In this article, we present a resource-efficient approach for electrocardiogram (ECG) based heartbeat classification using multi-feature fusion and bidirectional long short-term memory (Bi-LSTM). The dataset comprises five original classes from the MIT-BIH Arrhythmia Database: Normal (N), Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Premature Ventricular Contraction (PVC), and Paced Beat (PB). Preprocessing methods including the discrete wavelet transform and dual moving average windows are used to reduce noise and artifacts in the raw ECG signal, and extract the main points (PQRST) of the ECG waveform. Multi-feature fusion is achieved by utilizing time intervals and the proposed under-the-curve areas, which are inherently robust against noise, as input features. Simulations demonstrated that incorporating under-the-curve area features improved the classification accuracy for the challenging RBBB and LBBB classes from 31.4\% to 84.3\% for RBBB, and from 69.6\% to 87.0\% for LBBB. Using a Bi-LSTM network, rather than a conventional LSTM network, resulted in higher accuracy (33.8\% vs 21.8\%) with a 28\% reduction in required network parameters for the RBBB class. Multiple neural network models with varying parameter sizes, including tiny (84k), small (150k), medium (478k), and large (1.25M) models, are developed to achieve high accuracy \textit{across all classes}, a more crucial and challenging goal than overall classification accuracy.

翻译：本文提出一种基于多特征融合与双向长短期记忆网络（Bi-LSTM）的资源高效型心电图（ECG）心跳分类方法。所用数据集包含来自MIT-BIH心律失常数据库的五类原始心跳：正常搏动（N）、左束支传导阻滞（LBBB）、右束支传导阻滞（RBBB）、室性早搏（PVC）以及起搏心跳（PB）。预处理方法采用离散小波变换与双移动平均窗口，以降低原始ECG信号中的噪声与伪影，并提取ECG波形的关键点（PQRST）。通过融合时间间隔特征与本文提出的曲线下面积特征——该特征对噪声具有天然鲁棒性——实现多特征融合。仿真实验表明，引入曲线下面积特征将具有挑战性的RBBB与LBBB类别的分类准确率分别从31.4%提升至84.3%（RBBB）以及从69.6%提升至87.0%（LBBB）。采用Bi-LSTM网络相较于传统LSTM网络，在RBBB类别上实现了更高的准确率（33.8%对比21.8%），同时所需网络参数减少了28%。本研究开发了参数量各异的多种神经网络模型（微型84k、小型150k、中型478k、大型1.25M），旨在实现所有类别的高准确率分类——这一目标比追求整体分类准确率更具关键性与挑战性。