ECG signals filtering and analysis using the Compact Genetic Algorithm Based on Abstract Data Types in GPU/CUDA

Abstract

This paper presents the process of adaptive filtering of cardiovascular disease signals from the processing and cleaning of ECG signals developed by the Compact Genetic Algorithm Based on Abstract Data Types (CGAADT), implemented in MATLAB using GPU/CUDA architecture from the examples of the base of MIT-BIH data. The results show that CGAADT can improve the filtering, cleaning, detection and diagnosis of arrhythmias using a single algorithm (CGAADT) in the adoption of a representation for the population with fixed size of chromosomes, pre-established by fragmentation of the GPU base when implemented in high performance systems, aiming to improve the health systems offered to patients with cardiovascular problems.