Multi-Objective Feature Selection Method Based on Hybrid MI and PSO Algorithm
Feature selection is an important pre-processing in data mining, due to a lot of redundant and irrelevant features in datasets. A filter-wrapper multi-objective feature selection method based on hybrid mutual information and particle swarm optimization algorithm (HMIPSO) is proposed. Based on the nu...
Main Author: | |
---|---|
Format: | Article |
Language: | zho |
Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2020-01-01
|
Series: | Jisuanji kexue yu tansuo |
Subjects: | |
Online Access: | http://fcst.ceaj.org/CN/abstract/abstract2090.shtml |
id |
doaj-638a8f1023f04c1687824bc403418887 |
---|---|
record_format |
Article |
spelling |
doaj-638a8f1023f04c1687824bc4034188872021-07-30T05:05:34ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182020-01-01141839510.3778/j.issn.1673-9418.1901060Multi-Objective Feature Selection Method Based on Hybrid MI and PSO AlgorithmWANG Jinjie, LI Wei01. School of Computer Science and Technology, Anhui University, Hefei 230601, China 2. Key Laboratory of Intelligent Computing & Signal Processing, Ministry of Education, Anhui University, Hefei 230039, ChinaFeature selection is an important pre-processing in data mining, due to a lot of redundant and irrelevant features in datasets. A filter-wrapper multi-objective feature selection method based on hybrid mutual information and particle swarm optimization algorithm (HMIPSO) is proposed. Based on the number of iterations of the pbest of the particle from the last update, an adaptive mutation strategy is proposed to disturb the population and avoid the population falling into local optimum. Meanwhile, a new set concept based on the Pareto front and archive is proposed. Combining mutual information and the new set knowledge, a local search strategy is proposed, which enables particles in Pareto front to delete irrelevant and redundant features, and then the Pareto front before and after learning is updated by Elite. Finally, this paper compares the effectiveness of HMIPSO with other 4 multi-objective algorithms on 15 UCI datasets. The experimental results show that HMIPSO can reduce the number of features and classification error rate efficiently.http://fcst.ceaj.org/CN/abstract/abstract2090.shtmlmulti-objective optimizationfeature selection; mutual information (mi)particle swarm optimization(pso)pareto front; archive |
collection |
DOAJ |
language |
zho |
format |
Article |
sources |
DOAJ |
author |
WANG Jinjie, LI Wei |
spellingShingle |
WANG Jinjie, LI Wei Multi-Objective Feature Selection Method Based on Hybrid MI and PSO Algorithm Jisuanji kexue yu tansuo multi-objective optimization feature selection; mutual information (mi) particle swarm optimization(pso) pareto front; archive |
author_facet |
WANG Jinjie, LI Wei |
author_sort |
WANG Jinjie, LI Wei |
title |
Multi-Objective Feature Selection Method Based on Hybrid MI and PSO Algorithm |
title_short |
Multi-Objective Feature Selection Method Based on Hybrid MI and PSO Algorithm |
title_full |
Multi-Objective Feature Selection Method Based on Hybrid MI and PSO Algorithm |
title_fullStr |
Multi-Objective Feature Selection Method Based on Hybrid MI and PSO Algorithm |
title_full_unstemmed |
Multi-Objective Feature Selection Method Based on Hybrid MI and PSO Algorithm |
title_sort |
multi-objective feature selection method based on hybrid mi and pso algorithm |
publisher |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
series |
Jisuanji kexue yu tansuo |
issn |
1673-9418 |
publishDate |
2020-01-01 |
description |
Feature selection is an important pre-processing in data mining, due to a lot of redundant and irrelevant features in datasets. A filter-wrapper multi-objective feature selection method based on hybrid mutual information and particle swarm optimization algorithm (HMIPSO) is proposed. Based on the number of iterations of the pbest of the particle from the last update, an adaptive mutation strategy is proposed to disturb the population and avoid the population falling into local optimum. Meanwhile, a new set concept based on the Pareto front and archive is proposed. Combining mutual information and the new set knowledge, a local search strategy is proposed, which enables particles in Pareto front to delete irrelevant and redundant features, and then the Pareto front before and after learning is updated by Elite. Finally, this paper compares the effectiveness of HMIPSO with other 4 multi-objective algorithms on 15 UCI datasets. The experimental results show that HMIPSO can reduce the number of features and classification error rate efficiently. |
topic |
multi-objective optimization feature selection; mutual information (mi) particle swarm optimization(pso) pareto front; archive |
url |
http://fcst.ceaj.org/CN/abstract/abstract2090.shtml |
work_keys_str_mv |
AT wangjinjieliwei multiobjectivefeatureselectionmethodbasedonhybridmiandpsoalgorithm |
_version_ |
1721247863643570176 |