基于粒子群优化BP神经网络的心电信号分类方法  

Electrocardiographic Signal Classification Method Based on Particle Swarm Optimization BP Neural Network

作　　者：王莉[1] 张紫烨 郭晓东 牛群峰[1] WANG Li;ZHANG Zi-ye;GUO Xiao-dong;NIU Qun-feng(College of Electrical Engineering,Henan University of Technology,Zhengzhou 450001,China)

机构地区：[1]河南工业大学电气工程学院

出　　处：《自动化与仪表》2019年第9期84-87,93,共5页Automation & Instrumentation

基　　金：河南省科技厅自然科学项目(182102210089);河南工业大学校基金项目(2018XTCX02)

摘　　要：为了提高心电信号的分类精度,实现心电信号的智能诊断,该文提出了一种粒子群优化BP神经网络的心电信号分类算法。从正常、左束支传导阻滞、右束支传导阻滞3种心电信号中提取5组特征值作为特征向量,利用粒子群算法修正BP神经网络的初始权值和阈值,并对心电信号样本进行分类识别。实验结果表明,与BP神经网络相比,优化后的BP神经网络对心电信号分类精度更高,准确率达到了98.20%,同时收敛速度更快,明显提高了BP神经网络的全局寻优能力。In order to improve the classification accuracy of ECG signals and realize the intelligent diagnosis of ECG signals,an ECG signal classification algorithm based on particle swarm optimization BP neural network was proposed. Five sets of eigenvalues were extracted from normal,left bundle branch block,and right bundle branch block as feature vectors. Particle swarm algorithm was used to modify the initial weights and thresholds of BP neural network. Signal samples are classified and identified. The experimental results show that compared with BP neural network,the optimized BP neural network has higher accuracy of classification of ECG signals with an accuracy rate of 98.20%. At the same time,the convergence speed is faster,which significantly improves the global searching ability of BP neural network.

关 键 词：心电信号 粒子群算法 BP神经网络 分类 模式识别 QRS波群 

分 类 号：TN911[电子电信—通信与信息系统]