A Design of Cost-Effective Wireless Body Sensor Network with Electrocardiogram Acquisition System Using Hybrid Deep Learning Approaches

To create a cost-efficient Wireless Body Sensor Network (WBSN), essential components include low-energy, affordable wearable sensors that monitor basic physiological parameters such as blood pressure heart rate, and temperaturecontinuously. The CWBEHD model is a cost-saving health-monitoring system designed for continuous vital signs monitoring using WBSN. Heart rate, blood pressure is monitored by small wearable sensors linked to an ESP32 microcontroller, sending data through RF signals in a star network. Data after a local preprocessing step are transmitted in a secure way to the ThingsBoard IoT platform, which is the main place for classification, rule-based processing, and dynamic visualization. The model embraces deep learning architectures a Multi-Layer Perceptron (MLP) for rapid classification and a Convolutional Neural Network (CNN) for ECG feature extraction by both synthetic and in vivo data verified by professional ECG monitors. The parameter evaluation is accuracy, heart rate, blood pressure, body temperature, comparative accuracy calculation.