Publication

Abstract : The rising frequency of diabetes necessitates advanced technologies for timely monitoring, enabling visionary operation. The proposed methodology introduces a new approach by integrating sensor data collection, cloud-predicated storage, and machine learning models to enhance diabetes monitoring, visualization, and real-time monitoring of patient's health conditions. In the realm of diabetes operation, there exists a critical need for advanced systems that go beyond traditional periodic assessments and enable real-time monitoring of health parameters. The current terrain lacks a comprehensive result that seamlessly integrates sensor-predicated data collection, cloud-predicated storage, and machine learning models to give immediate perceptivity into dynamic physiological changes associated with diabetes. Addressing this gap is imperative to enhance the perfection and promptitude of interventions. In the proposed system non-invasive detectors such as the Pulse detector, TCS 3200, are used to calculate Blood Pressure and glucose levels. The acquired sensor data is transmitted to a cloud-predicated platform and a robust machine-learning model ensures real-time analysis for responsive and reliable monitoring. The approach leverages machine learning models like Random Forest Classifiers to produce a robust model. The objectification of cloud computing enhances scalability, effectiveness, and real-time processing. The study has redounded in the real-time monitoring of data which is visualized and duly studied by a health care professional enabling to monitor and improve the health conditions of a patient.