Title :
Human magnetocardiogram (MCG) modeling using evolutionary artificial neural networks
Author :
Georgopoulos, E.F. ; Likothanassis, S.D.
Author_Institution :
Dept. of Comput. Eng. & Inf., Patras Univ.
Abstract :
In the present work magnetocardiogram (MCG) recordings of normal subjects were analyzed using a hybrid training algorithm. This algorithm combines genetic algorithms and a training method based on the localized Extended Kalman Filter (EKF), in order to evolve the structure and train Multi-Layered Perceptrons (MLP) networks. Our goal is to examine the predictability of the MCG signal on a short predicting horizon
Keywords :
genetic algorithms; learning (artificial intelligence); magnetocardiography; medical signal processing; multilayer perceptrons; Multi-Layered Perceptrons; evolutionary artificial neural networks; genetic algorithms; hybrid training; localized Extended Kalman Filter; magnetocardiogram; Artificial neural networks; Biomedical engineering; Biomedical informatics; Filtering algorithms; Humans; Neural networks; Pattern recognition; Physics computing; SQUIDs; Superconducting magnets;
Conference_Titel :
Combinations of Evolutionary Computation and Neural Networks, 2000 IEEE Symposium on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-6572-0
DOI :
10.1109/ECNN.2000.886226
