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

Improved electrocardiosignal quick clustering analysis method

An ECG signal, cluster analysis technology, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve the problem of slow operation speed, reduced clustering effectiveness, difficulty in achieving operation speed, memory usage and classification accuracy balance, etc. problem, to achieve the effect of fast running speed and strong universality

Inactive Publication Date: 2019-10-25
FUDAN UNIV
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Many clustering algorithms have problems such as insufficient memory and slow operation speed
However, in order to improve the computing speed, the effectiveness of clustering often decreases, so it is difficult to achieve a balance between computing speed, memory usage and classification accuracy.

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
  • Improved electrocardiosignal quick clustering analysis method
  • Improved electrocardiosignal quick clustering analysis method
  • Improved electrocardiosignal quick clustering analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Embodiment 1: The method for fast cluster analysis of electrocardiographic signals of the present invention is applied to single-lead electrocardiographic signals. This embodiment adopts the St.Petersburg Institute of Cardiological Technics12-lead Arrhythmia Database database from the physiionet project, and the electrocardiographic data in the database are 12-lead arrhythmia data, and the data of wherein lead II is taken to carry out single-lead clustering, and the work The process is as follows:

[0044] (1) Read a section of single-lead ECG signal (digital signal) with a sampling rate of 257Hz.

[0045] (2) Step (1) is read to the data plus a 100-second window (i.e. window length t=100s), get 100-second ECG segment, and carry out preprocessing, use wavelet transform in the present embodiment, remove baseline drift. As shown in Figure 1, Figure 1(a) is a 100-second ECG segment, and Figure 1(b) is a segment of the ECG signal after wavelet transform to remove baseline ...

Embodiment 2

[0054] Embodiment 2: FIG. 7 is the implementation result of applying the method for rapid cluster analysis of ECG signals of the present invention to 12-lead ECG signals (ie, the number of leads m=12). In this example, the ECG signals of 12 leads are clustered at the same time. Heart beat segments are extracted from each corresponding channel of the 12-lead ECG signal. Then, the extracted cardiac beat segments of 12 leads are spliced ​​into a long waveform, and then the fast clustering analysis method of the present invention is implemented.

[0055] The electrocardiographic data in the present embodiment is also from the St.Petersburg Instituteof Cardiological Technics 12-lead Arrhythmia Database database of the physiionet project, and the electrocardiographic data in the database is 12 lead arrhythmia data, and the workflow is as follows:

[0056] (1) First read the 12-lead ECG data.

[0057](2) Add a 100-second window to the 12-lead ECG signal, and perform wavelet transfo...

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 relates to an improved electrocardiosignal quick clustering analysis method. The method includes steps: windowing electrocardiosignal, and preprocessing data in a window to remove interference; capturing a heart beat fragment from the preprocessed data, and performing time domain or frequency domain processing to obtain a new signal sequence; calculating a similarity coefficient of the sequence, comparing with a threshold to further perform heart beat classification, and extracting an average template of each type; moving the window to a next electrocardiosignal section, and repeating the process until the whole electrocardiosignal clustering is completed; subjecting the average templates obtained in each window to secondary clustering to obtain a final heart beat type and the heart beat quantity and the average template of the corresponding type. The method is suitable for short-term or long-term electrocardiosignals and also suitable for single-lead or multi-lead electrocardiosignals and can be used for electrocardiosignal quick clustering of normal sinus rhythm, single abnormal rhythm or various abnormal rhythms. The method can be popularized in electrocardiosignalactivation analysis and relevant quantitative research.

Description

technical field [0001] The invention relates to an improved fast cluster analysis method for electrocardiographic signals. Background technique [0002] ECG signals can comprehensively reflect the electrical activity of the heart, and play an important role in the diagnosis of heart disease and the evaluation of heart function. At present, ECG mapping technology is becoming more and more perfect, and it is more convenient to obtain human ECG signals before, during or after surgery, whether in or out of the hospital. Electrocardiogram has become a routine and important clinical examination method, which can assist doctors in diagnosing or evaluating patients. However, due to the wide variety of arrhythmias, and the ECG signals of patients may show different characteristics at different times, the individual differences are large, resulting in large variations in ECG signals, resulting in false detections. In addition, due to the low frequency and short duration of some abno...

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
CPCA61B5/7203A61B5/7235A61B5/316A61B5/318
Inventor 杨翠微何凯悦袁涵
Owner FUDAN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com