Projects

Zuzana Rošťáková

Project selection:

National projects

CARE-BCI – Cooperative AI-enhanced BCI-HMD rehabilitation for post-stroke recovery
Kooperatívna AI BCI-HMD rehabilitácia pre pacientov po cievnej mozgovej príhode
Program: SRDA
Duration: 1.9.2026 – 31.8.2030
Project leader: Ing. Mgr. Rosipal Roman, DrSc.
Annotation: This project aims to advance post-stroke neurorehabilitation through the development of an artificial intelligence (AI)-enhanced, collaborative brain–computer interface (BCI) system integrated with immersive head-mounted display (HMD)–based virtual reality (VR). AI serves as a central enabling component, supporting adaptive neural decoding, cognitive-state monitoring, and data-driven optimization of rehabilitation protocols. A key focus is on the creation ofcooperative, shared-action rehabilitation environments, in which the patient and therapist jointly perform the same task in real time. This combination of AI-driven adaptation and shared-action cooperation moves beyond isolated task execution toward socially interactive, coordinated motor rehabilitation with high ecological validity.The approach extends the state of the art by employing AI for adaptive neural decoding, cognitive-state monitoring, and longitudinal meta-analysis of rehabilitation trajectories. Active BCI components use personalized models to decode motor imagery under inter- and intra-subject variability, while passive BCI continuously monitors cognitive workload, mentalfatigue, and engagement. An exploratory component investigates the feasibility of an AI-assisted therapeutic agent capable of partially supporting therapist actions within immersive, cooperative VR environments, while preserving safety, interpretability, and clinical oversight.The ambition is to establish a scalable and personalized neurorehabilitation framework that enhances therapeutic efficacy, strengthens patient–therapist interaction through shared-action VR tasks, and reduces therapist workload. By integrating active and passive BCI, cooperative VR, and explainable AI within a single coherent system, the project aims to generatenew scientific insights into rehabilitation dynamics and provide a clinically relevant pathway toward accessible, data-driven post-stroke rehabilitation in clinical and home-based settings.
EDABSS – EEG data analysis by blind source separation methods
Analýza EEG signálu pomocou metód hľadania skrytých zdrojov
Program: Plán obnovy EÚ
Duration: 1.9.2024 – 31.8.2026
Project leader: Mgr. Rošťáková Zuzana, PhD.
Annotation: Blind source separation (BSS) approaches are unsupervised machine learning methods focused on the detection of hidden, directly unobservable (latent) structure of real-world data. They play a crucial role in image processing, medical imaging, and music. The proposed project focuses mainly on human electroencephalogram (EEG), for which BSS is beneficial when detecting the narrowband brain oscillations representing brain processes either in health or disease. Two-dimensional BSS methods like principal or independent component analysis are easily applicable and understandable for a broader medical and neurophysiological community. However, the estimated latent component properties are usually incompatible with the real electrophysiological signal character. Consequently, they miss their neurophysiological interpretation. Tensor decomposition is a complex but more flexible mathematical procedure that allows adapting the model structure and constraints to the solution to mimic real-world signal characteristics. The proposed project focuses on tensor decomposition as a tool for i) EEG preprocessing, artefact detection and removal, ii) EEG latent structure analysis using a nonnegative tensor decomposition with block structure allowing to model various relationships between latent components, and iii) post-decomposition analysis of latent component dynamic properties. Obtaining comprehensive information about EEG latent structure and developing novel, user-friendly algorithms is crucial for better understanding brain processes and new methods for treating neurophysiological diseases and disorders.