A novel deep neural network model incorporating automatic feature abstraction achieved an overall accuracy of 97.5% for heartbeat classification on the MIT-BIH arrhythmia database.
A novel deep learning model using modified frequency slice wavelet transform and stacked denoising auto-encoder achieved 97.5% accuracy in ECG heartbeat classification, demonstrating potential for automated arrhythmia diagnosis.
Heartbeat classification is a crucial step for arrhythmia diagnosis during electrocardiographic (ECG) analysis. The new scenario of wireless body sensor network- (WBSN-) enabled ECG monitoring puts forward a higher-level demand for this traditional ECG analysis task. Previously reported methods mainly addressed this requirement with the applications of a shallow structured classifier and expert-designed features. In this study, modified frequency slice wavelet transform (MFSWT) was firstly employed to produce the time-frequency image for heartbeat signal. Then the deep learning (DL) method was performed for the heartbeat classification. Here, we proposed a novel model incorporating automatic feature abstraction and a deep neural network (DNN) classifier. Features were automatically abstracted by the stacked denoising auto-encoder (SDA) from the transferred time-frequency image. DNN classifier was constructed by an encoder layer of SDA and a softmax layer. In addition, a deterministic patient-specific heartbeat classifier was achieved by fine-tuning on heartbeat samples, which included a small subset of individual samples. The performance of the proposed model was evaluated on the MIT-BIH arrhythmia database. Results showed that an overall accuracy of 97.5% was achieved using the proposed model, confirming that the proposed DNN model is a powerful tool for heartbeat pattern recognition.
Luo et al. (Sun,) conducted a other in Arrhythmia. Deep neural network (DNN) classifier with stacked denoising auto-encoder (SDA) was evaluated on Overall accuracy of heartbeat classification. A novel deep neural network model incorporating automatic feature abstraction achieved an overall accuracy of 97.5% for heartbeat classification on the MIT-BIH arrhythmia database.