Lesson 10: Discriminant Analysis
also: http://arxiv.org/pdf/1412.0265.pdf
5 Discriminant Analysis on Manifolds The kernelized version of linear discriminant analysis, known as Kernel Fisher Discriminant Analysis
Printer-friendly versionIntroduction
Discriminant analysis is a classification problem, where two or more groups or clusters or populations are known a priori and one or more new observations are classified into one of the known populations based on the measured characteristics. Let us look at three different examples.
Example 1 - Swiss Bank Notes:
We have two populations of bank notes, genuine, and counterfeit. Six measures are taken on each note:
- Length
- Right-Hand Width
- Left-Hand Width
- Top Margin
- Bottom Margin
- Diagonal across the printed area
Take a bank note of unknown origin and determine just from these six measurements whether or not it is real or counterfeit. Perhaps this is not as impractical as it might sound. A more modern equivalent is a scanner that would measure the notes automatically and makes a decision.
Example 2 - Pottery Data:
Pottery shards are sampled from four sites: L) Llanedyrn, C) Caldicot, I) Ilse Thornes, and A) Ashley Rails and the concentrations of the following chemical constituents were measured at a laboratory
- Al: Aluminum
- Fe: Iron
- Mg: Magnesium
- Ca: Calcium
- Na: Sodium
An archaeologist encounters a pottery specimen of unknown origin. To determine possible trade routes, the archaeologist may wish to classify its site of origin.
Example 3 - Insect Data:
Data were collected on two species of insects in the genus Chaetocnema, (a) Ch. concinna and (b) Ch. heikertlingeri. Three variables were measured on each insect:
- width of the 1st joint of the tarsus (legs)
- width of the 2nd joint of the tarsus
- width of the aedeagus (sex organ)
Our objective is to obtain a classification rule for identifying the insect species based on these three variables. An entomologist can identify these two closely related species, but the differences are so subtle that one has to have considerable experience to be able to tell the difference. If a classification rule may be developed, then this might be a more accurate way to help differentiate between these two different species.
Learning objectives & outcomes
Upon completion of this lesson, you should be able to do the following:
- Determine whether linear of quadratic discriminant analysis should be applied to a given data set;
- Be able to carry out both types of discriminant analyses using SAS/Minitab;
- Be able to apply the linear discriminant function to classify a subject by its measurements;
- Understand how to assess the efficacy of a discriminant analysis.
Kernel Methods on Riemannian Manifolds with ... - arXiv
arxiv.org/pdf/1412.0265
arXiv
by S Jayasumana - 2014 - Cited by 8 - Related articles
Mar 17, 2015 - support vector machines, discriminant analysis and principal component analysis can be generalized to ... powerful kernel methods to manifold-valued data. To ... gous to the linear kernel in Euclidean spaces, our kernels.Statistical Analysis of Manifold-Valued Data
manifoldstats.blogspot.com/
Jun 23, 2014 - Statistical Analysis of Manifold-Valued Data ... In the talk I show howlinear discriminant analysis reveals that there are substantive differences ...Riemannian Computing in Computer Vision
https://books.google.com/books?isbn=3319229575
Pavan K. Turaga, Anuj Srivastava - 2015 - Technology & Engineering
In a manifold setting, a given data set fxigmiD1, with each xi 2 M, is clustered into a ... Analysis on Manifolds The kernelized version of linear discriminant analysis, ... algorithm is a Euclidean representation of the original manifold-valued data, ...[PDF]Manifold Discriminant Analysis - VIPL
vipl.ict.ac.cn/.../19_Manifold%20Discriminant%20Analysis_CVPR2009....
by R Wang - Cited by 148 - Related articles
For classification tasks, Linear Discriminant Analysis. (LDA) has proved its ... learning discriminant function from training data with a given similarity function .... be produced whenever δ is specified to any value less than. 1. From Table 1, one[PDF]Combining Multiple Manifold-valued Descriptors for ...
www.robots.ox.ac.uk/.../dicta2013_multi_manifold...
University of Oxford
by S Jayasumana - Cited by 6 - Related articles
developed for Euclidean spaces assuming linear (vector space) structure of the data. ... representation of the manifold-valued data by approximating the manifold by ..... kernel Fisher discriminant analysis based classifier [32]. This could be an ...Kernel Methods on Riemannian Manifolds with Gaussian ...
www.ncbi.nlm.nih.gov/.../2...
National Center for Biotechnology Information
by S Jayasumana - 2015 - Cited by 8 - Related articles
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels. ... In this paper, we develop an approach to exploiting kernel methods with manifold-2.2. Manifold learning — scikit-learn 0.17.1 documentation
scikit-learn.org/stable/modules/manifold.html
Manifold learning is an approach to non-linear dimensionality reduction. ... Component Analysis (PCA), Independent Component Analysis, Linear Discriminant Analysis, and others. ... Locally linear embedding (LLE) seeks a lower-dimensional projection of thedata which preserves .... With absolute MDS, the value S_{ij} ...
scikit‑learn
[PDF]Projection Metric Learning on Grassmann Manifold With ...
www.cv-foundation.org/.../Huang_Projection_Metric_Learning_2015_C...
by Z Huang - 2015 - Cited by 8 - Related articles
linear subspaces with the same dimensionality reside on a special type of Riemannian ... ing discriminant analysis on the Grassmann manifold for video based face ...manifold-valued data and thus further improve them. 2. Related work.[PDF]Visualization of Riemannian-Manifold-Valued Elements by ...
https://pdfs.semanticscholar.org/.../fcbb40aceab44e5f79bae411da88cc44...
by S Fiori - Cited by 7 - Related articles
Feb 13, 2012 - high-dimensional manifold-valued data visualization. Section 4 ..... component analysis, factor analysis and linear discriminant analysis. Non-.[PDF]Learning from Manifold-Valued Data: An Application to ...
ecee.colorado.edu/~fmeyer/pub/juan-ramirez-ms.pdf
by J Ramirez Jr - 2012 - Related articles
Learning from Manifold-Valued Data: An Application to Seismic Signal Processing ..... Over the past 60 years, the analysis of seismic signals has led to a deeper .... it possible to discriminate between different seismic wave types because ..... Indeed, wavelet filters that are orthogonal, and subsequently have linear-phase,.
No comments:
Post a Comment