Research on automatic collection method of electrocardiogram data for wearable devices
Currently,wearable devices are susceptible to interference and noise in electrocardiogram data collection.In order to obtain more accurate electrocardiogram data,a lightweight heart beat convolutional network model was proposed based on the study of data automatically collected by wearable devices and optimization of electrocardiogram data analysis methods.The experimental results show that the lightweight heartbeat convolutional network model can accurately locate the R peak,with an accuracy rate of 98.78％,sensitivity of 99.32％,true positivity rate of 99.41％,and false detection rate of 1.39％,all of which are superior to the other four methods.By studying the automatic collection method of wearable device electrocardiogram data,not only does it provide a conven-ient,real-time,and accurate electrocardiogram data collection method,but it also improves the analysis and detection ability of elec-trocardiogram.By integrating electrocardiogram collection and analysis into wearable devices,individuals'heart health status can be monitored in real time,abnormal situations can be detected in a timely manner,and corresponding medical intervention measures can be provided.This is of great significance for promoting the application of wearable technology in the medical field.
wearable devicesautomatic collectionelectrocardiogramlightweightconvolutional network model
NETL
NSTL
万方数据
