Enhancing Elderly Care: Remote Glucose Monitoring for Health and Independence

This paper presents a comprehensive approach to non-invasive glucose monitoring for elderly diabetic patients by integrating machine learning algorithms, loT devices, and cloud computing. The literature review surveys existing re-search on ML algorithms and loT devices, revealing challenges in accuracy, portability, and cost-effectiveness. Building upon this, the proposed model employs the Support Vector Machine (SVM) algorithm for non-invasive glucose monitoring, utilizing MAX30100 sensors and ESP32 microcontrollers for real-time predictions. Cloud computing is integrated through Digilocker, ensuring secure storage and offline accessibility of sensitive health data. The loT parts include MAX30100 sensors, ESP32 micro-controllers, a 16x2 LCD screen, and Power Supply vl.2, forming the core of the continuous glucose monitoring (CGM) system. Implementation strategies involve data aggregation, visualization, and analysis, with considerations for challenges such as limited data storage and app integration. The model aims to provide an effective and user-friendly CGM system, addressing existing challenges and empowering elderly diabetic patients with real-time insights into their glucose levels. The paper concludes by discussing the potential impact of the proposed model on diabetes management and emphasizing the need for further research and development to enhance its capabilities.