TITLE

INTRINSIC DIMENSIONALITY ESTIMATION WITHIN NEIGHBORHOOD CONVEX HULL

AUTHOR(S)
LI, CHUN-GUANG; GUO, JUN; XIAO, BO
PUB. DATE
February 2009
SOURCE
International Journal of Pattern Recognition & Artificial Intell;Feb2009, Vol. 23 Issue 1, p31
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
In this paper, a novel method to estimate the intrinsic dimensionality of high-dimensional data set is proposed. Based on neighborhood information, our method calculates the non-negative locally linear reconstruction coefficients from its neighbors for each data point, and the numbers of those dominant positive reconstruction coefficients are regarded as a faithful guide to the intrinsic dimensionality of data set. The proposed method requires no parametric assumption on data distribution and is easy to implement in the general framework of manifold learning. Experimental results on several synthesized data sets and real data sets have shown the benefits of the proposed method.
ACCESSION #
37045985

 

Related Articles

  • Learn and Earn Through Testing on the Internet. Wyner, Gordon A. // Marketing Research;Fall2000, Vol. 12 Issue 3, p37 

    This article focuses on the opportunities provided by the Internet for market experimentation and optimization. Increasing digitization--the importance of information content over physical matter in business--will make it progressively easier to experimentally alter particular aspects of a...

  • Sliced space-filling designs. Qian, Peter Z. G.; Wu, C. F. Jeff // Biometrika;Dec2009, Vol. 96 Issue 4, p945 

    We propose an approach to constructing a new type of design, a sliced space-filling design, intended for computer experiments with qualitative and quantitative factors. The approach starts with constructing a Latin hypercube design based on a special orthogonal array for the quantitative factors...

  • Constructing Meta-Models for Computer Experiments. Allen, Theodore T.; Bernshteyn, Mikhail A.; Kabiri-Bamoradian, Khalil // Journal of Quality Technology;Jul2003, Vol. 35 Issue 3, p264 

    Provides comparisons of the accuracy of meta-models derived from computer experiments. Use of alternative approaches to experimentation and analysis; Interaction between relative meta-model accuracy and the choice of experimental design; Design of a plastic seal for an automotive application.

  • Response Surface Optimization of the Critical Medium Components for Pullulan Production by Aureobasidium pullulans FB-1. Ram Singh; Harpreet Singh; Gaganpreet Saini // Applied Biochemistry & Biotechnology;Jan2009, Vol. 152 Issue 1, p42 

    Abstract  Culture conditions for pullulan production by Aureobasidium pullulans were optimized using response surface methodology at shake flask level without pH control. In the present investigation, a five-level with five-factor central composite rotatable design of experiments was...

  • Editorial: Statistical experimental design: some recent advances and applications. Borror, Connie M.; Montgomery, Douglas C.; Runger, George C. // Quality & Reliability Engineering International;Sep2000, Vol. 16 Issue 5, p341 

    Discusses the eras in the modern development of statistical experimental design. Individuals who led each era; Outcomes of the debate on the engineering concepts and designs of Genichi Taguchi; Strategies for follow-up experiments to resolve ambiguities resulting from aliasing of effects.

  • A Framework for Initial Experimental Design in the Presence of Competing Prior Knowledge. VASTÓLA, JUSTIN T.; JYE-CHYI LU; CASCIATO, MICHAEL J.; HESS, DENNIS W.; GROVER, MARTHA A. // Journal of Quality Technology;Oct2013, Vol. 45 Issue 4, p301 

    An initial experimental design criteria is proposed for optimization problems by combining multiple, potentially competing, sources of prior information--engineering models, expert opinion, and data from past experimentation on similar, nonidentical systems. By leveraging prior information,...

  • Regular A-optimal design matrices X = (xij) with xij = -1, 0, 1. Graczyk, Malgorzata // Statistical Papers;Aug2009, Vol. 50 Issue 4, p789 

    New construction methods of the regular A-optimal design matrices with elements -- 1, 0, 1 are presented, under assumption of nonhomogeneity of variance error. The presented constructions are based on the incidence matrices of the balanced bipartite weighing designs.

  • Experimental Design or Happiness Is Planning the Experiment. Gibson, R. J. // BioScience;Mar1968, Vol. 18 Issue 3, p223 

    The article discusses the advantages of using the technique of experimental design when conducting experiments. The author specifically explains the benefits of this technique on the one doing the experiment. This technique gives experimenters a design that is both minimum in effort and maximum...

  • TWO-STAGE GROUP SEQUENTIAL DESIGNS FOR COMPARATIVE CLINICAL TRIALS. Bacanhı, Sevil; Peker, Özgür K.; Demirhan, Yaprak Parlak // Mathematical & Computational Applications;Apr2008, Vol. 13 Issue 1, p31 

    Group sequential designs are widely used in Phase II clinical trials, which are usually undertaken to evaluate the response probability of specific treatment regimen. In most randomized clinical trials with sequential patient entry, fixed sample size design is unjustified on ethical grounds and...

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics