Enhanced Health Monitoring Using IoT-Embedded Smart Glove and Machine Learning

An embedded system that integrates hardware and software has been designed to perform specific tasks, utilizing machine learning and Internet of Things (IoT) technologies. The IoT refers to the extension of Internet connectivity to everyday objects, enabling them to be interacted with and communicated among each other over the Internet. These smart devices, equipped with sensors and Internet connectivity, can be monitored and controlled remotely. In this study, a smart glove that collects and processes users' vital body readings through integrated sensors is presented. The data is then transmitted to MATLAB via an Arduino hardware package. To predict whether the user's body condition is normal or abnormal, machine learning algorithms, specifically the K-Nearest Neighbor classifier, are applied using the collected testing data. Based on the prediction, a prescription is generated, and a message regarding the user's health status is received by the user. In comparison to the existing RFID Tag Reader system, several advantages are offered by our proposed solution. It allows individualized monitoring of users and the granting of a separate login to each user. Additionally, the proposed system's compact size makes it more practical for everyday use. Furthermore, the efficiency of the proposed system surpasses that of the traditional RFID Tag Reader system. By harnessing the power of machine learning and IoT, personalized health monitoring is provided by our smart glove system, thereby enhancing the overall efficiency and effectiveness of remote health monitoring systems.