DocumentCode :
3251936
Title :
Classification of ECG patterns for diagnostic purposes by means of Neural Networks and Support Vector Machines
Author :
Conforto, Silvia ; Laudani, Antonino ; Oliva, Fabio ; Fulginei, Francesco Riganti ; Schmid, Maurizio
Author_Institution :
Dept. of Eng., Roma Tre Univ., Rome, Italy
fYear :
2013
fDate :
2-4 July 2013
Firstpage :
591
Lastpage :
595
Abstract :
This paper presents an application of Neural Networks (NNs) and Support Vector Machines (SVMs) for the detection and classification of heartbeats in electrocardiogram (ECG) signals. The preprocessing algorithm for the beats detection is based on well-known Pan-Tompkins´ algorithm. The proposed approach is robust to different types of noise and shows good performances both in beat analysis and QRS morphology extraction. The proposed method in combination with radial basis function SVM and adaptive NNs, brought remarkable results on the classification of different kind of cardiac arrhythmia as shown by suitable numerical simulations presented at the end of the paper.
Keywords :
adaptive signal processing; diseases; electrocardiography; feature extraction; medical signal processing; neural nets; numerical analysis; radial basis function networks; signal classification; support vector machines; ECG pattern classification; Pan-Tompkins algorithm; QRS morphology extraction; SVM; adaptive neural networks; beat analysis; cardiac arrhythmia; diagnostic purposes; electrocardiogram signals; heartbeat classification; heartbeat detection; numerical simulations; preprocessing algorithm; radial basis function; support vector machines; Algorithm design and analysis; Artificial neural networks; Classification algorithms; Electrocardiography; Heart beat; Support vector machines; Training; Arrhythmia beat recognition; ECG pattern classification; SVM; neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Telecommunications and Signal Processing (TSP), 2013 36th International Conference on
Conference_Location :
Rome
Print_ISBN :
978-1-4799-0402-0
Type :
conf
DOI :
10.1109/TSP.2013.6614003
Filename :
6614003
Link To Document :
بازگشت