A subspace recursive and selective feature transformation method for classification tasks
Abstract Background Practitioners and researchers often found the intrinsic representations of high-dimensional problems has much fewer independent variables. However such intrinsic structure may not be easily discovered due to noises and other factors. A supervised transformation scheme RST is prop...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2017-12-01
|
| Series: | Big Data Analytics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s41044-017-0025-5 |
| _version_ | 1811316274788040704 |
|---|---|
| author | Xuan Zhao Steven Sheng-Uei Guan |
| author_facet | Xuan Zhao Steven Sheng-Uei Guan |
| author_sort | Xuan Zhao |
| collection | DOAJ |
| description | Abstract Background Practitioners and researchers often found the intrinsic representations of high-dimensional problems has much fewer independent variables. However such intrinsic structure may not be easily discovered due to noises and other factors. A supervised transformation scheme RST is proposed to transform features into lower dimensional spaces for classification tasks. The proposed algorithm recursively and selectively transforms the features guided by the output variables. Results We compared the classification performance of linear classifier and random forest classifier on the original data sets, data sets being transformed with RST and data sets being transformed by principle component analysis and linear discriminant analysis. On 7 out 8 data sets RST shows superior classification performance with linear classifiers but less ideal with random forest classifiers. Conclusions Our test shows the proposed method’s capability to reduce features dimensions in general classification tasks and preserve useful information using linear transformations. Some limitations of this method are also pointed out. |
| first_indexed | 2024-04-13T11:45:59Z |
| format | Article |
| id | doaj.art-67b927c3bddd4b6a87c835087d89d58b |
| institution | Directory Open Access Journal |
| issn | 2058-6345 |
| language | English |
| last_indexed | 2024-04-13T11:45:59Z |
| publishDate | 2017-12-01 |
| publisher | BMC |
| record_format | Article |
| series | Big Data Analytics |
| spelling | doaj.art-67b927c3bddd4b6a87c835087d89d58b2022-12-22T02:48:10ZengBMCBig Data Analytics2058-63452017-12-012111010.1186/s41044-017-0025-5A subspace recursive and selective feature transformation method for classification tasksXuan Zhao0Steven Sheng-Uei Guan1Department of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool UniversityDepartment of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool UniversityAbstract Background Practitioners and researchers often found the intrinsic representations of high-dimensional problems has much fewer independent variables. However such intrinsic structure may not be easily discovered due to noises and other factors. A supervised transformation scheme RST is proposed to transform features into lower dimensional spaces for classification tasks. The proposed algorithm recursively and selectively transforms the features guided by the output variables. Results We compared the classification performance of linear classifier and random forest classifier on the original data sets, data sets being transformed with RST and data sets being transformed by principle component analysis and linear discriminant analysis. On 7 out 8 data sets RST shows superior classification performance with linear classifiers but less ideal with random forest classifiers. Conclusions Our test shows the proposed method’s capability to reduce features dimensions in general classification tasks and preserve useful information using linear transformations. Some limitations of this method are also pointed out.http://link.springer.com/article/10.1186/s41044-017-0025-5Machine learningFeature transformationFeature selectionClassificationSubspace learning |
| spellingShingle | Xuan Zhao Steven Sheng-Uei Guan A subspace recursive and selective feature transformation method for classification tasks Big Data Analytics Machine learning Feature transformation Feature selection Classification Subspace learning |
| title | A subspace recursive and selective feature transformation method for classification tasks |
| title_full | A subspace recursive and selective feature transformation method for classification tasks |
| title_fullStr | A subspace recursive and selective feature transformation method for classification tasks |
| title_full_unstemmed | A subspace recursive and selective feature transformation method for classification tasks |
| title_short | A subspace recursive and selective feature transformation method for classification tasks |
| title_sort | subspace recursive and selective feature transformation method for classification tasks |
| topic | Machine learning Feature transformation Feature selection Classification Subspace learning |
| url | http://link.springer.com/article/10.1186/s41044-017-0025-5 |
| work_keys_str_mv | AT xuanzhao asubspacerecursiveandselectivefeaturetransformationmethodforclassificationtasks AT stevenshengueiguan asubspacerecursiveandselectivefeaturetransformationmethodforclassificationtasks AT xuanzhao subspacerecursiveandselectivefeaturetransformationmethodforclassificationtasks AT stevenshengueiguan subspacerecursiveandselectivefeaturetransformationmethodforclassificationtasks |