SAMSUNG R& D INSTITUTE INDIA BANGALORE PRIVATE LIMITED
发明人:
CHAKROBORTY, SANDIPAN,BERA, DEEP
申请号：
IN359CH2013
公开号：
IN359CH2013A
申请日:
2013.01.28
申请国别(地区):
IN
年份:
2015
代理人:
摘要：
The present invention provides a method and apparatus for classifying cardiac arrhythmia using an auto associative neural network. in an embodiment, the method includes receiving an electrocardiogram (ECG) signal representing an electrical activity of a heart of an individual over a period of time, wherein the ECG signal comprising ECG beats. The method further includes generating synthetic beats corresponding to each of the ECG beats using an auto associative neural network (AANN) corresponding to each of arrhythmia classes, wherein each of the arrhythmia classes corresponds to a specific type of cardiac arrhythmia. Further, the method includes determining a synthetic beat corresponding to one of the arrhythmia classes among the synthetic beats as substantially matching the respective ECG beat. Furthermore, the method includes providing the arrhythmia class corresponding to the specific type of cardiac arrhythmia based on the identified synthetic beat substantially matching the ECG beat. Figure 2
