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

Continuous simulate quantitative time series data mining method

A technology of time series and data mining, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of affecting the mining effect, losing key information, etc., and achieve the effect of avoiding a huge amount of calculation

Inactive Publication Date: 2017-02-22
XIAMEN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of discretization of analog quantities, many key information will inevitably be lost, which may affect the final mining 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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following examples will further illustrate the present invention.

[0027] Embodiments of the present invention include the following steps:

[0028] 1) Data cleaning, discovering and correcting identifiable errors in data files, including checking data consistency, dealing with invalid and missing values, etc.;

[0029] 2) Determine cycle division; the cycle division can be set as a cycle of production according to the natural cycle, and the natural cycle can be one of day, week, month, quarter, year, etc.

[0030] 3) Determine the number of output points of the Fourier transform and the number n of sampling points of the sampled data; the number of output points of the Fourier transform may be 8-24, too many may lead to clustering failure.

[0031] 4) Perform Fourier transform on the data in the period, set the data in the period as x, Among them, F(x) represents the Fourier transform of x, and n represents the number of sampling points;

[0032] 5) Data sampl...

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

Continuous simulate quantitative time series data mining method comprises the step that 1, data clean; 2, cycle determination and separation; 3, Fourier transformation output sample point and sample data sampling point determination; 4, in-cycle data Fourier transformation; 5, in-cycle data sample, every cycle and Fourier transform same point sample, as representation of time domain characteristic; 6, Fourier transform output data and sample data storing as a section point; 7, calculation of overall average section point density; 8, all section points marked as unvisited; 9, an unclassified point P x marking random selected as unvisited; 10, in case point P x neighbor S territory at least m point, new cluster Cn construct and P x with cluster Cn augment; 11, ordering N as P x neighbor S section point collection; 12, every section point PNi in every N transform; 13, unvisited section point check, if yes answer, to step 9; 14, cluster C output.

Description

technical field [0001] The invention relates to continuous analog quantities, in particular to a time series data mining method for continuous analog quantities. Background technique [0002] Most of the quantities in real work, such as temperature, humidity, rainfall, brain waves, etc., are continuous analog quantities. Many industrial sensors output continuous analog quantities. Analog quantities can be considered as having infinite states. The effective mining of the information contained in brain waves, ECG signals, etc. is helpful for objectively judging the patient's condition. However, most of the current mature data mining algorithms are aimed at discrete variables, and the complexity of the algorithm will increase sharply due to the increase in discrete states. . Time is the key to judging before and after the occurrence of an event. By discretizing different analog quantities and arranging them in chronological order for data mining, a more commonly used method is...

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): G06F17/30
CPCG06F16/215G06F16/2465
Inventor 缪孟良彭侠夫仲训昱
Owner XIAMEN 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