arXiv subjects

Sergey V. Stasenko

Publications and source records attributed to Sergey V. Stasenko.

10 recordsLinked to original sources

arXiv2025

Using machine learning methods to predict cognitive age from psychophysiological tests

This study introduces a novel method for predicting cognitive age using psychophysiological tests. To determine cognitive age, subjects were asked to complete a series of psychological tests measuring various cognitive functions, including reaction time and cognitive conflict, short-term memory, verbal functions, and color and spatial perception. Based on the tests completed, the average completion time, proportion of correct answers, average absolute delta of the color campimetry test, number of guessed words in the M\"unsterberg matrix, and other parameters were calculated for each subject. The obtained characteristics of the subjects were preprocessed and used to train a machine learning algorithm implementing a regression task for predicting a person's cognitive age. These findings contribute to the field of remote screening using mobile devices for human health for diagnosing and monitoring cognitive aging.

q-bio.NC↗

arXiv2025

Error correction in multiclass image classification of facial emotion on unbalanced samples

This paper considers the problem of error correction in multi-class classification of face images on unbalanced samples. The study is based on the analysis of a data frame containing images labeled by seven different emotional states of people of different ages. Particular attention is paid to the problem of class imbalance, in which some emotions significantly prevail over others. To solve the classification problem, a neural network model based on LSTM with an attention mechanism focusing on key areas of the face that are informative for emotion recognition is used. As part of the experiments, the model is trained on all possible configurations of subsets of six classes with subsequent error correction for the seventh class, excluded at the training stage. The results show that correction is possible for all classes, although the degree of success varies: some classes are better restored, others are worse. In addition, on the test sample, when correcting some classes, an increase in key quality metrics for small classes was recorded, which indicates the promise of the proposed approach in solving applied problems related to the search for rare events, for example, in anti-fraud systems. Thus, the proposed method can be effectively applied in facial expression analysis systems and in tasks requiring stable classification under skewed class distribution.

cs.CV↗

arXiv2025

Computational Advances in Taste Perception: From Ion Channels to Neural Coding

Recent advances in computational neuroscience demand models that balance biophysical realism with scalability. We present a hybrid neuron model combining the biophysical fidelity of Hodgkin-Huxley (HH) dynamics for taste receptor cells with the computational efficiency of Izhikevich spiking neurons for large-network simulations. Our framework incorporates biomorphic taste cell models, featuring modality-specific receptor dynamics (T1R/T2R, ENaC, PKD) and Goldman-Hodgkin-Katz (GHK)-driven ion currents to accurately simulate gustatory transduction. Synaptic interactions are modeled via glutamate release kinetics with alpha-function profiles, AMPA receptor trafficking regulated by phosphorylation, and spike-timing-dependent plasticity (STDP) to enforce temporal coding. At the network level, we optimize multiscale learning, leveraging both temporal spike synchrony (van Rossum metrics) and combinatorial population coding (rank-order patterns). This approach bridges single-cell biophysics with ensemble-level computation, enabling efficient simulation of gustatory pathways while retaining biological fidelity.

q-bio.NC↗

arXiv2024

Preservation of dissipativity in dimensionality reduction

Systems with predetermined Lyapunov functions play an important role in many areas of applied mathematics, physics and engineering: dynamic optimization methods (objective functions and their modifications), machine learning (loss functions), thermodynamics and kinetics (free energy and other thermodynamic potentials), adaptive control (various objective functions, stabilization quality criteria and other Lyapunov functions). Dimensionality reduction is one of the main challenges in the modern era of big data and big models. Dimensionality reduction for systems with Lyapunov functions requires it preserving dissipativity: the reduced system must also have a Lyapunov function, which is expected to be a restriction of the original Lyapunov function on the manifold of the reduced motion. An additional complexity of the problem is that the equations of motion themselves are often unknown in detail in advance and must be determined in the course of the study, while the Lyapunov function could be determined based on incomplete data. Therefore, the projection problem arises: for a given Lyapunov function, find a field of projectors such that the reduction of it any dissipative system is again a dissipative system. In this paper, we present an explicit construction of such projectors and prove their uniqueness. We have also taken the first step beyond the approximation by manifolds. This is required in many applications. For this purpose, we introduce the concept of monotone trees and find a projection of dissipative systems onto monotone trees that preserves dissipativity.

math.DS↗

arXiv2024

Firing rate model for brain rhythms controlled by astrocytes

We propose a new mean-field model of brain rhythms governed by astrocytes. This theoretical framework describes how astrocytes can regulate neuronal activity and contribute to the generation of brain rhythms. The model describes at the population level the interactions between two large groups of excitatory and inhibitory neurons. The excitatory population is governed by astrocytes via a so-called tripartite synapse. This approach allows us to describe how the interactions between different groups of neurons and astrocytes can give rise to various patterns of synchronized activity and transitions between them. Using methods of nonlinear analysis we show that astrocytic modulation can lead to a change in the period and amplitude of oscillations in the populations of neurons.

q-bio.NC↗

arXiv2023

Astrocyte control bursting mode of spiking neuron network with memristor-implemented plasticity

A mathematical model of a spiking neuron network accompanied by astrocytes is considered. The network is composed of excitatory and inhibitory neurons with synaptic connections supplied by a memristor-based model of plasticity. Another mechanism for changing the synaptic connections involves astrocytic regulations using the concept of tripartite synapses. In the absence of memristor-based plasticity, the connections between these neurons drive the network dynamics into a burst mode, as observed in many experimental neurobiological studies when investigating living networks in neuronal cultures. The memristive plasticity implementing synaptic plasticity in inhibitory synapses results in a shift in network dynamics towards an asynchronous mode. Next,it is found that accounting for astrocytic regulation in glutamatergic excitatory synapses enable the restoration of 'normal' burst dynamics. The conditions and parameters of such astrocytic regulation's impact on burst dynamics established.

q-bio.NC↗

arXiv2022

Domain Adaptation Principal Component Analysis: base linear method for learning with out-of-distribution data

Domain adaptation is a popular paradigm in modern machine learning which aims at tackling the problem of divergence (or shift) between the labeled training and validation datasets (source domain) and a potentially large unlabeled dataset (target domain). The task is to embed both datasets red into a common space in which the source dataset is informative for training while the divergence between source and target is minimized. The most popular domain adaptation solutions are based on training neural networks that combine classification and adversarial learning modules, frequently making them both data-hungry and difficult to train. We present a method called Domain Adaptation Principal Component Analysis (DAPCA) that identifies a linear reduced data representation useful for solving the domain adaptation task. DAPCA algorithm introduces positive and negative weights between pairs of data points, and generalizes the supervised extension of principal component analysis. DAPCA is an iterative algorithm that solves a simple quadratic optimization problem at each iteration. The convergence of the algorithm is guaranteed, and the number of iterations is small in practice. We validate the suggested algorithm on previously proposed benchmarks for solving the domain adaptation task. We also show the benefit of using DAPCA in analyzing the single-cell omics datasets in biomedical applications. Overall, DAPCA can serve as a practical preprocessing step in many machine learning applications leading to reduced dataset representations, taking into account possible divergence between source and target domains.

cs.LG↗

arXiv2022

Dynamic image recognition in a spiking neuron network supplied by astrocytes

Mathematical model of spiking neuron network (SNN) supplied by astrocytes is investigated. The astrocytes are specific type of brain cells which are not electrically excitable but inducing chemical modulations of neuronal firing. We analyzed how the astrocytes influence on images encoded in the form of dynamic spiking pattern of the SNN. Serving at much slower time scale the astrocytic network interacting with the spiking neurons can remarkably enhance the image recognition quality. Spiking dynamics was affected by noise distorting the information image. We demonstrated that the activation of astrocyte can significantly suppress noise influence improving dynamic image representation by the SNN.

q-bio.NC↗

arXiv2022

Failure of neuron network coherence induced by SARS-CoV-2-infected astrocytes

Coherent activations of brain neuron networks underlay 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, the rhythmicity can be induced by various mechanisms of intrinsic oscillations in neurons or network circulation of excitation between synaptically coupled neurons. One of the specific mechanisms 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), entering the central nervous system and infecting astrocytes, causes various metabolic disorders. Specifically, Covid-19 can depress the synthesis of astrocytic glutamate and GABA. It is also known that in the postcovid state, patients may suffer from symptoms of anxiety and impaired cognitive functions, which may be a consequence of disturbed brain rhythms. We propose a mathematical model of a spiking neural network accompanied by astrocytes capable to generate quasi-synchronous rhythmic bursting discharges. The model predicts that if the astrocytes are infected, and the release of glutamate is depressed, then normal burst rhythmicity suffers dramatically. Interestingly, in some cases, the failure of network coherence may be intermittent with intervals of normal rhythmicity, or the synchronization can completely disappears.

q-bio.NC↗

arXiv2021

High-dimensional separability for one- and few-shot learning

This work is driven by a practical question: corrections of Artificial Intelligence (AI) errors. These corrections should be quick and non-iterative. To solve this problem without modification of a legacy AI system, we propose special `external' devices, correctors. Elementary correctors consist of two parts, a classifier that separates the situations with high risk of error from the situations in which the legacy AI system works well and a new decision for situations with potential errors. Input signals for the correctors can be the inputs of the legacy AI system, its internal signals, and outputs. If the intrinsic dimensionality of data is high enough then the classifiers for correction of small number of errors can be very simple. According to the blessing of dimensionality effects, even simple and robust Fisher's discriminants can be used for one-shot learning of AI correctors. Stochastic separation theorems provide the mathematical basis for this one-short learning. However, as the number of correctors needed grows, the cluster structure of data becomes important and a new family of stochastic separation theorems is required. We refuse the classical hypothesis of the regularity of the data distribution and assume that the data can have a fine-grained structure with many clusters and peaks in the probability density. New stochastic separation theorems for data with fine-grained structure are formulated and proved. The multi-correctors for granular data are proposed. The advantages of the multi-corrector technology were demonstrated by examples of correcting errors and learning new classes of objects by a deep convolutional neural network on the CIFAR-10 dataset. The key problems of the non-classical high-dimensional data analysis are reviewed together with the basic preprocessing steps including supervised, semi-supervised and domain adaptation Principal Component Analysis.

cs.LG↗