Course information
Instructor: Theodora Chaspari
Credits: 3
Lecture Time & Location: TR 9.35am-10.50am, HRBB 126
Office Hours: Tuesday, 11am-1pm, HRBB 315D
Syllabus: here
Tentative Roadmap: here
Course description
This course covers hands-on applications of methods, algorithms, and systems that are able to model, quantify, and interpret human behavior. We will examine the integrated computational study of physical well-being, mental health, and human behavior through the use of both overt behavioral signal information (e.g. speech, language, gestures, facial expressions) and covert biomarkers (e.g. physiological signals). We will further see how integrated data scientific and machine learning approaches can yield personalized measures of human behavior used for health, education, security, and other applications.
Prerequisites
No pre-requisites are stated. An understanding of machine learning (CSCE 633 or equivalent) and speech processing (CSCE 630) is recommended for project purposes.
Learning Outcomes
- Students will be able to process human-derived signals (e.g. physiology, speech).
- Students will be able to associate bio-behavioral markers to clinical and non-clinical outcomes.
- Students will be able to identify and quantify predictive features for an application of interest relevant to affective computing.
- Students will be able to design projects that generate new findings and algorithmic contributions to the fields of behavioral signal processing and behavioral analytics.
- Students will be able to critically analyze state-of-the-art research papers including the experimental design, methodology, technical approach, and system through the critical evaluation of state-of-the-art research papers and hands-on modeling through coding assignments.