Anna University of Technology Tirunelveli 2011 B.Tech Information Technology B.e/ s, /e- -university question paper

B.E/B.TECH DEGREE exams MAY/JUNE-2011
REGULATIONS 2008
SIXTH SEMESTER
CS 701- DATA WAREHOUSING AND DATA MINING
info TECHNOLOGY

TIME: 3 hours Maximum:100 marks

ans ALL ques.
PART-A(10*2=20 marks)
1. State what data cleaning routines attempt to fill?
2. What is multidimensional database?
3. Classify OLAP tools?
4. What is fact constellation?
5. What is classification?
6. State why data preprocessing is an important problem for data warehousing and data mining?
7. List the 2 interesting measures of an association rule
8. State the need for pruning phase in decision tree construction
9. describe clustering
10. What is outlier analysis?

PART-B(5*16=80 marks)
11(a) List and explain the characteristics and main functions performed by the components of a data warehouse. provide diagrammatic illustration? (16)

or

(b)(i) discuss why a data warehouse is well equipped for providing the data for data mining?(8)
(ii) List and explain the 3 important problems that have to be addressed during data integration?(8)

12(a) In data warehouse technology, a multiple dimensional view can be implemented by a relational database technique(ROLAP), or by a multidimensional database technique(MOLAP) or by a hybrid database technique(HOLAP). define every implementation technique(16)

or

(b) With relevant examples explain the various OLAP operations(16)

13(a) describe every of the subsequent data mining functionalities, characterization, discrimination, association and correlation analysis, classification, prediction, clustering and evolution analysis. provide examples of every data mining functionality, using areal-life. Database that you familiar with.(16)

or

(b) With an example how a data mining system can be integrated with a data warehouse(16)

14(a) Develop a algorithm for classification using decision trees. Illustrate the algorithm with a relevant example.(16)

or

(b) explain the apriori algorithm for generating association rules. Illustrate the algorithm with a relevant example.(16)

15(a) Consider 5 points {X1,X2,X3,X4,X5} with the subsequent coordinates as a 2 dimensional sample for clustering
X1=(0,2)
X2=(0,);
X3=1,5,0);
X4=(5,0);
X5=(5,2)
illustrate the k-Means partitioning algorithm using the above set of data set (16)

or

(b) explain any 2 applications of data mining(16)

Earning:   Approval pending.