ECG signal classification using block-based neural networks

This paper investigates the application of evolvable block-based neural networks (BbNNs) to ECG signal classification. A BbNN consists of a two-dimensional (2-D) array of modular basic blocks that can be easily implemented using reconfigurable digital hardware. BbNNs are evolved for each patient in order to provide personalized health monitoring. A genetic algorithm evolves the internal structure and associated weights of a BbNN using training patterns that consist of morphological and temporal features extracted from the ECG signal of a patient. The remaining part of the ECG record serves as the test signal. The BbNN was tested for ten records collected from different patients provided by the MIT-BIH Arrhythmia database. The evolved BbNNs produced higher than 90% classification accuracies.