Classification of cardiac arrhythmia by random forests with features constructed by kaizen programming with linear genetic programming

Classification of cardiac arrhythmia by random forests with features constructed by kaizen programming with linear genetic programming

Author Sotto, Leo F. D. P. Autor UNIFESP Google Scholar
Coelho, Regina C. Autor UNIFESP Google Scholar
de Melo, Vinicius V. Autor UNIFESP Google Scholar
Abstract Cardiac rhythm disorders may cause severe heart diseases, stroke, and even sudden cardiac death. Some arrhythmias are so serious that can cause injury to other organs, for instance, brain, kidneys, lungs or liver. Therefore, early and correct diagnosis of cardiac arrhythmia is essential to the prevention of serious problems. There are expert systems to classify arrhythmias from electrocardiograms signals. However, it has been shown that not only selecting the correct features from the dataset but also generating combined features could be the key to having real progress in classification. Therefore, this paper investigates a novel hybrid evolutionary technique to perform both tasks at the same time, finding complementary features that cover different characteristics of the data. The new features were tested with a widely-used classifier called Random Forests. The method reduced a dataset with 279 attributes to 26 attributes and achieved accuracies of 86.39% for binary classification and 77.69% for multiclass. Our approach outperformed several popular feature selection, feature generation, and state-of-the-art related work from the literature.
Keywords Kaizen Programming
Linear Genetic Programming
Random Forests
Ecg
ArrhythmiaMachine
Language English
Date 2016
Published in Gecco'16: Proceedings Of The 2016 Genetic And Evolutionary Computation Conference. New york, p. 813-820, 2016.
Publisher Wiley
Extent 813-820
Origin http://dx.doi.org/10.1145/2908812.2908882
Access rights Open access Open Access
Type Conference paper
Web of Science ID WOS:000382659200103
URI http://repositorio.unifesp.br/handle/11600/49394

Show full item record




File

File Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Search


Browse

Statistics

My Account