The following information was submitted:
Transactions: PARTIAL DIFFERENTIAL EQUATIONS – New Techniques and Methodologies in Engineering Problems
Transactions ID Number: 10-125
Full Name: Pedro Reis Gomes
Position: Assistant Professor
Age: ON
Sex: Male
Address: Largo Tinoco de Sousa 4760-108 V. N. Famalicao
Country: PORTUGAL
Tel: +351252309200
Tel prefix:
Fax: +351252376363
E-mail address: pedroreis@fam.ulusiada.pt
Other E-mails: pedrorgomes@netcabo.pt
Title of the Paper: ECG Classification by Using Wavelet-Domain Hidden Markov Models
Authors as they appear in the Paper: Pedro R. Gomes, Filomena O. Soares, J. H. Correia, C. S. Lima
Email addresses of all the authors: pedroreis@fam.ulusiada.pt,filomena.soares@dei.uminho.pt,higino.correia@dei.uminho.pt,carlos.lima@dei.uminho.pt
Number of paper pages: 10
Abstract: This article is concerned with the classification of ECG pulses by using state of the art Continuous Density Hidden Markov Models (CDHMM's). The ECG signal is simultaneously observed at different level of focus by means of the Wavelet Transform (WT). The types of beat being selected are normal (N), premature ventricular contraction (V) which is often precursor of ventricular arrhythmia, two of the most common class of supra-ventricular arrhythmia (S), named atrial fibrillation (AF), atrial flutter (AFL), and normal rhythm (N). Based on long term statistics taken from MIT-BIH Arrhythmia Database a threshold is established above which no misclassifications were obtained. ECG pulses which likelihood is below this threshold are selected for a posterior physician analysis. Experimental results were obtained in real data from MIT-BIH Arrhythmia Database and also in data acquired from a developed low-cost Data-Acquisition System.
Keywords: Hidden Markov Models, Wavelets, Cardiac Arrhythmia Classification.
EXTENSION of the file: .doc
Special (Invited) Session: Cardiac Arrhythmia Help – Diagnosis System Using Wavelets and Hidden Markov Models
Organizer of the Session: Paper 618-264
How Did you learn about congress:
IP ADDRESS: 194.79.71.201
