JoWUA

Abstract

The fast development of ubiquitous computing technologies has empowered the effectiveness of constant control over patient health and provision of individual medical services. This paper provides the description of a Context-Aware Decision Support System (CADSS) that is capable of combining multimodal physiological indicators, behavioral tendencies, and environmental conditions to facilitate intelligent and adaptable healthcare services. The system engages context acquisition and reasoning by machine learning-intensive to produce dynamic patient-specific suggestions. As shown by experimental findings test in simulated ubiquitous settings, the proposed CADSS is 91.7 per cent accurate, 89.2 per cent precise, 92.5 per cent recall, and 90.4 per cent F1-score, which is more effective than traditional decision models. The model is also highly adaptive to changing circumstances in the environment and is also effective in detecting early health anomalies at the lowest possible false identifications. The results are a confirmation that context-aware intelligence greatly increases bespoke care, predictive dependability, and active healthcare control. The suggested architecture is scalable and provides a solid platform to the next generation ubiquitous healthcare applications.