Design Of Intelligent Diagnostic Terminal Algorithm Of Electrocardiogram And Realization Of Software Based On Android System

Cardiovascular disease is a kind of sudden illness which has high disability ratio and death ratio,and each year the number of death from heart disease accounted for 1/3 of the number of death.Early long-term monitoring is the best control method to prevent sudden illness.Long-term inspection in hospital not only consumes long time,but also costs much,which is a heavy burden to common people.At present,the household Electrocardiogram(ECG)monitor already appeared in the market has the disadvantages of bulkiness and lacking local diagnosis.While the ECG monitoring system based on mobile platform not only saves the cost of equipment and reduces the size of equipment,but also can achieve local ECG diagnosis and telematics,which will be the design trends of mobile medical product.Therefore,this paper presents the design of the ECG intelligent algorithm and the implement of the terminal software on the Android system.According to the needs of the project,designing the framework of entire system was the first step,then analyzed the main content of this paper and the problems need to address.This paper concretely introduced the design of intelligent diagnosis terminal algorithm of ECG and development of software.The intelligent diagnosis algorithm included signal preprocessing,feature extraction and classification.First applied the wavelet transform combined with morphological filtering method for signal preprocessing to get the relatively clean signal.Then extracted feature parameters of QRS complex by using K-means clustering algorithm.Besides,the calibration samples and prediction samples were established according to the feature parameters,and finally adopt the Extreme Learning Machine(ELM)classifier for sample training match and classification recognition.This paper used the data from the MIT-BIH Arrhythmia database as analysis object,and the final results demonstrated that this algorithm could accurately diagnose with Premature Ventricular Contraction(PVC)and Atrial Premature Contraction(APC).Eventually the positive detection rate(P+)of PVC was up to 94.20%,the detection sensitivity(Se)of PVC was up to 96.30%,and the P+ of APC was up to 98.02%,the detection Se of APC was up to 99%.The algorithm was embedded into the Android client after tested and verified,and realized the real-time analysis and processing.The function of Android client included blue-tooth transmission,real-time graphics,user management,design of interface and other functions.The result was uploaded by client to the web server via the Internet.The web server would response to client's request in real time.For example,it stored the data uploaded by client into database,or sent the data read from the database to the client.The web server realized the management and maintenance of data as well.This system has the advantages of simple operation,stable running and good scalability,and the following step is to extend the functions of communication by network and remote diagnosis,which has the positive significance to the prevention and control of cardiovascular disease.