About
I am a research scientist and academic in applied AI and neural engineering with 15+ years of experience building machine learning systems for clinical neural signals and time-series data. My work spans EEG, intracranial EEG (iEEG), MEG, and fNIRS, across both research and clinical environments.
My research focuses on deep learning architectures for neural time-series — transformers, contrastive self-supervised learning, and domain adaptation — with applications in epilepsy, motor rehabilitation, and cognitive neuroscience. I have direct clinical experience working alongside neurosurgeons and neurologists on intracranial EEG data from drug-resistant epilepsy patients, and over a decade of experience building real-time brain-computer interface systems, including NIH-funded clinical trials in stroke rehabilitation.
Research Areas
Clinical iEEG & Epilepsy
AI-driven analysis of intracranial EEG for epilepsy: HFO detection and classification, epileptogenic zone localization, seizure detection from long-term recordings, and presurgical decision support.
Real-Time BCI & Neurorehabilitation
Closed-loop EEG-based brain-computer interfaces for motor rehabilitation in stroke and spinal cord injury populations, from signal acquisition through real-time decoding and device control.
Applied AI & Deep Learning for Neural Time-Series
Transformer architectures, contrastive self-supervised pretraining, domain adaptation across heterogeneous patient cohorts, and large language models for automated clinical report generation from neural signal outputs.
Multimodal Neural Signal Processing
Signal processing across scalp EEG, iEEG, MEG, fNIRS, and EMG. Time-frequency analysis, ICA, source localization, HFO detection, and large-scale analysis on HPC and GPU infrastructure.
Selected Publications
2026: Qamar, W.U.R., Abibullaev, B. Multi-Scale EEG Feature Decoding with Swin Transformers for Subject-Independent Motor Imagery BCIs. Scientific Reports, 16(1):2503. [Link]
2025: Qamar, W.U.R., Lee, M., Abibullaev, B. Deep Learning in Intracranial EEG for Seizure Detection: Advances, Challenges, and Clinical Applications. Frontiers in Neuroscience, 19:1677898. [Link]
2024: Keutayeva, A., Abibullaev, B. Compact Convolutional Transformer for Subject-Independent Motor Imagery EEG-Based BCIs. Scientific Reports, 14(1):25775. [Link]
2024: Keutayeva, A., Abibullaev, B. Data Constraints and Performance Optimization for Transformer-Based Models in EEG-Based BCIs: A Survey. IEEE Access, 12:62628–62647. [Link]
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 ERPs Using a Small Number of Training Subjects. IEEE Transactions on Human-Machine 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]
Professional Activities
- IEEE Senior Member (2020)
- Associate Editor, IEEE Access (2020 to present)
Associate Editor, PeerJ Computer Science (2022 to present)
Contact
I welcome collaboration on applied AI, neural engineering, and clinical signal processing.
Feel free to reach out.