Real-Time Arrhythmia Classification Algorithm Using Time-Domain ECG Feature Based on FFNN and CNN

Abstract

To solve the problem of real-time arrhythmia classification, this paper proposes a real-time arrhythmia classification algorithm using deep learning with low latency, high practicality, and high reliability, which can be easily applied to a real-time arrhythmia classification system. In the algorithm, a classifier detects the QRS complex position in real time for heartbeat segmentation. Then, the ECG_RRR feature is constructed according to the heartbeat segmentation result. Finally, another classifier classifies the arrhythmia in real time using the ECG_RRR feature. This article uses the MIT-BIH arrhythmia database and divides the 44 qualified records into two groups (DS1 and DS2) for training and evaluation, respectively. The result shows that the recall rate, precision rate, and overall accuracy of the algorithm’s interpatient QRS complex position prediction are 98.0%, 99.5%, and 97.6%, respectively. The overall accuracy for 5-class and 13-class interpatient arrhythmia classification is 91.5% and 75.6%, respectively. Furthermore, the real-time arrhythmia classification algorithm proposed in this paper has the advantages of practicability and low latency. It is easy to deploy the algorithm since the input is the original ECG signal with no feature processing required. And, the latency of the arrhythmia classification is only the duration of one heartbeat cycle.

Exploring ECG Signal Analysis Techniques for Arrhythmia Detection: A Review

“…Given its high performance in detecting pathological classes such as SVEBs and VEBs, this study presents a promising method for ECG classification tasks, especially in scenarios where the number of patients is limited. Jing Cai et.al [44] This paper presents a real-time arrhythmia classification algorithm based on deep learning, aiming for low latency, high practicality, and reliability suitable for real-time arrhythmia classification systems. The algorithm begins by detecting the QRS complex position in real-time for heartbeat segmentation, followed by the construction of the ECG_RRR feature based on the segmentation results.…”

Real-time Signal Processing of UWB Fuze Based On 1D-CNN Model

“…There are fewer studies using neural networks for UWB fuze signal processing. Xie et al [7] applied 1D-CNN to radar automatic target recognition, but the input channel includes power spectrum and power transform spectrum in addition to the signal time domain waveform, which is very time-consuming to perform the spectral transform on the actual hardware circuit, and does not meet the high requirements of fuze for real-time; Cai et al [8] successfully applied 1D-CNN to the diagnosis of ECG signal derangement, but its convolutional layers C1 and C2 are fully connected, such a simple network structure has poor performance when facing the fuze echo signal in the actual complex noise environment.…”