Title :
Robust ECG R-R wave detection using evolutionary-programming-based fuzzy inference system (EPFIS), and application to assessing brain-gut interaction
Author :
Wang, Z.S. ; Chen, J.D.Z.
Author_Institution :
Med. Branch, Texas Univ., Galveston, TX, USA
fDate :
11/1/2000 12:00:00 AM
Abstract :
Some recent studies have shown that gastric electrical stimulation can entrain gastric dysrhythmia, reduce chronic symptoms and accelerate gastric emptying. However, possible mechanisms involved remain unknown. It is investigated whether or not electrical stimulation is vagally mediated by assessing the heart rate variability (HRV). The study is performed in six healthy female hound dogs implanted with four pairs of bipolar serosal electrodes, which are used to measure gastric myoelectrical activity. A special fuzzy neural network, which is called the evolutionary programming-based fuzzy inference system (EPFIS), is developed to identify the R-R wave to precisely extract the R-R interval and derive the HRV data. A high-resolution adaptive time-frequency analysis method based on ARMA modelling previously developed by the author is used to obtain high quality HRV spectral parameters
Keywords :
biological organs; brain; electrocardiography; evolutionary computation; fuzzy neural nets; medical signal detection; medical signal processing; time-frequency analysis; R-R interval; brain-gut interaction assessment; electrodiagnostics; evolutionary-programming-based fuzzy inference system; gastric myoelectrical activity measurement; healthy female hound dogs; heart rate variability; high-resolution adaptive time-frequency analysis method; implanted bipolar serosal electrodes; robust ECG R-R wave detection;
Journal_Title :
Science, Measurement and Technology, IEE Proceedings -
DOI :
10.1049/ip-smt:20000852