Pre-screening-based density peak clustering method and system
A density peak and clustering method technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of high computational complexity, and achieve the effect of reducing time complexity and space complexity.
Inactive Publication Date: 2018-09-07
CHINA UNIV OF MINING & TECH
View PDF0 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The density peak clustering algorithm does not need to pre-set the number of clusters and can be applied to data of any shape, but the computational complexity is high
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
[0023] Such as figure 1 As shown, this implementation case includes the following steps:
[0024] Input: data set X = {x 1 ,x 2 ,...,x n}, cutoff distance d c , delete the proportion a, any point x c , the radius parameter λ of the circle.
[0025] Output: Clustering result labels.
[0026] Step 1. Map the data points into different circles according to the law.
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 provides a pre-screening-based density peak clustering method and system, and mainly solves the problem of relatively high calculation complexity of an original density peak clustering algorithm. The method comprises the following steps of 1, removing a data point which impossibly becomes a clustering center as far as possible by using a new screening method; 2, by utilizing a decision graph method, performing clustering center selection in residual data sets after screening; and 3, allocating residual points by using an "nearest neighbor" algorithm. The method not only can effectively lower the calculation complexity of the density peak algorithm but also has a good clustering effect as same as that of the original density peak clustering algorithm.
Description
technical field [0001] The invention provides a density peak clustering method and system based on pre-screening, which can cluster data sets of arbitrary shapes, and relates to the fields of pattern recognition and machine learning. In particular, it involves the use of a new pre-screening method to remove some points that are definitely not likely to be cluster centers, select the cluster centers according to the screened points, and then allocate the remaining points to obtain accurate clustering results. Background technique [0002] Cluster analysis is to group data objects into multiple classes or clusters according to a certain measure (similarity or dissimilarity). Objects in the same cluster have a high similarity, and objects in different clusters have a low similarity. It has certain application value in market analysis, pattern recognition, gene research, image processing and other fields. Clustering algorithms can be roughly divided into partition-based method...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06F17/30
CPCG06F18/2321
Inventor 丁世飞徐晓
Owner CHINA UNIV OF MINING & TECH