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

Chaotic neural network with complex value weight and application thereof in electrocardiogram classification

A neural network and chaotic technology, applied in the field of signal processing, can solve problems such as difficult to achieve recognition effect and poor recognition accuracy, and achieve the effect of improving global optimization ability, high recognition accuracy, and improving recognition accuracy

Pending Publication Date: 2021-12-24
QILU UNIV OF TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the recognition accuracy of the existing chaotic neural network is not good, and it is difficult to achieve a more accurate recognition effect

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
  • Chaotic neural network with complex value weight and application thereof in electrocardiogram classification
  • Chaotic neural network with complex value weight and application thereof in electrocardiogram classification
  • Chaotic neural network with complex value weight and application thereof in electrocardiogram classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] A kind of chaotic neural network with complex-valued weights involved in this embodiment adopts complex-valued Logistic chaos mapping (CLCM), and CLCM expands the variable of Logistic mapping from the real domain to the complex domain, increasing the ergodicity of the chaotic system, and the CLCM mathematical model defined as:

[0052]

[0053] where w n =x n +jy n is the state variable in the complex domain, stands for imaginary number, z n Indicates the output sequence, a and b are system parameters, a is a real number, b=b 1 +jb 2 is a complex parameter.

[0054] Will W n The real and imaginary parts of are separated to obtain a three-dimensional 3D-CLCM:

[0055]

[0056] The bifurcation diagram describes the process from bifurcation to chaos, which is of great significance for analyzing the characteristics of chaos; let b 1 ∈(-1.33, 1.33), a∈(-0.1, 8.9) The bifurcation graph of the variable changing with the parameter b is as follows figure 1 Shown...

Embodiment 2

[0074] This embodiment relates to the application of a chaotic neural network with complex-valued weights in electrocardiogram classification.

[0075] The most commonly used database in the field of ECG is the MIT-BIH arrhythmia database, which contains 48 records, a duration of 30 minutes, a total of 648,000 sampling points, and a total of 109,500 heartbeats, of which abnormal heartbeats account for about 30%.

[0076] The QRS complex is the most pronounced and sharpest in each frequency band of each type of heartbeat, and is easier to detect than other bands, known as the "singularity" peak point (or trough point) of the QRS complex, showing a steep slope change and non-conductive points. According to this characteristic, a variety of processing methods can be used for detection, such as filtering method, wavelet transform method and so on. After preprocessing the data, the heartbeat signal is intercepted, and the training and testing of the chaotic neural network are comp...

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 the technical field of signal processing, in particular to a chaotic neural network with a complex value weight and application of the chaotic neural network in electrocardiogram classification. The method comprises the steps: providing a complex Logistic chaotic mapping with a complex value parameter, and analyzing a bifurcation diagram, a Lyapunov index and a chaotic attractor of the complex Logistic chaotic mapping; optimizing the weight of the CNN by using the traversal of the CLCM and a new neuron function; employing an MIT-BIH database for verifying the method; through band-pass filtering and dual-threshold processing, processing electrocardiosignals into signals with more single and more prominent waveforms as input of the designed CNN. The the result shows that the accuracy of electrocardiogram classification by the CNN with complex weights is improved to a certain extent. The complex weight chaos neural network has the capability of preventing the network from falling into local minimum, the electrocardiogram recognition precision is improved, and the recognition accuracy is high.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to a chaotic neural network with complex-valued weights and its application in electrocardiogram classification. Background technique [0002] Electrocardiogram plays an important role in the diagnosis of arrhythmia, myocardial ischemia, ventricular premature beats and other diseases. However, there are many types of ECG abnormalities, and the possibility of variation is high. Images of the same disease are very different. Accurate diagnosis requires doctors to have a wealth of knowledge accumulation and clinical experience. For a long time, doctors have been engaged in a large number of electrocardiogram diagnosis work, which is easy to cause misdiagnosis due to fatigue. Therefore, the automatic recognition of ECG has been a research hotspot in the field of artificial intelligence, which has greatly promoted the progress and development of medical care. [0003] Exist...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/08G06F2218/12
Inventor 张芳芳陈泺冰寇磊舒明雷张雪胡志强
Owner QILU UNIV OF TECH
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