Identifying the Mislabeled Training Samples of ECG Signals using Machine Learning

TL;DR

This paper presents a machine learning-based method using cross validation and multiple classifiers to identify and remove mislabeled ECG training samples, improving classification accuracy on the MIT-BIH arrhythmia database.

Contribution

It introduces a novel approach combining multiple classifiers and cross validation to effectively detect and eliminate mislabeled ECG training samples.

Findings

Improved classification accuracy after removing mislabeled samples

Effective identification of mislabeled ECG data using the proposed method

Validated results on the MIT-BIH arrhythmia database

Abstract

The classification accuracy of electrocardiogram signal is often affected by diverse factors in which mislabeled training samples issue is one of the most influential problems. In order to mitigate this negative effect, the method of cross validation is introduced to identify the mislabeled samples. The method utilizes the cooperative advantages of different classifiers to act as a filter for the training samples. The filter removes the mislabeled training samples and retains the correctly labeled ones with the help of 10-fold cross validation. Consequently, a new training set is provided to the final classifiers to acquire higher classification accuracies. Finally, we numerically show the effectiveness of the proposed method with the MIT-BIH arrhythmia database.