[1]王巍,丁辉,夏旭,等.基于遗传算法优化C-LSTM模型的心律失常分类方法[J].中国医学物理学杂志,2024,41(2):233-240.[doi:DOI:10.3969/j.issn.1005-202X.2024.02.017]
　WANG Wei,DING Hui,XIA Xu,et al.Arrhythmia classification method based on genetic algorithm optimization of C-LSTM model[J].Chinese Journal of Medical Physics,2024,41(2):233-240.[doi:DOI:10.3969/j.issn.1005-202X.2024.02.017]
点击复制

基于遗传算法优化C-LSTM模型的心律失常分类方法()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第2期
页码:
233-240
栏目:
医学信号处理与医学仪器
出版日期:
2024-03-13

文章信息/Info

Title:
Arrhythmia classification method based on genetic algorithm optimization of C-LSTM model
文章编号:
1005-202X（2024）02-0233-08
作者:
王巍; 丁辉; 夏旭; 吴浩; 张迎; 郭家成
重庆邮电大学光电工程学院， 重庆 400065
Author(s):
WANG Wei;  DING Hui;  XIA Xu;  WU Hao;  ZHANG Ying;  GUO Jiacheng
School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
关键词:
心律失常分类; 遗传算法; GC-LSTM模型; 超参数
Keywords:
Keywords: arrhythmia classification genetic algorithm GC-LSTM model hyper-parameter
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2024.02.017
文献标志码:
A
摘要:
结合遗传算法全局寻优的特点提出一种GC-LSTM模型，该模型通过特定遗传策略的遗传算法自动迭代搜寻C-LSTM模型最佳超参数配置。利用遗传迭代结果配置模型，并按照医疗仪器促进协会制定分类标准在MIT-BIH心律失常数据库上进行验证。经过测试，本文提出的GC-LSTM模型在分类准确率（99.37%）、灵敏度（95.62%）、精确度（95.17%）、F1值（95.39%）上相较于手动搭建模型均有所提升，且与现有主流方法相比亦具备一定优势。实验结果表明该方法在避免大量实验调参的同时取得较好的分类性能。
Abstract:
Abstract: A GC-LSTM model is proposed based on the characteristics of global optimization of genetic algorithm. The model automatically and iteratively searches the optimal hyper-parameter configuration of the C-LSTM model through the genetic algorithm of a specific genetic strategy, and it is configured using the genetic iteration results and validated on the MIT-BIH arrhythmia database according to the classification criteria of the Association for the Advancement of Medical Instrumentation. The testing shows that the classification accuracy, sensitivity, accuracy and F1 value of GC-LSTM model are 99.37%, 95.62%, 95.17% and 95.39%, respectively, higher than those of the manually established model, and it is also advantageous over the existing mainstream methods. Experimental results demonstrate that the proposed method can achieve better classification performance while avoiding a large number of experimental parameters.

相似文献/References:

[1]陈元华,周正东,王东东,等.Varian Clinac iX 15 MeV光子束能谱重建[J].中国医学物理学杂志,2013,30(06):4503.[doi:10.3969/j.issn.1005-202X.2013.06.009]
[2]席卫文,张春辉,王飞,等.一种基于改进遗传算法的医学题库自动组卷设计与实现[J].中国医学物理学杂志,2016,33(8):861.[doi:10.3969/j.issn.1005-202X.2016.08.021]
　[J].Chinese Journal of Medical Physics,2016,33(2):861.[doi:10.3969/j.issn.1005-202X.2016.08.021]
[3]陈敏,王娆芬. 基于总体局部均值分解方法的心律失常特征提取与分类[J].中国医学物理学杂志,2019,36(10):1211.[doi:DOI:10.3969/j.issn.1005-202X.2019.10.019]
　CHEN Min,WANG Raofen. Feature extraction and classification of arrhythmia using ensemble local mean decomposition method[J].Chinese Journal of Medical Physics,2019,36(2):1211.[doi:DOI:10.3969/j.issn.1005-202X.2019.10.019]
[4]徐逸帆,曹乐,黄经纬,等.基于精英保留策略遗传算法的生物电阻抗特征参数提取[J].中国医学物理学杂志,2021,38(2):214.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.016]
　XU Yifan,CAO Le,HUANG Jingwei,et al.Extraction of bio-impedance characteristic parameters through genetic algorithm based on elitist preservation strategy[J].Chinese Journal of Medical Physics,2021,38(2):214.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.016]
[5]刘元峰,刘立波,刘云.基于CT图像的颅内血肿检测与分割[J].中国医学物理学杂志,2021,38(9):1090.[doi:10.3969/j.issn.1005-202X.2021.09.008]
　LIU Yuanfeng,LIU Libo,LIU Yun.Detection and segmentation of intracranial hematoma in CT image[J].Chinese Journal of Medical Physics,2021,38(2):1090.[doi:10.3969/j.issn.1005-202X.2021.09.008]

备注/Memo

备注/Memo:
【收稿日期】2023-08-12 【基金项目】重庆市科技局产业化项目（CSTC2018JSZX-CYZTZX0211, CSTC2018JSZX-CYZTZX0048） 【作者简介】王巍，博士后，教授，研究方向：数字多媒体信号处理及VLSI设计，E-mail: wangwei@cqupt.edu.cn
更新日期/Last Update: 2024-02-27