Unlock instant, AI-driven research and patent intelligence for your innovation.
Weight-adjustable high-dimensional data dimension reduction method and system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of high-dimensional data and weight adjustment, which is applied in the fields of instruments, artificial life, computing, etc., can solve the problems of low dimensionality reduction accuracy and large errors, achieve excellent Bouldin index, solve dimensionality reduction problems, and improve clustering effects Effect
Pending Publication Date: 2022-05-13
SOUTHWEAT UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] In order to overcome the deficiencies of the prior art, the present invention provides a high-dimensional data dimensionality reduction method and system with adjustable weights, which solves the problems of low dimensionality reduction accuracy and large errors in the prior art
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0062] like Figure 1 to Figure 9 As shown, this embodiment takes complex high-dimensional medical record data as an example.
[0064] Step1: Preprocess complex high-dimensional medical record data: form n pieces of data into an experimental data set, and each piece of data contains m attributes, and then standardize n pieces of m-dimensional data to form the data matrix X used in the experiment ;
[0065]
[0066] where x ik It is the data of row i and column k of high-dimensional data, n>2 and a positive integer, m>3 and a positive integer, i is a positive integer and 1≤i≤n, k is a positive integer and 1≤k≤m ;
[0067] Step2: Use SVD and Critic weight method to calculate the weight of the n*m data matrix;
[0068] Step3: Bring the weight value calculated in Step2 into the high-dimensional space point-to-Euclidean distance calculation formula, and multiply the distance between each component by the correspon...
Embodiment 2
[0087] like Figure 1 to Figure 9 As shown, as a further optimization of Embodiment 1, this embodiment includes all the technical features of Embodiment 1. In addition, this embodiment also includes the following technical features:
[0088] This embodiment takes complex high-dimensional medical record data as an example.
[0089] First, select n pieces of complex high-dimensional medical record data. Since each piece of data has m attributes, a data matrix X of n*m is formed, and then the matrix is standardized;
[0090]
[0091] where x ik It is the data of row i and column k of high-dimensional data, n>2 and a positive integer, m>3 and a positive integer, i is a positive integer and 1≤i≤n, k is a positive integer and 1≤k≤m ;
[0092] x i =[x i1 x i2 … x ik … x im ].
[0093] Second, calculate the attribute weight of the formed data matrix X through SVD and Critic weight method to obtain the weight a and weight b two weights;
[0094] weight a =[w a1 …...
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
Login to View More
Abstract
The invention relates to the technical field of data dimension reduction, and discloses a weight-adjustable high-dimensional data dimension reduction method and a weight-adjustable high-dimensional data dimension reduction system, the dimension reduction method comprises the following steps: Step 1, extracting data; step 2, obtaining an attribute weight matrix; step 3, calculating the distance of the weighted Euclidean point pair; step 4, calculating a high-dimensional space joint probability; and Step 5, obtaining low-dimensional space point distribution. According to the method, the problems of relatively low dimension reduction accuracy, relatively large error and the like in the prior art are solved.
Description
technical field [0001] The invention relates to the technical field of data dimensionality reduction, in particular to a method and system for dimensionality reduction of high-dimensional data with adjustable weights. Background technique [0002] At present, human society is entering the era of big data. With the rapid development of computer information technology, all walks of life in society are gradually digitized, and more and more data is generated and stored. How to transform these complex and high-dimensional data into low-dimensional data that we can observe and facilitate further use is an important problem that needs to be solved urgently. Most of the dimension reduction methods are divided into linear and nonlinear, mainly represented by PCA, MDS, t-SNE, etc., in which t-SNE measures the similarity between high-dimensional space and low-dimensional space point pairs through conditional probability, And using the KL divergence as the objective function enables t...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More