Published:
CigAware helps participants log smoking/craving events with quick EMAs, then turns those into daily progress, streaks, and weekly insights—backed by gentle, motivational nudges.
Published:
CardioMate. CardioMate not only reminds participants to initiate BP readings using an Omron HeartGuide wearable monitor but also prompts them multiple times a day to report stress levels. Additionally, it collects other useful information including medications, environmental conditions, and daily interactions. Through the app’s messaging system, efficient contact and interaction between users and study admins ensure smooth progress.
Recommended citation: Kargarandehkordi, A., Slade, C., & Washington, P. (2024). Personalized AI-Driven Real-Time Models to Predict Stress-Induced Blood Pressure Spikes Using Wearable Devices: Proposal for a Prospective Cohort Study. JMIR Research Protocols, 13(1), e55615. https://www.researchprotocols.org/2024/1/e55615/
Published:
A personalized mobile-based EMA app for periodically recording a log about their substance use and craving throughout the day with the ability to send reminders (notifications)
Recommended citation: Sun, Y., Kargarandehkordi, A., Slade, C., Jaiswal, A., Busch, G., Guerrero, A., ... & Washington, P. (2024). Personalized Deep Learning for Substance Use in Hawaii: Protocol for a Passive Sensing and Ecological Momentary Assessment Study. JMIR Research Protocols, 13(1), e46493. https://www.researchprotocols.org/2024/1/e46493
Published:
LabelLab is an innovative application designed to reimagine the TikTok experience with a focus on data labeling. It enables users to not only enjoy and share videos but also to label video content and hashtags, contributing to a rich dataset. This dataset then serves as a foundation for developing advanced models for emotion and human activity recognition. LabelLab stands out as a crowdsourcing labeling platform, allowing for the importation of video datasets and the efficient recruitment of crowdworkers for data labeling tasks.
Published:
Based on an EMA based intervention, this study intends to use all modalities to efficiently recognize stress, a commonly experienced emotional state. The study will involve collecting data (visual, speech, text, and time series) from participants for a month and then analyzing the data to identify the key features associated with accurately recognizing stress and anxiety.