Dehydration is a serious yet widely overlooked health condition that occurs when the body loses more fluid than it takes in, potentially leading to complications such as heat injury, kidney problems, seizures, and hypovolemic shock. Despite these risks, millions of people worldwide fail to monitor their hydration levels adequately. AquaDermAI addresses this gap by developing a dehydration-sensing wearable that measures key physiological indicators — skin moisture via galvanic skin response, heart rate via photoplethysmography, and body temperature via thermistor — to detect and predict dehydration in real time. This solution is broadly applicable across diverse populations, from athletes and construction workers to individuals managing chronic illnesses, empowering users to proactively maintain healthy hydration habits.
AquaDermAI integrates three sensors — a PPG heart rate monitor, a GSR skin conductance sensor, and a DS18B20 thermistor — into a compact wearable built around an ESP32-S3 microcontroller. The device transmits raw physiological data wirelessly via Bluetooth Low Energy (BLE) to a companion Android mobile application, where a trained machine learning classification model (evaluated across logistic regression, random forest, and support vector machine approaches) processes the data to determine the user's hydration status. The mobile app, developed in Kotlin with Jetpack Compose, displays real-time readings and trend data through an intuitive color-coded interface, making complex biosignal data accessible to everyday users.
The AquaDermAI team successfully delivered a fully functional wearable prototype and companion mobile application capable of classifying users into three hydration levels: hydrated, mildly hydrated, and dehydrated. Training and validation data were collected across participants with varying skin types and fitness levels, and the ML model achieved stable accuracy as shown in the model convergence results. Despite hardware setbacks — including a microcontroller short during soldering that required pivoting from a perfboard to a small breadboard enclosure — the team produced an integrated, wrist-worn device that reliably transmits sensor data to the app via BLE and correctly predicts user hydration status in real time.