<![CDATA[Smoking is one of the leading risk factors for various chronic diseases. Although many smokers successfully quit, the urge to smoke again (craving) remains a major cause of relapse. This study aims to develop an Artificial Intelligence (AI)-Based Adaptive Lifestyle Recommendation System to assist former smokers in managing and reducing craving levels. The proposed system utilizes the Random Forest algorithm to predict craving levels based on several factors, including mood, time of day, daily activities, coffee consumption, and sleep duration. The AI model is trained and evaluated using a prepared dataset, with performance measured using Mean Squared Error (MSE). Prediction results are then used to generate adaptive lifestyle recommendations tailored to the user's craving risk level. The system is implemented as a mobile application integrated with a backend API service. The research methodology consists of requirements analysis, AI model and system design, application development, limited user testing, and system evaluation. The expected outputs include a craving prediction model, an AI-based adaptive recommendation application, and scientific publications. This research is expected to provide an innovative digital solution that supports former smokers in maintaining a smoke-free lifestyle and reducing the risk of relapse.]]>
Copyrights © 2026
