Sense2Quit is a smart health technology that uses wearable sensors and machine learning to detect smoking and pre-smoking behaviors in real time. Built on smartwatch and finger-motion sensing, the system identifies the characteristic gestures associated with reaching for, preparing, and smoking a cigarette—allowing intervention before smoking occurs.

Traditional cessation tools rely heavily on self-report, periodic counseling, or pharmacological aids. In contrast, Sense2Quit provides continuous, objective monitoring and enables just-in-time support, making cessation assistance more responsive and personalized. Using deep learning methods and spectrogram-based motion analysis, the system achieves high accuracy in distinguishing smoking from everyday activities and significantly improves pre-smoking behavior detection through multi-sensor fusion.

Sense2Quit integrates these sensing capabilities into a mobile application that delivers timely alerts, behavioral feedback, and encouragement aligned with evidence-based quitting strategies. The project is grounded in prior clinical work with underserved communities and aims to reduce tobacco-related health disparities by offering a scalable, real-time, and data-driven cessation platform.