SmartSense:AI-Driven Low-Cost Wearable for Real-Time Symptom Detection and Risk Estimation

Abstract

Asthma is a chronic respiratory condition that demands continuous symptom monitoring to prevent severe health complications. This project aims to create Smart- Sense, a low-cost, wearable prototype designed to detect early symptoms of asthma using real-time physiological monitoring. The device integrates a conductive rubber band to track chest expansion and a digital microphone for cough detection. A microcontroller samples the sensor data, performs onboard signal processing using FFT for breathing analysis, and applies a quantized neural network model for AIbased cough classification. Processed data is transmitted to a companion mobile application via BLE, enabling real-time visualization, alerts, and symptom tracking. Emphasis is placed on local data processing and energy efficiency to support extended autonomous operation. Testing showed promising results in detecting respiratory patterns and classifying cough events, although challenges such as background noise sensitivity and sensor nonlinearity remain. SmartSense demonstrates the feasibility of affordable, embedded AI in wearable health technologies and lays the groundwork for future clinical validation and commercial development.