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

Slope-based elastic similarity measurement method

A similarity measurement and slope technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of DTW high time complexity and limit the scope of use, and achieve the effect of elastic measurement

Active Publication Date: 2018-04-03
HARBIN ENG UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

DTW is a classic elasticity measurement method, however, the high time complexity of DTW limits its scope of use

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
  • Slope-based elastic similarity measurement method
  • Slope-based elastic similarity measurement method
  • Slope-based elastic similarity measurement method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following examples describe the present invention in more detail.

[0027] Input: time series x = {x 1 ,x 2 ,...,x m} and y={y 1 ,y 2 ,...,y n}, l 1 Filtering parameter λ and segmentation parameter d.

[0028] Output: Metric distance Dist(x,y).

[0029] Step 1: Input the time series x and y and the filter parameter λ, and perform l 1 Trend filtering. Output polyline segments X and Y.

[0030] Step 2: Calculate the linear segmented sequence X and Y weighted slopes expressed as k x and k y ;Set the interpolation threshold d, and interpolate weighted slope values ​​at equal intervals.

[0031] Step 3: After interpolation, two new unequal length sequences k are formed x and k y , using DTW(k x ,k y ) to calculate the trend distance.

[0032] (1) Since time series usually have high dimensionality, large amount of data and serious noise interference, directly performing similarity measurement on time series not only costs high storage and calculation, but...

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 a slope-based elastic similarity measurement method. The method comprises the steps of 1: inputting time sequences x and y and a filtering parameter lambda, performing l1 trendfiltering, and outputting fold lines X and Y; 2: calculating weighted slopes of sections of the fold lines X and Y, representing the weighted slopes of the fold lines X and Y as kx and ky, setting anequidistance interval parameter d, and inserting the weighted slopes equidistantly; and 3: through interpolation processing, forming two new sequences different in length, and calculating a trend distance of the sequences different in length by using a DTW (Dynamic Time Warping) distance. The time sequences are represented as the fold line sections through filtering features, the trend informationis reserved, and the dimension reduction is realized; the weighted slopes of the line sections can realize measurement and comparison of trends; and through equidistant interpolation, DTW equal-interval calculation is adapted, so that elastic measurement is realized.

Description

technical field [0001] The invention relates to a method for mining time series data from a large amount of time series data generated by sensors in the process of target tracking and detection. Background technique [0002] In the sea trial test and evaluation, the sensor generates a large amount of time series data in the process of target tracking and detection. These time series data are large in number, multi-dimensional, and contain a lot of noise. However, these time series data hide the trend and law of the development of things, and mining time series data is of great significance. Time series mining includes time series similarity search, classification, clustering, prediction and outlier detection. In these studies, time series similarity measurement is the premise and foundation of the research, and a good measurement method can significantly improve the efficiency and accuracy of time series mining. [0003] Time series similarity measures are mainly based on ...

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): G06K9/62
CPCG06F18/22
Inventor 王念滨张海彬宋奎勇王红滨周连科白云鹏原明旗王勇军陈田田何茜茜
Owner HARBIN ENG 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