ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine
Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol... more Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol and drug use), and lead to cardiovascular diseases and cancer. Continuous assessment of stress from sensors can be used for timely delivery of a variety of interventions to reduce or avoid stress. We investigate the feasibility of continuous stress measurement via two field studies using wireless physiological sensors - a four-week study with illicit drug users (n = 40), and a one-week study with daily smokers and social drinkers (n = 30). We find that 11+ hours/day of usable data can be obtained in a 4-week study. Significant learning effect is observed after the first week and data yield is seen to be increasing over time even in the fourth week. We propose a framework to analyze sensor data yield and find that losses in wireless channel is negligible; the main hurdle in further improving data yield is the attachment constraint. We show the feasibility of measuring stress minutes prec...
We present TeamVis, a set of tools for sensing and visualization of objective team performance in... more We present TeamVis, a set of tools for sensing and visualization of objective team performance in a simulated medical scenario. TeamVis helps teams, instructors, and researchers in observation, analysis, and evaluation of team behavior. The current system supports analysis of team movements and verbal communication. The system has potential to provide deeper insight into team performance, enabling design of more effective simulation training scenarios. Furthermore, the observed metrics can aid trainee debriefings by providing another mechanism for learning through self-reflection.
Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol... more Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol and drug use), and lead to cardiovascular diseases and cancer. Continuous assessment of stress from sensors can be used for timely delivery of a variety of interventions to reduce or avoid stress. We investigate the feasibility of continuous stress measurement via two field studies using wireless physiological sensors — a four-week study with illicit drug users (n = 40), and a one-week study with daily smokers and social drinkers (n = 30). We find that 11+ hours/day of usable data can be obtained in a 4-week study. Significant learning effect is observed after the first week and data yield is seen to be increasing over time even in the fourth week. We propose a framework to analyze sensor data yield and find that losses in wireless channel is negligible; the main hurdle in further improving data yield is the attachment constraint. We show the feasibility of measuring stress minutes preceding events of interest and observe the sensor-derived stress to be rising prior to self-reported stress and smoking events.
Studies in health technology and informatics, 2014
We present TeamVis, a set of tools for sensing and visualization of objective team performance in... more We present TeamVis, a set of tools for sensing and visualization of objective team performance in a simulated medical scenario. TeamVis helps teams, instructors, and researchers in observation, analysis, and evaluation of team behavior. The current system supports analysis of team movements and verbal communication. The system has potential to provide deeper insight into team performance, enabling design of more effective simulation training scenarios. Furthermore, the observed metrics can aid trainee debriefings by providing another mechanism for learning through self-reflection.
Proceedings of the 4th Conference on Wireless Health - WH '13, 2013
ABSTRACT We present a mobile avatar system designed to provide a constant user-avatar interface f... more ABSTRACT We present a mobile avatar system designed to provide a constant user-avatar interface for health behavior change therapy. The presented Android application replaces the user's phone background with an animated avatar. The avatar's level of physical activity is made to match the physical activity level of the user. This activity level is inferred using a decision-tree-based frequency analysis of the built-in phone accelerometers. User physical activity data collected is also sent via a mobile analytics platform (Countly) to be stored in a server. Also included in our demo is a simple website which pulls information from this server and places a user's avatar among other people's avatars. In this display a user can see how their avatar's physical activity compares to others', and observe their real-life physical activity behavior directly impacting the performance of their avatar in the virtual world.
Abstract: A system for providing interaction between a virtual human and a user, the system compr... more Abstract: A system for providing interaction between a virtual human and a user, the system comprising: a tangible interface providing a physical interface between the user and the virtual human, an imaging system directed towards the physical interface to provide images of the user interacting with the tangible interface; a tracking system tracking at least one position or the user; a microphone capturing speech from the user; a simulation system receiving inputs from the tangible interface, the imaging system, the tracking system and ...
This paper proposes after-action review (AAR) with human-virtual human (H-VH) experiences. H-VH e... more This paper proposes after-action review (AAR) with human-virtual human (H-VH) experiences. H-VH experiences are seeing increased use in training for real-world, H-H experiences. To improve training, the users of H-VH experiences need to review, evaluate, and get feedback on them. AAR enables users to review their H- VH interaction, evaluate their actions, and receive feedback on how to improve future real-world, H-H experiences. The Interpersonal Scenario Visualizer (IPSViz), an AAR tool for H-VH experiences, is presented. IPSViz allows medical students to review their interactions with VH patients. To enable review, IPSViz generates spatial, temporal, and social visualizations of H- VH interactions. Visualizations are generated by treating the interaction as a set of signals. Interaction signals are captured, logged, and processed to generate visualizations for review, evaluation and feedback. In a study (N=27), reviewing the visualizations helped students become self-aware of their actions with a virtual human and gain insight into how to improve interactions with real humans.
ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine
Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol... more Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol and drug use), and lead to cardiovascular diseases and cancer. Continuous assessment of stress from sensors can be used for timely delivery of a variety of interventions to reduce or avoid stress. We investigate the feasibility of continuous stress measurement via two field studies using wireless physiological sensors - a four-week study with illicit drug users (n = 40), and a one-week study with daily smokers and social drinkers (n = 30). We find that 11+ hours/day of usable data can be obtained in a 4-week study. Significant learning effect is observed after the first week and data yield is seen to be increasing over time even in the fourth week. We propose a framework to analyze sensor data yield and find that losses in wireless channel is negligible; the main hurdle in further improving data yield is the attachment constraint. We show the feasibility of measuring stress minutes prec...
We present TeamVis, a set of tools for sensing and visualization of objective team performance in... more We present TeamVis, a set of tools for sensing and visualization of objective team performance in a simulated medical scenario. TeamVis helps teams, instructors, and researchers in observation, analysis, and evaluation of team behavior. The current system supports analysis of team movements and verbal communication. The system has potential to provide deeper insight into team performance, enabling design of more effective simulation training scenarios. Furthermore, the observed metrics can aid trainee debriefings by providing another mechanism for learning through self-reflection.
Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol... more Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol and drug use), and lead to cardiovascular diseases and cancer. Continuous assessment of stress from sensors can be used for timely delivery of a variety of interventions to reduce or avoid stress. We investigate the feasibility of continuous stress measurement via two field studies using wireless physiological sensors — a four-week study with illicit drug users (n = 40), and a one-week study with daily smokers and social drinkers (n = 30). We find that 11+ hours/day of usable data can be obtained in a 4-week study. Significant learning effect is observed after the first week and data yield is seen to be increasing over time even in the fourth week. We propose a framework to analyze sensor data yield and find that losses in wireless channel is negligible; the main hurdle in further improving data yield is the attachment constraint. We show the feasibility of measuring stress minutes preceding events of interest and observe the sensor-derived stress to be rising prior to self-reported stress and smoking events.
Studies in health technology and informatics, 2014
We present TeamVis, a set of tools for sensing and visualization of objective team performance in... more We present TeamVis, a set of tools for sensing and visualization of objective team performance in a simulated medical scenario. TeamVis helps teams, instructors, and researchers in observation, analysis, and evaluation of team behavior. The current system supports analysis of team movements and verbal communication. The system has potential to provide deeper insight into team performance, enabling design of more effective simulation training scenarios. Furthermore, the observed metrics can aid trainee debriefings by providing another mechanism for learning through self-reflection.
Proceedings of the 4th Conference on Wireless Health - WH '13, 2013
ABSTRACT We present a mobile avatar system designed to provide a constant user-avatar interface f... more ABSTRACT We present a mobile avatar system designed to provide a constant user-avatar interface for health behavior change therapy. The presented Android application replaces the user's phone background with an animated avatar. The avatar's level of physical activity is made to match the physical activity level of the user. This activity level is inferred using a decision-tree-based frequency analysis of the built-in phone accelerometers. User physical activity data collected is also sent via a mobile analytics platform (Countly) to be stored in a server. Also included in our demo is a simple website which pulls information from this server and places a user's avatar among other people's avatars. In this display a user can see how their avatar's physical activity compares to others', and observe their real-life physical activity behavior directly impacting the performance of their avatar in the virtual world.
Abstract: A system for providing interaction between a virtual human and a user, the system compr... more Abstract: A system for providing interaction between a virtual human and a user, the system comprising: a tangible interface providing a physical interface between the user and the virtual human, an imaging system directed towards the physical interface to provide images of the user interacting with the tangible interface; a tracking system tracking at least one position or the user; a microphone capturing speech from the user; a simulation system receiving inputs from the tangible interface, the imaging system, the tracking system and ...
This paper proposes after-action review (AAR) with human-virtual human (H-VH) experiences. H-VH e... more This paper proposes after-action review (AAR) with human-virtual human (H-VH) experiences. H-VH experiences are seeing increased use in training for real-world, H-H experiences. To improve training, the users of H-VH experiences need to review, evaluate, and get feedback on them. AAR enables users to review their H- VH interaction, evaluate their actions, and receive feedback on how to improve future real-world, H-H experiences. The Interpersonal Scenario Visualizer (IPSViz), an AAR tool for H-VH experiences, is presented. IPSViz allows medical students to review their interactions with VH patients. To enable review, IPSViz generates spatial, temporal, and social visualizations of H- VH interactions. Visualizations are generated by treating the interaction as a set of signals. Interaction signals are captured, logged, and processed to generate visualizations for review, evaluation and feedback. In a study (N=27), reviewing the visualizations helped students become self-aware of their actions with a virtual human and gain insight into how to improve interactions with real humans.
Uploads
Papers by Andrew Raij
continuous stress measurement via two field studies using wireless
physiological sensors — a four-week study with illicit drug users
(n = 40), and a one-week study with daily smokers and social
drinkers (n = 30). We find that 11+ hours/day of usable data can
be obtained in a 4-week study. Significant learning effect is observed
after the first week and data yield is seen to be increasing
over time even in the fourth week. We propose a framework to analyze
sensor data yield and find that losses in wireless channel is
negligible; the main hurdle in further improving data yield is the
attachment constraint. We show the feasibility of measuring stress
minutes preceding events of interest and observe the sensor-derived
stress to be rising prior to self-reported stress and smoking events.
continuous stress measurement via two field studies using wireless
physiological sensors — a four-week study with illicit drug users
(n = 40), and a one-week study with daily smokers and social
drinkers (n = 30). We find that 11+ hours/day of usable data can
be obtained in a 4-week study. Significant learning effect is observed
after the first week and data yield is seen to be increasing
over time even in the fourth week. We propose a framework to analyze
sensor data yield and find that losses in wireless channel is
negligible; the main hurdle in further improving data yield is the
attachment constraint. We show the feasibility of measuring stress
minutes preceding events of interest and observe the sensor-derived
stress to be rising prior to self-reported stress and smoking events.