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

Low-dimensional parallel coordinate graph construction method based on Isomap algorithm layout

A technology of parallel coordinates and construction methods, applied in the field of visualization, can solve problems such as difficulty in obtaining information

Pending Publication Date: 2020-08-04
SHANXI UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitation of spatial imagination ability, it is difficult for people to obtain information directly from this kind of data.

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
  • Low-dimensional parallel coordinate graph construction method based on Isomap algorithm layout
  • Low-dimensional parallel coordinate graph construction method based on Isomap algorithm layout
  • Low-dimensional parallel coordinate graph construction method based on Isomap algorithm layout

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] A method for constructing a low-dimensional parallel coordinate graph based on the Isomap algorithm layout, comprising the following steps:

[0075] Step S1, using the Isomap algorithm to perform dimension correlation calculation and layout;

[0076] Step S1.1 data preprocessing;

[0077] Data cleaning, filling missing values, building a data set, and treating the values ​​of the data set dimensions as vectors;

[0078] There are n samples in the data set D, and the attributes of the samples are m-dimensional, then the data set D and the i-th item a i Expressed as:

[0079] D={a 1 ,a 2 ,...,a n}

[0080] a i ={v i1 ,v i2 ,...,v im}

[0081] Among them, v ij Indicates the j-th dimension value of the i-th item;

[0082] Treating each numeric dimension as a vector gives:

[0083] D = {d 1 ,d 2 ,...,d m}

[0084] d j ={v 1j ,v 2j ,...,v nj}

[0085] Among them, d j Indicates the jth dimension, and n is the number of samples.

[0086] Step S1.2 calcu...

Embodiment 2

[0118] The data in this example comes from the image segmentation dataset in the UCI machine learning repository. The data selected 7 different outdoor pictures, and each picture was manually divided into 30 pieces, and 20 metric values ​​were selected to form a data set containing 210 pieces of images with 20 feature values. In this embodiment, each image is regarded as a class, the feature value is regarded as a dimension, and each segmented image is regarded as a sample. A dataset of 210 samples in 20 dimensions is formed.

[0119] The data is normalized according to the dimensions, and the 20 dimensions of the data set are regarded as 20 vectors, which are laid out on a two-dimensional plane using the Isomap algorithm, and the threshold is selected according to the requirements.

[0120] For the clarity of the layout results, the dimensions are identified as X1 to X20. The data layout and dimension set selection results are attached figure 1 As shown in the figure. Dep...

Embodiment 3

[0136] Data source for this example: Medical data Informatics is an increasingly important research field in healthcare, and visualization can improve the verifiability of data by showing that combinations of related dimensions correspond to specific clinical outcomes. The data in this example comes from the medical data set of early chronic kidney disease of UCI. The data is collected from the Apollo Hospital in India, with a total of 400 data samples. Among them, 250 samples were patients and 150 samples were non-patients. The data set includes 24 indicator features, 13 types of categorical variables and 11 types of numerical variables. After completing the missing values ​​in the data set, the preprocessing is completed. Finally, a data set of 24 dimensions with 400 samples is obtained.

[0137] Since the Isomap algorithm is based on the MDS and uses the shortest path algorithm, the distance between each dimension is changed from the Euclidean distance to the long distan...

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 belongs to the technical field of visualization, and particularly relates to a low-dimensional parallel coordinate graph construction method based on Isomap algorithm layout. According to the method, correlation calculation among all dimensions is carried out on data, layout is carried out according to the correlation calculation, then dimension subsets are divided according to a layout result, and finally the dimension subsets are arranged in sequence and a parallel coordinate graph is constructed. On the basis of an equidistant feature mapping method, a large number of short distances are used for measuring long distances, so all dimensions are better arranged, and a low-dimensional parallel coordinate graph is constructed accordingly. Therefore, the finally obtained visualimage can reduce errors caused by distance projection distortion, the display space is effectively utilized under the condition that a large amount of effective information of original data is reserved as much as possible, and a result facilitating extraction and interpretation of related dimension information is presented.

Description

technical field [0001] The invention belongs to the technical field of visualization, and in particular relates to a method for constructing a low-dimensional parallel coordinate map based on an Isomap algorithm layout. Background technique [0002] With the advent of the era of big data, the amount of data generated by people is increasing, and the update speed of data is also accelerating. What the era of big data brings is not only an increase in the amount of data, but also a lot of changes in the data itself. Compared with the past, a large part of the massive data generated under the modern information flow is high-dimensional data. However, due to the limitation of spatial imagination, it is difficult for people to obtain information directly from this kind of data. In this situation, how to effectively process high-dimensional data and how to obtain valuable information from high-dimensional data has become a problem to be solved. [0003] Nowadays, data visualiza...

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): G06F16/904
CPCG06F16/904
Inventor 牛奉高赵欣蕊
Owner SHANXI 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