RESEARCH ON THE TECHNICAL FRAMEWORK OF WEARABLE INTERNET OF THINGS DEVICES IN MENTAL HEALTH SOCIAL WORK INTERVENTIONS

Abstract

Mental health disorders impact an estimated 500 million individuals globally, yet conventional service delivery models encounter considerable challenges, including geographic constraints, limited accessibility, and suboptimal resource distribution. This study introduces a comprehensive technical framework that integrates wearable Internet of Things (IoT) devices with social work interventions to enhance mental health care delivery. Employing a mixed-methods research design, the investigation involved 240 participants, allocated into experimental and control groups, over a 12-week duration. The proposed system architecture consists of four layers: data collection, data processing, decision-making algorithms, and evaluation display. It utilizes a range of wearable sensors, such as smartwatches, health bracelets, and physiological monitoring devices. Machine learning analyses yielded an overall accuracy of 89.3%, with convolutional neural network (CNN) models achieving 92% accuracy in analysing multidimensional time series data. The results reveal significant correlations between physiological metrics and mental health status (correlation coefficients ranging from 0.55 to 0.81), with heart rate variability exhibiting the strongest association with stress indices (r = 0.81). Post-intervention assessments demonstrated notable improvements on standardized mental health measures, with effect sizes surpassing Cohen’s d = 0.8. The framework effectively facilitates real-time alerts, personalized recommendations, peer support, and access to professional consultation. User acceptance analysis indicated high satisfaction concerning convenience and individualized service experiences, although privacy concerns were identified as areas necessitating further attention.