1 UNC, Stat & OR Hailuoto Workshop Object Oriented Data Analysis, I J. S. Marron Dept. of Statistics and Operations Research, University of North Carolina.

Slides:



Advertisements
Similar presentations
STOR 892 Object Oriented Data Analysis Radial Distance Weighted Discrimination Jie Xiong Advised by Prof. J.S. Marron Department of Statistics and Operations.
Advertisements

Component Analysis (Review)
Independent Component Analysis Personal Viewpoint: Directions that maximize independence Motivating Context: Signal Processing “Blind Source Separation”
1/20 Using M-Reps to include a-priori Shape Knowledge into the Mumford-Shah Segmentation Functional FWF - Forschungsschwerpunkt S092 Subproject 7 „Pattern.
These improvements are in the context of automatic segmentations which are among the best found in the literature, exceeding agreement between experts.
Object Orie’d Data Analysis, Last Time Finished NCI 60 Data Started detailed look at PCA Reviewed linear algebra Today: More linear algebra Multivariate.
The UNIVERSITY of Kansas EECS 800 Research Seminar Mining Biological Data Instructor: Luke Huan Fall, 2006.
Caudate Shape Discrimination in Schizophrenia Using Template-free Non-parametric Tests Y. Sampath K. Vetsa 1, Martin Styner 1, Stephen M. Pizer 1, Jeffrey.
Towards a Multiscale Figural Geometry Stephen Pizer Andrew Thall, Paul Yushkevich Medical Image Display & Analysis Group.
Statistics – O. R. 892 Object Oriented Data Analysis J. S. Marron Dept. of Statistics and Operations Research University of North Carolina.
Probability of Error Feature vectors typically have dimensions greater than 50. Classification accuracy depends upon the dimensionality and the amount.
Statistics – O. R. 892 Object Oriented Data Analysis J. S. Marron Dept. of Statistics and Operations Research University of North Carolina.
Object Orie’d Data Analysis, Last Time OODA in Image Analysis –Landmarks, Boundary Rep ’ ns, Medial Rep ’ ns Mildly Non-Euclidean Spaces –M-rep data on.
Object Orie’d Data Analysis, Last Time
Analyzing Configurations of Objects in Images via
Object Orie’d Data Analysis, Last Time Distance Weighted Discrimination: Revisit microarray data Face Data Outcomes Data Simulation Comparison.
Object Orie’d Data Analysis, Last Time Statistical Smoothing –Histograms – Density Estimation –Scatterplot Smoothing – Nonpar. Regression SiZer Analysis.
Return to Big Picture Main statistical goals of OODA: Understanding population structure –Low dim ’ al Projections, PCA … Classification (i. e. Discrimination)
1 UNC, Stat & OR Nonnegative Matrix Factorization.
A Challenging Example Male Pelvis –Bladder – Prostate – Rectum.
Statistics – O. R. 891 Object Oriented Data Analysis J. S. Marron Dept. of Statistics and Operations Research University of North Carolina.
Statistics – O. R. 891 Object Oriented Data Analysis J. S. Marron Dept. of Statistics and Operations Research University of North Carolina.
Robust PCA Robust PCA 3: Spherical PCA. Robust PCA.
Object Orie’d Data Analysis, Last Time Discrimination for manifold data (Sen) –Simple Tangent plane SVM –Iterated TANgent plane SVM –Manifold SVM Interesting.
Object Orie’d Data Analysis, Last Time Classification / Discrimination Classical Statistical Viewpoint –FLD “good” –GLR “better” –Conclude always do GLR.
1 UNC, Stat & OR Hailuoto Workshop Object Oriented Data Analysis, II J. S. Marron Dept. of Statistics and Operations Research, University of North Carolina.
ECE 8443 – Pattern Recognition LECTURE 08: DIMENSIONALITY, PRINCIPAL COMPONENTS ANALYSIS Objectives: Data Considerations Computational Complexity Overfitting.
Object Orie’d Data Analysis, Last Time
Object Orie’d Data Analysis, Last Time SiZer Analysis –Zooming version, -- Dependent version –Mass flux data, -- Cell cycle data Image Analysis –1 st Generation.
Maximal Data Piling Visual similarity of & ? Can show (Ahn & Marron 2009), for d < n: I.e. directions are the same! How can this be? Note lengths are different.
Common Property of Shape Data Objects: Natural Feature Space is Curved I.e. a Manifold (from Differential Geometry) Shapes As Data Objects.
1 UNC, Stat & OR PCA Extensions for Data on Manifolds Fletcher (Principal Geodesic Anal.) Best fit of geodesic to data Constrained to go through geodesic.
Return to Big Picture Main statistical goals of OODA: Understanding population structure –Low dim ’ al Projections, PCA … Classification (i. e. Discrimination)
Object Orie’d Data Analysis, Last Time SiZer Analysis –Statistical Inference for Histograms & S.P.s Yeast Cell Cycle Data OODA in Image Analysis –Landmarks,
1 UNC, Stat & OR ??? Place ??? Object Oriented Data Analysis J. S. Marron Dept. of Statistics and Operations Research, University of North Carolina January.
Statistics – O. R. 893 Object Oriented Data Analysis Steve Marron Dept. of Statistics and Operations Research University of North Carolina.
Statistics – O. R. 893 Object Oriented Data Analysis Steve Marron Dept. of Statistics and Operations Research University of North Carolina.
Statistical Shape Analysis of Multi-object Complexes June 2007, CVPR 2007 Funding provided by NIH NIBIB grant P01EB and NIH Conte Center MH
1 UNC, Stat & OR U. C. Davis, F. R. G. Workshop Object Oriented Data Analysis J. S. Marron Dept. of Statistics and Operations Research, University of North.
Object Orie’d Data Analysis, Last Time PCA Redistribution of Energy - ANOVA PCA Data Representation PCA Simulation Alternate PCA Computation Primal – Dual.
Object Orie’d Data Analysis, Last Time PCA Redistribution of Energy - ANOVA PCA Data Representation PCA Simulation Alternate PCA Computation Primal – Dual.
GWAS Data Analysis. L1 PCA Challenge: L1 Projections Hard to Interpret (i.e. Little Data Insight) Solution: 1)Compute PC Directions Using L1 2)Compute.
1 UNC, Stat & OR Hailuoto Workshop Object Oriented Data Analysis, III J. S. Marron Dept. of Statistics and Operations Research, University of North Carolina.
Participant Presentations Draft Schedule Now on Course Web Page: When You Present: Please Load Talk on Classroom.
Return to Big Picture Main statistical goals of OODA: Understanding population structure –Low dim ’ al Projections, PCA … Classification (i. e. Discrimination)
PCA Data Represent ’ n (Cont.). PCA Simulation Idea: given Mean Vector Eigenvectors Eigenvalues Simulate data from Corresponding Normal Distribution.
Anatomic Geometry & Deformations and Their Population Statistics (Or Making Big Problems Small) Stephen M. Pizer, Kenan Professor Medical Image.
Kernel Embedding Polynomial Embedding, Toy Example 3: Donut FLD Good Performance (Slice of Paraboloid)
Cornea Data Main Point: OODA Beyond FDA Recall Interplay: Object Space  Descriptor Space.
Distance Weighted Discrim ’ n Based on Optimization Problem: For “Residuals”:
SigClust Statistical Significance of Clusters in HDLSS Data When is a cluster “really there”? Liu et al (2007), Huang et al (2014)
1 UNC, Stat & OR Place Name OODA of Tree Structured Objects J. S. Marron Dept. of Statistics and Operations Research October 2, 2016.
Landmark Based Shapes As Data Objects
Return to Big Picture Main statistical goals of OODA:
Object Orie’d Data Analysis, Last Time
University of Ioannina
LECTURE 10: DISCRIMINANT ANALYSIS
CH 5: Multivariate Methods
Statistics – O. R. 881 Object Oriented Data Analysis
Statistics – O. R. 881 Object Oriented Data Analysis
Maximal Data Piling MDP in Increasing Dimensions:
Landmark Based Shape Analysis
Principal Nested Spheres Analysis
Today is Last Class Meeting
Object Modeling with Layers
“good visual impression”
Principal Components Analysis
LECTURE 09: DISCRIMINANT ANALYSIS
I  Linear and Logical Pulse II  Instruments Standard Ch 17 GK I  Linear and Logical Pulse II  Instruments Standard III  Application.
Statistics – O. R. 891 Object Oriented Data Analysis
Presentation transcript:

1 UNC, Stat & OR Hailuoto Workshop Object Oriented Data Analysis, I J. S. Marron Dept. of Statistics and Operations Research, University of North Carolina March 6, 2016

2 UNC, Stat & OR Object Oriented Data Analysis, I What is the “atom” of a statistical analysis? 1 st Course: Numbers Multivariate Analysis Course : Vectors Functional Data Analysis: Curves More generally: Data Objects

3 UNC, Stat & OR Functional Data Analysis, I Curves as Data Objects Important Duality: Curve Space  Point Cloud Space Illustrate with Travis Gaydos Graphics 2 dim’al curves (easy to visualize)

4 UNC, Stat & OR Functional Data Analysis, Toy EG I

5 UNC, Stat & OR Functional Data Analysis, Toy EG II

6 UNC, Stat & OR Functional Data Analysis, Toy EG III

7 UNC, Stat & OR Functional Data Analysis, Toy EG IV

8 UNC, Stat & OR Functional Data Analysis, Toy EG V

9 UNC, Stat & OR Functional Data Analysis, Toy EG VI

10 UNC, Stat & OR Functional Data Analysis, Toy EG VII

11 UNC, Stat & OR Functional Data Analysis, Toy EG VIII

12 UNC, Stat & OR Functional Data Analysis, Toy EG VIII

13 UNC, Stat & OR Functional Data Analysis, Toy EG IX

14 UNC, Stat & OR Functional Data Analysis, Toy EG X

15 UNC, Stat & OR Functional Data Analysis, 10-d Toy EG 1

16 UNC, Stat & OR Functional Data Analysis, 10-d Toy EG 1

17 UNC, Stat & OR Functional Data Analysis, 10-d Toy EG 2

18 UNC, Stat & OR Functional Data Analysis, 10-d Toy EG 2

19 UNC, Stat & OR Object Oriented Data Analysis, I What is the “atom” of a statistical analysis? 1 st Course: Numbers Multivariate Analysis Course : Vectors Functional Data Analysis: Curves More generally: Data Objects

20 UNC, Stat & OR Object Oriented Data Analysis, II Examples: Medical Image Analysis Images as Data Objects? Shape Representations as Objects Micro-arrays Just multivariate analysis?

21 UNC, Stat & OR Object Oriented Data Analysis, III Typical Goals: Understanding population variation Principal Component Analysis + Discrimination (a.k.a. Classification) Time Series of Data Objects

22 UNC, Stat & OR Object Oriented Data Analysis, IV Major Statistical Challenge, I: High Dimension Low Sample Size (HDLSS) Dimension d >> sample size n “Multivariate Analysis” nearly useless Can’t “normalize the data” Land of Opportunity for Statisticians Need for “creative statisticians”

23 UNC, Stat & OR Object Oriented Data Analysis, V Major Statistical Challenge, II: Data may live in non-Euclidean space Lie Group / Symmetric Spaces Trees/Graphs as data objects Interesting Issues: What is “the mean” (pop’n center)? How do we quantify “pop’n variation”?

24 UNC, Stat & OR Statistics in Image Analysis, I First Generation Problems: Denoising Segmentation Registration (all about single images)

25 UNC, Stat & OR Statistics in Image Analysis, II Second Generation Problems: Populations of Images Understanding Population Variation Discrimination (a.k.a. Classification) Complex Data Structures (& Spaces) HDLSS Statistics

26 UNC, Stat & OR HDLSS Statistics in Imaging Why HDLSS (High Dim, Low Sample Size)? Complex 3-d Objects Hard to Represent Often need d = 100’s of parameters Complex 3-d Objects Costly to Segment Often have n = 10’s cases

27 UNC, Stat & OR Object Representation Landmarks (hard to find) Boundary Rep’ns (no correspondence) Medial representations Find “skeleton” Discretize as “atoms” called M-reps

28 UNC, Stat & OR 3-d m-reps Bladder – Prostate – Rectum (multiple objects, J. Y. Jeong) Medial Atoms provide “skeleton” Implied Boundary from “spokes”  “surface”

29 UNC, Stat & OR Personal HDLSS Viewpoint: Data Images (cases) are “Points” In Feature Space Features are Axes Data set is “Point Clouds” Use Proj’ns to visualize

30 UNC, Stat & OR Personal HDLSS Viewpoint: PCA Rotated Axes Often Insightful One set of Dir’ns Others Useful, too

31 UNC, Stat & OR Cornea Data, I Images as data ~42 Cornea Images Outer surface of eye Heat map of curvature (in radial direction) Hard to understand “population structure”

32 UNC, Stat & OR Cornea Data, II PC 1 Starts at Pop’n Mean Overall Curvature Vertical Astigmatism Correlated! Gaussian Projections Visualization: Can’t Overlay (so use movie)

33 UNC, Stat & OR Cornea Data, III PC 2 Horrible Outlier! (present in data) But look only in center: Steep at top -- bottom Want Robust PCA For HDLSS data ???

34 UNC, Stat & OR Cornea Data, IV Robust PC 2 No outlier impact See top – bottom variation Projections now Gaussian

35 UNC, Stat & OR PCA for m-reps, I Major issue: m-reps live in (locations, radius and angles) E.g. “average” of: = ??? Natural Data Structure is: Lie Groups ~ Symmetric spaces (smooth, curved manifolds)

36 UNC, Stat & OR PCA for m-reps, II PCA on non-Euclidean spaces? (i.e. on Lie Groups / Symmetric Spaces) T. Fletcher: Principal Geodesic Analysis Idea: replace “linear summary of data” With “geodesic summary of data”…

37 UNC, Stat & OR PGA for m-reps, Bladder-Prostate-Rectum Bladder – Prostate – Rectum, 1 person, 17 days PG 1 PG 2 PG 3 (analysis by Ja Yeon Jeong)

38 UNC, Stat & OR PGA for m-reps, Bladder-Prostate-Rectum Bladder – Prostate – Rectum, 1 person, 17 days PG 1 PG 2 PG 3 (analysis by Ja Yeon Jeong)

39 UNC, Stat & OR PGA for m-reps, Bladder-Prostate-Rectum Bladder – Prostate – Rectum, 1 person, 17 days PG 1 PG 2 PG 3 (analysis by Ja Yeon Jeong)