Instructor: Berdakh Abibullaev, Ph.D.
Office hours: Mon, Wed, Fri 14:00 — 16:00 and by appointment
Office location: 7e318
Email: [email protected]
TA: Zhenis Otarbay
Office hours: by appointment
Email: [email protected]
Brain-machine interface (BMI) systems are an emerging interdisciplinary field at the intersection of engineering, neuroscience, and medicine. They offer promising new perspectives on human-machine interaction by using brain activity. This course offers an introduction to the fundamentals of BMI technology, including its applications. We will cover invasive and non-invasive BMI systems allowing users to control user interfaces, prosthetic arms, wheelchairs, and robotic exoskeletons. Additionally, we will discuss other clinical applications of BMI technology, such as for patients with locked-in syndrome and its usefulness in restoring movement and mobility in severely paralyzed persons. We will also study non-clinical uses of BMI technology and conduct hands-on experiments/projects for applications such as security, alertness monitoring, entertainment, gaming, and education or human augmentation.
The course will be delivered through mixed lectures with case studies, discussions of research papers led by student groups, and in-class demonstrations of BMI systems using the systems available at NU. The lecture series will cover core topics related to neural signal processing and machine learning algorithms that convert EEG features into control commands. Python-related signal processing and machine-learning libraries will be used extensively.
Prerequisite(s): CSCI 501 – Software Principles and Practice (or equivalent); CSCI 501 – Software Principles and Practice (or equivalent) Recommended Preparation: Linear Algebra, Probability, Optimization, Numerical Python
Successful students will:
The course aims to equip students with the necessary know-how, experience, and skills to: