Friday, November 14, 2008

Cluster analysis Question

1. What is cluster analysis? What are the typical applications of cluster analysis? 2 to 8
2. What are the requirements of clustering in data mining? 9 to 13
3. What are the types of data that occur in cluster analysis and the way to
process them for analysis purposes?
4. Explain about interval‐scaled variables in cluster analysis. 18 to 23
5. Explain about binary variables in cluster analysis. 24 to 30
6. Explain about nominal, ordinal, and ratio‐scaled variables in cluster analysis. 31 to 38
7. Explain about mixed‐type variables in cluster analysis. 39 to 41
8. Briefly introduce the major clustering methods 42 to 51
9. Explain the centroid‐based k‐means method 52 to 59
10. Explain the variations of centroid‐based k‐means method 60 to 68
11. Explain about CLARA, a sampling‐based method 69 to 73
12. Write a short note on hierarchical clustering 74
13. Explain agglomerative and divisive hierarchical clustering 75 to 81
14. Explain the BIRCH method of hierarchical clustering 82 to 88
15. Explain about CURE – clustering 89 to 93
16. Explain about ROCK , a hierarchical clustering algorithm 94
17. Explain the dynamic modeling of clustering technique – chameleon 95 to 100
18. Explain about DBSCAN, a density based clustering method 101 to 109
19. Explain about the cluster analysis method – OPTICS 110 to 114
20. Explain about the density based clustering method – DENCLUE 115 to 120
21. Explain about STING, the grid‐based multiresolution clustering technique 121 to 127
22. Write about WaveCluster, a multiresolution clustering algorithm 128 to 130
23. Explain the CLIQUE (CLusering In QUEst) clustering algorithm that integrates
density‐based and grid‐based clustering
24. Explain different model‐bases statistical clustering methods 136 to 148
25. Explain different neural networks‐based clustering methods 149 to 152
26. Write a short note on outlier analysis including the causes of outliers and the
applications of outlier analysis
27. Explain how outliers are detected using the discordancy‐test and its variations 158
28. Write the outlines of algorithms for mining distance‐based outliers and
explain them
29. What is meant by deviation‐based outlier detection and explain the two
techniques of deviation‐based outlier techniques

No comments: