Experimental Evaluation of an Internet of Things enabled Blood Pressure Prediction System using Enhanced Learning Methodology

There are several needs and immense challenges in the existing health care conditions for which necessitates the development of a new model for blood pressure prediction in an IoT enabled environment. Many traditional models and systems do not have the accuracy or processing speed characteristics that allow real-time analysis of health information. The paper illustrates IoT-based Blood pressure prediction system with the help of Enhanced Learning Methodology (ELM) using Hybrid GoogleNet-SVM model. The system reads smart blood pressure monitors and wearable health monitors to stream in live data on key vital stats like systolic and diastolic BP, resting heart rate, and more. Using a middleware platform, the data is transmitted in real-time to a centralized server via CoAP (Constrained Application Protocol) and saved in the cloud platform Azure. Preprocessing steps like data aggregation, timestamp alignment, data cleaning, and data transformation to have an appropriate dataset from all relevant features. The hybrid GoogleNet-SVM model uses both deep learning with GoogleNet to extract complex patterns from the data and for precise blood pressure predictions leveraging the classification power of SVM. Able to deliver highly reliable real-time health advice with an accuracy of $97.56 \%$, the system allows to manage blood pressure proactively and safely. It is a powerful, scalable platform for continuous health monitoring, representing an important leap forward in the field of predictive healthcare technology.