A Health Monitoring System with Multi-Sensor Information Fusion (HMS-MSIF) using a Deep Learning Approach

In recent years, the Health Monitoring System (HMS) is a complicated technology that offers numerous benefits over conventional patient health management systems. These systems comprise a wearable wireless device, such as a bracelet, with sensors, incoming sensors, EEG sensors, and other features linked to a smartphone application that allows a doctor to obtain medical data remotely through a cloud platform. The cloud platform handles the information storage and retrieval management. Multi-sensor management involves managing or coordinating various sensor resources to govern environment perception activities. The innovative study on multi-sensor fusion is becoming the most significant factor in creating and researching modern multi-sensor-supported healthcare systems. Therefore, this research finds a solution by designing a health monitoring system with multi-sensor information fusion (HMS-MSIF) using a deep neural network. This model designs a deep neural network for learning sensor representations from the raw sensor-based health data. The simulation results show the highest prediction accuracy of 97.58%, reliability ratio of 97.23% and signal-to-noise ratio of 98.64%. The proposed model gives the lowest error rate of 19.76%, thus suggesting real-time implementation.