Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation

Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation

Accurate tumor classification is crucial to the proper treatment of cancer. To now, sparse representation (SR) has shown its great performance for tumor classification. This paper conceives a new SR-based method for tumor classification by using gene expression data. In the proposed method, we first...

Full description

Bibliographic Details
Main Authors: Bin Gan, Chun-Hou Zheng, Jun Zhang, Hong-Qiang Wang
Format: Article
Language:English
Published: Hindawi Limited 2014-01-01
Series:BioMed Research International
Online Access:http://dx.doi.org/10.1155/2014/420856
id doaj-6de78a937ca94df2a428dac1e622fdef
record_format Article
spelling doaj-6de78a937ca94df2a428dac1e622fdef2020-11-25T00:00:47ZengHindawi LimitedBioMed Research International2314-61332314-61412014-01-01201410.1155/2014/420856420856Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank RepresentationBin Gan0Chun-Hou Zheng1Jun Zhang2Hong-Qiang Wang3College of Information and Communication Technology, Qufu Normal University, Rizhao 276800, ChinaCollege of Information and Communication Technology, Qufu Normal University, Rizhao 276800, ChinaCollege of Electrical Engineering and Automation, Anhui University, Hefei 230000, ChinaIntelligent Computing Lab, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230000, ChinaAccurate tumor classification is crucial to the proper treatment of cancer. To now, sparse representation (SR) has shown its great performance for tumor classification. This paper conceives a new SR-based method for tumor classification by using gene expression data. In the proposed method, we firstly use latent low-rank representation for extracting salient features and removing noise from the original samples data. Then we use sparse representation classifier (SRC) to build tumor classification model. The experimental results on several real-world data sets show that our method is more efficient and more effective than the previous classification methods including SVM, SRC, and LASSO.http://dx.doi.org/10.1155/2014/420856
collection DOAJ
language English
format Article
sources DOAJ
author Bin Gan
Chun-Hou Zheng
Jun Zhang
Hong-Qiang Wang
spellingShingle Bin Gan
Chun-Hou Zheng
Jun Zhang
Hong-Qiang Wang
Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation
BioMed Research International
author_facet Bin Gan
Chun-Hou Zheng
Jun Zhang
Hong-Qiang Wang
author_sort Bin Gan
title Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation
title_short Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation
title_full Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation
title_fullStr Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation
title_full_unstemmed Sparse Representation for Tumor Classification Based on Feature Extraction Using Latent Low-Rank Representation
title_sort sparse representation for tumor classification based on feature extraction using latent low-rank representation
publisher Hindawi Limited
series BioMed Research International
issn 2314-6133
2314-6141
publishDate 2014-01-01
description Accurate tumor classification is crucial to the proper treatment of cancer. To now, sparse representation (SR) has shown its great performance for tumor classification. This paper conceives a new SR-based method for tumor classification by using gene expression data. In the proposed method, we firstly use latent low-rank representation for extracting salient features and removing noise from the original samples data. Then we use sparse representation classifier (SRC) to build tumor classification model. The experimental results on several real-world data sets show that our method is more efficient and more effective than the previous classification methods including SVM, SRC, and LASSO.
url http://dx.doi.org/10.1155/2014/420856
work_keys_str_mv AT bingan sparserepresentationfortumorclassificationbasedonfeatureextractionusinglatentlowrankrepresentation
AT chunhouzheng sparserepresentationfortumorclassificationbasedonfeatureextractionusinglatentlowrankrepresentation
AT junzhang sparserepresentationfortumorclassificationbasedonfeatureextractionusinglatentlowrankrepresentation
AT hongqiangwang sparserepresentationfortumorclassificationbasedonfeatureextractionusinglatentlowrankrepresentation
_version_ 1725443408120512512

Similar Items