--

Affective Computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affect/emotion. Emotion is fundamental to human experience, influencing cognition, perception, and everyday tasks such as learning, communication, and even rational decision-making. However, while computers cannot detect, respond to, or simulate affect, they remain crippled in the ways that they can respond intelligently and efficiently to humans.

This course will cover methods of detecting emotion such as facial expression recognition and physiological sensing. You will develop interfaces that respond to users' emotion in intelligent ways and/or simulate human emotion. We will also read and discuss research papers pertaining to the field of Affective Computing.

You will develop a system that detects and responds to and/or simulates emotion over the course of the semester in an area of your interest. You will have the opportunity to learn how to evaluate your system scientifically. Innovative and original work can be submitted to student research competitions or for publication. There will be no exams.


Professor: Beste Filiz Yuksel

Email: byuksel@usfca.edu

Office: HR 540

Office Hours: Tuesdays 4-6pm and Wednesdays 2:45-3:45pm or by appointment

Teaching Assistants:

Name: Thomas Oropeza

Email: thomasoropeza@gmail.com

Technical support for Affectiva, Android Studio, and Unity. Will answer questions by email.

Name: Yiding Liu

Email: yliu224@dons.usfca.edu

Technical support for Empatica. Will answer questions by email.

Name: Carlos De Leon

Email: carlosd93@gmail.com

Grader for coding assignments. Will answer questions by email regarding grading.

Objectives:



  • An introduction to the field of affective computing.
  • Learn how to critically read, evaluate, and write about scientific papers in this field.
  • Build affective systems that detect, respond to, and/or simulate emotion.
  • Learn how to use facial expression recognition systems and physiological sensors as part of affective systems.
  • A long-term project to build an independent, affective interface which will be evaluated through scientific testing and analysis.
  • Learn the fundamentals of becoming a researcher.

Textbooks

In addition to the handouts and relevant readings assigned for each week, we will refer to the following texts:

Prerequisites

This is an advanced class that involves a lot of independent work. Therefore it requires a prerequisite of CS 212 or equivalent.

Grading

The course will be graded on a A-F basis. The grade distribution will be as follows:

  • Assignments: 30%
  • Final Project: 40%
  • Scientific Papers: 30%
    • Reports - 15%
    • Presentation - 10%
    • Class Participation - 5%
The evaluation will be based on successfully finishing every assignment and report. There will be no mid-terms or finals. Grades will be assigned as follows.

100.0-93.0A
92.9-90.0A-
89.9-87.0B+
86.9-83.0B
82.9-80.0B-
79.9-77.0C+
76.9-73.0C
72.9-70.0C-
69.9-67.0D+
66.9-63.0D
62.9-60.0D-
59.9-0F

Labs and Projects



Labs and projects are due at 11:59pm on the due date. For any late submissions for programming assignments, 20% of your received points will be deducted per day for two days, after which there will be no credit.

Attendance Policy



Attendance is mandatory. Absences are only excused in cases of verified family or medical emergency.

Students with Disabilities



If you are a student with a disability or disabling condition, or if you think you may have a disability, please contact USF Student Disability Services (SDS) at (415) 422-2613 within the first week of class, or immediately upon onset of disability, to speak with a disability specialist. If you are determined eligible for reasonable accommodations, please provide me with your SDS Verified Individualized Services and Accommodations (VISA) form, and we will discus your needs for this course. For more information, please visit: http://www.usfca.edu/sds or call (415) 422-2613.

Academic Dishonesty

Students are required to follow the University's Honor Code: "As a Jesuit institution committed to cura personalis- the care and education of the whole person- USF has an obligation to embody and foster the values of honesty and integrity. USF upholds the standards of honesty and integrity from all members of the academic community. All students are expected to know and adhere to the University's Honor Code. " You can find the full text of the code online at www.usfca.edu/fogcutter.

This includes but is not limited to the following:

  • ALL assignments are to be completed individually unless specified, in writing, on the assignment. Academic dishonesty will NOT be tolerated. This is your warning! Students are encouraged to meet with me if they have questions regarding assignments or this policy. Students caught cheating will face severe penalty.
Students may:

  • receive help from the professor and the TA.
  • discuss the requirements of the assignments, the meaning of programs, or high-level algorithms with other students or outside sources. If you have any doubt with respect to what is acceptable to discuss, speak with the professor first.
Students may NOT:

  • look at another student's code.
  • look at another student's solutions to homework problems.
  • receive unapproved help from an outside source including a tutor or a family member.
  • submit code which has, in whole or in part, been copied from any other source (including another student, a web page, or another text).
  • submit solutions to problems which have, in whole or in part, been copied from any other source (including another student, a web page, or another text).
Requirements

  • Any help from a source other than the professor, the lab assistant, or a TA must be acknowledged. Example sources that must be cited are a parent, a family friend, and an outside tutor.
  • If you wish to get a tutor in the course, speak with the professor.
  • Any code submitted by a student must be completely original. No portion of a student's code may be copied from any other source (including, but not limited to, another student, a web page, or another text).
Penalties

  • Students caught violating the academic honesty policy will face severe penalty. A first offense will result in a zero on the assignment and a report to the Dean's office. A second offense will result in the student failing the course.