A fixed-point blind source extraction algorithm and its application to ECG data analysis

2012 ◽  
Author(s):  
Hongjuan Zhang ◽  
Zikai Wu ◽  
Shuxue Ding ◽  
Luonan Chen
Keyword(s):  
Fixed Point ◽  
Data Analysis ◽  
Blind Source Extraction ◽  
Extraction Algorithm ◽  
Source Extraction ◽  
Ecg Data

A Method for Extracting Signals with Specific Normalized Kurtosis Range

2013 ◽  
Vol 756-759 ◽  
pp. 3845-3848
Author(s):  
Yong Jian Zhao ◽  
Mei Xia Qu ◽  
Hai Ning Jiang
Keyword(s):  
A Priori ◽  
Signal Separation ◽  
Blind Signal Separation ◽  
Validity And Reliability ◽  
Original Source ◽  
Blind Source Extraction ◽  
Blind Signal ◽  
Extraction Algorithm ◽  
Fastica Algorithm ◽  
Source Extraction

The famous FastICA algorithm has been widely used for blind signal separation. For every process, it only converges to an original source which has the maximum negentropy of the underlying signals. To ensure the first output is the desired signal, we incorporate a priori knowledge as a constraint into the FastICA algorithm to construct a robust blind source extraction algorithm. One can extract the desired signal if its normalized kurtosis is known to lie in a specific range, whereas other unwanted signals do not belong to this range. Experimental results on biomedical signals illustrate the validity and reliability of the proposed method.

An Improved Blind Source Extraction Algorithm

2014 ◽  
Vol 926-930 ◽  
pp. 2964-2967
Author(s):  
Shou Cheng Zhang
Keyword(s):  
Computational Complexity ◽  
Independent Component Analysis ◽  
Reference Signal ◽  
Component Analysis ◽  
Independent Component ◽  
Blind Source Extraction ◽  
Extraction Algorithm ◽  
Source Signal ◽  
Constrained Independent Component Analysis ◽  
Source Extraction

One-unit independent component analysis with reference (ICA-R) is an efficient method capable of extracting a desired source signal by using reference signal. In this paper, a new fast one-unit ICA-R algorithm is derived by using kurtosis contrast function based on new constrained independent component analysis (cICA) theory. The proposed algorithm has lower computational complexity and accurate extraction. Experiments with synthetic signals demonstrate the efficacy and accuracy of the proposed algorithm.

An Intelligent Atrial Fibrillation Wireless Monitoring System Based on Nonlinear Bind Source Extraction Algorithm

2011 ◽  
Vol 128-129 ◽  
pp. 74-78
Author(s):  
Kai Xu ◽  
Ying Hai Shao ◽  
Gang Wang
Keyword(s):  
Atrial Fibrillation ◽  
Monitoring System ◽  
Liquid Crystal Display ◽  
Low Cost ◽  
Sensor Nodes ◽  
Long Distance ◽  
Blind Source Extraction ◽  
Extraction Algorithm ◽  
Healthcare Monitoring ◽  
Source Extraction

The proposed system is designed to monitor patients with atrial fibrillation (AF) in family. This system mainly consists of wireless sensor networks (WSNs), which contains several mobile sensor nodes and coordinator for acquisition of bio-signals, and an embedded computer (EC) for signal processing. The WSNs are responsible to acquire and transmit Electrocardiogram (ECG). The EC is to extract the AF signal using nonlinear blind source extraction (BSE) algorithm. The extracted AF signal is then utilized to intelligently judge whether or not AF is on, based on which the system will send alert information to related doctors via Ethernet. In the meantime, the extracted AF signal is displayed on liquid crystal display (LCD), and then is also sent to relate doctors. The system aims to be low-cost, low-power consumption, small size and long-distance (up to thirty meters) transmission, can be further integrated into other healthcare monitoring system, and is expected to have great potential in family monitoring.

FECG Extraction Algorithm Based on BSS Using Temporal Structure and DWT

2014 ◽  
Vol 571-572 ◽  
pp. 209-212 ◽  
Author(s):  
Rui Li ◽  
Bao Feng Chen
Keyword(s):  
Wavelet Transformation ◽  
Temporal Structure ◽  
Discrete Wavelet ◽  
Fetal Electrocardiogram ◽  
Second Order Statistics ◽  
Blind Source Extraction ◽  
Extraction Algorithm ◽  
Source Extraction ◽  
Noise Reduction Technique ◽  
Source Number

Fetal electrocardiogram (FECG) blind source extraction (BSE) algorithm based on temporal structure and discrete wavelet transformation (DWT) in noise is proposed in this paper. After building the basic blind source separation (BSS) and BSE models for FECG, some preprocessing procedures based on the temporal structure of the FECG are constructed. Using DWT we can move the conventional time-domain signals to the wavelet-domain, and then the source number is detected and the robust noise reduction technique in FECG can be deduced too. According this preprocessing and second-order statistics (SOS), the proposed robust FECG extraction algorithm is derived.

Sign in / Sign up

Export Citation Format

Share Document