Arrhythmia Classification Using Local Hölder Exponents and Support Vector Machine

Abstract

Abstract. We propose a novel hybrid Hölder-SVM detection algorithm for arrhythmia classification. The Hölder exponents are computed efficiently using the wavelet transform modulus maxima (WTMM) method. The hybrid system performance is evaluated using the benchmark MIT-BIH arrhythmia database. The implemented model classifies 160 of Normal sinus rhythm, 25 of Ventricular bigeminy, 155 of Atrial fibrillation and 146 of Nodal (A-V junctional) rhythm with 96.94% accuracy. The distinct scaling properties of different types of heart rhythms may be of clinical importance.

Estimations of Hölder Regularities and Direction of Singularity by Hart Smith and Curvelet Transforms

“…This regularity information can be used for example in denoising, classification, or re-construction of signals [16,19,21]. However, due to its isotropic nature, wavelets are not optimal for analyzing anisotropic features like edges.…”

Engineering Principles in Biomedical Informatics

“…For these kinds of data a variety of methods are available to extract clinically interesting features and to provide decision-making instruments to clinicians and researchers [39][40][41][42][43][44][45]. For these kinds of data a variety of methods are available to extract clinically interesting features and to provide decision-making instruments to clinicians and researchers [39][40][41][42][43][44][45].…”

Baire Typical Results for Mixed Hölder Spectra on Product of Continuous Besov or Oscillation Spaces

“…dim E h f ). These spectra are useful in denoising, classification, or reconstruction of signals (see [22,23,35]). Definition 1.1.…”