Incremental learning of ensemble classifiers on ECG data

We develop novel methods of incremental learning based on the bagging and boosting approaches to ensemble learning. Our method combines perceptron decision trees obtained with a margin maximizing algorithm into an ensemble in an incremental way. We demonstrate practical functionality of our algorithm on the task of ECG records classification. Our results are promising since comparable or superior accuracy is achieved when compared with results obtained by other existing methods of classification of ECG records, namely with the C5.0 decision tree algorithm.