Everyone has some kind of routine. Whether it's how you get ready each morning or how you drive your car, routines are behavior blueprints that help us purposefully accomplish repetitive tasks. Modeling those routines, though, is anything but mundane. It provides important insight into situations where those routines occur, and may help people change their habits or improve their efficiency.
Personal information management and privacy is a major and increasing challenge. New internet architectures will make people and their interactions more transparent to others than ever, and increase our digital footprints online. In a set of projects, we are studying user perspectives on anonymity and privacy online.
We have built an emotion recognition system based on prosodic features (i.e. intensity, pitch, formant frequencies of sounds) combined with short-term perceptual features for classifying the following emotions: anger, fear, happy, sad, surprise, and neutral. Additional emotional states can be included. Prosodic information applies to syllables, words, or phrases. An interactive dialog elicits responses from the user.
VRAs are applications of wearable devices which track patient home exercises in order to quantify exercise metrics regarding compliance, performance, and symptom levels. VRAs are designed to provide Physical Therapists (PTs) with precise, quantitative data regarding patients' home exercises. This precise information can then be used by PTs to improve their decision making regarding treatment adjustments.
This Virtual Coach evaluates and offers corrections and feedback for rehabilitation of stroke survivors. The Virtual Coach is composed of a tablet for clinician programming, a Kinect for monitoring motion, and a machine learning model to evaluate the quality of the exercise.
The goal of Seating Coach (SC) is to facilitate power wheelchair users to utilize auxiliary seating functions for health management while preventing potential hazard due to inappropriate usage. The SC detects seating activities, analyzes user behaviors, and responds accordingly to provide suggestions or reminders. The SC is an intelligent system, integrating sensors, machine intelligence and user-friendly interfaces.
Our contention is that multi-user health kiosks, designed with input from older adults and situated in convenient community locations, offer a way to bolster their self-management confidence and capabilities, regardless of personal resources or distance from health services. We are expanding the features and functions of the Health Kiosk to include numerous self-report and performance-based measures, interactive elements, and health intervention modules.
Our Connection Machines project investigates nonverbal and verbal behaviors of two partners in a conversation setting in the context of rapport. We have collected data on teenagers conducting a peer tutoring task in linear algebra. We are currently investigating nonverbal behaviors, such as smile, gaze, prosody and pitch, and verbal content, such as second person pronoun use, of the participants in the dialogue.
The AdaptErrEx project, funded by the U.S. Department of Education, has developed materials to support learning of decimals through erroneous examples. The main goals are to support deeper, more robust learning and to improve error-detection skills. All the materials developed on the AdaptErrEx project will eventually be freely available through MathTutor, a website that helps middle school students learn math.
The Project on Virtual Possessions investigates how people make sense of and construct value with their ever-increasing collections of virtual things. These include items that were formerly material (i.e.
