Computer Science ›› 2016, Vol. 43 ›› Issue (6): 312-315.doi: 10.11896/j.issn.1002-137X.2016.06.062

Previous Articles     Next Articles

Kernel-based Supervised Neighborhood Projection Analysis Algorithm

ZHENG Jian-wei, KONG Chen-chen, WANG Wan-liang, QIU Hong and ZHANG Hang-ke   

  • Online:2018-12-01 Published:2018-12-01

Abstract: A new algorithm called KSNPA which exhibits a nonlinear form of discriminative elastic embedding (DEE) was proposed.KSNPA integrates class labels and linear projection matrix into the final objective function,as well as uses kernel function to deal with nonlinear embedding situation.According to two different strategies for optimizing the objective function,the algorithm is divided into kernel-based supervised neighborhood projection analysis algorithm 1(KSNPA1) and supervised neighborhood projection analysis algorithm 2 (KSNPA2).Furthermore,a deliberately selected search direction,termed as Laplacian Direction,is applied in KSNPA1 for achieving faster convergence rate and lower computational complexit.Experimental results on several databases demonstrate that the proposed algorithm achieves powerful pattern revealing capability for complex manifold data.Moreover,the algorithm is more efficient and robust than DEE and related dimensionality reduction algorithms.

Key words: Elastic embedding,Kernel method,Projection analysis,Supervised learning

[1] Huang Jin-jie,Lv Ning,Li Shuang-quan,et al.Feature selection for classificatory analysis based on information-theoretic criteria[J].Acta Automatica Sinica,2008,34(3):383-392
[2] Venna J,Pectone J,Nybo K,et al.Information retrieval perspective to nonlinear dimensionality reduction for data visualization[J].Journal of Machine Learning Research,2010,11(1):451-490
[3] Yang W Y,Liang W,Xin L,et al.Subspace semi-supervised fisher discriminant analysis[J].Acta Automatica Sinica,2009,35(12):1513-1519
[4] Alfaro C A,Aydin B,Valencia C E,et al.Dimension reduction in principal component analysis for trees[J].Computational Statistics & Data Analysis,2014,74:157-179
[5] Yang W,Wu H.Regularized complete linear discriminant analysis[J].Neurocomputing,2014,137:185-191
[6] Machado J T.Multidimensional scaling analysis of fractionalsystems[J].Computers & Mathematics with Applications,2012,64(10):2966-2972
[7] Tenenbaum J,Silva V,Langford J C.A global geometric framework for nonlinear dimensionality reduction[J].Science,2000,290:2319-2323
[8] Roweis S T,Lawrance K S.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290:2323-2326
[9] Yin X S,Chen S C,Hu E L.Regularized soft K-means for discriminant analysis[J].Neurocomputing,2013,103(1):29-42
[10] Maras K L,et al.Mental imagery scanning in autism spectrum disorder[J].Research in Autism Spectrum Disorders,2014,8(10):1416-1423
[11] Hinton G,Roweis S T.Stochastic neighbor embedding[M]∥Advances in Neural Information Processing Systems 15.MIT Press,2003:833-840
[12] Maaten L,Hinton G.Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9(11):2579-2605
[13] Lunga D,Ersoy O.Spherical stochastic neighbor embedding of hyperspectral data[J].IEEE Transactions on Geoscience and remote sensing,2013,51(2):857-871
[14] Lee J A,Verleysen M.Shift-invariant similarities circumventdistance concentration in stochastic neighbor embedding and variants[J].Procedia Computer Science,2011,4:538-547
[15] Carreira-Perpian M A.The elastic embedding algorithm for dimensionality reduction[C]∥27th International Conference on Machine Learning.2010:167-174
[16] Zheng J W,Zhang H K,Cattani C,et al.Dimensionality reduction by supervised neighbor embedding using laplacian search[J].Computational and Mathematical Methods in Medicine,2014:2014(1):594379
[17] Yang W,Wang K Q,Zuo W M.Fast neighborhood component analysis[J].Neurocomputing,2012,83:31-37
[18] Zheng J W,et al.Fast Discriminative Stochastic Neighbor Embedding Analysis[J].Computational and Mathematical Methods in Medicine,2013,2013(11):367-371
[19] Nocedal J,Wright S.Numerical Optimization(Second edition)[M].Springer-Verlag,2006

No related articles found!
Full text



No Suggested Reading articles found!