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
III
Research on ECG signals reconstruction algorithm based on a
Multi-scale Feature Fusion Transform Neural Network
Abstract
An ageing population seriously challenges the sustainability of society and health care
systems. Heart rate monitoring is an effective way to prevent cardiovascular disease, which
is the main cause of death in the elderly. Ballistocardiogram (BCG) signals acquisition
device based on piezoelectric film sensor can continuously record human physiological
information without disturbance or trauma. Since the collected BCG signals are highly
correlated with electrocardiogram (ECG) signals in reflecting heart activity, BCG signals are
often used for heart rate monitoring in home scenarios. However, compared with ECG, the
BCG wave shape is less clear to distinguish between heartbeats, and the contact-free
measurement method is easy to lead to distortion of waveform characteristics, which
increases the difficulty of heart rate detection and disease identification. Moreover, BCG
signals have not yet formed the standard of medical diagnosis. Therefore, the conversion of
BCG signals into ECG signals plays an important role in improving the accuracy of heart
rate detection at home, and provides a reliable technical solution for further promoting the
clinical application of BCG signals.
An Attention Mechanism Based on Encoder-Decoder Network(AMEDN) is used to
study the reconstruction of ECG signals based on BCG signals. AMEDN uses the attention
module to weight the position of each wavelet of the ECG signals, instructing the encoder-
decoder network to learn the hidden characteristics of the ECG signals from the BCG signals,
and thus reconstructs the ECG signals with the same dimension as the ECG signals by the
decoder. AMEDN is applied to subjects with different heights, genders, ages and weights.
The experimental results show that AMEDN can reconstruct the subjects' ECG signals from
the BCG signals.
In order to solve the problem of distortion and deviation of small waveform features of
reconstructed ECG signals, A Multi-scale Feature Fusion Transform Neural Network
(MFFTNN) is proposed based on the idea of sequence transform and multi-scale feature on
the basis of AMEDN. By setting different sizes of filters in each branch in the multi-scale
feature module, MFFTNN extracts multi-scale features of the BCG signals, realizing the
complementary information of different scales of the BCG signals through feature fusion.
Therefore, the detailed features of the ECG signals are enhanced, and the small waveform
IV
features of the ECG signals are recovered. In view of the differences between ECG signals
and BCG signals of different people, MFFTNN respectively sets the sequence transform
module at the front and end of the network. The sequence transform module can standardize
the input BCG signals and calibrate the reconstructed ECG signals to reduce waveform shift
and attenuation of the reconstructed ECG signals, thus improved the generalization and
reconstruction accuracy of MFFTNN. The experimental results show that MFFTNN can
effectively reconstruct the wavelet and RR intervals of ECG signals. Experiments have
verified that the multi-scale feature fusion module can learn the characteristics of different
scales of BCG signals, effectively improved the reconstruction effect of ECG signals, and
effectively inhibited the amplitude attenuation of P, Q, S, T weak wave group features.
Finally, the heart rate detection of reconstructed ECG signals and BCG signals are compared.
The results show that the heart rate detection of MFFTNN based on reconstructed ECG
signals are closer to the heart rate value based on ECG signals than that based on BCG
signals directly
.
Keywords:
Ballistocardiogram signals, Electrocardiogram signals, Reconstruction, Multi-scale
Feature Fusion Transform Neural Network,Heart rate monitoring
目 录
第 1 章 绪论............................................................................................... 1
1.1 研究背景及意义 ............................................................................... 1
1.2 心率监测系统的研究现状 .............................................................. 2
1.3 重构心电信号的现状 ....................................................................... 3
1.4 本文主要研究内容及章节安排 ...................................................... 5
第 2 章 心冲击信号的生理意义和采集设备 .......................................... 7
2.1 心冲击信号与心电信号的生理机制 .............................................. 7
2.1.1 心冲击信号和心电信号产生机理 ............................................. 7
2.1.2 心冲击图和心电图特征 ............................................................. 7
2.1.3 心冲击图和心电图的对应关系 ................................................. 9
2.2 心冲击信号采集系统 ..................................................................... 11
2.2.1 心冲击信号采集设备 ............................................................... 11
2.2.2 软件信号处理模块 ................................................................... 13
2.3 本章小结 ......................................................................................... 14
第 3 章 基于 AMEDN 算法心电信号的重构 ........................................ 15
3.1 编码器-解码器网络 ....................................................................... 15
3.2 注意力网络 ..................................................................................... 16
3.3 AMEDN 算法 .................................................................................. 16
3.4 数据集构建 ..................................................................................... 20
3.5 实验与分析 ..................................................................................... 21
3.5.1 实验设置与评价指标 ............................................................... 21
3.5.2 网络优化 ................................................................................... 22
3.5.3 实验结果 ................................................................................... 24
3.6 本章小结 ......................................................................................... 28
第 4 章 基于 MFFTNN 算法的心电信号重构 ...................................... 29
4.1 多尺度特征融合变换神经网络模型 ............................................ 29
4.1.1 多尺度特征融合模块 ............................................................... 29
4.1.2 序列变换模块 ........................................................................... 31
4.2 MFFTNN 重构心电信号原理 ........................................................ 33
4.3 实验与分析 ..................................................................................... 33
4.4 心率计算 ......................................................................................... 40
4.5 本章小结 ......................................................................................... 41
第 5 章 总结与展望 ................................................................................ 43
5.1 总结 ................................................................................................. 43
5.2 展望 ................................................................................................. 43
参考文献 ................................................................................................... 45
第 1 章 绪论
1
第 1 章 绪论
1.1
研究背景及意义
目前, 中国的人口老龄化速度在持续增长,根据相关统计,心血管疾病
(Cardiovascular Disease,CVD) 已经成为导致我国中老年人死亡的最主要原因
[1]
,严重
威胁人类健康,给社会和家庭带来极大的挑战。高血压,冠心病等常见的老年慢性病
往往都会反映在心脏节律、跳动波形的异常上,早期发现和干预可降低心脏病发作的
风险
[2]-[3]
。居家监测心率状况是改善心脏疾病管理的有效途径,对预防和治疗心脏疾
病,确保老年人的心脏健康具有重要意义。
心电图 (Electrocardiogram,ECG) 是一种用于记录心脏电活动的曲线图形,包含
丰富的心脏活动生理信息,是心脏疾病诊断的金标准,在过去的几十年里得到了广泛
的应用
[4]-[5]
。心电图通过多导联的电极片来采集,电极片需要与患者的皮肤直接接触,
由于其中包含一些化学物质,长时间使用易造成皮肤过敏,接触性皮炎以及心理上的
影响。传统的心电图扫描是有限时长,忽略了间歇性心脏疾病特征,尤其是在检查时
没有出现症状的心脏疾病
[3]
。因此,心电图不适用于心脏居家长期监测。随着传感器
技术与数字信号处理的发展,光电容积脉搏波图 (Photoplethysmogram,PPG) 和心冲
击图 (Ballistocardiogram,BCG) 引起人们的广泛关注。PPG 信号是用光学传感器检
测人体血液体积的变化。然而,接触式的可穿戴式采集设备会让人有束缚感。BCG 信
号是用压力传感器搜集人体血管运动产生的信号,该运动反映了心脏血液循环流动的
强度。BCG 信号采集设备将压力传感器置于床垫、椅垫或枕头中,无需与人体直接
接触就可以无感知,非侵入性地持续监测到心脏活动的变化情况。例如,在床垫下放
置压力薄膜传感器采集心冲击信号,采集过程中无需医护人员操作,在放松状态下可
准确反映心血管系统的搏动状态
[6]
。与 PPG 信号和 ECG 信号相比,BCG 信号更适用
于长期居家心率监测。本文基于床垫式 BCG 信号采集系统研究基于心冲击信号的心
脏监测,为独居老人和养老机构提供可靠的心率监测系统。
在心脏疾病监测领域心电图是医学诊断的标准,心血管疾病专家已从心电图中总
结出可反应心脏正常活动的特征指标,例如 R-R 间隔。现有研究表明,心冲击信号与
心电信号共同反映心脏的活动。BCG 信号与 ECG 信号是采用不同传感器测量的反映
心脏信息的两种生理信号,同样具有周期性,BCG 信号提取的一些特征(如 JJ 间隔)
剩余51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
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