Events for 04/10/2019 from all calendars
First Year Graduate Student Seminar
Time: 5:30PM - 6:30PM
Location: BLOC 628
Speaker: Student panel
Title: Panel discussion: advice from graduating students
AMUSE
Time: 6:00PM - 7:00PM
Location: BLOC 220
Speaker: Dr. Theodora Chaspari, Department of Computer Science & Engineering, TAMU
Title: Computational models of human behavior for education and well-being applications
Abstract: Bio-behavioral signal processing and systems modeling enable an integrated computational approach to the study of human behavior and performance. Recent converging advances in sensing and computing, including wearable technologies, allow the unobtrusive long-term tracking of individuals yielding rich multimodal signal measurements from real-life. In this talk, we will present the development of computational approaches for analyzing, quantifying, and interpreting these bio-behavioral signals. The first part of the talk will describe a novel knowledge-driven signal representation framework able to efficiently handle the large volume of acquired data and the noisy signal measurements. Our approach involves the use of sparse approximation techniques and the design of signal-specific dictionaries learned through Bayesian methods, outperforming previously proposed models in terms of signal reconstruction and information retrieval criteria. The second part of the talk will describe novel population-specific and contextual models of human behavior. Individual differences (e.g., personality, demographics) and contextual factors (e.g., time of day) are integrated into machine learning models through the use of adaptation techniques and multi-task learning. In order to address the scarcity of labelled data related to human behavior, the final part of the talk will outline the development of transfer learning techniques for detecting various aspects of affect in speech. We will demonstrate how knowledge related to human emotion and behavior can be transferred between various datasets collected under constrained and real-life settings, and discuss how results from this analysis can be employed toward designing human-assistive personalized bio-feedback systems able to promote healthy routines, increase emotional wellness and awareness, and revolutionize educational training.