Feasibility of probabilistic neural networks, Kohonen self-organizing maps and fuzzy clustering for source localization of ventricular focal arrhythmias from intravenous catheter measurements

Date

2009-02-01

Author

Sunay, Ahmet Sertac
Cunedioglu, Ugur
Yilmaz, Buelent

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

64
views

0
downloads

An important goal of clinical electrophysiological studies is estimation of the source of rhythm disturbances (arrhythmia) in the heart. 15% of ventricular arrhythmias are known to originate from the outer surface of the heart (epicardium). One localization approach targeting the epicardium uses multielectrode catheters placed in the coronary veins. However, epicardial measurement sites from these catheters are limited to locations reached via the coronary veins. This study investigates the feasibility of several pattern classification and neural network approaches for localization of the source of ventricular arrhythmias from sparse measurements acquired from within coronary veins. Specifically, we studied Kohonen self-organizing maps and fuzzy C-means clustering methods for the construction of the target vector in neural networks from experimental high-resolution activation-time patterns. We also studied two neural network techniques, probabilistic neural networks and backpropagation networks, for the training and test procedures. The results of this study showed that it was possible to localize the arrhythmia source in a relatively small region for approximately 70% of cases. This study, in general, showed that the combination of probabilistic neural networks, Kohonen self-organizing maps and fuzzy C-means clustering approaches is feasible in catheter-based epicardial arrhythmia source localization.

Subject Keywords

Control and Systems Engineering, Theoretical Computer Science, Computational Theory and Mathematics, Artificial Intelligence

URI

https://hdl.handle.net/11511/66259

Journal

EXPERT SYSTEMS

DOI

https://doi.org/10.1111/j.1468-0394.2008.00492.x

Collections

Graduate School of Natural and Applied Sciences, Article

Suggestions

OpenMETU
Core

Improving the k-nearest neighbour rule: using geometrical neighbourhoods and manifold-based metrics ALTINCAY, HAKAN (Wiley, 2011-09-01) Sample weighting and variations in neighbourhood or data-dependent distance metric definitions are three principal directions considered for improving the k-NN classification technique. Recently, manifold-based distance metrics attracted considerable interest and computationally less demanding approximations have been developed. However, a careful comparison of these alternative approaches is missing. In this study, an extensive comparison is firstly performed for three alternative neighbourhood definitions...
Coordination of intelligent agents in real-time search Cakir, A; Polat, Faruk (Wiley, 2002-05-01) Search is a fundamental problem-solving method in artificial intelligence. Traditional off-line search algorithms attempt to find an optimal solution whereas real-time search algorithms try to find a suboptimal solution more quickly than traditional algorithms to meet real-time constraints. In this work, a new multi-agent real-time search algorithm is developed and its effectiveness is illustrated on a sample domain, namely maze problems. Searching agents can see their environment with a specified visual de...
Introduction to the Special Issue on Fuzzy Analytics and Stochastic Methods in Neurosciences Kropat, E.; Turkay, M.; Weber, Gerhard Wilhelm (Institute of Electrical and Electronics Engineers (IEEE), 2020-01-01) The papers in this special section examine the use of fuzzy analytics and stochastic methods in the field of neuroscience. Recent theoretical and technological advancements provide new and deeper insights into the fundamental mechanisms of information processing in the neural system. This important process is accompanied by the tremendous rise of experimental data, which are waiting for further exploration. Modern methodologies and tools from neuroimaging, brain imaging, optogenetic devices, and in vitro an...
Usage of spline interpolation in catheter-based cardiac mapping Yilmaz, Bulent; Cunedioglu, Ugur; Baysoy, Engin (2010-01-01) Due to their minimal invasiveness catheters are highly preferred in cardiac mapping techniques used in the source localization of rhythm disturbances in the heart. In cardiac mapping, standard steerable catheters and multielectrode basket catheters are the two alternatives for the characterization of the underlying tissue on the inner (endocardium) and outer (epicardium) surfaces of the heart. As with any discrete sampling technique, an important question for catheter-based cardiac mapping is how to determi...
Estimation of the Balance-Keeping Control Law Applied by a Human Being Upon a Sudden Sagittal Tilt Perturbation BİLGİN, NURDAN; Özgören, Mustafa Kemal (2019-04-01) This study aims to estimate the control law employed by the central nervous system (CNS) to keep a person in balance after a sudden disturbance. For this aim, several experiments were carried out, in which the subjects were perturbed sagittally by using a single-axis tilt-platform and their motions were recorded with appropriate sensors. The analysis of the experimental results leads to the contribution of this paper as a conjecture that the CNS commands the muscular actuators of the joints according to an ...

Citation Formats

A. S. Sunay, U. Cunedioglu, and B. Yilmaz, “Feasibility of probabilistic neural networks, Kohonen self-organizing maps and fuzzy clustering for source localization of ventricular focal arrhythmias from intravenous catheter measurements,” EXPERT SYSTEMS, pp. 70–81, 2009, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/66259.