Title :
Using FNN for classification of cardiac arrhythmia
Author :
Hou, Jianjun ; Wang, Tao ; Wu, Beiling
Author_Institution :
Northern Jiaotong Univ., Beijing, China
Abstract :
A method based on FNN (fuzzy neural network) is developed to create fuzzy membership functions for classification of cardiac arrhythmia in this paper. A FNN of Sugeno type is constructed firstly. The R-R interval and QRS complex are used as the inputs of the FNN. Then the cam delta learning algorithm is used to train the FNN through which the membership functions can be obtained. Fuzzy recognition using these membership functions can classify cardiac arrhythmia. The verification result shows that this method is effective.
Keywords :
cardiology; fuzzy neural nets; learning (artificial intelligence); medical computing; pattern classification; FNN training; QRS complex; R-R interval; Sugeno type; cam delta learning algorithm; cardiac arrhythmia classification; fuzzy membership functions; fuzzy neural network; fuzzy recognition; Algorithm design and analysis; Application software; Artificial intelligence; Electrocardiography; Fuzzy neural networks; Fuzzy sets; Monitoring; Resonance; Signal analysis; Signal mapping;
Conference_Titel :
TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering
Print_ISBN :
0-7803-7490-8
DOI :
10.1109/TENCON.2002.1181367
