Feature Extraction for Breast Cancer Data Based on Geometric Algebra Theory and Feature Selection Using Differential Evolution_Journal of Biomedical Engineering

Authors：

 LIJing ^1,2 , HONGWenxue ²

1. School of Science, Yanshan University, Qinhuangdao 066004, China;
2. School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China;

Corresponding author：

LIJing, Email: 01016888@sina.com

Keywords：

feature extraction; feature selection; geometric algebra; differential evolution

DOI：

10.7507/1001-5515.20140231

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.

Citation： LIJing, HONGWenxue. Feature Extraction for Breast Cancer Data Based on Geometric Algebra Theory and Feature Selection Using Differential Evolution. Journal of Biomedical Engineering, 2014, 31(6): 1218-1222,1228. doi: 10.7507/1001-5515.20140231 Copy

1.	YANG X R, CHANG-CLAUDE J, GOODE E L, et al. Associations of breast cancer risk factors with tumor subtypes:a pooled analysis from the breast cancer association consortium studies[J]. J Natl Cancer Inst, 2011, 103(3):250-263.
2.	THEODORIDIS S, KOUTROUMBAS K. Pattern recognition[M]. 2nd ed. New York:Academic Press, 2003:1-30.
3.	DUIN R P W, PEKALSKA E. The science of pattern recognition. Achievements and perspectives[M]//DUCH W, MANDZIUK J. Challenges for computational intelligence. Berlin Heidelberg:Springer Berlin Heidelberg, 2007, 63:221-259.
4.	王金甲,李静,张涛,等.二次映射和遗传算法用于鉴别可视化特征提取[J].系统仿真学报,2009,21(16):5080-5083, 5087.
5.	李静,王金甲,洪文学.生物医学数据的可视化图形特征提取方法[J].生物医学工程学杂志,2011,28(5):916-921.
6.	曹文明,冯浩.仿生模式识别与信号处理的几何代数方法[M].北京:科学出版社,2010.
7.	BAYRO-CORROCHANO E J, ARANA-DANIEL N. Clifford support vector machines for classification, regression, and recurrence[J]. IEEE Trans Neural Netw, 2010, 21(11):1731-1746.
8.	袁林旺,闾国年,罗文,等.GIS多维统一计算的几何代数方法[J].科学通报,2012,57(4):282-290.
9.	DAS S, SUGANTHAN P N. Differential evolution:a survey of the state-of-the-art[J]. IEEE Trans Evolut Comput, 2011, 15(1):4-31.
10.	STOEAN R, STOEAN C. Modeling medical decision making by support vector machines, explaining by rules of evolutionary algorithms with feature selection[J]. Expert Syst Appl, 2013, 40(7):2677-2686.
11.	CHANG P C, LIN J J, LIU Chenhao. An attribute weight assignment and particle swarm optimization algorithm for medical database classifications[J]. Comput Methods Programs Biomed, 2012, 107(3):382-392.
12.	CHEN T C, HSU T C. A GAs based approach for mining breast cancer pattern[J]. Expert Syst Appl, 2006, 30(4):674-681.
13.	CHEN Hui-ling, YANG Bo, LIU Jie, et al. A support vector machine classifier with rough set-based feature selection for breast Cancer diagnosis[J]. Expert Syst Appl, 2011, 38(7):9014-9022.
14.	LI D C, LIU C W, HU S C. A fuzzy-based data transformation for feature extraction to increase classification performance with small medical data sets[J]. Artif Intell Med, 2011, 52(1):45-52.
15.	DUCH W, JANKOWSKI N. Datasets used for classification comparison of results (2010-06-02)[2014-01-06]. http://www.is.umk.pl/projects/datasets.html.

1. YANG X R, CHANG-CLAUDE J, GOODE E L, et al. Associations of breast cancer risk factors with tumor subtypes:a pooled analysis from the breast cancer association consortium studies[J]. J Natl Cancer Inst, 2011, 103(3):250-263.
2. THEODORIDIS S, KOUTROUMBAS K. Pattern recognition[M]. 2nd ed. New York:Academic Press, 2003:1-30.
3. DUIN R P W, PEKALSKA E. The science of pattern recognition. Achievements and perspectives[M]//DUCH W, MANDZIUK J. Challenges for computational intelligence. Berlin Heidelberg:Springer Berlin Heidelberg, 2007, 63:221-259.
4. 王金甲,李静,张涛,等.二次映射和遗传算法用于鉴别可视化特征提取[J].系统仿真学报,2009,21(16):5080-5083, 5087.
5. 李静,王金甲,洪文学.生物医学数据的可视化图形特征提取方法[J].生物医学工程学杂志,2011,28(5):916-921.
6. 曹文明,冯浩.仿生模式识别与信号处理的几何代数方法[M].北京:科学出版社,2010.
7. BAYRO-CORROCHANO E J, ARANA-DANIEL N. Clifford support vector machines for classification, regression, and recurrence[J]. IEEE Trans Neural Netw, 2010, 21(11):1731-1746.
8. 袁林旺,闾国年,罗文,等.GIS多维统一计算的几何代数方法[J].科学通报,2012,57(4):282-290.
9. DAS S, SUGANTHAN P N. Differential evolution:a survey of the state-of-the-art[J]. IEEE Trans Evolut Comput, 2011, 15(1):4-31.
10. STOEAN R, STOEAN C. Modeling medical decision making by support vector machines, explaining by rules of evolutionary algorithms with feature selection[J]. Expert Syst Appl, 2013, 40(7):2677-2686.
11. CHANG P C, LIN J J, LIU Chenhao. An attribute weight assignment and particle swarm optimization algorithm for medical database classifications[J]. Comput Methods Programs Biomed, 2012, 107(3):382-392.
12. CHEN T C, HSU T C. A GAs based approach for mining breast cancer pattern[J]. Expert Syst Appl, 2006, 30(4):674-681.
13. CHEN Hui-ling, YANG Bo, LIU Jie, et al. A support vector machine classifier with rough set-based feature selection for breast Cancer diagnosis[J]. Expert Syst Appl, 2011, 38(7):9014-9022.
14. LI D C, LIU C W, HU S C. A fuzzy-based data transformation for feature extraction to increase classification performance with small medical data sets[J]. Artif Intell Med, 2011, 52(1):45-52.
15. DUCH W, JANKOWSKI N. Datasets used for classification comparison of results (2010-06-02)[2014-01-06]. http://www.is.umk.pl/projects/datasets.html.

Journal of Biomedical Engineering

Feature Extraction for Breast Cancer Data Based on Geometric Algebra Theory and Feature Selection Using Differential Evolution

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content