Arrhythmia Detection using Mutual Information-Based Integration Method
This work addresses arrhythmia detection for medical diagnosis, but it is incremental as it applies an existing ensemble technique to a specific domain.
The paper tackled arrhythmia detection by applying a mutual information-based ensemble method to classify heartbeats, achieving an overall ensemble accuracy of 98.25%.
The aim of this paper is to propose an application of mutual information-based ensemble methods to the analysis and classification of heart beats associated with different types of Arrhythmia. Models of multilayer perceptrons, support vector machines, and radial basis function neural networks were trained and tested using the MIT-BIH arrhythmia database. This research brings a focus to an ensemble method that, to our knowledge, is a novel application in the area of ECG Arrhythmia detection. The proposed classifier ensemble method showed improved performance, relative to either majority voting classifier integration or to individual classifier performance. The overall ensemble accuracy was 98.25%.