Method for solving optimal value in even distribution with L1 norm and cosine law
A technology of L1 norm and cosine theorem, applied in the direction of electrical digital data processing, text database clustering/classification, special data processing applications, etc., to achieve the effect of reducing the dependence of the optimal clustering number
Inactive Publication Date: 2018-07-06
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the method of the elbow rule often needs to present the number of clusters in the specified search range and the corresponding average degree of distortion in the form of a relationship curve, and then estimate the elbow point on the relationship curve (the best cluster The number of clusters), this method of obtaining the optimal number of clusters through human observation has personal subjectivity, so it is not very conducive to its use in automated systems and the promotion and use of other fields
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0031] Embodiment 1: as Figure 1-5 As shown, a method of using the L1 norm and the law of cosines to find the optimal value in a uniform distribution includes the following steps:
[0032] (1) Set the range of the optimal K value to be searched in the K-Means clustering algorithm [K n , K m ];
[0033] (2) Use the K-Means mean value clustering algorithm to calculate the search range [K n , K m K in ] m -K n The average degree of distortion corresponding to the number of +1 clusters and the L1 norm normalization of all calculated average distortion degrees;
[0034] (3) K after normalizing the L1 norm m -K n +1 average distortion degree number and search range [K n , K m K in ] m -K n +1 clustering number packed into K m -K m +1 data point;
[0035] (4) Utilize the law of cosines to find the above packaged K m -K n +1 The included angle between every three adjacent data points in the data point, find the smallest included angle among all included angles, and the...
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 a method for solving an optimal value in even distribution with the L1 norm and the cosine law, and belongs to the technical field of clustering analysis in machine learning.The method includes the steps that firstly, the optimal clustering K value range [K<n>, K<m>] of even-distributed sample data is set and searched in the K-Means clustering algorithm; secondly, the average distortion degree corresponding to K<m>-K<n+1> even-distributed clustering data in the searching range is computed; finally, the obtained K<m>-K<n+1> average distortion degree data after computing is normatively processed with the L1 norm and processed with the Elbow Method modified through the cosine law, and therefore the optimal clustering K value is solved from the even-distributed data.By means of the method, the obtained optimal K value can have the better objectivity.
Description
technical field [0001] The present invention relates to a method of using L1 norm and cosine theorem to find the optimal value in uniform distribution. The technologies involved in the present invention include K-Means clustering algorithm, cosine theorem and Elbow Method in machine learning. , L1 norm normalization to normalize the data obtained in the K-Means clustering algorithm, package the normalized data and the number of clusters within the search range into a data point set, and then gather the data points every three The method for obtaining the minimum angle value from the included angles in two adjacent data points to obtain the corresponding K value, thereby identifying the optimal K value belongs to the technical field of cluster analysis in machine learning. Background technique [0002] With the development of society, all industries related to electronics have developed rapidly, everything is online, and the world has become a network. The world is at a turn...
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
Login to View More IPC IPC(8): G06F17/30
CPCG06F16/35
Inventor 戴伟秦天骏王锋邓辉卫守林张晓丽石聪明朱彦飞
Owner KUNMING UNIV OF SCI & TECH