Improved LDA algorithm and research on rank limitation

doi:10.3778/j.issn.1002-8331.2010.32.005

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (32): 17-20.DOI: 10.3778/j.issn.1002-8331.2010.32.005

• 博士论坛 • Previous Articles Next Articles

Improved LDA algorithm and research on rank limitation

LIU Zhong-bao^1，2，WANG Shi-tong¹

1.School of Information，Jiangnan Univerisity，Wuxi，Jiangsu 214122，China
2.Department of Information Engineering，Business College of Shanxi University，Taiyuan 030031，China

Received:2009-07-22 Revised:2009-09-10 Online:2010-11-11 Published:2010-11-11
Contact: LIU Zhong-bao

改进的LDA算法及秩限制问题研究

刘忠宝^1，2，王士同¹

1.江南大学信息学院，江苏无锡 214122
2.山西大学商务学院信息工程系，太原 030031

通讯作者: 刘忠宝

Abstract

Abstract: Improved Linear Discriminant Analysis（ILDA） is presented to improve the classification performance of LDA by modifying the original Fisher discriminant criterion，which aims at not only overcoming the rank limitaiton of LDA，but also solving the small size sample problem.This paper mainly discusses the effectiveness of ILDA in overcoming rank limitation.Experiments on some publicly available datasets and one artificial dataset show that the proposed algorithm ILDA has good performance and arrives at the target of getting much more discriminant features.

Key words: Linear Discriminant Analysis（LDA）, between-class scatter matrix, within-class scatter matrix, rank limitation

摘要： 针对经典线性判别分析中存在的秩限制和小样本问题，通过改进原有的Fisher准则，提出了一种改进的线性判别分析算法ILDA，以克服秩限制问题并同时解决了小样本问题。重点研究了ILDA在解决样本类间离散度矩阵秩限制方面的有效性。在多个国际标准数据集和人工数据集上实验的结果表明ILDA算法不仅有效地突破了秩限制，达到提取更多判别特征的目的，而且具有良好的识别效果。

关键词: 线性判别分析, 类间离散度矩阵, 类内离散度矩阵, 秩限制问题

CLC Number:

TP391.4

LIU Zhong-bao^1，2，WANG Shi-tong¹. Improved LDA algorithm and research on rank limitation[J]. Computer Engineering and Applications, 2010, 46(32): 17-20.

刘忠宝^1，2，王士同¹. 改进的LDA算法及秩限制问题研究[J]. 计算机工程与应用, 2010, 46(32): 17-20.

[1]	HUANG Guangjun, DENG Yuanlong. Polarizer Visual Defect Detection and Classification Based on Improved LBP and SVM Algorithm [J]. Computer Engineering and Applications, 2020, 56(22): 251-255.
[2]	XU Jingze, WU Zuohong, XU Yan, ZENG Jianhang. Face Recognition Based on PCA，LDA and SVM Algorithms [J]. Computer Engineering and Applications, 2019, 55(18): 34-37.
[3]	LIU Qinghua1, LAI Yuping2, DING Hongwei1, YANG Zhijun1, Cui Xiaolong3. Protein Subcellular Localization Prediction Based on SVM [J]. Computer Engineering and Applications, 2019, 55(11): 136-141.
[4]	GUO Keyou, WANG Yiwei, GUO Xiaoli. Lane classification algorithm combined LDA and LSD [J]. Computer Engineering and Applications, 2017, 53(24): 219-225.
[5]	HUANG Wei, WANG Xiaohui, JIANG Yuzhen. Linear discriminant analysis method based on column for face recognition [J]. Computer Engineering and Applications, 2017, 53(13): 211-215.
[6]	ZHONG Wei1, HUANG Yuanliang2, HAO Zhenzhen3, JIANG Tiantian1. Research on implementation method of LDA algorithm based on Particle Swarm Optimization [J]. Computer Engineering and Applications, 2017, 53(1): 39-43.
[7]	WU Bin1, MA Guixiang2, WU Xiaohong2. Classification of apples using near infrared spectroscopy with FUDT [J]. Computer Engineering and Applications, 2016, 52(3): 193-196.
[8]	ZHANG Jijun1, MA Dengwu2, WANG Lin1. Recognition and diagnosis of incipient faults in analog circuit using improved HMM [J]. Computer Engineering and Applications, 2014, 50(3): 261-264.
[9]	XUE Sizhong, CHEN Xiuhong. Novel kernel-based nonlinear discriminant analysis [J]. Computer Engineering and Applications, 2013, 49(2): 181-183.
[10]	HUANG Yong. Sparse discriminant analysis for expression recognition [J]. Computer Engineering and Applications, 2012, 48(7): 172-173.
[11]	CHENG Kun, SHU Qin, LUO Wei. Fusion of Gabor and local tangent space alignment for face recognition [J]. Computer Engineering and Applications, 2012, 48(10): 208-211.
[12]	ZHU Minghan，SHAO Xiangyi. Fisher linear discriminant analysis algorithm based on vector muster [J]. Computer Engineering and Applications, 2011, 47(6): 205-207.
[13]	ZHANG Yan^1，2，ZHENG Wei¹，HU Yong¹. Parameterized direct LDA in hidden space and its application [J]. Computer Engineering and Applications, 2011, 47(6): 212-215.
[14]	GAO Enzhi1，WANG Shitong2，ZHANG Ruyan1. Algorithm of geodesic distance approximating dimension reduction [J]. Computer Engineering and Applications, 2011, 47(33): 172-175.
[15]	ZHANG Aihua，KONG Lingjie. Wavelet packet transform and principal component analysis for identifying sub-health state [J]. Computer Engineering and Applications, 2011, 47(26): 238-241.

Improved LDA algorithm and research on rank limitation

改进的LDA算法及秩限制问题研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics