An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques

In the paper, several data reduction techniques for machine learning from big datasets are discussed and evaluated. The discussed approach focuses on combining several techniques including stacking, rotation, and data reduction aimed at improving the performance of the machine classification. Stacki...

Full description

Saved in:
Bibliographic Details
Main Authors: Ireneusz Czarnowski, Piotr Jędrzejowicz
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2018/7404627
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156883539656704
author Ireneusz Czarnowski
Piotr Jędrzejowicz
author_facet Ireneusz Czarnowski
Piotr Jędrzejowicz
author_sort Ireneusz Czarnowski
collection DOAJ
description In the paper, several data reduction techniques for machine learning from big datasets are discussed and evaluated. The discussed approach focuses on combining several techniques including stacking, rotation, and data reduction aimed at improving the performance of the machine classification. Stacking is seen as the technique allowing to take advantage of the multiple classification models. The rotation-based techniques are used to increase the heterogeneity of the stacking ensembles. Data reduction makes it possible to classify instances belonging to big datasets. We propose to use an agent-based population learning algorithm for data reduction in the feature and instance dimensions. For diversification of the classifier ensembles within the rotation also, alternatively, principal component analysis and independent component analysis are used. The research question addressed in the paper is formulated as follows: does the performance of a classifier using the reduced dataset be improved by integrating the data reduction mechanism with the rotation-based technique and the stacking?
format Article
id doaj-art-32dadf8e69db4abbba23da07fefe08d0
institution OA Journals
issn 1076-2787
1099-0526
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-32dadf8e69db4abbba23da07fefe08d02025-08-20T02:24:22ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/74046277404627An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning TechniquesIreneusz Czarnowski0Piotr Jędrzejowicz1Department of Information Systems, Gdynia Maritime University, Morska 83, 81-225 Gdynia, PolandDepartment of Information Systems, Gdynia Maritime University, Morska 83, 81-225 Gdynia, PolandIn the paper, several data reduction techniques for machine learning from big datasets are discussed and evaluated. The discussed approach focuses on combining several techniques including stacking, rotation, and data reduction aimed at improving the performance of the machine classification. Stacking is seen as the technique allowing to take advantage of the multiple classification models. The rotation-based techniques are used to increase the heterogeneity of the stacking ensembles. Data reduction makes it possible to classify instances belonging to big datasets. We propose to use an agent-based population learning algorithm for data reduction in the feature and instance dimensions. For diversification of the classifier ensembles within the rotation also, alternatively, principal component analysis and independent component analysis are used. The research question addressed in the paper is formulated as follows: does the performance of a classifier using the reduced dataset be improved by integrating the data reduction mechanism with the rotation-based technique and the stacking?http://dx.doi.org/10.1155/2018/7404627
spellingShingle Ireneusz Czarnowski
Piotr Jędrzejowicz
An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques
Complexity
title An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques
title_full An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques
title_fullStr An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques
title_full_unstemmed An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques
title_short An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques
title_sort approach to data reduction for learning from big datasets integrating stacking rotation and agent population learning techniques
url http://dx.doi.org/10.1155/2018/7404627
work_keys_str_mv AT ireneuszczarnowski anapproachtodatareductionforlearningfrombigdatasetsintegratingstackingrotationandagentpopulationlearningtechniques
AT piotrjedrzejowicz anapproachtodatareductionforlearningfrombigdatasetsintegratingstackingrotationandagentpopulationlearningtechniques
AT ireneuszczarnowski approachtodatareductionforlearningfrombigdatasetsintegratingstackingrotationandagentpopulationlearningtechniques
AT piotrjedrzejowicz approachtodatareductionforlearningfrombigdatasetsintegratingstackingrotationandagentpopulationlearningtechniques