CS 680: Brain-Computer Interaction

Course Syllabus

Professor:	Erin Solovey
Email:	erin.solovey @ drexel.edu
Office:	University Crossings 108
Office Hours:	Please email me for an appointment!

Description

This course will explore the current state of brain sensing and its application to human-computer interaction research. We will read important research papers on relevant topics, including background on brain function, sensing technology, machine learning methods, and applications of brain-computer interfaces in various domains.

Coursework will involve reading and critiquing research papers each week, as well as leading 1-2 discussions of research papers. There will be a required project that you work on over the term, and the scope and focus of the project will vary, depending on the interests and backgrounds of the students in the class.

Goals and Objectives

This course aims for students to (1) obtain the background to conduct research in brain-computer interaction and human-computer interaction; (2) understand the literature in the field of brain sensing for human-computer interaction research; (2) understand the various tools used in brain sensing, with a focus on functional near-infrared spectroscopy (fNIRS) research at Drexel; (3) understand the steps required to use real-time brain sensing data as input to an interactive system; (4) understand the domains and contexts in which brain-computer interfaces may be effective; (5) understand the open questions and challenges in brain-computer interaction research today.

Students will practice research skills such as writing a technical paper, critically reading research papers, and giving a technical presentation.

Classes

Classes will consist of student presentations and discussions on recent research on brain sensing and human-computer interaction on various topics, including:

introduction to brain sensing in human-computer interaction
brain sensing devices (fNIRS, EEG, fMRI, etc.)
signal processing, feature selection, machine learning approaches for classifying brain data
direct control vs. passive BCI
BCI for disabled
what can we realistically measure?
experimental designs for exploring brain sensing for HCI
brain sensor data as input to interactive systems, as a user interface evaluation method, as neurofeedbeck, and many application domains (education, driving, video games, human-robot interaction, communication, control, human computation, etc.)
human values, ethics, privacy as it relates to BCI

Readings

There is no required textbook for this course; We will mainly be reading recent research articles.

Assignments

Assignments will focus on skills needed to conduct research in brain-computer interfaces and human-computer interaction. Each week, there will be 2-4 assigned papers to read. It is expected that students will read the papers and be prepared to discuss in class. To solidify understanding and for practice in critical reading, paper critiques will be required for several papers, which will be due 24 hours before class (Sundays at 6pm). In addition, students will lead the discussion of 2-4 papers throughout the semester.

Project

You'll be choosing a research project and writing a term paper. You'll turn in a draft of your project paper a few weeks before the end of the semester. Part of your project grade will be based on the quality of this draft. You'll then update your paper based on my feedback and that from your fellow students. As mentioned below, your course project will be worth 50% of your overall class grade. 55% of this grade will be on your final paper, 20% will be based on your draft, 10% will be based on your proposal, and 15% will be based on your in-class presentation. If there are two people on your project, you will be given a longer time for your presentation and each person should do half. I will describe this process in more detail, and how to go about finding a project.

Exams

There are no exams.

Grading

All aspects of this course are important for developing an understanding of and appreciation for brain-computer interaction. The grading breakdown will be as follows:

Project: 50%
Paper critiques: 10%
Class Participation: 10%
Review: 5%
Paper Presentations: 25%

Assignments turned in up to one day late incur a 50% penalty; assignments turned in more than one day late cannot be accepted and receive a score of 0.

Communication

The instructor will disseminate important announcements by email through the course mailing list, and also post these announcements on the course web site. Also, the web site contains a timeline with links to all information (lecture slides, assignments, etc.) relevant to the course.

Policies

Attendance for class is expected. If you cannot make it to class, email me beforehand so that it does not affect your class participation grade.
Academic honesty is essential. Cheating, academic misconduct, plagiarism, and fabrication of any submitted material, including both code and prose, are serious breaches of academic integrity and will be dealt with accordingly. Violations will result minimally in a grade of zero for the exam/assignment in question, and a report of the violation to Drexel administration; further penalties may also apply at the discretion of the instructor, department, and university. PLEASE NOTE: CCI now has a "Two strikes and you are out of CCI" policy. Please refer to the Department of Computer Science Academic Integrity Policy and the Drexel University Academic Integrity Policy for more information.