没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
II
摘 要
心血管疾病的检测和预防是当下研究的热门。由于便利、经济等特点,心电信
号的检测成为了辅助医生诊断患者是否患有血管疾病的重要方法。传统的检测方
法需要临床医生根据自己的经验对心电信号进行分类,但医生对大量的数据进行
检测时容易产生疲劳,导致漏诊、误诊。针对以上问题,本文设计出了心电信号自
动检测方法,可以成为辅助临床医生检测的工具。随着对心电信号研究的深入,科
学人员发现,患者在发生睡眠呼吸暂停(Sleep apnea,SA)事件时,其心电信号会
产生特定规律的变化,根据这个变化可以判断出患者是否患有睡眠呼吸暂停。因此,
本文设计出一种基于心电信号的睡眠呼吸暂停检测方法。
论文主要工作如下:
(1) 根据心电信号的采样频率及其噪声特点,本文采用小波变换的方法去除信
号中掺杂的噪音。与采用中值滤波去噪的方法相比,小波变换在保证去除低频噪音
的基础上,对高频噪音也有着很好的去噪效果。这一部分为后续的工作奠定了基础。
(2) 为了将心电信号分成正常心拍或异常心拍,本文设计出了心电信号二分类
方法。现有深度学习方法在处理具有特异性的心电信号数据集时,所采用的交叉熵
损失寻找到分界面不会进一步优化,导致在心电信号这种具有特异性的数据集上
泛化能力较弱,针对这一不足,本文设计了一种基于结构风险最小化(Structural
Risk Minimization,SRM)的卷积神经网络(Convolutional Neural Network,CNN),
提升了模型对病人间数据集的泛化能力。相比于传统方法,所 设计的方法进一步提
升了分类器的性能。
(3) 在对心电信号进行二分类基础上,本文设计出了心电信号多分类方法。首
先,为了减轻传统网络进行多次卷积时导致的梯度消失问题,所设计的方法将每层
卷积的结果和上一层卷积的结果进行融合。接下来,针对使用的数据集类别严重不
平衡,引入了 focal loss 损失函数作为模型的优化目标。通过与其它方法对比,所
设计的方法具有更好的性能。
(4) 本文设计了一种基于心电信号的睡眠呼吸暂停检测方法。首先,提取出心
电信号的派生 RR 间期信号和 R 峰信号作为输入;然后,利用多尺度残差网络对
派生信号进行特征提取,以获取不同视角的敏感特征;最后,引入 focal loss 损失
函数代替传统的交叉熵损失函数,使模型在训练阶段更加侧重于困难样本的学习,
以减轻数据不平衡的影响。实验结果表明,本文方法与其他方法相比具有更高的准
确率。同时,还有效解决了类别不平衡导致的敏感性过低问题。
关键词:心电信号;小波变换;卷积神经网络;多尺度残差网络;focal loss 函数
III
ABSTRACT
The detection and prevention of cardiovascular disease is a hot research topic. Because
of its convenience and economy, Electrocardiogram (ECG) detection has become an
important method to assist doctors in diagnosing patients with vascular diseases.
Traditional detection methods require clinicians to classify ECG signal according to their
own experience, but doctors are prone to fatigue when detecting a large number of data,
resulting in missed diagnosis and misdiagnosis. Aiming at the above problems, this thesis
proposes an automatic detection method of ECG signal, which can be a tool to assist
clinicians in detection. With the in-depth study of ECG, scientists have found that the
ECG of patients will change regularly in the event of sleep apnea. According to this
change, we can judge whether the patient has sleep apnea. Therefore, this thesis proposes
a method to detect sleep apnea based on ECG signal.
The main work of this thesis is as follows:
(1) According to the sampling frequency and noise characteristics of ECG signal, this
thesis uses wavelet transform to remove the doped noise in the signal. Compared with the
median filtering method, wavelet transform has a good dryness effect on high frequency
noise on the basis of ensuring the removal of low frequency noise. This part lays the
foundation for the follow-up work of this thesis.
(2) In order to classify ECG signal into normal beats or abnormal beats, a two-
classification method of ECG signal is proposed in this thesis. When the existing deep
learning methods are used to deal with the specific ECG data set, the cross entropy loss
adopted to find the interface will not be further optimized, resulting in the weak
generalization ability on the specific ECG data set. Aiming at this deficiency, this thesis
proposes a convolutional neural network (CNN) based on structural risk minimization
(SRM), which improves the generalization ability of the model to the data set between
patients. Compared with the traditional methods, the proposed method further improves
the performance of the classifier.
(3) Based on the two-classification of ECG signal, a multi-classification method of
ECG signal is proposed in this thesis. First, in order to alleviate the gradient disappearance
problem caused by multiple convolutions in traditional networks, the proposed method
fuses the convolution results of each layer with the convolution results of the previous
layer. Next, aiming at the serious imbalance of the categories of data sets used, the focal
loss function is introduced as the optimization goal of the model. Compared with other
IV
methods, the proposed method has better performance.
(4) A sleep apnea detection method based on ECG signal is proposed in this thesis.
First, the derived RR interval signal and R-peak signal of ECG signal are extracted as
inputs. Then, the multi-scale residual network is used to extract the features of the derived
signal to obtain the sensitive features from different perspectives. Finally, the focal loss
function is introduced to replace the traditional cross entropy loss function, which makes
the model pay more attention to the learning of difficult samples in the training stage, so
as to reduce the impact of data imbalance. Experimental results show that this method has
higher accuracy than other methods. At the same time, it also effectively solves the
problem of low sensitivity caused by category imbalance.
KEYWORDS: Electrocardiogram; Wavelet Transform; Convolutional Neural Network;
Multi-Scale Residual Network; Focal Loss Function
V
目 录
第一章 绪论 .................................................................................................................... 1
1.1 研究背景及意义 ............................................................................................... 1
1.2 国内外研究现状 ............................................................................................... 2
1.2.1 不同的范式类型 .................................................................................... 2
1.2.2 心电信号分类的研究现状 .................................................................... 3
1.2.3 睡眠呼吸暂停的研究现状 .................................................................... 5
1.3 论文主要研究内容与结构 ............................................................................... 6
第二章 心电信号及其预处理 ........................................................................................ 8
2.1 引言 ................................................................................................................... 8
2.2 心电信号的产生 ............................................................................................... 8
2.3 心电信号的去噪 ............................................................................................... 9
2.3.1 心电信号噪声分析 .............................................................................. 10
2.3.2 基于中值滤波去除基线漂移 .............................................................. 10
2.3.3 基于小波变换的去噪方法 ................................................................... 11
2.3.4 小波基数的选择 .................................................................................. 12
2.4 常见心律失常原因分析 ................................................................................. 14
2.5 心电信号与睡眠呼吸暂停的关系 ................................................................. 14
2.6 心电信号数据集介绍 ..................................................................................... 15
2.6.1 心电信号分类数据集 .......................................................................... 15
2.6.2 睡眠呼吸暂停数据集 .......................................................................... 16
第三章 心电信号的二分类方法 .................................................................................. 17
3.1 引言 ................................................................................................................. 17
3.2 数据集的处理 ................................................................................................. 17
3.3 基于传统机器学习的异常心拍分类 ............................................................. 18
3.3.1 支持向量机 .......................................................................................... 18
3.3.2 随机森林 .............................................................................................. 18
3.4 基于结构风险最小化的异常心拍分类 ......................................................... 19
3.4.1 卷积神经网络基本理论 ...................................................................... 19
3.4.2 基于结构风险最小化的损失函数 ...................................................... 20
3.4.3 二分类方法模型结构 .......................................................................... 21
3.5 实验结果展示 ................................................................................................. 22
3.5.1 评价指标 .............................................................................................. 22
VI
3.5.2 实验结果分析 ...................................................................................... 23
3.6 小结 ................................................................................................................. 25
第四章 心电信号的多分类方法 .................................................................................. 26
4.1 引言 ................................................................................................................. 26
4.2 数据集预处理 ................................................................................................. 26
4.2.1 去噪与心拍分割 .................................................................................. 26
4.2.2 R 峰值检测 .......................................................................................... 27
4.3 模型结构的设计 ............................................................................................. 27
4.3.1 改进的 DenseNet 结构 ........................................................................ 27
4.3.2 损失函数设计 ...................................................................................... 29
4.3.3 多分类方法模型结构 .......................................................................... 29
4.4 实验结果展示 ................................................................................................. 31
4.4.1 实验数据划分 ...................................................................................... 31
4.4.2 实验结果与分析 .................................................................................. 32
4.5 小结 ................................................................................................................. 36
第五章 睡眠呼吸暂停检测 .......................................................................................... 37
5.1 引言 ................................................................................................................. 37
5.2 数据集处理 ..................................................................................................... 38
5.2.1 信号去噪 .............................................................................................. 38
5.2.2 R 峰定位及派生信号提取 .................................................................. 38
5.2.3 数据不平衡处理 .................................................................................. 39
5.3 多尺度残差网络 ............................................................................................. 39
5.3.1 残差网络 .............................................................................................. 39
5.3.2 多尺度网络的设计 .............................................................................. 40
5.4 实验结果 ......................................................................................................... 42
5.4.1 评价指标 .............................................................................................. 43
5.4.2 睡眠呼吸暂停检测实验 ...................................................................... 43
5.4.3 判断患者是否患有睡眠呼吸暂停 ...................................................... 45
5.4.4 在 UCD 数据集上测试模型 ................................................................ 45
5.4.5 同类研究结果对比 .............................................................................. 46
5.5 小结 ................................................................................................................. 47
第六章 总结与展望 ...................................................................................................... 48
6.1 全文的总结 ..................................................................................................... 48
6.2 对未来的展望 ................................................................................................. 49
剩余60页未读,继续阅读
资源评论
2201_75761617
- 粉丝: 19
- 资源: 7339
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 电子设计竞赛的单相不间断电源设计
- cutcamera1715961370938.png
- 基于MATLAB的图像处理课程设计报告.doc
- tensorflow-gpu-2.6.0-cp38-cp38-manylinux2010-x86-64.whl
- mmexport1715960553858.png
- tensorflow-gpu-2.6.0-cp37-cp37m-manylinux2010-x86-64.whl
- 通过 .NET 应用程序中的源代码查找 SQL 注入
- 电子设计竞赛2007年B题 无线识别装置.doc
- Wox全局搜索工具,一款win下的全局搜索软件
- 使用高级集群管理 (ACM) 模板来管理用户、组和命名空间
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功