1. Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology A modified version of the K-means algorithm with a distance based on cluster symmetry Advisor ： Dr. Hsu Reporter ： Chun Kai Chen Author ： Mu-Chun Su and Chien-Hsing Chou IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2001

2. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Outline Motivation Objective Introduction The Point Symmetry Distance Experimental Results Conclusions Personal Opinion

3. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Motivation  Since clusters can be of arbitrary shapes and sizes, the Minkowski metrics seem not a good choice for situations where no a priori information about the geometric characteristics of the data set to be clustered exists

4. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Objective  Therefore, we have to find another more flexible measure ─ One of the basic features of shapes and objects is symmetry  Propose a nonmetric measure based on the concept of point symmetry

5. Intelligent Database Systems Lab N.Y.U.S.T. I. M. K-means Partitional Clustering 0 1 2 3 4 5 6 7 8 9 10 0123456789 Update the cluster means reassign

6. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Symmetry-based version of the K-means algorithm 0 1 2 3 4 5 6 7 8 9 10 0123456789 Update the cluster means reassign Update the cluster means Fine- Tuning reassign Coarse-Tuning

7. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Introduction(1/4)  Most of the conventional clustering methods assume that patterns having similar locations or constant density create a single cluster ─ Location or density becomes a characteristic property of a cluster

8. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Introduction(2/4)  Mathematically identify clusters in a data set ─ usually necessary to first define a measure of similarity or proximity which will establish a rule for assigning patterns to the domain of a particular cluster center ─ the most popular similarity measure the Euclidean distance

9. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Introduction(3/4)  Euclidean distance as a measure of similarity ─ hyperspherical-shaped clusters of equal size are usually detected  Mahalanobis distance ─ take care of hyperellipsoidal-shaped clusters, is one of the popular choices

10. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Introduction(4/4)  The major difficulties using the Mahalanobis distance ─ have to recompute the inverse of the sample covariance matrix every time a pattern changes its cluster domain, which is computationally expensive ─ In fact, not only similarity measures, but also the number of clusters which cannot always be defined a priori will influence the clustering results  In this paper ─ we focus on the selection of similarity measures

11. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Symmetry  Symmetry is so common in the abstract and in nature ─ reasonable to assume some kinds of symmetry exit in the structures of clusters ─ immediate problem is how to find a metric to measure symmetry

12. Intelligent Database Systems Lab N.Y.U.S.T. I. M. The Point Symmetry Distance  The point symmetry distance is defined as follows: Given N patterns, x i ; i=1,…,N, and a reference vector c (e.g., a cluster centroid) ─ the denominator term is used to normalize ─ If the right hand term of (2) is minimized when x i = x j*, then the pattern x j* is denoted as the symmetrical pattern relative to x j with respect to c

13. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Example of The Point Symmetry Distance

14. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Symmetry-based version of the K-means algorithm(1/3)  Step 1: Initialization ─ randomly choose K data points from the data set to initialize K cluster centroids, c1, c2... ; c K.  Step 2: Coarse-Tuning ─ use the ordinary K-means algorithm with the Euclidean distance to update the K cluster centroids ─ after the K cluster centroids converge or some kind of terminating criteria is satisfied

15. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Symmetry-based version of the K-means algorithm(2/3)  Step 3: Fine-Tuning ─ For pattern x, find the cluster centroid nearest it in the symmetrical sense ─ If the point symmetry distance is smaller than a prespecified parameter θ, then assign the data point x to the k*th cluster ds(x,c k ) is the point symmetry distance ─ Otherwise, the data point is assigned to the cluster centroid k using the following criterion: d(x,c k ) is the Euclidean distance

16. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Symmetry-based version of the K-means algorithm(3/3)  Step 4: Updating ─ Compute the new centroids of the K clusters ─ where S k (t) is the set whose elements are the patterns assigned to the kth cluster at time t and N k is the number of elements in S k.  Step 5: Continuation ─ If no patterns change categories or the number of iterations has reached a prespecified maximum number, then stop. Otherwise, go to Step 3.

17. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Experimental Results  Used four examples to compare the SBKM algorithm and the SBCL algorithm  In addition, we use one example to show how to use the point symmetry distance in face detections

18. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Mixture of Spherical and Ellipsoidal clusters ordinary K-means SBKM SBCL

19. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Ring-shaped clusters SBKM SBCL ordinary K-means

20. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Linear structures SBKM SBCL ordinary K-means

21. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Combination of ring-shaped, compact, and linear clusters ordinary K-means SBKM SBCL

22. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Detecting a face in a complex background

23. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Conclusion  Both use the point symmetry distance as the dissimilarity measure, the SBKM algorithm outperformed the SBCL algorithm in many cases  The proposed SBKM algorithm can be used to group a given data set into a set of clusters of different geometrical structures  Besides, we can also apply the point symmetry distance to detect human faces. The experimental results are encouraging

24. Intelligent Database Systems Lab N.Y.U.S.T. I. M. Personal Opinion Advantage Idea, innovate Application clustering Future Work Adopt symmetry distance on SOM