A real-time ECG signal classification algorithm
作者单位：Nankai University Institute of Robotics ＆ Automatic Information System
会议名称：《第三十九届中国控制会议》
会议日期：2020年
学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 0711[理学-系统科学] 07[理学] 08[工学] 1010[医学-医学技术（可授医学、理学学位）] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 10[医学]
关 键 词：embedded systems ECG deep neural network autonomous learning
摘 要：Embedded systems are widely used in diagnostic equipment due to their small size,low power consumption,and low ***,because of their small memory and low frequency,some high-precision algorithms are restricted from achieving the desired *** at the above this problems,a simple deep neural network algorithm is *** addition,the electrocardiogram（ECG） signal is a specific signal and it is difficult for a fixed classifier to meet the accuracy ***,an autonomous learning algorithm based on posterior probability estimation is used to screen heartbeats that are both characteristic and *** beats are marked by the doctor and will then be used to fine-tune the classifier ***,the algorithm proposed by the author is compared with other ECG signal classification *** classification accuracy of the algorithm for supraventricular arrhythmias and ventricular arrhythmias reached 99.3% and 99.6%,*** average time for the algorithm to classify a single heartbeat is 43.68 ms.