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

Waveform Classification Method Based on Dynamic Time Warping and Partitioning Algorithm

A technology of dynamic time warping and division algorithm, applied in computing, computer components, character and pattern recognition, etc., can solve problems such as not being able to represent a family well, and achieve the effect of reducing the error of horizon interpretation

Active Publication Date: 2018-12-04
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, existing methods for defining the center of a family cannot represent the characteristics of a family well

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
  • Waveform Classification Method Based on Dynamic Time Warping and Partitioning Algorithm
  • Waveform Classification Method Based on Dynamic Time Warping and Partitioning Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to facilitate those skilled in the art to understand the technical content of the present invention, the content of the present invention will be further explained below in conjunction with the accompanying drawings.

[0038] Dynamic Time Warping (DTW, Dynamic Time Wrapping) is a method to measure the similarity of two time series. Unlike Euclidean distance, it can not only compare the similarity between two time series of equal length, but also for Time series of different lengths can also be compared for similarity, while eliminating phase effects between the series.

[0039]In the waveform classification, the data obtained according to horizon windowing is a waveform. Due to the existence of horizon interpretation errors and the three-dimensional data intercepted by horizon, the distance between the first point of each track and the actual horizon profile is not the same , there is a certain phase error. For this reason, the method of dynamic time warping i...

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 discloses a waveform classification method based on dynamic time warping and partitioning algorithm, by determining the seismic data sample set; and then determining the classification number k of the seismic data sample set according to the seismic phase type of the seismic data sample set; from the seismic data sample set Select k samples as the initial centroid; then, based on the DTW distance, assign the sample data that is not selected as the initial centroid to the cluster where the corresponding centroid is located; update the centroid of the cluster iteratively; judge whether the upper limit of the number of iterations is reached, and if so, end, and get The final allocated k clusters; otherwise, proceed to step S4 according to the updated centroids of the clusters obtained in step S5 for reallocation. Using dynamic time warping to align seismic data reduces the influence of horizon interpretation errors and more accurately measures the similarity between two seismic data; using the centroid of the cluster as the center of the cluster, compared with the traditional division algorithm The center of the cluster defined in is more accurate and more representative of the characteristics of a cluster.

Description

technical field [0001] The invention belongs to the field of seismic data processing, and in particular relates to a seismic waveform classification technology. Background technique [0002] Seismic waveform is the basic nature of seismic data. It contains all qualitative and quantitative information, such as reflection mode, phase, frequency, and amplitude. reflect the characteristics of the underground structure. The waveform classification method is the most commonly used seismic facies analysis method. By classifying the seismic signal waveforms, the division of seismic facies can be realized. Waveform classification is aimed at seismic data sample sets containing various waveforms, and through appropriate classification or clustering methods, the samples are divided into different categories to achieve the purpose of distinguishing waveform samples. [0003] Waveform classification techniques are divided into cluster analysis and statistical classification. Cluster a...

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 Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/23213
Inventor 钱峰昌艳胡光岷宋承云
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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