Research On Ecg Intelligent Diagnosis Based On Edge Cloud Collaborative Intelligent Medical Architecture

With the Internet of things devices are widely used in the collection of human medical data,how to collect and analyze the data in real time in practical application,and how to effectively diagnose and feedback in real time has become a very challenging problem.The maturity of edge computing and deep learning technology provides strong support for solving this problem.Electrocardiogram is one of the most commonly used clinical tests,which is widely used.At present,with the application of deep learning in the field of ECG,the automatic detection of ECG has made great progress.However,there are still some problems in the application of deep learning model based on cloud platform in real-time ECG monitoring,such as low availability,unable to meet the standard of daily monitoring such as blood pressure and pulse.Under the above background,this paper focuses on the two problems that the current intelligent medical architecture can not meet the real-time diagnosis of ECG and the serious imbalance of ECG data in the era of the Internet of things.The main work is as follows:First,a new hybrid intelligent Healthcare Architecture Based on edge computing and cloud computing,named edgecn,is proposed.This architecture can flexibly learn medical data from edge devices.Specifically,deep learning model is deployed to run on edge devices,which makes real-time analysis and diagnosis closer to Internet of things data sources.This can significantly reduce learning latency and network I / O,reduce the pressure of large user groups and massive data on the cloud platform,and greatly reduce the cost of building and maintaining the cloud platform.Secondly,relying on the edgecan architecture,this paper designs a simple and efficient ECG edge computing diagnosis model and learning algorithm based on convolutional neural network(CNN),and successfully deployed it on edge devices under the edgecan hybrid architecture.The model can infer ECG in real time closer to data source,and get a good balance between diagnosis accuracy and resource loss.Experimental results show that compared with cloud computing only architecture,edgecn not only ensures reasonable accuracy,but also has obvious advantages in diagnosis delay,network I / O,application availability and resource cost.More importantly,it can effectively protect the privacy of IOT device user data.Thirdly,due to the serious lack and imbalance of original data in ECG research,the current ECG diagnosis is limited to a few categories.In this paper,we propose a method to enhance ECG data by dcgan.Dcgan is a stable network architecture based on CNN extension,which has a very high credibility in unsupervised learning.Data enhancement can provide enough data quantity and category for ECG diagnosis based on edgecn architecture.The experimental results show that after the data enhancement of ECG data related categories,not only the overall accuracy of the deep learning model is improved,but also the ECG categories that the model can diagnose are greatly expanded,which greatly improves the practical usability of the system.