Course Description: The possibility of transferring the brain signal to a computer device introduces many communication and control applications in both research and clinical domains. Within past several decades a new emerging technique, called brain-computer interface (BCI), has opened new channels to better understanding the brain functions, and facilitated techniques that can be used for the diagnosis and treatment of a wide range of neurological impairments. This course presents novel interfaces between brain and computer devices and explains the existing challenges in this domain. Through this course, different components of a BCI system including signal acquisition, signal preprocessing, feature extraction, and feature translation will be discussed. Conceptual and mathematical techniques to decode and encode the neural signals including spatial and temporal filtering, independent component analysis (ICA), principal component analysis (PCA), common spatial pattern (CSP), wavelet transform, mutual information (MI), Bayes classifier, and linear discriminant analysis (LDA) will be covered. Practical experiments on brain signal recording, the design of appropriate BCI experimental setup, and the implementable neural signal processing and classification approaches will also be covered.

Textbook: “Brain-Computer Interfaces” by Jonathan R. Wolpaw and Elizabeth Winter Wolpaw and “Analyzing Neural Time Series Data” by Mike X. Cohen are required as your textbook. The book by Dr. Wolpaw gives necessary BCI concepts and introduces the prominent challenges in this domain. The book by Dr. Cohen explains the most common techniques used in analyzing neural time series. This book also gives useful Matlab exercises which helps the reader get familiar with practical analysis of neural data.

Recommended Materials: As additional resources “Independent Component Analysis” by Aapo Hyvarinen, Juha Karhunen, and Erkki Oja is recommended. This book covers the basic concepts behind the random process and mathematical preliminaries which are necessary for various types of brain signal processing techniques. “Rhythms of the Brain” by György Buzsáki is also recommended as another additional resource. This book is beneficial for a better understanding the brain mechanisms at both structural and functional levels.

Course Prerequisites: 
{calculus (MTH 243 or equivalent), probability and statistics (MTH 451 or STA 409 or ISE 411 or equivalent), signal processing (ELE 314 or equivalent), and Matlab programming} or permission of instructor. Familiarity with topics in ELE 501, 506, and 509 is highly recommended.

Assessment and Grading Policy: 
Class projects & assignments (40%)
Exam (30%)
Final project, term paper, and presentation (30% in total: final project and term paper (25%), final presentation (5%))