CS9264 DATA WAREHOUSING AND DATA MINING Question Paper

M.E./M.Tech. DEGREE EXAMINATION, MAY/JUNE 2012

Elective

Computer Science Engineering

CS 9264/241083/8241083/CS 964/10244 CSE 51—DATA WAREHOUSING AND

DATA MINING)

(Common to M.E. Software Engineering and M.Tech. Information Technology)

(Regulation 2009)

Time: Three hours Maximum: 100 marks

Answer ALL the Questions

PART A—(10 × 2 = 20 marks)

1. How can the data warehouse data can be accessed efficiently?
2. What is the use of back end process in data warehouse design?
3. Give two examples for Multi-level Association rule.
4. Write the difference between Boolean association rule and quantitative association rule.
5. How do you evaluate accuracy of a classifier?
6. How do you overcome the problem of over-fitting the data?
7. What is dissimilarity matrix?
8. Write the special feature of model-based clustering.
9. Write the difference between time-series databases and sequence databases.
10. How does latent semantic indexing reduce the size of the term “time frequency matrix”?

PART B—(5 × 16 = 80 marks)

11. (a) (i) With a neat sketch explain the architecture of data warehousing. (10)
(ii) Explain the types of OLAP server. (6)

Or

(b) (i) Explain the data model which is suitable for data warehouse with examples. (6)
(ii) Discuss the typical OLAP operation with an example. (10)

12. (a) (i) Suppose that the data for analysis include the attribute age. The age values
for the data tuples are 13, 15, 16, 19, 20, 21, 22, 22, 25, 25, 25, 30, 33, 33, 35, 35, 35, 36,
40, 45, 46 52, 70 (7+5+4)
(1) Use smoothing by bin means to smooth the above data, using a bin depth of 3. Illustrate
your steps.
(2) How will you determine outliers in the data.
(3) What other methods are there for data smoothing?

Or

(b) Discuss about constraint-based association rule mining with examples.

13. (a) Explain the Backpropagation algorithm for classification using an example.

Or

(b) (i) Briefly outline the major steps of decision tree classification. (8)
(ii) What are the advantages and disadvantages of decision tree over the classification
technique? (8)

14. (a) (i) Discuss the different types of clustering methods. (8)
(ii) Describe the working of PAM (Partitioning Around Medoids) algorithm. (8)

Or

(b) Describe the working of DBSCAN algorithm and Explain the concept of clusters used in
DBSCAN.

15. (a) What is spatial database? Explain the methods of mining spatial databases?

Or

(b) (i) Discuss the social impacts of data mining. (8)
(ii) Discuss the method of mining text databases in detail. (8)