|本期目录/Table of Contents|

[1]朱晓铭,王仲悦,陈林海,等.基于卷积自编码器的心电压缩方法[J].电子设计工程,2019,27(22):65-69.
 ZHU Xiaoming,WANG Zhongyue,CHEN Linhai,et al.ECG compression method based on convolutional auto encoder[J].SAMSON,2019,27(22):65-69.
点击复制

基于卷积自编码器的心电压缩方法(PDF)
分享到:

《电子设计工程》[ISSN:1674-6236/CN:61-1477/TN]

卷:
27
期数:
2019年22期
页码:
65-69
栏目:
计算机技术应用
出版日期:
2019-11-20

文章信息/Info

Title:
ECG compression method based on convolutional auto encoder
文章编号:
1674-6236(2019)22-0065-05
作者:
朱晓铭123 王仲悦4 陈林海1 张 帅1 王云峰123
(1.中国科学院微电子研究所 北京 100029;2.中国科学院大学 北京 100049;3.新一代通信射频芯片技术北京市重点实验室 北京 100029;4. 烟台工程职业技术学院 山东 烟台 264006)
Author(s):
ZHU Xiao?ming123WANG Zhong?yue4CHEN Lin?hai1ZHANG Shuai1WANG Yun?feng123
(1.Institute of Microelectronics of Chinese Academy of Sciences, Beijing 100029, China; 2.University of Chinese Academy of Sciences, Beijing 100049, China;3.Beijing Key Laboratory of Radio Frequency IC Technology for Next Generation Communications,Beijing 100029,China;4.Yantai Engineering & Technology College. Yantai 264006,China)
关键词:
计算机神经网络 心电压缩 卷积自编码器 心电图
Keywords:
computer neural network electrocardiography compression convolutional auto encoder electrocardiography
分类号:
TN919
DOI:
-
文献标志码:
A
摘要:
为了有效地实现心电信号压缩,以便心电数据的传输和存储,提出了一种基于卷积自编码器的心电压缩方法。通过卷积神经网络对心电图特征提取易实现降维,在卷积自编码器的编码过程中来实现心电压缩,将编码层作为压缩结果。卷积神经网络处理多通道的输入,因此可以实现导联体系的心电压缩。结果采用均方根百分误差和压缩比作为评判标准,单导联心电图压缩比为16,十二导联心电图压缩比为24,均方根损失误差在3%左右,从而验证了卷积自编码器的有效性。
Abstract:
To effectively compress electrocardiography (ECG) data for transmission and storage, an ECG compression algorithm based on convolutional auto encoder (CAE) is proposed. Extract features for dimensionality reduction by convolutional neural network (CNN), compress the ECG data by CAE, and the coding layer is used as the compression result. CNN can process the input of multiple channels, so the ECG compression for lead system is also achieved. The results are judged by the root mean square error and compression ratio. The compression ratio of signal lead is 16 and the compression ratio of 12-lead is 24. The root mean square error loss is about 3%. All of these prove that CAE works well on ECG compression.

参考文献/References:

[1] Zhang J, Gu Z, Yu Z L, et al. Energy-efficient ECG compression on wireless biosensors via minimal coherence sensing and weighted ? minimization reconstruction[J]. IEEE Journal of Biomedical & Health Informatics, 2017,19(2):520-528. [2] He K, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017(99):1.[3] Jiang H, Learned-Miller E. Face Detection with the Faster R-CNN[C]// IEEE International Conference on Automatic Face & Gesture Recognition. 2017.[4] Esteva A,Kuprel B,Novoa R A,et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017,542(7639):115-118.[5] 凌佳佳,袁晓兵. 联合噪声分类和掩码估计的语音增强方法[J]. 电子设计工程, 2018(17):30-34.[6] Du B,Xiong W,Wu J,et al. Stacked Convolutional Denoising Auto-Encoders for Feature Representation[J]. IEEE Transactions on Cybernetics, 2017, 47(4):1017-1027.[7] Attia M, Hossny M, Nahavandi S, et al. Surgical tool segmentation using a hybrid deep CNN-RNN auto encoder-decoder[C]// IEEE International Conference on Systems, 2017.[8] 刘兴旺,王江晴,徐科. 一种融合AutoEncoder与CNN的混合算法用于图像特征提取[J]. 计算机应用研究, 2017,34(12):3839-3843.[9] Chen H, Zhang Y, Kalra M K, et al. Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN).[J]. IEEE Trans Med Imaging, 2017(99):1.[10]Tewari A, Zollhofer M, Kim H, et al. MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction[C]// 2017.[11]Hamker F H. Predictions of a model of spatial attention using sum- and max-pooling functions[J]. Neurocomputing, 2018, 56(1):329-343.[12]Tan C, Zhang L. A novel ECG data compression method based on adaptive Fourier decomposition[C]// Second International Conference on Robotics and Machine Vision, 2017.[13]Rezaii T Y, Beheshti S, Shamsi M, et al. ECG signal compression and denoising via optimum sparsity order selection in compressed sensing framework[J]. Biomedical Signal Processing & Control, 2018(41):161-171.[14]Elgendi M, Al-Ali A, Mohamed A, et al. Improving Remote Health Monitoring: A Low-Complexity ECG Compression Approach[J]. Diagnostics, 2018,8(1):10.[15]Elgendi M, Mohamed A, Ward R. Efficient ECG Compression and QRS Detection for E-Health Applications[J]. Scientific Reports, 2017,7(1):459.[16]王玉娇,刘昱, 陈林海,等. 一种改进的基于压缩感知的心电压缩算法[J]. 计算机测量与控制, 2018,26(7):275-279.[17]严新华.基于压缩感知算法的目标跟踪系统设计[J].自动化与仪器仪表,2018(12):136-138.[18]李新颖,彭静,刘玉红,等.基于压缩感知的图像重构算法研究[J].自动化与仪器仪表,2015(7): 152-154,158.

相似文献/References:

[1]魏 明,罗 希.基于三层架构的分布式心电采集模式[J].电子设计工程,2018,26(02):31.
 WEI Ming,LUO Xi.Distributed ECG acquisition mode based on three?tier architecture[J].SAMSON,2018,26(22):31.

备注/Memo

备注/Memo:
收稿日期:2019-04-08 稿件编号:201904036基金项目:国家重点研发计划(2018YFC2001200);国家自然基金项目(61774167)作者简介:朱晓铭(1995—),男,河北邢台人,硕士研究生。研究方向:数据挖掘。
更新日期/Last Update: 2019-11-22