About

My research focuses on machine learning systems that generalize reliably under distribution shift, subject variability, and real-world deployment constraints — with applications in neural signal processing, brain-computer interfaces, and time-series analysis.

Neural and physiological signals (EEG, intracranial EEG) serve as a demanding testbed for this work. Insights from this setting transfer directly to medical monitoring, wearable devices, and industrial time-series systems.

Research Areas

Invariant Representation Learning — methods that remain stable across subjects, acquisition sites, and deployment environments by explicitly modeling heterogeneity rather than assuming it away.

Deep Learning for Neural & Time-Series Data — transformer and CNN architectures for EEG/iEEG analysis, event-related decoding, and multimodal physiological modeling, with evaluation protocols that reflect real deployment constraints.

Selected Publications

• 2023: Abibullaev, B., Keutayeva, A., & Zollanvari, A. Deep Learning in BCIs: A Comprehensive Review of Transformer Models, Advantages, Challenges, and Applications. IEEE Access. [Link]
• 2022: Abibullaev, B., Kunanbayev, K., & Zollanvari, A. Subject-Independent Classification of P300 Event-Related Potentials Using a Small Number of Training Subjects. IEEE Transactions on Human-Machine Systems. [Link]
• 2021: Abibullaev, B. & Zollanvari, A. A Systematic Deep Learning Model Selection for P300-Based Brain-Computer Interfaces. IEEE Transactions on Systems, Man, and Cybernetics: Systems. [Link]
• 2019: Abibullaev, B. & Zollanvari, A. Learning Discriminative Spatiospectral Features of ERPs for Accurate Brain-Computer Interfaces. IEEE Journal of Biomedical and Health Informatics. [Link]

Contact

I welcome collaboration on robust ML, temporal modeling, and deployable biomedical AI. Feel free to reach out.