A Fast Density Peaks Clustering Algorithm Based on Pre-Screening

Density peaks clustering algorithm (DPC) is a new density-based clustering algorithm proposed to obtain any shape of the clusters. It finds cluster centers according to the decision graph which drawn based on the density-distance. However, in the process of calculating local density and distance of...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International Conference on Big Data and Smart Computing s. 513 - 516
Hlavní autoři: Xu, Xiao, Ding, Shifei, Sun, Tongfeng
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.01.2018
Témata:
Clustering algorithms
Computer science
Data mining
decision graph
density peaks clustering algorithm
large-scale data set
pre screening
Shape
Time complexity
ISSN:2375-9356
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Density peaks clustering algorithm (DPC) is a new density-based clustering algorithm proposed to obtain any shape of the clusters. It finds cluster centers according to the decision graph which drawn based on the density-distance. However, in the process of calculating local density and distance of each point, the time complexity is O(n^2), which limits the application of DPC. In this paper, we propose a fast density peaks clustering algorithm based on pre-screening (PDPC), which can effectively reduce the calculation complexity on the basis of ensuring the accuracy of clustering. According to the uneven distribution of data sets, the novel pre-screening method is used to remove some points with sparse local density first, and then the cluster centers are selected by using the decision graph. Theoretical analysis and experimental results show that this algorithm can not only reduce the time complexity, but also cluster correctly.
ISSN:2375-9356
DOI:10.1109/BigComp.2018.00084