Paper Details: Downloads: 447
Serial Number: P1120836329
Title: ECG Beats Classification Using ELM/HMM Classifiers
Authors: Mahmoud A. Ismail
Abstract: This paper proposes a new approach for the automated classification of Electrocardiogram (ECG) signals, based on the framework of probabilistic modelling. The approach makes use of a number of techniques from machine learning, speech recognition and time-frequency analysis. The approach adopted in this paper is to train an Extreme Learning Machine (ELM) using data driven from hidden Markov models (HMMs) trained using a data set features driven from of ECG waveforms. This hybrization benefits from HMMs powerful generative nature and ELM discriminative nature. The performance of this new hybrid technique has been tested and the results were promising.
Keywords: ECG classification, Hidden Markov models, Extreme Learning Machine
Journal/Conference: International Journal of Artificial Intelligence and Machine Learning
Volume:
Issue:
Submission Date: 8/30/2008 12:00:00 AM
Review Date: 9/13/2008 12:00:00 AM
Publishing Date: 9/19/2008 12:00:00 AM
Article Downloads: 447
Download:

Facebook