Feature extraction based on time-singularity multifractal spectrum distribution in intracardiac atrial fibrillation signals

Journal Title: TecnoLógicas - Year 2017, Vol 20, Issue 40

Abstract

Non-linear analysis of electrograms (EGM) has been proposed as a tool to detect critical conduction sites (e.g., rotors vortex, multiple wavefronts) in atrial fibrillation (AF). Likewise, studies have shown that multifractal analysis is useful to detect critical activity in EGM signals. However, the multifractal spectrum does not consider the temporal information. There is a new mathematical formalism to overcome this limitation: the time-singularity multifractal spectrum distribution (TS-MFSD), which involves the time variation of the spectrum. In this manuscript, we describe the methodology to compute the TS-MFSD from EGM signals. Moreover, we propose a methodology to extract features fromtime-singularity spectrum and from singularity energy spectrum (SES). We tested the features in an EGM database labeled by experts as: non-fragmented, discrete fragmented potentials, disorganized activity, and continuous activity. We tested the area underthe receiver operating characteristic (ROC) curve. The proposed features achieve an area under the ROC curve of 95.17% when detecting signals with continuous activity. These results outperform those reported using multifractal analysis. To our knowledge, this is the first work that report the use of TS-MFSD in biomedical signals and our findings suggest that time-singularity has the potential to be used in the study of non-stationary behavior of EGM signals in AF.

Authors and Affiliations

Robert D. Urda-Benitez, Andrés E. Castro-Ospina, Andrés Orozco-Duque

Keywords

Related Articles

Equivalent circuits for simulating irregular PV arrays under partial shading conditions

Modeling and simulation of photovoltaic (PV) systems are open research areas since I-V and P-V curves are commonly required to analyze the performance of PV installations. To obtain such curves commercial software packag...

Videogame for Water Conservation Teaching

Teaching water sustainability is a key element for environmental protection. Although that is true at all educational levels, it is vitally important during primary education because it enables students to develop adequa...

Microfabrication of position reference patterns onto glass microscope slides for high-accurate analysis of dynamic cellular events

Los portaobjetos de microscopio se utilizan ampliamente como sustratos base in situ para larealización de diversos sistemas o elementos microfabricados. Para estos fines, el proceso de microfabricación consiste en trans...

Mathematical model of photovoltaic systems for distributed maximum power point tracking

This paper presents a model of photovoltaic generation systems oriented to evaluate the performance of distributed maximum power point tracking algorithms. The model considers the series connection of n module-converter...

Comparison of multiobjective harmony search, cuckoo search and bat-inspired algorithms for renewable distributed generation placement

Electric power losses have a significant impact on the total costs of distribution networks. The use of renewable energy sources is a major alternative to improve power losses and costs, although other important issues a...

Download PDF file
  • EP ID EP346382
  • DOI 10.22430/22565337.716
  • Views 99
  • Downloads 0

How To Cite

Robert D. Urda-Benitez, Andrés E. Castro-Ospina, Andrés Orozco-Duque (2017). Feature extraction based on time-singularity multifractal spectrum distribution in intracardiac atrial fibrillation signals. TecnoLógicas, 20(40), 97-111. https://europub.co.uk./articles/-A-346382