Improvement of K-means clustering algorithm based on MIP optimization

Wenbing Chang; Xinglong Yuan; Shenghan Zhou

doi:10.1088/1742-6596/1053/1/012100

Improvement of K-means clustering algorithm based on MIP optimization

Wenbing Chang
, Xinglong Yuan
, Shenghan Zhou

School of Reliability and Systems Engineering

Beihang University

Research output: Contribution to journal › Conference article › peer-review

Abstract

The k-means algorithm is a widely used partition clustering algorithm. The traditional k-means algorithm has two problems: it is easy to fall into the local optimal solution; it is very sensitive to the initial solution. In this paper, a k-means algorithm model based on mixed integer linear programming is established. The experiment shows that the effect of the new algorithm is better than the traditional k-means algorithm, and the above two problems are solved well.

Original language	English
Article number	012100
Journal	Journal of Physics: Conference Series
Volume	1053
Issue number	1
DOIs	https://doi.org/10.1088/1742-6596/1053/1/012100
State	Published - 26 Jul 2018
Event	1st International Conference on Physics, Mathematics and Statistics, ICPMS 2018 - Shanghai, China Duration: 12 May 2018 → 14 May 2018

Access to Document

10.1088/1742-6596/1053/1/012100

Cite this

@article{fb374b44e34648a08c82c121afdb2dd4,

title = "Improvement of K-means clustering algorithm based on MIP optimization",

abstract = "The k-means algorithm is a widely used partition clustering algorithm. The traditional k-means algorithm has two problems: it is easy to fall into the local optimal solution; it is very sensitive to the initial solution. In this paper, a k-means algorithm model based on mixed integer linear programming is established. The experiment shows that the effect of the new algorithm is better than the traditional k-means algorithm, and the above two problems are solved well.",

author = "Wenbing Chang and Xinglong Yuan and Shenghan Zhou",

note = "Publisher Copyright: {\textcopyright} Published under licence by IOP Publishing Ltd.; 1st International Conference on Physics, Mathematics and Statistics, ICPMS 2018 ; Conference date: 12-05-2018 Through 14-05-2018",

year = "2018",

month = jul,

day = "26",

doi = "10.1088/1742-6596/1053/1/012100",

language = "英语",

volume = "1053",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

number = "1",

}

TY - JOUR

T1 - Improvement of K-means clustering algorithm based on MIP optimization

AU - Chang, Wenbing

AU - Yuan, Xinglong

AU - Zhou, Shenghan

N1 - Publisher Copyright: © Published under licence by IOP Publishing Ltd.

PY - 2018/7/26

Y1 - 2018/7/26

N2 - The k-means algorithm is a widely used partition clustering algorithm. The traditional k-means algorithm has two problems: it is easy to fall into the local optimal solution; it is very sensitive to the initial solution. In this paper, a k-means algorithm model based on mixed integer linear programming is established. The experiment shows that the effect of the new algorithm is better than the traditional k-means algorithm, and the above two problems are solved well.

AB - The k-means algorithm is a widely used partition clustering algorithm. The traditional k-means algorithm has two problems: it is easy to fall into the local optimal solution; it is very sensitive to the initial solution. In this paper, a k-means algorithm model based on mixed integer linear programming is established. The experiment shows that the effect of the new algorithm is better than the traditional k-means algorithm, and the above two problems are solved well.

UR - https://www.scopus.com/pages/publications/85051389550

U2 - 10.1088/1742-6596/1053/1/012100

DO - 10.1088/1742-6596/1053/1/012100

M3 - 会议文章

AN - SCOPUS:85051389550

SN - 1742-6588

VL - 1053

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

IS - 1

M1 - 012100

T2 - 1st International Conference on Physics, Mathematics and Statistics, ICPMS 2018

Y2 - 12 May 2018 through 14 May 2018

ER -

Improvement of K-means clustering algorithm based on MIP optimization

Abstract

Access to Document

Other files and links

Fingerprint

Cite this