Optimal DNN architecture search using Bayesian Optimization Hyperband for arrhythmia detection

Automatic detection of arrhythmia using electrocardiogram (ECG) signal is an important role in the early diagnosis of cardiovascular diseases. Most of the arrhythmia detection researches have focused on the analysis of 1D time-series ECG signals, where deep neural network architecture have been applied due to its reliable and high performance. However, the hyperparameters of the deep learning model are mostly chosen empirically by the developer, which could be often suboptimal. For the optimal hyperparameter search, we propose the application of Bayesian optimization hyperband (BOHB) to the architectures of convolutional neural networks (CNN) and long short-term memory (LSTM). To evaluate the performance of the efficiently obtained DNN structures, we measured the overall accuracy and macro-averaged F1 score were measured, which were 0.7280 and 0.5931, while the overall accuracy and macro-averaged F1 score of empirically designed DNN were 0.7110 and 0.5679, respectively. The results demonstrate the optimized model outperforms the empirically designed model.