[1]Mudasser NASEER,秦世引.基于非线性降维多项式逻辑斯蒂回归的图像/非图像数据的分类与识别[J].智能系统学报,2010,5(1):85-93.
Mudasser NASEER,QIN Shi yin.Classification and recognition of image/nonimage data based on multinomial logistic regression with nonlinear dimensionality reduction[J].CAAI Transactions on Intelligent Systems,2010,5(1):85-93.
点击复制
Mudasser NASEER,QIN Shi yin.Classification and recognition of image/nonimage data based on multinomial logistic regression with nonlinear dimensionality reduction[J].CAAI Transactions on Intelligent Systems,2010,5(1):85-93.
基于非线性降维多项式逻辑斯蒂回归的图像/非图像数据的分类与识别
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
5
期数:
2010年第1期
页码:
85-93
栏目:
学术论文—机器感知与模式识别
出版日期:
2010-02-25
- Title:
- Classification and recognition of image/nonimage data based on multinomial logistic regression with nonlinear dimensionality reduction
- 文章编号:
- 1673-4785(2010)01-0085-09
- Keywords:
- nonlinear dimensionality reduction; data classification; multinomial logistic regression; image/nonimage data
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 在面向大规模复杂数据的模式分类和识别问题中，绝大多数的分类器都遇到了维数灾难这一棘手的问题.在进行高维数据分类之前，基于监督流形学习的非线性降维方法可提供一种有效的解决方法.利用多项式逻辑斯蒂回归方法进行分类预测，并结合基于非线性降维的非监督流形学习方法解决图像以及非图像数据的分类问题，因而形成了一种新的分类识别方法.大量的实验测试和比较分析验证了本文所提方法的优越性.
- Abstract:
- In pattern classification and recognition oriented to massively complex data most classifiers suffer from the curse of dimensionality. Manifold learning based nonlinear dimensionality reduction (NLDR) methods provide a good preprocessing to reduce dimensionality before applying any classification method on high dimensional data. Multinomial logistic regression (MLR) can be used to predict the class membership of feature data. In this study several unsupervised NLDR methods are employed to reduce dimensions of the data and the MLR is used for class prediction of image/nonimage data so that a new method of classification and recognition oriented to massively complex image/nonimage data is proposed based on multinomial Logistic regression with nonlinear dimensionality reduction. Through a series of experiments and comparative analysis with supervised NLDR methods for a lot of typical test data the new proposed method is validated to outperform other supervised NLDR ones.
- 参考文献/References:
-
［1］JAMES M. Classification algorithms［M］. New York： John Wiley & Sons Inc, 1985.
［2］ROWEIS S T, SAUL L K, Nonlinear dimensionality reduction by locally linear embedding［J］. Science, 2000, 290: 23232326.
［3］TENENBAUM J B, SILVA V D, LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction［J］. Science, 2000, 290: 23192323.
［4］BELKIN M, NIYOGI P. Laplacian eigenmaps and spectral techniques for embedding and clustering［J］. Neural Computations, 2003, 15(6): 13731396.
［5］COIFMAN R R, LAFON S. Diffusion maps［J］. Applied and Computational Harmonic Analysis, 2006, 21(1): 530.
［6］DONOHO D L, GRIMES C E. Hessian eigenmaps: new locally linear embedding techniques for highdimensional data［J］. Proceedings of the National Academy of Sciences of the USA, 2003, 100(10): 55915596.
［7］ZHANG Zhenyue, ZHA Hongyuan. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment［J］. SIAM Journal on Scientific Computing, 2004, 26(1): 313338.
［8］BUSA F K, KOCSOR A. Locally linear embedding and its variants for feature extraction［C］//IEEE International Workshop on Soft Computing Applications (SOFA). Szeged, Hungary and Arad, Romania, 2005: 216222.
［9］RIDDER D, DUIN R P W. Locally linear embedding for classification. Delft: PH200201［R］. Pattern Recognition Group, Dept of Image Science & Technology, Delft University of Technology. Delft, Netherlands, 2002.
［10］RIDDER D, KOUROPTEVA O, OKUN O, et al. Supervised locally linear embedding［C］//Proceedings of Artificial Neural Networks and Neural Information Processing (ICANN/ICONIP). Istanbul, Turkey, 2003: 333341.
［11］VLACHOS M, DOMENICONI C, GUNOPULOS D, et al. Nonlinear dimensionality reduction techniques for classification and visualization［C］//Proceedings of 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Edmonton, Canada, 2002: 645651.
［12］GENG Xin, ZHAN Dechuan, ZHOU Zhihua. Supervised nonlinear dimensionality reduction for visualization and classification［J］. IEEE Transactions on Systems, Man, and CyberneticsPart B: Cybernetics, 2005, 35(6): 10981107.
［13］LI Hongyu, CHEN Wenbin, SHEN Ifan. Supervised local tangent space alignment for classification［C］//Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Edinburgh, Scotland, 2005: 16201621.
［14］ROSS D A, LIM J, LIN R S, et al. Incremental learning for robust visual tracking［J］. International Journal of Computer Vision, 2008, 77(1): 125141.
［15］BENGIO Y, PAIEMENT JF, VINCENT P, et al. Outofsample extensions for LLE, Isomap, MDS, eigenmaps, and spectral clustering［J］. Advances in Neural Information Processing Systems, 2004(16): 177184.
［16］HO T K. Nearest neighbors in random subspaces［J］. LNCS: Advances in Pattern Recognition, 1998, 1451: 640648.
?［17］HOSMER D W, LEMESHOW S. Applied logistic regerssion［M］. 2nd ed. New York: John Wiley & Sons Inc, 2000: 128135.
［18］FUKUNAGA K. Introduction to statistical pattern recognition［M］. 2nd ed. San Diago: Academic Press, 1990: 219237.
- 相似文献/References:
-
[1]蒲凌杰,曾繁慧,汪培庄.因素空间理论下基点分类算法研究[J].智能系统学报,2020,15(3):528.[doi:10.11992/tis.201903031]
PU Lingjie,ZENG Fanhui,WANG Peizhuang.Base point classification algorithm based on factor space theory[J].CAAI Transactions on Intelligent Systems,2020,15():528.[doi:10.11992/tis.201903031]
备注/Memo
Received Data：2009-08-15.
Foundation Item：This work is supported by The Major Program of Hitechnology Research and Development (863) of China.(2008AA12A200) and Programs of National Natural Science Foundation of China (60875072 ).
Corresponding Author：QIN Shi-yin.E-mail:qsy@buaa.edu.cn.
About the authors：
Mudasser NASEER received his Master’s and M.Phil degrees in Statistics from Govt. College University Lahore, Pakistan, in 1990 and 2001. He completed his MS in CS from LUMS Lahore in 2004. Presently he is pursuing his PhD in Pattern Recognition from Beihang University，Beijing，China.?
?秦世引, received his Bachelor Degree and Master’s Degree for Engineering Science in Automatic Controls and Industrial Systems Engineering from Lanzhou Jiaotong University in 1978 and 1984 respectively, and his PhD Degree in Industrial Control Engineering and Intelligent Automation from Zhejiang University in 1990.
更新日期/Last Update:
2010-03-31