[1]尘昌华,乔风娟,李 彬.一种用于心电图分类的改进神经网络算法[J].计算机技术与发展,2023,33(01):178-186.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 027]
　CHEN Chang-hua,QIAO Feng-juan,LI Bin.An Improved Neural Network Algorithm for ECG Classification[J].,2023,33(01):178-186.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 027]
点击复制

一种用于心电图分类的改进神经网络算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年01期
页码:
178-186
栏目:
人工智能
出版日期:
2023-01-10

文章信息/Info

Title:
An Improved Neural Network Algorithm for ECG Classification
文章编号:
1673-629X(2023)01-0178-09
作者:
尘昌华1 ; 乔风娟2 ; 李 彬2
1. 上海开放大学奉贤分校,上海 201499;
2. 齐鲁工业大学(山东省科学院) 数学与统计学院,山东 济南 250353
Author(s):
CHEN Chang-hua1 ; QIAO Feng-juan2 ; LI Bin2
1. Shanghai Open University Fengxian Branch,Shanghai 201499,China;
2. School of Mathematics and Statistics,Qilu University of Technology ( Shandong Academy of Sciences) ,Jinan 250353,China
关键词:
极限学习机; 局部感受野; 双向长短时记忆网络; 注意力机制; 心电图
Keywords:
extreme learning machine; local receptive field; bidirectional long short-term memory network; attention mechanism; electrocardiogram
分类号:
TP183
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 01. 027
摘要:
心血管疾病的死亡率在所有疾病中居于首位,心电图能够反映人体的电信号活动情况,它已成为医生用来诊断心血管疾病的重要依据。 随着计算机辅助 ECG 诊断技术的快速发展,深度学习方法已能够实现 ECG 信号的特征提取和分类。 为了较好地提高 ECG 信号的分类识别率和处理效率,该文提出了一种新的心电图分类方法。 首先,对原始数据进行去噪,提出了基于经验小波变换( EWT) 的提升小波阈值去噪方法。 然后,重构经过提升小波阈值去噪技术处理过的模态分量。 在训练过程中,设计了基于局部感受野的极限学习机( ELM-LRF)和双向长短时记忆网络( BLSTM) 结合的神经网络算法,并利用注意力机制优化该算法,提出了 LRF-BLSTM-Attention 模型。 最后,在 CCDD 和 MIT-BIH 数据集上对提出算法的性能进行验证,准确率分别达到 86. 12% 和 99. 87% ,证明了该算法在临床心血管疾病智能诊断中的实用性。 与其他模型相比,该模型的收敛速度更快,收敛的损失值更小。
Abstract:
The mortality of cardiovascular disease ranks first among all diseases. ECG can reflect the activity of human electrical signals,which has become an important basis for doctors to diagnose cardiovascular diseases. With the rapid development of computer - aidedECG diagnosis technology,deep learning method has been able to realize the feature extraction and classification of ECG signals. In orderto better improve the classification and recognition rate and processing efficiency of ECG signals,a new ECG classification method is proposed. First of all, the original data is denoised and an improved wavelet threshold denoising method based on empirical wavelettransform ( EWT ) is proposed, and then the modal components processed by lifting wavelet threshold denoising technology arereconstructed. In the training process,a neural network algorithm combining local receptive fields based extreme learning machine (ELM-LRF) and bidirectional long short-term memory network ( BLSTM) is designed,and the attention mechanism is introduced to optimizethe model. Finally, the performance of the proposed algorithm is verified on CCDD and MIT - BIH Arrhythmia Datasets. Theclassification accuracy rates have reached 86. 12% and 99. 87% ,respectively,proving the algorithm爷 s practicability and effectiveness inclinical intelligent diagnosis of cardiovascular diseases. Compared with other models,the convergence speed of such model is faster andthe loss of convergence is smaller.

相似文献/References:

[1]刘作志,刘欢,林耀海. 基于极限学习机的图像压缩算法[J].计算机技术与发展,2015,25(05):13.
　LIU Zuo-zhi,LIU Huan,LIN Yao-hai. Image Compression Algorithm Based on Extreme Learning Machine[J].,2015,25(01):13.
[2]邓万宇,张 倩,屈玉涛.基于ELM-AE 的二进制非线性哈希算法[J].计算机技术与发展,2017,27(12):61.[doi:10.3969/ j. issn.1673-629X.2017.12.014]
　DENG Wan-yu,ZHANG Qian,QU Yu-tao.A Binary Nonlinear Hashing Algorithm with ELM Auto-encoders[J].,2017,27(01):61.[doi:10.3969/ j. issn.1673-629X.2017.12.014]
[3]佘雅莉,周 良.基于改进在线序列学习机的危险源识别算法[J].计算机技术与发展,2018,28(09):72.[doi:10.3969/ j. issn.1673-629X.2018.09.016]
　SHE Ya-li,ZHOU Liang.Hazard Identification Algorithm Based on Improved Online Sequential Extreme Learning Machine[J].,2018,28(01):72.[doi:10.3969/ j. issn.1673-629X.2018.09.016]
[4]朱小明.基于多光谱遥感图像信息的水质污染监测研究[J].计算机技术与发展,2018,28(11):52.[doi:10.3969/ j. issn.1673-629X.2018.11.012]
　ZHU Xiao-ming.Research on Water Quality Monitoring Based on Multi-spectral Remote Sensing Imagery[J].,2018,28(01):52.[doi:10.3969/ j. issn.1673-629X.2018.11.012]
[5]刘俊杰,张昕,杨乐,等.基于 DELM 的不确定数据流分类算法[J].计算机技术与发展,2019,29(03):101.[doi:10.3969/ j. issn.1673-629X.2019.03.022]
　LIU Jun-jie,ZHANG Xin,YANG Le,et al.An Uncertain Data Stream Classification Algorithm Based on Distributed Extreme Learning Machine[J].,2019,29(01):101.[doi:10.3969/ j. issn.1673-629X.2019.03.022]
[6]许二戗,于化龙.基于粒子群的多标记阈值自适应极限学习机[J].计算机技术与发展,2019,29(04):47.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 010]
　XU Er-qiang,YU Hua-long.An Extreme Learning Machine of Multi-label Threshold Adaptation Based on Particle Swarm Optimization[J].,2019,29(01):47.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 010]
[7]范馨月.基于小波降噪的深度极限学习机交通流量预测[J].计算机技术与发展,2021,31(11):41.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 007]
　FAN Xin-yue.Traffic Flow Prediction Based on Deep Extreme Learning Machine with Wavelet De-noising[J].,2021,31(01):41.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 007]
[8]陆子豪,荆晓远.基于改进 SMOTE 的半监督极限学习机缺陷预测[J].计算机技术与发展,2021,31(12):21.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 004]
　LU Zi-hao,JING Xiao-yuan.Semi-supervised Extreme Learning Machine Based on Improved SMOTE for Software Defect Prediction[J].,2021,31(01):21.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 004]
[9]丁胜夺,谭 昆,田 琨,等.基于自适应遗传算法的极限学习机改进算法[J].计算机技术与发展,2022,32(S1):26.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 006]
　DING Sheng-duo,TAN Kun,TIAN Kun,et al.Improved Algorithm of Extreme Learning Machine Based on Adaptive Genetic Algorithm[J].,2022,32(01):26.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 006]
[10]周慧婕,陈小惠*,于舒洋,等.基于 PSO-ELM 的无创血压检测方法[J].计算机技术与发展,2022,32(12):63.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 010]
　ZHOU Hui-jie,CHEN Xiao-hui*,YU Shu-yang,et al.Non-invasive Blood Pressure Detection Method Based on PSO-ELM[J].,2022,32(01):63.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 010]

更新日期/Last Update: 2023-01-10