Electrocardiogram compressed sensing reconstruction system based on deep learning

A compressed sensing reconstruction and deep learning technology, applied in the field of ECG compressed sensing reconstruction system, can solve problems such as inability to complete tasks

Pending Publication Date: 2021-08-31
ZHENGZHOU UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for systems that require real-time performance, the corresponding tasks cannot be completed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Electrocardiogram compressed sensing reconstruction system based on deep learning
  • Electrocardiogram compressed sensing reconstruction system based on deep learning
  • Electrocardiogram compressed sensing reconstruction system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical solutions of the present invention will be described in further detail below through specific implementation methods.

[0048] Such as figure 1 As shown, an ECG compressive sensing reconstruction system based on deep learning, the system includes:

[0049] Compress the original ECG signal according to different compression ratios to obtain compressed data;

[0050] transpose the compressed signal and normalize the transposed projection data;

[0051] Input the processed data into CNN and LSTM network models for ECG signal reconstruction.

[0052] Given data set X={(x (1) ,z (1) ),..., (x (i) ,z (i) ),..., (x (n) ,z (n) )}, the original signal compression is completed through the following steps:

[0053]

[0054] x (i) is the i-th ECG signal,

[0055] is the observation matrix fixed in the experiment, and its dimension is n×m,

[0056] the y (i) is the compressed signal obtained by random projection of the observation matrix.

[0057] Th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an electrocardiogram compressed sensing reconstruction system based on deep learning. According to the technical scheme, firstly, electrocardiosignals are sampled and compressed at the same time through an observation matrix, then the compressed signals are subjected to transposition projection operation, it is guaranteed that the size of the transposition projection signals is the same as that of the original electrocardiosignals, and meanwhile Z-Score standardization is conducted on the transposition projection signals; then, direct learning of a mapping relation between the transposed projection signals and the original signals is conducted by using the CNN, and the electrocardiosignals are reconstructed initially; and finally, secondary reconstruction is carried out on the CNN reconstructed signals by using LSTM, and the reconstruction quality of the signal is further improved. The invention provides a non-iterative electrocardiogram compressed sensing reconstruction algorithm (CSNet) in combination with compressed sensing and deep learning, and electrocardiogram signals can be quickly and accurately reconstructed.

Description

technical field [0001] The invention belongs to the technical field of electrocardiogram monitoring, and in particular relates to an electrocardiogram compression sensing reconstruction system based on deep learning. Background technique [0002] The suddenness of cardiovascular disease leads to higher and higher mortality rate of cardiovascular disease. According to 2016 mortality statistics, an estimated 17 million people died from cardiovascular disease, accounting for 31% of all deaths worldwide. For patients with cardiovascular diseases, remote ECG monitoring based on wearable devices plays a very important role in the prevention and treatment of cardiovascular diseases. However, long-term monitoring of ECG generates a large amount of data. For example, when the sampling rate is 400Hz and the resolution is 12 bits, a single-lead ECG signal needs to store or transmit 26MB of data; when the resolution is 16 bits, two leads need to transmit 138MB of data. In addition, s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): A61B5/346
CPCA61B5/7232A61B5/7264
Inventor张宏坡董忠仁孙梦雅谷红壮
OwnerZHENGZHOU UNIV