盲信号分离
独立成分分析
计算机科学
语音识别
源分离
模式识别(心理学)
增强子
人工智能
萃取(化学)
化学
电信
色谱法
生物化学
基因
频道(广播)
基因表达
作者
Abhinav Gupta,Madhur Srivastava,Vineet Khandelwal,Abhilekh Gupta
标识
DOI:10.1109/icics.2007.4449716
摘要
Eight out of one thousand born live infants have some form of heart defect, making it the single most common class of congenital abnormalities. Identification of these cases during early pregnancy reduces risks by timely treatment or planned delivery. The non-invasive fetal ECG (FECG) monitoring by means of abdominal surface electrodes provides valuable information about the cardiac electrical activity of fetus. In this paper, analysis and comparative study of four channel adaptive maternal ECG canceller-adaptive fetal ECG enhancer (FAMC-AFE) and blind source separation (BSS-ICA) methods are presented. These methods have been applied to real multichannel ECG recordings obtained from a pregnant woman's skin and synthetic biomedical signals. After investigation of the results the BSS-ICA AFE approach, proposed by us, has been shown to be superior for extraction and enhancement of fetal ECG compared to other BSS scheme.
科研通智能强力驱动
Strongly Powered by AbleSci AI