Development of machine learning and deep learning models (both supervised and unsupervised) for various tasks on multivariate biological time series (EEG, EMG, ECG, IMU, SpO2, etc.), including anomaly detection, classification, and diagnostic support.
Development of machine learning and deep learning-based methods for data quality analysis, automatic labeling, and artifact removal.
Development of methods for extracting latent components that explain inter-individual and intra-individual variability under normal and pathological conditions.
Development of methods for brain-computer interfaces (BCI) based on different paradigms (motor imagery, ERP, etc.).
Extraction of standard features for computational neuroscience, including power analysis, time-domain and frequency-domain features, cortico-muscular coherence measures, cross-frequency coupling measures, and multimodal analysis from heterogeneous datasets.
Development of open-source software (see section "Open source code").