AI for Health and Well-Being | Yiyang "Diana" Wang

CultivAgents

Fri, 22 May 2026 00:00:00 +0000

Gardening supports well-being, cultural continuity, and food autonomy, yet most digital tools give generic advice that ignores a gardener’s skills, local ecology, and cultural context. CultivAgents is a relationship-centered multi-agent system, grounded in an ethics of care, that coordinates three specialized agents — an Experience Agent attuned to skill level, an Environmental Agent grounded in local and seasonal conditions, and an Ethnobotanical Agent that connects plants to cultural knowledge.

My role. I led this project, designing the system and a three-phase mixed-methods evaluation with domain experts, HCI researchers, and community gardeners. Participants reported increased confidence, motivation, and trust in acting on AI advice, and valued the complementary perspectives of the agents — while also surfacing limits in cultural specificity and agent coordination that motivate future work.

CultivAgents: Cultivating Relationship-Centered Multi-Agent Systems for Personalized Gardening

Fri, 22 May 2026 00:00:00 +0000

Abstract

Gardening supports well-being, cultural continuity, and food autonomy, yet digital tools often give generic advice that overlooks gardeners’ skills, local ecologies, and cultural contexts. We introduce CultivAgents, a relationship-centered multi-agent system grounded in ethics of care that coordinates an Experience Agent, an Environmental Agent, and an Ethnobotanical Agent to deliver personalized, socio-culturally grounded support. A three-phase mixed-methods study with experts, HCI researchers, and community gardeners found that CultivAgents helped gardeners translate interest into situated action and increased their confidence, motivation, and trust in acting on AI advice.

📄 PuffEM presented at CHASE 2025

Tue, 24 Jun 2025 00:00:00 +0000

, an e-cigarette sleeve that estimates user nicotine intake through multimodal sensing, was presented at the ACM/IEEE International Conference on Connected Health (CHASE 2025).

PuffEM

Tue, 24 Jun 2025 00:00:00 +0000

Understanding vaping behavior and nicotine intake is essential for addiction research and cessation support, but self-reports and gesture-based methods are unreliable and miss real-time events. PuffEM is a low-power, versatile e-cigarette sleeve that detects vaping events using a touch sensor and an on-the-surface magnetometer, and estimates the amount of vaporized nicotine. Paired with a mobile app, it captures sensor and contextual data to support behavioral research and health interventions.

My role. I co-led this project (equal first-authorship). We validated PuffEM in the lab across three ENDS devices and in a five-day in-the-wild deployment that demonstrated high usability and low burden. The work was published at ACM/IEEE CHASE 2025.

PuffEM: An E-cigarette Sleeve for Estimating User Nicotine Intake

Tue, 24 Jun 2025 00:00:00 +0000

Abstract

With the increasing prevalence of Electronic Nicotine Delivery Systems (ENDS), understanding vaping behaviors and nicotine intake is essential. We introduce PuffEM, a low-power, versatile system that reliably detects vaping events using a touch sensor and on-the-surface magnetometer to estimate nicotine intake. Integrated with a mobile app, PuffEM collects sensor and contextual data to support vaping and addiction research and health interventions. Lab tests confirm its ability to detect vaping events across three ENDS devices and estimate vaporized nicotine liquid, and a five-day in-wild study demonstrated high usability and low burden.

Phantom Puffs: A Phantom Lung to Emulate Smoking Behavior

Tue, 10 Sep 2024 00:00:00 +0000

Abstract

Testing sensors on human subjects is fraught with challenges such as extensive setup times and inconsistent data collection. We explore phantom organs to streamline sensor testing and validation, developing a phantom lung capable of emulating human breathing patterns. This provides a consistent, repeatable testing environment for ENDS monitoring sensors, reducing reliance on human subjects while enabling experimentation with novel sensing mechanisms.