Research on Heart Rate Signal Recognition based on Improved LSTM Network

ECG signal is an important means for diagnosing arrhythmia diseases. Utilizing artificial intelligence algorithms for ECG signal recognition can greatly improve diagnostic efficiency. In response to the issues of vanishing and exploding gradients in traditional Long Short-Term Memory (LSTM) networks, making it difficult to handle long-term dependencies in sequential data, this paper proposes an improved LSTM network model for arrhythmia recognition. Firstly, the original ECG signals are processed by wavelet transform to increase the diversity of temporal and spectral features of the ECG signals. Then, self-attention mechanism is incorporated into the Bidirectional LSTM network to construct the arrhythmia recognition network model. Experimental results show that the improved BiLSTM network for arrhythmia signal recognition is able to effectively identify five types of ECG signals including Normal beat, Supraventricular ectopic beat, Ventricular ectopic beats, Fusion beats, and Unclassified beats, with a mean Average Precision (mAP) of $\mathbf{9 8 . 1 5 \%}$.

I. Introduction

With the increasing prevalence of cardiovascular diseases such as coronary heart disease and hypertension, improving the quality of life of the population, maintaining sustainable economic development, and fully implementing the grand goal of health strategy pose a great challenge. Electrocardiogram (ECG), as an efficient tool for recording and analyzing the periodic electrophysiological activity of the heart over a certain period of time, provides an important basis for doctors to evaluate individual heart health. This is not only because of its low cost, fast recording speed, and non-invasive nature, but also because in clinical practice, the ECG has become the preferred method for non-invasive examination of heart disease patients. However, current intelligent identification technology for diagnosing cardiac arrhythmias mainly relies on the inherent experience of designers, which to some extent is constrained by the diagnostic level of doctors and the rich clinical experience rules. It has a certain subjectivity, and in the actual diagnosis and treatment process, the diagnostic needs of ECG require the detailed observation of doctors and the support and guidance of their rich diagnostic experience.