About Me

I am a machine learning researcher with over a decade of experience developing AI-driven solutions in healthcare, neurotechnology, and biomedical engineering. My expertise spans deep learning, neural signal processing, and large-scale data analytics, with a proven record of translating research into real-world impact—including patented brain–computer interface (BCI) rehabilitation systems.

I have led multidisciplinary teams, mentored graduate students and engineers, and built strong collaborations across academia, industry, and clinical partners to advance the frontiers of AI in neuroscience and healthcare.

Core Expertise

• Machine Learning & AI: Deep learning (CNNs, RNNs, Transformers), classical algorithms (SVM, Random Forest, clustering), advanced time-series modeling, and feature engineering for EEG/ECG data.
• Programming & Tools: Expert in Python (NumPy, pandas, scikit-learn, TensorFlow, PyTorch, MNE), MATLAB, C/C++; proficient with Git, Linux, and cloud-based development environments.
• Data Science: Comprehensive experience in data preprocessing, statistical analysis, data visualization (Matplotlib, Seaborn), scalable data pipelines, and SQL/database integration.
• Domain Expertise: Brain–computer interfaces (BCIs), biomedical signal processing, neural engineering, healthcare analytics, and human–robot interaction.

Experience

Associate Professor, Robotics & Machine Learning
Nazarbayev University, Astana, Kazakhstan
2015 – Present

• Lead a multidisciplinary research lab advancing AI applications in neurotechnology and healthcare; mentor graduate students and engineers in EEG-based BCI, assistive robotics, and data analytics.
• Designed and deployed scalable deep learning models (CNN, LSTM, Transformer) for neural signal decoding, achieving state-of-the-art results in cognitive and motor intent recognition.
• Secured and managed competitive research grants focused on AI-driven epilepsy diagnostics and rehabilitation, overseeing projects from conception to clinical validation.
• Collaborated with clinicians and engineers to develop and validate BCI-powered assistive devices, successfully translating research prototypes into real-world healthcare solutions.

NIH Postdoctoral Research Fellow, Electrical & Computer Engineering
University of Houston, Houston, TX, USA
2014 – 2015

• Conducted NIH-funded research on brain–machine interfaces, pioneering advanced signal processing and neural network algorithms for decoding cognitive states from EEG data.
• Investigated the role of the mirror-neuron system in infant motor learning through analysis of non-invasive neural recordings.
• Collaborated with neuroscientists and clinicians at Texas Medical Center to address complex challenges in neurorehabilitation.

Research Scientist, Neurology Department
Samsung Medical Center (Sungkyunkwan University), Seoul, South Korea
2013 – 2014

• Engineered advanced ML techniques for ECoG/EEG analysis to identify epileptogenic zones for surgical planning.
• Collaborated on presurgical evaluations for treatment-resistant epilepsy, enhancing patient treatment via data-driven insights.
• Co-invented an EEG-driven rehabilitation training system (US Patent #9081890).

Research Scientist, BCI R&D
Daegu Gyeongbuk Institute of Science & Technology (DGIST), Daegu, South Korea
2010 – 2013

• Led R&D on advanced BCI systems and neuroprosthetics; optimized signal-processing pipelines to improve response time and accuracy.
• Developed EEG-driven assistive device prototypes; fostered international collaborations and published key findings.
• Co-invented a brain-signal-driven rehabilitation system combining EEG intent detection with functional electrical stimulation.

Education

• Ph.D. in Electronic Engineering
  Specialization: Machine Learning & Neural Signal Processing
  Yeungnam University, South Korea (2006–2010)

• M.Sc. in Electronic Engineering
  Yeungnam University, South Korea (2004–2006)

• B.Sc. in Information Technology
  Tashkent University of Information Technologies, Uzbekistan (2000–2004)

Certifications & Affiliations

• IEEE Senior Member – Honored for significant professional achievements in electrical and computer engineering
• US Patent 9,081,890 – Co-inventor of an EEG-based rehabilitation training system for neurotechnology applications
• Open-Source Maintainer – Lead developer of EEG-PyTorch and P3Net BCI deep learning toolkits on GitHub
• YouTube Educator (2.9K+ subscribers): Creator of educational content on machine learning, brain–computer interfaces, microcontrollers, and Python for neural data analysis
  YouTube Playlists

Selected Publications

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