APJ Abdul Kalam Technological University
First Semester M.Tech Degree Examination, 2015

Branch: Computer Science and Engineering (Cluster 01)
01CS6151 Data Warehousing & Mining

Time: 3 Hours Max. Marks: 60 Instructions: Answer two questions from each module.
Part A
a. How is the effectiveness or usefulness associated with data mining tasks

measured? (4)

. How are KDD and data mining related? How are they different? (4) C. Illustrate

the use ofvarious OLAP primitives. (6.5) 2.

a. A data warehouse can be modeled by either a Slar schema or a snowflake
schema. Briefly describe the similarities and the differences of the two models,
and then analyze their advantages and disadvantages with regard to one
another. (4)

b. Data Mining is used in extracting information from data. Discuss four critical
implementation issues associated with data mining. (6.5)

a. When is data reduction used for preprocessing of data? How is data reduction done
using principal component analysis? (6)

b. What are the main characteristics that make a data warehouse distinctly different
from a database? (I)

©. Choose any normalization method to normalize the following data.
13,15,16,16,19,20,20,21,22,22,25,25,25,25,25,30,33,33,35. Justify the choice of
normalization method. (3.5)

Part B

a. Given two objects represented by the tuples (22, |, 42, 10) and (20, 0, 36, 8), compute the cosine
similarity between the two tuples.

b. With the training data given, derive a regression equation to model the data
and classify data as short (represented using 0) or medium (represented using
|). The data is: { (1.6,0), (1.9, 0, (1.88, |), (1.7,0), (1.85,1), ( | .6,0), (1 .7,0), (1.8,
I), | .95, |). (1.9, 1). 1.8.1), (1.75, 1). (7.5)

a. Whenis|R algorithm used for classification? Show how the algorithm can be used

for classification. (5.5)