AURA Ascertaining Un-Reported Affect

Intelligent Tutoring Systems (ITSs) functions as virtual tutors that adapt to student responses. Such ITSs, however, do not yield student learning improvements equivalent to students tutored by human instructors. Ascertaining Un-Reported Affect (AURA) is a closed-loop, platform-independent"front-end"for informing ITSs with near real-time inferences of student engagement and affect during learning sessions to further improve student learning and minimize student frustration. AURA leverages low-cost, non-invasive sensors to monitor students without disrupting their learning experience. Such an approach enables the large-scale deployment of AURA to students using ITSs. The key innovation in AURA is the ability to serve as a modular component that informs an ITS of changes in a student"s emotional or physical state that can affect the learning process by leveraging audio, video, and user interface feedback. During AURA Phase 2 we will implement an engineering prototype composed of established signal processing algorithms selected during Phase 1. We will evaluate the prototype using operational data collected from student"s interacting with a computer tutorial. AURA leverages 21st Century Technologies expertise developing systems for the military in speech and audio processing, image processing, and creating machine learning algorithms.