[1]谈 超,吉根林.一种基于迭代分解的增量流形学习算法[J].南京师范大学学报(自然科学版),2016,39(01):14.
 Tan Chao,Ji Genlin.An Incremental Manifold Learning Algorithm Based onIterative Decomposition[J].Journal of Nanjing Normal University(Natural Science Edition),2016,39(01):14.
点击复制

一种基于迭代分解的增量流形学习算法()
分享到:

《南京师范大学学报》(自然科学版)[ISSN:1001-4616/CN:32-1239/N]

卷:
第39卷
期数:
2016年01期
页码:
14
栏目:
数学
出版日期:
2016-03-31

文章信息/Info

Title:
An Incremental Manifold Learning Algorithm Based onIterative Decomposition
作者:
谈 超吉根林
南京师范大学计算机科学与技术学院,江苏 南京 210023
Author(s):
Tan ChaoJi Genlin
School of Computer Science and Technology,Nanjing Normal University,Nanjing 210023,China
关键词:
流形学习迭代分解增量流形学习
Keywords:
manifold learningiterative decompositionincremental learning
分类号:
TP181
文献标志码:
A
摘要:
流形学习可以用于发现大型高维数据集的内在结构,并给出理解该数据集的潜在方式,已被视为一种有效的非线性降维方法. 近年来,新数据点不断地从数据流中产生,将改变已有数据点及其邻域点的坐标,传统流形学习算法不能有效地用于寻找高维数据流的内在信息. 为了解决该问题,本文提出了一种基于迭代分解的增量流形学习算法IMLID(Incremental Manifold Learning Algorithm Based on Iterative Decomposition),可以检测到数据流形中的逐步变化,校准逐渐变化中的流形,可提高在取样于真实世界的特征集上分类效果的精确率,利用真实数据集进行实验验证,结果表明本文提出的算法是有效的,与其他相关算法相比,其性能具有优势,在模式识别、生物信息等领域具有应用价值.
Abstract:
Manifold learning is used to discover intrinsic low-dimensional manifolds of data points embedded in high-dimensional spaces,which is useful in nonlinear dimension reduction. In recent years,new data points come continually,which will change the existing data points’ neighborhoods and their local distributions. Tranditional methods cannot discover intrinsic information of high dimensional data streams effectively. To solve this problem,we propose an Incremental Manifold Learning Algorithm Based on Iterative Decomposition(IMLID),which can detect the change of manifold and improve the classification accuracy of the feature set sampling in the real world. Experiments on real-life datasets validate the effectiveness of the proposed method which has important significance and extensive application value in pattern recognition and so on.

参考文献/References:

[1] ARMBRUST M,FOX A,GRIFFITH R,et al. A view of cloud computing[J]. Communications of the ACM,2010,53(4):50-58.
[2] ATZORI L,IERA A,MORABITO G. The Internet of things:a survey[J]. Computer networks,2010,54(15):2 787-2 805.
[3] FUNG P T,LIN C,LI Z Z,et al. DragonNet:a robust mobile internet service system for long-distance trains[J]. IEEE transactions on mobile computing,2013,12(11):2 206-2 218.
[4] HAEWOON K,CHANGHYUN L,et al. What is twitter,a social network or a news media?[C]//Proceedings of the 19th International Conference on World Wide Web,Raleigh,2010:591-600.
[5] LABRINIDIS A,JAGADISH H V. Challenges and opportunities with big data[J]. Proc VLDB Endow,2012,5(12):2 032-2?033.
[6] XUE Q ZENG,GUO Z L. Incremental partial least squares analysis of big streaming data[J]. Pattern recognition,2014,47(11):3 726-3 735.
[7] GULISANO V. Streamcloud:an elastic and scalable data streaming system[J]. IEEE transactions on parallel and distributed systems,2012,23(12):2 351-2 365.
[8] LEI C,RUNDENSTELNER E. Robust distributed query processing for streaming data[J]. ACM transactions on database system,2014,39(2):1-45.
[9] TENENBAUM J B,SILVA D V,LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction[J]. Science,2000,290:2 319-2 323.
[10] ROWEIS S T,SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science,2000,290:2 323-2 326.
[11] BELKIN M,NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation,2003,15(6):1 373-1 396.
[12] DONOHO D L,GRIMES C. Hessian eigenmaps:locally linear embedding techniquesfor high-dimensional data[J]. Proceedings of the national academy of sciences,2003,100:5 591-5 596.
[13] ZHANG Z Y,ZHA H Y. Principal manifolds and nonlinear dimensionality reduction viatangent space alignment[J]. SIAM journal of scienti?c computing,2004,26:313-338.
[14] LIU X M,YIN J W,FENG Z L,et al. Incremental manifold learning via tangent space alignment[C]//Artificial Neural Networks in Pattern Recognition,Ulm,Germany,2006:107-121.
[15] JIA P,YIN J,et al. Incremental Laplacianeigenmaps by preserving adjacent information between data points[J]. Pattern recognition letters,2009,30:1 457-1 463.
[16] KOUROPTEVA O,OKUN O,et al. Incremental locally linear embedding[J]. Pattern recognition,2005,38:1 764-1 767.
[17] ABDEL M O,BEN H A,et al. Incremental Hessian locally linear embedding algorithm[C]//The 9th International Symposium on Signal Processing and Its Applications,Sharjah,United Arab Emirates,2007:1-4.
[18] ABDEL M O,BEN H A,et al. Incremental line tangent space alignment algorithm[C]//Canadian Conference on Electrical and Computer Engineering,Vancouver,BC,2007:1 329-1 332.
[19] LAW M H C,JAIN A K. Incremental nonlinear dimensionality reduction by manifold learning[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2006,28:377-391.
[20] LI Y M,XU L Q,MORPHETT J,et al. An integrated algorithm of incremental and robust PCA[C]//International Conference on Image Processing,Barcelona,2003(1):245-248.
[21] LI Y M. On incremental and robust subspace learning[J]. Pattern recognition,2004,37:1 509-1 518.
[22] TAN C,GUAN J H. A new manifold learning algorithm based on incremental spectral decomposition[C]//Advanced Data Mining and Applications,Nanjing,2012.
[23] NING H Z,XU W,et al. Incremental spectral clustering by efficiently updating the eigen-system[J]. Pattern recognition,2010,43:113-127.
[24] GOLUB G H,VAN L C F. Matrix computations[M]. Baltimore:Johns Hopkins University Press,2012.

备注/Memo

备注/Memo:
收稿日期:2015-09-20. 
基金项目:江苏省高校自然科学基金(15KJB520022)、国家自然科学基金(41471371). 
通讯联系人:谈超,博士,讲师,研究方向:机器学习、模式识别. E-mail:73022@njnu.edu.cn
doi:10.3969/j.issn.1001-4616.2016.01.002
更新日期/Last Update: 2016-03-30