1. Object Orie’d Data Analysis, Last Time Statistical Smoothing –Histograms – Density Estimation –Scatterplot Smoothing – Nonpar. Regression SiZer Analysis –Replaces bandwidth selection –Scale Space –Statistical Inference: Which bumps are “ really there ” ? –Visualization

2. Kernel Density Estimation Choice of bandwidth (window width)? Very important to performance Fundamental Issue: Which modes are “really there”?

3. SiZer Background Fun Scale Spaces Views (Incomes Data) Surface View

4. SiZer Background SiZer analysis of British Incomes data:

5. SiZer Background Finance "tick data": (time, price) of single stock transactions Idea: "on line" version of SiZer for viewing and understanding trends

6. SiZer Background Finance "tick data": (time, price) of single stock transactions Idea: "on line" version of SiZer for viewing and understanding trends Notes: trends depend heavily on scale double points and more background color transition (flop over at top)

7. SiZer Background Internet traffic data analysis: SiZer analysis of time series of packet times at internet hub (UNC) Hannig, Marron, and Riedi (2001)

8. SiZer Background Internet traffic data analysis: SiZer analysis of time series of packet times at internet hub (UNC) across very wide range of scales needs more pixels than screen allows thus do zooming view (zoom in over time) –zoom in to yellow bd ’ ry in next frame –readjust vertical axis

9. SiZer Background Internet traffic data analysis (cont.) Insights from SiZer analysis: Coarse scales: amazing amount of significant structure Evidence of self-similar fractal type process? Fewer significant features at small scales But they exist, so not Poisson process Poisson approximation OK at small scale??? Smooths (top part) stable at large scales?

10. Dependent SiZer Rondonotti, Marron, and Park (2007) SiZer compares data with white noise Inappropriate in time series Dependent SiZer compares data with an assumed model Visual Goodness of Fit test

11. Dep ’ ent SiZer : 2002 Apr 13 Sat 1 pm – 3 pm

12. Zoomed view (to red region, i.e. “ flat top ” )

13. Further Zoom: finds very periodic behavior!

14. Possible Physical Explanation IP “ Port Scan ” Common device of hackers Searching for “ break in points ” Send query to every possible (within UNC domain): –IP address –Port Number Replies can indicate system weaknesses Internet Traffic is hard to model

15. SiZer Overview Would you like to try a SiZer analysis? Matlab software: http://www.unc.edu/depts/statistics/postscript/papers/marron/Matlab6Software/Smoothing/ JAVA version (demo, beta): Follow the SiZer link from the Wagner Associates home page: http://www.wagner.com/www.wagner.com/SiZer/ More details, examples and discussions: http://www.stat.unc.edu/faculty/marron/DataAnalyses/SiZer_Intro.html

16. PCA to find clusters Return to PCA of Mass Flux Data:

17. PCA to find clusters SiZer analysis of Mass Flux, PC1

18. PCA to find clusters SiZer analysis of Mass Flux, PC1 Conclusion: Found 3 significant clusters! Correspond to 3 known “ cloud types ” Worth deeper investigation

19. Recall Yeast Cell Cycle Data “ Gene Expression ” – Micro-array data Data (after major preprocessing): Expression “ level ” of: thousands of genes (d ~ 1,000s) but only dozens of “ cases ” (n ~ 10s) Interesting statistical issue: High Dimension Low Sample Size data (HDLSS)

20. Yeast Cell Cycle Data, FDA View Central question: Which genes are “ periodic ” over 2 cell cycles?

21. Yeast Cell Cycle Data, FDA View Periodic genes? Na ï ve approach: Simple PCA

22. Yeast Cell Cycle Data, FDA View Central question: which genes are “ periodic ” over 2 cell cycles? Na ï ve approach: Simple PCA No apparent (2 cycle) periodic structure? Eigenvalues suggest large amount of “ variation ” PCA finds “ directions of maximal variation ” Often, but not always, same as “ interesting directions ” Here need better approach to study periodicities

23. Yeast Cell Cycles, Freq. 2 Proj. PCA on Freq. 2 Periodic Component Of Data

24. Frequency 2 Analysis

25. Project data onto 2-dim space of sin and cos (freq. 2) Useful view: scatterplot Angle (in polar coordinates) shows phase Colors: Spellman ’ s cell cycle phase classification Black was labeled “ not periodic ” Within class phases approx ’ ly same, but notable differences Now try to improve “ phase classification ”

26. Yeast Cell Cycle Revisit “ phase classification ”, approach: Use outer 200 genes (other numbers tried, less resolution) Study distribution of angles Use SiZer analysis (finds significant bumps, etc., in histogram) Carefully redrew boundaries Check by studying k.d.e. angles

27. SiZer Study of Dist ’ n of Angles

28. Reclassification of Major Genes

29. Compare to Previous Classif ’ n

30. New Subpopulation View

31. OODA in Image Analysis First Generation Problems: Denoising Segmentation (find object boundaries) Registration (align objects) (all about single images)

32. OODA in Image Analysis Second Generation Problems: Populations of Images –Understanding Population Variation –Discrimination (a.k.a. Classification) Complex Data Structures (& Spaces) HDLSS Statistics

33. HDLSS Data in Image Analysis 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 of cases

34. Image Object Representation Major Approaches for Images: Landmark Representations Boundary Representations Medial Representations

35. Landmark Representations Main Idea: On each object find important points Treat point locations as features I.e. represent objects by vectors of point locations (in 2-d or 3-d) (Fits in OODA framework)

36. Landmark Representations Basis of Field of Statistical Shape Analysis: (important precursor of FDA & OODA) Main References: Kendall (1981, 1984) Bookstein (1984) Dryden and Mardia (1998) (most readable and comprehnsive)

37. Landmark Representations Nice Example: Fly Wing Data (Drosophila fruit flies) From George Gilchrist, W. & M. U. http://gwgilc.people.wm.edu/ Graphic Illustrating Landmarks (next page) –Same veins appear in all flies –And always have same relationship –I.e. all landmarks always identifiable

38. Landmark Representations Landmarks for fly wing data:

39. Landmark Representations Important issue for landmark approaches: Location, i. e. Registration Illustration with Fly Wing Data (next slide) Problem: coordinates are “ locations in photo ” & unclear where wing is positioned …

40. Landmark Representations Illustration of Registration, with Fly Wing Data

41. Landmark Representations Standard Approach to Registration Problem: Procrustes Analysis Idea: mod out location Can also mod out rotation Can also mod out size Recommended reference: Dryden and Mardia (1988)

42. Landmark Representations Procustes Results for Fly Wing Data

43. Landmark Representations Effect of Procrustes Analysis: Study Difference Between Continents Flies from Europe & South America Look for important differences Project onto mean difference direction Visualize with movie –Equal time spacing –Through range of data

44. Landmark Representations No Procrustes Adjustment: Movies on Difference Between Continents

45. Landmark Representations Effect of Procrustes Analysis: Movies on Difference Between Continents Raw Data –Driven by location effects –Strongly feels size –Hard to understand shape

46. Landmark Representations Location, Rotation, Scale Procrustes: Movies on Difference Between Continents

47. Landmark Representations Effect of Procrustes Analysis: Movies on Difference Between Continents Raw Data –Driven by location effects –Strongly feels size –Hard to understand shape Full Procrustes –Mods out location, size, rotation –Allows clear focus on shape

48. Landmark Representations Major Drawback of Landmarks: Need to always find each landmark Need same relationship I.e. Landmarks need to correspond Often fails for medical images E.g. How many corresponding landmarks on a set of kidneys, livers or brains???

49. Landmark Representations Landmarks for brains??? (thanks to Liz Bullit) Very hard to identify

50. Landmark Representations Look across people: Some structure in common But “folds” are different Consistent Landmarks???

51. Landmark Representations Look across people: Some structure in common But “folds” are different Consistent Landmarks???

52. Boundary Representations Major sets of ideas: Triangular Meshes –Survey: Owen (1998) Active Shape Models –Cootes, et al (1993) Fourier Boundary Representations –Keleman, et al (1997 & 1999)

53. Boundary Representations Example of triangular mesh rep’n: From:www.geometry.caltech.edu/pubs.htmlwww.geometry.caltech.edu/pubs.html

54. Boundary Representations Example of triangular mesh rep’n for a brain: From : meshlab.sourceforge.net/SnapMeshLab.brain.jpgmeshlab.sourceforge.net/SnapMeshLab.brain.jpg

55. Boundary Representations Main Drawback: Correspondence For OODA (on vectors of parameters): Need to “match up points” Easy to find triangular mesh –Lots of research on this driven by gamers Challenge match mesh across objects –There are some interesting ideas…

56. Medial Representations Main Idea: Represent Objects as: Discretized skeletons (medial atoms) Plus spokes from center to edge Which imply a boundary Very accessible early reference: Yushkevich, et al (2001)

57. Medial Representations 2-d M-Rep Example: Corpus Callosum (Yushkevich)

58. Medial Representations 2-d M-Rep Example: Corpus Callosum (Yushkevich) Atoms Spokes Implied Boundary

59. Medial Representations 3-d M-Rep Example: From Ja-Yeon Jeong Bladder – Prostate - Rectum Atoms - Spokes - Implied Boundary

60. Medial Representations 3-d M-reps: there are several variations Two choices: From Fletcher (2004)

61. Medial Representations Statistical Challenge M-rep parameters are: –Locations –Radii –Angles (not comparable) Stuffed into a long vector I.e. many direct products of these

62. Medial Representations Statistical Challenge: How to analyze angles as data? E.g. what is the average of: – ??? (average of the numbers) – (of course!) Correct View of angular data: Consider as points on the unit circle

63. Medial Representations What is the average (181 o ?) or (1 o ?) of:

64. Medial Representations Statistical Analysis of Directional Data: Common Examples: –Wind Directions (0-360) –Magnetic Fields (0-360) –Cracks (0-180) There is a literature (monographs): –Mardia (1972, 2000) –Fisher, et al (1987, 1993)

65. Medial Representations Statistical Challenge Many direct products of: –Locations –Radii –Angles (not comparable) Appropriate View: Data Lie on Curved Manifold Embedded in higher dim ’ al Eucl ’ n Space

66. Medial Representations Data on Curved Manifold Toy Example:

67. Medial Representations Data on Curved Manifold Viewpoint: Very Simple Toy Example (last movie) Data on a Cylinder = Notes: –Simplest non-Euclidean Example –2-d data, embedded on manifold in –Can flatten the cylinder, to a plane –Have periodic representation –Movie by: Suman Sen Same idea for more complex direct prod ’ s