arXiv subjects

Petr V. Nazarov

Publications and source records attributed to Petr V. Nazarov.

5 recordsLinked to original sources

arXiv2026

Multimodal Digital Biomarker for Asthma: Complementary Roles of Vocal, Clinical and Demographic Factors

Asthma affects over 260 million people worldwide, yet diagnosis remains dependent on spirometry and specialist assessment, limiting accessibility in primary care and low-resource settings. Vocal biomarkers offer a promising non-invasive alternative, but prior studies have largely focused on acoustic features without integrating clinical context. We present a multimodal Mixture-of-Experts framework for asthma identification that adaptively combines acoustic embeddings from sustained vowel phonation and reading passage tasks with structured clinical and demographic data. The model was evaluated on a matched cohort of 1,218 self-reported asthma cases and healthy controls from the Colive Voice study. The multimodal model achieved an AUROC of 0.83 and Brier score of 0.18, outperforming unimodal approaches. Exploratory analysis of the gating mechanism in asthma cases showed that greater respiratory symptom burden was associated with increased weighting of reading-passage modality and reduced weighting of sustained-vowel phonation modality. These findings support the feasibility of voice-based identification of self-reported asthma; however, independent prospective validation remains necessary before clinical use.

eess.AS↗

arXiv2025

RodEpil: A Video Dataset of Laboratory Rodents for Seizure Detection and Benchmark Evaluation

We introduce a curated video dataset of laboratory rodents for automatic detection of convulsive events. The dataset contains short (10~s) top-down and side-view video clips of individual rodents, labeled at clip level as normal activity or seizure. It includes 10,101 negative samples and 2,952 positive samples collected from 19 subjects. We describe the data curation, annotation protocol and preprocessing pipeline, and report baseline experiments using a transformer-based video classifier (TimeSformer). Experiments employ five-fold cross-validation with strict subject-wise partitioning to prevent data leakage (no subject appears in more than one fold). Results show that the TimeSformer architecture enables discrimination between seizure and normal activity with an average F1-score of 97%. The dataset and baseline code are publicly released to support reproducible research on non-invasive, video-based monitoring in preclinical epilepsy research. RodEpil Dataset access - DOI: 10.5281/zenodo.17601357

cs.CV↗

arXiv2023

Glioma subtype classification from histopathological images using in-domain and out-of-domain transfer learning: An experimental study

We provide in this paper a comprehensive comparison of various transfer learning strategies and deep learning architectures for computer-aided classification of adult-type diffuse gliomas. We evaluate the generalizability of out-of-domain ImageNet representations for a target domain of histopathological images, and study the impact of in-domain adaptation using self-supervised and multi-task learning approaches for pretraining the models using the medium-to-large scale datasets of histopathological images. A semi-supervised learning approach is furthermore proposed, where the fine-tuned models are utilized to predict the labels of unannotated regions of the whole slide images (WSI). The models are subsequently retrained using the ground-truth labels and weak labels determined in the previous step, providing superior performance in comparison to standard in-domain transfer learning with balanced accuracy of 96.91% and F1-score 97.07%, and minimizing the pathologist's efforts for annotation. Finally, we provide a visualization tool working at WSI level which generates heatmaps that highlight tumor areas; thus, providing insights to pathologists concerning the most informative parts of the WSI.

eess.IV↗

arXiv2023

Stability of stochastic dynamic systems of a random structure with Markov switchings in the presence of concentration points

This article aims to investigate sufficient conditions for the stability of stochastic differential equations with a random structure, particularly in contexts involving the presence of concentration points. The proof of asymptotic stability leverages the use of Lyapunov functions, supplemented by additional constraints on the magnitudes of jumps and jump times, as well as the Markov property of the system solutions. The findings are elucidated with an example, demonstrating both stable and unstable conditions of the system.

math.PR↗

arXiv2022

Stabilization of stochastic dynamical systems of a random structure with Markov switches and Poisson perturbations

An optimal control for a dynamical system optimizes a certain objective function. Here we consider the construction of an optimal control for a stochastic dynamical system with a random structure, Poisson perturbations and random jumps, which makes the system stable in probability. Sufficient conditions of the stability in probability are obtained, using the second Lyapunov method, in which the construction of the corresponding functions plays an important role. Here we provide a solution to the problem of optimal stabilization in a general case. For a linear system with a quadratic quality function, we give a method of synthesis of optimal control based on the solution of Riccati equations. Finally, in an autonomous case, a system of differential equations was constructed to obtain unknown matrices that are used for the building of an optimal control. The method of a small parameter is justified for the algorithmic search of an optimal control. This approach brings a novel solution to the problem of optimal stabilization for a stochastic dynamical system with a random structure, Markov switches and Poisson perturbations.

math.OC↗