Subspace Clustering Based on Differential Evolution

Subspace clustering approaches cluster high dimensional data in different subspaces. It means grouping the data with different relevant subsets of dimensions. This technique has become very effective as a distance measure becomes ineffective in a high dimensional space. This chapter presents a novel evolutionary approach to a bottom up subspace clustering SUBSPACE_DE which is scalable to high dimensional data. SUBSPACE_DE uses a self-adaptive DBSCAN algorithm to perform clustering in data instances of each attribute and maximal subspaces. Self-adaptive DBSCAN clustering algorithms accept input from differential evolution algorithms. The proposed SUBSPACE_DE algorithm is tested on 14 datasets, both real and synthetic. It is compared with 11 existing subspace clustering algorithms. Evaluation metrics such as F1_Measure and accuracy are used. Performance analysis of the proposed algorithms is considerably better on a success rate ratio ranking in both accuracy and F1_Measure. SUBSPACE_DE also has potential scalability on high dimensional datasets.

Download Full-text

Improvement of Subspace Clustering Based on Differential Evolution

10.1109/ccet52649.2021.9544480 ◽

2021 ◽

Author(s):

Xi Huang ◽

Yulu Yang

Keyword(s):

Differential Evolution ◽

Subspace Clustering

Download Full-text

Differential evolution-based subspace clustering via thresholding ridge regression

2017 Tenth International Conference on Contemporary Computing (IC3) ◽

10.1109/ic3.2017.8284359 ◽

2017 ◽

Cited By ~ 1

Author(s):

Ankur Kulhari ◽

Mukesh Saraswat

Keyword(s):

Differential Evolution ◽

Ridge Regression ◽

Subspace Clustering

Download Full-text

Subspace Clustering Mutation Operator for Developing Convergent Differential Evolution Algorithm

Mathematical Problems in Engineering ◽

10.1155/2014/154626 ◽

2014 ◽

Vol 2014 ◽

pp. 1-18 ◽

Cited By ~ 2

Author(s):

Zhongbo Hu ◽

Shengwu Xiong ◽

Xiuhua Wang ◽

Qinghua Su ◽

Mianfang Liu ◽

...

Keyword(s):

Differential Evolution ◽

Optimization Problems ◽

Differential Evolution Algorithm ◽

Subspace Clustering ◽

Convergence In Probability ◽

Mutation Operator ◽

Mutation Operators ◽

Evolution Algorithm ◽

The Difference ◽

Theoretical Analyses

Many researches have identified that differential evolution algorithm (DE) is one of the most powerful stochastic real-parameter algorithms for global optimization problems. However, a stagnation problem still exists in DE variants. In order to overcome the disadvantage, two improvement ideas have gradually appeared recently. One is to combine multiple mutation operators for balancing the exploration and exploitation ability. The other is to develop convergent DE variants in theory for decreasing the occurrence probability of the stagnation. Given that, this paper proposes a subspace clustering mutation operator, called SC_qrtop. Five DE variants, which hold global convergence in probability, are then developed by combining the proposed operator and five mutation operators of DE, respectively. The SC_qrtop randomly selects an elite individual as a perturbation’s center and employs the difference between two randomly generated boundary individuals as a perturbation’s step. Theoretical analyses and numerical simulations demonstrate that SC_qrtop prefers to search in the orthogonal subspace centering on the elite individual. Experimental results on CEC2005 benchmark functions indicate that all five convergent DE variants with SC_qrtop mutation outperform the corresponding DE algorithms.

Download Full-text