<![CDATA[Urban mental health is increasingly challenged by environmental stressors such as noise pollution, high population density, and air quality degradation. This study proposes an integrated framework combining Internet of Things (IoT) sensor networks with artificial intelligence (AI) analytics to monitor and predict mental health outcomes across metropolitan districts. A total of 300 participants from three urban areas contributed self-reported psychological data, which were combined with real-time environmental measurements including noise, air quality, temperature, humidity, and pedestrian density. Quantitative analyses, including correlation, multiple regression, and AI-based predictive modeling, revealed that noise and crowd density were the strongest predictors of elevated stress, while green spaces and improved air quality were positively associated with mood. The predictive models achieved 15–20% higher accuracy than survey-only models, and mapping of high-risk zones aligned with actual mental health service usage. These findings demonstrate the potential of IoT and AI-driven approaches to provide actionable insights for policymakers, urban planners, and healthcare providers. Future research should expand longitudinal and cross-city validation, integrate additional environmental and social indicators, and explore real-time interventions to create resilient and human-centered urban environments.]]>
Copyrights © 2024
