Faculty of Biology and Biotechnology

Publications

• Book

  Alshanskaia E., Martynova O.

  2023 Fifth International Conference Neurotechnologies and Neurointerfaces (CNN) 18-20 Sept. 2023

   Cognitive and emotional load in the course of increasing the complexity of tasks leads to the activation of various parts of the autonomic nervous system (ANS) and can be accompanied by an increase in the efficiency of problem solving. An increase in cognitive load under the condition of high motivation is a stress factor and is expressed in a different reaction of the sympathetic and parasympathetic links in response to the load. This study explored the ANS reactions by measuring the pupil size of 61 healthy sub-clinical volunteers in response to the gradually increasing complexity of tasks. The experiment included 3 blocks of a combined visual search and 1-back task with six levels of difficulty. K-mean clustering method was used for the analysis. An increase in the complexity of the task from the first to the sixth level led to different dynamics of the pupil size in the three clustered groups. In one group, an intense high switchability and an active reaction with a large amplitude of changes were visible, in the second group the dynamics of changes was minimal, and a third intermediate group was also identified. Our results highlight individual differences in the reaction of the sympathetic and parasympathetic branches of ANS under cognitive workload depending on biometric and psychometric parameters. 

  IEEE, 2023.

• Article

  Tyshetskaya A., Vartanov S., Olga Kalachikova.

  From banking and telephony to media: The case of Russian digital ecosystems

  This article examines media resources within Russian digital ecosystems (RDESs) for which the media industry has never been a core business and which are now actively expanding their presence in this area: Sber, MTS, and T-Technologies (T-Bank). It discusses how each of the analyzed non-media companies has transformed into a digital ecosystem in recent years, not least through the development of their own or partner media resources. It also shows the differences between the media resources within the analyzed DESs and the social media functions performed by the media resources within these ecosystems. 

  World of Media. Journal of Russian Media and Journalism Studies. 2026. No. 1. P. 5-29.

• Book chapter

  Klenitskiy A., Fatkulin A., Denisova D. et al.

  Encode Me If You Can: Learning Universal User Representations via Event Sequence Autoencoding

  Building universal user representations that capture the essential aspects of user behavior is a crucial task for modern machine learning systems. In real-world applications, a user’s historical interactions often serve as the foundation for solving a wide range of predictive tasks, such as churn prediction, recommendations, or lifetime value estimation. Using a task-independent user representation that is effective across all such tasks can reduce the need for task-specific feature engineering and model retraining, leading to more scalable and efficient machine learning pipelines. The goal of the RecSys Challenge 2025 by Synerise was to develop such Universal Behavioral Profiles from logs of past user behavior, which included various types of events such as product purchases, page views, and search queries.

  We propose a method that transforms the entire user interaction history into a single chronological sequence and trains a GRU-based autoencoder to reconstruct this sequence from a fixed-size vector. If the model can accurately reconstruct the sequence, the latent vector is expected to capture the key behavioral patterns. In addition to this core model, we explored several alternative methods for generating user embeddings and combined them by concatenating their output vectors into a unified representation. This ensemble strategy further improved generalization across diverse downstream tasks and helped our team, ai_lab_recsys, achieve second place in the RecSys Challenge 2025.

  In bk.: RecSysChallenge '25: Proceedings of the Recommender Systems Challenge 2025. Association for Computing Machinery (ACM), 2025. P. 26-30.

• Working paper

  Kochetkova E., Sysoeva O., Martynova O. et al.

  Novelty, category and orientation tuning for printed characters: A magnetoencephalography study with fast periodic visual stimulation

  Letter recognition is assumed to involve several levels of analysis, including coarse tuning for category and novelty and more fine tuning, related to letter orientation. We employed an oddball fast periodic visual stimulation (FPVS) paradigm with magnetoencephalography (Elekta VectorView, 306 sensors) to study neural discrimination responses in the source space. Using contrasts between native letters and foreign letters, digits, or inverted native letters, we aimed to isolate the neural responses to visual novelty, category, and orientation during character analysis. The study was conducted with a cohort of 25 adults. The response topography demonstrated bilateral organization, including language-related brain regions as ventral occipitotemporal cortex, inferior parietal cortex and middle temporal areas. Comparing conditions, we revealed right lateralized parietal clusters, associated with novelty tuning, and left lateralized occipitotemporal clusters exhibiting higher activity for letters among digits discrimination, supporting the role of this area in letter processing. No distinct spatial patterns specific to orientation tuning were observed in comparison to novelty and category tuning. We proposed that expertise-dependent orientation-specific tuning mechanisms may operate within an embedded, spatially overlapping with coarse tuning neural framework, characterized by special spatiotemporal patterns.

  2025.11.29.691313. biorxiv, 2025