Arrhythmias Classification Using the Fractal Behavior of the Power Spectrum Density of the QRS Complex and ANN - Université d'Orléans Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Arrhythmias Classification Using the Fractal Behavior of the Power Spectrum Density of the QRS Complex and ANN

Mohamed Lamine Talbi
  • Fonction : Auteur
  • PersonId : 916818
Abdelfatah Charef
  • Fonction : Auteur
  • PersonId : 916819

Résumé

In this paper we propose a method to discriminate arrhythmias using the fractal behavior of the power spectrum density of the QRS complexes. The linear interpolation of the QRS complex power spectrum density in Bode diagram in two different frequency intervals gives two straight lines with two different slopes. The scatter plot of one slope versus the other shows that we can distinct the normal beats from the abnormal one. Therefore, two experiences have been elaborated to verifier usefulness of the proposed method. The PVC beats are clustered using a Self Organizing Map (SOM) neural network fed by the two slopes of the QRS complex power spectrum in the first experience, in the second experience we use multilayer perceptron (MLP) neural network to classify RBBB and normal beats. The MIT/BIH arrhythmia database is then used to evluate the usefulness of the proposed method.
Fichier non déposé

Dates et versions

hal-00655509 , version 1 (29-12-2011)

Identifiants

Citer

Mohamed Lamine Talbi, Abdelfatah Charef, Philippe Ravier. Arrhythmias Classification Using the Fractal Behavior of the Power Spectrum Density of the QRS Complex and ANN. International Conference on High Performance Computing and Simulation, Jun 2010, Caen, France. pp.399-404, ⟨10.1109/HPCS.2010.5547107⟩. ⟨hal-00655509⟩
38 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More