Automatic Detection of QRS Complexes using Quantum Neural Networks

The paper presents an approach to automatically detect QRS complexes using a novel type of neural networks, quantum neural networks(QNNs). QNNs are designed to achieve the goal through multilevel partitioning of the feature space. The capacity of QNNs for autonomously forming multilevel partitions of the feature space arises from their ability to create graded internal representations of the sample information provided by ECG signals. The fuzzy feature is expected to enhance the reliability of the network, which is critical for improving desirable diagnosis accuracy. The simulated results based on the MIT-BIH Arrhythmia Database confirmed the feasibility of the proposed approach.