PROGRAM
8:30
9:15 9:30 10:30 11:30 12:15 1:30 2:45 4:00 4:15 5:15 6:15 6:30 8:00 |
Registration & Breakfast
Opening Remarks by Dr. Catherine Burns Opening Keynote by Kimberly Tee Podium Presentations: AI Podium Presentations: AR/VR Lunch Podium Presentations: Driving and Autonomous Vehicles Podium Presentations: Healthcare Break Poster Session Closing Keynote by Dr. Lennart Nacke Closing Remarks by Dr. Plinio Pelegrini Morita Evening Social End of IUW 19 |
MEET OUR KEYNOTE SPEAKERS
Think, explore, build: Providing value as a researcher throughout product development
|
Storytelling in UX Design
|
PODIUM PRESENTATIONS
10:30 am
AI
Fahimeh Rajabiyazdi
|
|
Kayla Pedret
|
|
Apurva Misra
|
|
Shekhar Kumar
|
Classifying Cognitive Load on Drivers based on Physiological Measures and Long Short-Term Memory
With the rise of vehicle infotainment systems and portable electronic devices, there is increasing mental workload on drivers. This can result in impaired driving performance and a reduction in safety. Thus, it is useful to estimate drivers’ cognitive workload and intervening through adaptive interfaces when necessary. Previous research has investigated the use of supervised machine learning algorithms to classify drivers’ cognitive load. Limitations with this methodology include the use of research-grade EEG systems, which are intrusive, and unable to provide a true reflection of driving conditions. Additionally, these models rely on an individual’s driving history data, which reduced the models’ generalizability and robustness. To overcome these limitations, this paper adopted a model based on long short-term memory, a recurrent neural network architecture, to estimate drivers’ cognitive load. The training and test data was collected from 33 participants in a driving simulator environment. This data consisted of three physiological features that were used to estimate an individual’s cognitive workload: heart rate (HR), galvanic skin response (GSR) and electroencephalography (EEG). The EEG data was collected using a consumer-grade EEG device. When incorporating drivers’ historical data from the same group of participants for training, the proposed model reached an accuracy 88.5% in classifying three levels of cognitive load, imposed by a non-driving-related tasks: no-task, modified 1-back, and modified 2-back. Further, the model achieved 82.7% accuracy if non-historical data was used (i.e., using the model trained on the data from some of the drivers and estimate the cognitive load of other drivers). These results indicate the feasibility of detecting drivers’ high cognitive load using less intrusive EEG systems and non-historical data.
|
11:30 am
AR/VR
Fan He
|
|
Holland Vasquez
|
|
Adam Reiner
|
|
1:30 pm
Driving and Autonomous Vehicles
Davide Gentile
|
|
Dengbo He
|
|
Chelsea DeGuzman
|
|
Braden Joseph Hansma
|
|
Kuan-Ting Chen
|
Communicating automation reliability through music quality: a sonification approach to driver feedback
Background: With increasing vehicle automation, drivers may engage more in non-driving related tasks. However, drivers may still be required to regain control of driving when automation limitations are reached. One way to improve drivers’ situation awareness is to provide drivers with continuous feedback of system uncertainty/reliability. Sonification is a process to transform data or information into the form of acoustic signal for the purposes of facilitating interpretation. It has been widely used for process monitoring. To the best of our knowledge, the attempt to combine music and sonification technique together is still limited in the automated driving context.
Objective: The aim of this study was to explore the feasibility of blending continuous sound feedback into drivers’ music listening experience and to improve driver takeover behavior in conditional automated driving. Method: A driving simulator study consisted of 36 participants was conducted. Participants were randomly assigned into three feedback groups, i.e. continuous, intermittent and no feedback group. Drivers’ gaze behavior as well as driving behavior data were collected. Progress to Date: We have completed the experiment and data collection for the study. For the driving behavior data, the preliminary result of linear mixed effects model showed that participants within continuous feedback group had significant faster manual response time than the no feedback group. Participants in no feedback group showed larger steering wheel correction comparing to the continuous group. No substantial difference was found in the NASA-TLX score among all three groups. Future work: Future works include finishing gaze data analysis and interpreting the analysis results for future feedback design implication. |
2:45 pm
Healthcare
Taylor Kunkes
|
|
Laura Fadrique
|
|
Robert P Gauthier
|
|
Christopher Moore
|
|
Tina Chan
|
|
POSTER SESSION
4:15 pm
Bella (Yigong) Zhang
|
Ubiquitous Cognitive Assessment in the Aging Population |
Elliot Biltekoff
|
A Fuzzy Logic, Virtue-Ethics-Based Moral Framework Modeling Approach |
Sheldon Hawley
|
Evaluating differences in performance, movement strategies and environmental influence during a lifting task in real versus virtual environments. |
Marco Moran-Ledesma
|
Interacting in Virtual Reality with 3D Physical Props |
Yaoyu Fu
|
The effects of long duration of augmented reality head-mounted display use during laparoscopic surgery |
Julian Potvin-Bernal
|
Influencing Greater Adoption of Eco-Driving Practices Using an Associative Graphical Display |
Sardar Elias
|
Feedback-Based Interface Design to Reduce Driver Impatience at Traffic Intersections |
Su Shen
|
Integrated Analysis of Automation Failures in Highly Automated Driving |
Warda Azad
|
Smart Parking |
Catherine Solis
|
Designing Visual Guides for Casual Listeners of Live Orchestral Music |
Marina Wada
|
Rheumatoid Arthritis Patients Engaging in Shared Decision Making: An Exploratory User Needs Study |
Ryan Tennant
|
A comparative task analysis between a developed mHealth communication app and current healthcare tracking tools for families of children with medical complexities who receive home care services |
Suzan Ayas
|
A Systematic Review of Mitigation Strategies for the Operating Room Distractions |
Pedro Augusto
|
Blockchain Platform for Consent Management in Healthcare |
Leila Homaeian
|
Group vs Individual: Impact of TOUCH and TILT Cross-Device Interactions on Mixed-Focus Collaboration |