No abstract

In this study, two variants of genetic programming, namely linear genetic programming (LGP) and multi-expression programming (MEP) are utilized to detect atrial fibrillation (AF) episodes. LGP-and MEP-based models are derived to classify samples of AF and Normal episodes based on the analysis of RR interval signals. A weighted least-squares (WLS) regression analysis is performed using the same features and data sets to benchmark the models. Another important contribution of this paper is identification of the effective time domain features of heart rate variability (HRV) signals upon an improved forward floating selection (IFFS) analysis. The models are developed using MIT-BIH arrhythmia database. The diagnostic performances of the LGP and MEP classifiers are evaluated through receiver operating characteristics (ROC) analysis. The results indicate that the LGP and MEP models are able to diagnose the AF arrhythmia with an acceptable high accuracy. The proposed models have significantly better diagnosis performances than the regression and several models found in the literature.