[1]许春冬,龙清华.基于优化后向传播神经网络的基础心音分类[J].中国医学物理学杂志,2020,37(9):1181-1187.[doi:10.3969/j.issn.1005-202X.2020.09.019]
　XU Chundong,LONG Qinghua.Fundamental heart sound classification based on optimized back-propagation neural network[J].Chinese Journal of Medical Physics,2020,37(9):1181-1187.[doi:10.3969/j.issn.1005-202X.2020.09.019]
点击复制

基于优化后向传播神经网络的基础心音分类()
分享到：

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

卷:
37
期数:
2020年第9期
页码:
1181-1187
栏目:
医学人工智能
出版日期:
2020-09-25

文章信息/Info

Title:
Fundamental heart sound classification based on optimized back-propagation neural network
文章编号:
1005-202X（2020）09-1181-07
作者:
许春冬; 龙清华
江西理工大学信息工程学院，江西赣州341000
Author(s):
XU Chundong;  LONG Qinghua
School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
关键词:
人工蜂群算法; 后向传播神经网络; 混沌系统; 基础心音分类
Keywords:
artificial bee colony algorithm back-propagation neural network chaotic system fundamental heart sound classification
分类号:
R318；TN912.1
DOI:
10.3969/j.issn.1005-202X.2020.09.019
文献标志码:
A
摘要:
针对后向传播（BP）神经网络高度依赖初始权值、收敛慢且易陷入局部极值，标准人工蜂群算法开发能力弱、局部 搜索能力差等问题，提出一种基于改进人工蜂群算法优化BP神经网络的分类方法。引入自适应和全局最优策略改进人 工蜂群算法中跟随蜂蜜源全局搜索、概率选择算法，使用当前迭代的最优解来提高其开发能力。此外，利用混沌系统产生 初始种群，以增强人工蜂群算法全局收敛性。最后，将本文算法应用到基础心音分类。结果表明本文算法较经典分类算 法分类准确率有较大的提升。梅尔频率倒谱特征参数下，本文算法的分类准确率达到94%以上。
Abstract:
For solving the problems of back-propagation (BP) neural network such as highly relying on initial weights, slow convergence and easily falling into local extremum, and the weak development capability and poor local search ability of standard artificial bee colony (ABC) algorithm, a classification method based on improved ABC algorithm is proposed to optimize BP neural network. The adaptive and global optimal strategies are introduced to improve the global search and probability selection algorithm of honey sources in ABC algorithm, and the optimal solution of the current iteration is used to improve the development capability. In addition, chaotic systems are used to generate initial populations, thus enhancing the global convergence of ABC algorithm. Finally, the proposed algorithm is applied in fundamental heart sound recognition. The experimental results show that the classification accuracy of the proposed algorithm is superior to that of the classical classification algorithms. Based on Mel-scale frequency cepstral coefficients, the proposed algorithm can achieve a classification accuracy rate above 94%.

相似文献/References:

[1]杨 菲,郭旭东,翟 刚.用于胶囊内窥镜方位求解的LM人工蜂群算法[J].中国医学物理学杂志,2015,32(03):322.[doi:10.3969/j.issn.1005-202X.2015.03.005]
[2]马玉良,刘卫星,张淞杰,等.基于ABC-SVM的运动想象脑电信号模式分类[J].中国医学物理学杂志,2018,35(9):1056.[doi:10.3969/j.issn.1005-202X.2018.09.012]
　MAYuliang,LIUWeixing,ZHANG Songjie,et al.Pattern classification of motor imagery EEG signals based on ABC-SVM algorithm[J].Chinese Journal of Medical Physics,2018,35(9):1056.[doi:10.3969/j.issn.1005-202X.2018.09.012]

备注/Memo

备注/Memo:
【收稿日期】2020-03-21 【基金项目】国家自然科学基金（11704164, 11864016） 【作者简介】许春冬，博士，副教授，研究方向：语音信号处理、心音信号 处理，E-mail: 939022210@qq.com
更新日期/Last Update: 2020-09-25