo enduring shifts between the coexisting states, achieved through the self-regulation of a controlling parameter. Recently, SOB has been established in a scale-free network as a recurrent transition to a short-living state of global synchronization. Here, we embark on a theoretical exploration that extends the boundaries of the SOB concept on a higher-order network (implicitly embedded microscopically within a simplicial complex) while considering the limitations imposed by coupling constraints. By applying Ott-Antonsen dimensionality reduction in the thermodynamic limit to the higher-order network, we derive SOB requirements under coupling limits that are in good agreement with numerical simulations on systems of finite size. We use continuous synchronization diagrams and statistical data from spontaneous synchronized events to demonstrate the crucial role SOB plays in initiating and terminating temporary synchronized events. We show that under weak-coupling consumption, these spontaneous occurrences closely resemble the statistical traits of the epileptic brain functioning.

Intermittency of intermittencies.

A phenomenon of intermittency of intermittencies is discovered in the temporal behavior of two coupled complex systems. We observe for the first time the coexistence of two types of intermittent behavior taking place simultaneously near the boundary of the synchronization regime of coupled chaotic oscillators. This phenomenon is found both in the numerical and physiological experiments. The laws for both the distribution and mean length of laminar phases versus the control parameter values are analytically deduced. A very good agreement between the theoretical results and simulation is shown.

Loss of neuron network coherence induced by virus-infected astrocytes: a model study.

Coherent activations of brain neuron networks underlie many physiological functions associated with various behavioral states. These synchronous fluctuations in the electrical activity of the brain are also referred to as brain rhythms. At the cellular level, rhythmicity can be induced by various mechanisms of intrinsic oscillations in neurons or the network circulation of excitation between synaptically coupled neurons. One specific mechanism concerns the activity of brain astrocytes that accompany neurons and can coherently modulate synaptic contacts of neighboring neurons, synchronizing their activity. Recent studies have shown that coronavirus infection (Covid-19), which enters the central nervous system and infects astrocytes, can cause various metabolic disorders. Specifically, Covid-19 can depress the synthesis of astrocytic glutamate and gamma-aminobutyric acid. It is also known that in the post-Covid state, patients may suffer from symptoms of anxiety and impaired cognitive functions. We propose a mathematical model of a spiking neuron network accompanied by astrocytes capable of generating quasi-synchronous rhythmic bursting discharges. The model predicts that if the release of glutamate is depressed, normal burst rhythmicity will suffer dramatically. Interestingly, in some cases, the failure of network coherence may be intermittent, with intervals of normal rhythmicity, or the synchronization can disappear.

Analysis of Publication Activity and Research Trends in the Field of AI Medical Applications: Network Approach.

Artificial intelligence (AI) has revolutionized numerous industries, including medicine. In recent years, the integration of AI into medical practices has shown great promise in enhancing the accuracy and efficiency of diagnosing diseases, predicting patient outcomes, and personalizing treatment plans. This paper aims at the exploration of the AI-based medicine research using network approach and analysis of existing trends based on PubMed. Our findings are based on the results of PubMed search queries and analysis of the number of papers obtained by the different search queries. Our goal is to explore how are the AI-based methods used in healthcare research, which approaches and techniques are the most popular, and to discuss the potential reasoning behind the obtained results. Using analysis of the co-occurrence network constructed using VOSviewer software, we detected the main clusters of interest in AI-based healthcare research. Then, we proceeded with the thorough analysis of publication activity in various categories of medical AI research, including research on different AI-based methods applied to different types of medical data. We analyzed the results of query processing in the PubMed database over the past 5 years obtained via a specifically designed strategy for generating search queries based on the thorough selection of keywords from different categories of interest. We provide a comprehensive analysis of existing applications of AI-based methods to medical data of different modalities, including the context of various medical fields and specific diseases that carry the greatest danger to the human population.