The INIT Lab has been fortunate to receive funding from several federal grant agencies and industry sponsors.

Explainable, Fair, Reproducible and Collaborative Surgical Artificial Intelligence: Integrating Data, Algorithms and Clinical Reasoning for Surgical Risk Assessment (XAI-IDEALIST)

NIH Award #s: R01GM110240 (Aug 2022 to May 2026)
PIs: Azra Bihorac (UF College of Medicine) and Parisa Rashidi (UF BME), Co-Is: Lisa Anthony, Louise Kendall Webb, Tezcan Ozrazgat Baslanti, William Hogan, Tyler John Loftus, Yulia Aleksandrovna Strekalova, Jessica M. Ray (UF)

We are supporting this large NIH project by contributing our approach to user-centered design for the high-stakes scenario of surgical risk assessment.

Projects Partially or Fully Supported:

• XAI-IDEALIST (page coming soon!)

ENKIx: Enabling Knowledgeable Task Guidance In the Extremes

DARPA Award #s: HR0011-22-2-0004 (Dec 2021 to Dec 2025)
PI: Jaime Ruiz, Co-PIs: Lisa Anthony, James Fairbanks (UF CISE), David Kaber (UF ISE), Taskin Padir (Northeastern University), Maryam Zahabi (Texas A&M University), Evan Patterson (Topos Institute), Isaac Wang (James Madison University)

This grant is funding our investigation into designing and developing an assistive system powered by AI that can guide users through procedural tasks in high-stress and high-stakes environments. The INIT and Ruiz labs’ contributions focus on the design of the mixed-initiative user interface with the system, which must be able to adapt based on the task, stress, situation, and other contextual factors.

Projects Partially or Fully Supported:

• ENKIx (page coming soon!)

Family Fit: Promoting Family-Based Physical Activity and Weight Gain Prevention Through Mobile Technology

NIH Award #s: R21HD100743 (Aug 2021 to Jul 2024)
PI: Danielle Jake-Schoffman (UF HHP), Co-Is: Lisa Anthony, David Andrew Fedele, Stephen D. Anton, and JeeWon Cheong (UF)

We collaborate with Danielle Jake-Schoffman as a consultant on her R21 to provide expertise in user-centered design, child-centered design, and qualitative methodologies for design in support of a mobile app for parent-child dyads to get more active together.

Collaborative Research: SaTC: CORE: Medium: Toward Age-Aware Continuous Authentication on Personal Computing Devices

NSF Award #s: 2039379 / 2039373 (Apr 2021 to Mar 2023)
PI: Lisa Anthony, Co-PI: Jaime Ruiz (Collaborative with PI: Tempestt Neal and Co-PI: Shaun Canavan at University of South Florida)

This grant funded our investigation into multi-generational users’ mental models of authentication methods, especially continuous authentication.

Projects Partially or Fully Supported:

• Biometrics / SATC

Evaluation of an Adaptive Intervention for Weight Loss Maintenance

NIH Project #s: 1R01DK119244-01A1 (Jul 2019 to Mar 2024)
PI: Kathryn Ross (UF PHHP), Co-Is: Lisa Anthony, Jaime Ruiz, and Peihua Qiu (UF Biostatistics)

We collaborate with Dr. Kathryn Ross by working on a mobile app for delivering targeted data visualizations and questionnaires to participants in support of their long-term weight loss maintenance. This grant is also funding our investigation into HCI related questions about engagement with mobile health apps, long-term use and habituation, and motivation and behavior change.

Projects Partially or Fully Supported:

• MyTrack+

CAREER: Natural User Interfaces for Children

NSF Award #s: 1552598 (Jan 2016 to Dec 2021)
PI: Lisa Anthony

This grant funded our investigation into multimodal interaction with natural user interface modalities, like touch, gesture, whole body, and speech, for elementary school children ages 5 to 10.

Projects Partially or Fully Supported:

• ​MTAGIC
• Understanding Gestures
• $-Family of Gesture Recognizers
• Pose
• TIDRC

Think Globally, Interact Locally: Advancing Science Learning using Interactive Spherical Displays to Model Global, Physical Systems

NSF Award #s: 1612485 (Sep 2016 to Aug 2019)
PI: Kathryn A. Stofer (UF IFAS AEC), Co-PI: Lisa Anthony

This grant funded our investigation into the affordances of touch-interactive spherical displays for learning, especially in the context of visualizations of data representing global ocean phenomena over time.

Projects Partially or Fully Supported:

• TIDESS