Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electrocardiosignal classifying method and system based on LRF-ELM and BLSTM

A LRF-ELM, ECG signal technology, used in medical science, sensors, diagnostic recording/measurement, etc., can solve the problems of deep learning algorithm memory consumption, affecting the classification effect, large amount of calculation, etc., to prevent insufficient computer memory , Good classification and recognition performance, efficient and fast extraction effect

Active Publication Date: 2019-12-13
山东山科智心科技有限公司
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The inventors of the present disclosure found that the current research on the recognition of ECG signals has the following problems: (1) manual extraction of features requires a certain amount of experience and knowledge, and there are many human interventions, which are likely to cause problems such as data loss; (2) ECG data sets are often Large amount, using a single deep learning algorithm consumes a lot of memory and requires high computer hardware configuration; (3) Based on computationally intensive deep learning methods, the calculation is complex and the amount of calculation is large; (4) Most deep learning algorithms need to be iterated Tuning the parameters, inappropriate parameter selection will affect the accuracy of feature extraction, thereby affecting the classification effect
Therefore, feature extraction using deep learning often requires a long training time

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
  • Electrocardiosignal classifying method and system based on LRF-ELM and BLSTM
  • Electrocardiosignal classifying method and system based on LRF-ELM and BLSTM
  • Electrocardiosignal classifying method and system based on LRF-ELM and BLSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] like Figure 1-6 As shown, Embodiment 1 of the present disclosure provides an ECG signal classification method based on LRF-ELM and BLSTM, the steps are as follows,

[0054] Obtain and preprocess the ECG signal data to obtain a data set, and use the ECG signal data in the data set as the input data of the neural network;

[0055] Using the LRF-ELM network as a feature extractor, it learns the spatial information in the ECG signal data, and extracts the feature data of different dimensions in the ECG signal data through three stacked random convolution and pooling processes;

[0056] The extracted feature data is fused as the input of the sequence learning stage, and the deep BLSTM network is used for sequence learning, and finally the ECG signal classification result is output.

[0057] In this embodiment, its performance is verified on the MIT-BIH data set. In this embodiment, 99863 samples in the data set are first divided, and each type of sample in the data set is ...

Embodiment 2

[0092] Embodiment 2 of the present disclosure provides an ECG signal classification system based on LRF-ELM and BLSTM, using the ECG signal classification method based on LRF-ELM and BLSTM described in Embodiment 1, including:

[0093] The preprocessing module is configured to: obtain and preprocess the ECG signal data to obtain a data set, and use the ECG signal data in the data set as the input data of the neural network;

[0094] The feature extraction module is configured to: use the LRF-ELM network as a feature extractor to learn the spatial information in the ECG signal data, and extract different dimensions of the ECG signal data through three stacked random convolution and pooling processes feature;

[0095] The sequence learning module is configured to: use the extracted features as the input of the sequence learning stage after fusion, use the deep BLSTM network for sequence learning, and finally output the ECG signal classification result.

Embodiment 3

[0097] Embodiment 3 of the present disclosure provides a medium on which a program is stored. When the program is executed by a processor, the steps in the ECG signal classification method based on LRF-ELM and BLSTM as described in Embodiment 1 of the present disclosure are implemented.

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 electrocardiosignal classifying method and system based on LRF-ELM and BLSTM. The electrocardiosignal classifying method includes the steps: acquiring electrocardiosignal data, preprocessing the electrocardiosignal data to obtain a dataset, and using the electrocardiosignal data in the dataset as input data of a neural network; using a LRF-ELM network as a feature extractor, learning spatial information in the electrocardiosignal data, and through three stacked random convolution and pooling processes, extracting feature data of different dimensions in the electrocardiosignal data; and after fusion, using the extracted feature data as input of a sequence learning stage, adopting a deep BLSTM network to carry out sequence learning, and finally outputting electrocardiosignal classifying results. According to the electrocardiosignal classifying method and system based on the LRF-ELM and the BLSTM, time information and spatial information of electrocardiosignals are taken into account at the same time, and therefore, not only can electrocardiosignal features be extracted efficiently and rapidly, but also good classification and identification properties are ensured.

Description

technical field [0001] The present disclosure relates to the technical field of ECG signal classification, in particular to a method and system for ECG signal classification based on LRF-ELM and BLSTM. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] Electrocardiography is a technique in which hospitals use an electrocardiogram machine to connect to the body surface to measure the electrical activity generated by the beating of the human heart and reflect it on the image. A complete heartbeat mainly includes P wave, QRS wave and T wave. Because there is a potential difference between the inside and outside of the myocardial cell membrane, when the myocardial cells are depolarized sequentially from the endocardium to the epicardium, positive ions enter the membrane from the outside of the membrane, making the potential in the membrane cha...

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
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/0402A61B5/00
CPCA61B5/725A61B5/7264A61B5/7267A61B5/318
Inventor 李彬乔风娟李伟郭红丽张友梅杨雪
Owner 山东山科智心科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products