Development of a wearable device for heart rate monitoring and fall detection using machine learning to analyze and detect early anomaly of cardiovascular conditions

Abstract

Cardiovascular disease is the leading cause of death globally. This research implements a system for monitoring heart rate, electrocardiogram, and providing alerts for potential risks to patients based on data collected using the LSTM machine learning model. The wearable device is compact in size with a long battery life. The information collected from the device can be remotely monitored by doctors through a visual interface on a web server model, and patients can self-monitor their electrocardiogram status through an application on a mobile device. By integrating the LSTM model into the design, this study has addressed two issues: predicting the trend of the electrocardiogram signal and detecting abnormalities in the predicted signal. This allows users to self-monitor their personal status and doctors to better adjust the treatment method for the patient’s health.

Keywords

• cardiovascular diseases
• lora
• wearable device
• anomaly detection
• lstm