Application Of Logistic Algorithms In ECG R-wave Monitoring

As we all know,heart disease is harmful and lethal.Therefore,the research on various diagnostic methods of heart disease has become a research hotspot of wisdom health and wisdom medicine.The heart is mainly composed of four parts: left atrium,right atrium,left ventricle and right ventricle.Atrial problems usually do not cause immediate death,but if there is a ventricular problem,it is likely to lead to death.Because ventricular diseases are extremely harmful and difficult to detect early,targeted monitoring is needed.From the point of view of paying attention to health and cherishing life,there are more and more wearable medical devices on the market,which can facilitate people to monitor their heart,blood pressure and so on at any time and anywhere,timely detect diseases and carry out early intervention and treatment.R wave can not only reflect ventricular problems,but also calculate heart rate,and prevent arrhythmia by heart rate monitoring in advance.In this paper,the feasibility of applying logistic algorithm in wearable ECG monitoring is studied based on R-wave monitoring and analysis.At present,in the R-wave monitoring,the traditional algorithm is often used to extract R-wave,which makes the real-time graph of R-wave inaccurate,that is,the accuracy of extracting R-wave from ECG data is not high,leading to inaccurate ECG and heart rate monitoring.In order to solve this problem,this paper compares different monitoring methods of ECG signals,aiming at selecting appropriate data preprocessing methods and monitoring algorithms to improve the accuracy of ECG and heart rate monitoring of wearable ECG monitoring equipment.This paper combines logistic algorithm with fast median filter and arithmetic average filter to extract R-wave.The experimental results show that compared with the two mostcommonly used algorithms for R-wave monitoring in mobile wearable ECG patches,the combination of logistic algorithm,fast median filter and arithmetic average filter improves the accuracy of R-wave classification and extraction,and the running speed is within a reasonable range,and it will not slow down the real-time display of data on the mobile end;and it is also compared with KNN and neural network.After comparison,the running speed is more in line with the real-time requirement of the equipment when the accuracy is similar.Therefore,the monitoring method presented in this paper is feasible to improve the accuracy of wearable equipment ECG R wave monitoring.