Está en la página 1de 2

Code: 15A05602 R15

B.Tech III Year II Semester (R15) Supplementary Examinations December/January 2018/19


DATA WAREHOUSING & MINING
(Computer Science & Engineering)
Time: 3 hours Max. Marks: 70
PART – A
(Compulsory Question)
*****
1 Answer the following: (10 X 02 = 20 Marks)
(a) List the five primitives for specifying a data mining task.
(b) Why do we need to apply data reduction technique? List data reduction techniques.
(c) Define data warehouse.
(d) Define full materialization and partial materialization for given base cuboid.
(e) Define closed frequent item set and minimal frequent itemsets.
(f) Explain k-fold cross validation technique for accessing accuracy of a classifier.
(g) List at least four typical requirements of clustering algorithm.
(h) Define grid based clustering.
(i) What is time-series database? List few applications which require time series database.
(j) What is graph mining? Identify few applications where graph mining can be adopted.

PART – B
(Answer all five units, 5 X 10 = 50 Marks)
UNIT – I
2 Describe the challenges to data mining regarding data mining methodology, user iteration issues and
performance issues.
OR
3 (a) In real world data, tuples with missing values for some attributes are a common occurrence. Describe the
various methods for handling this problem.
(b) Explain the operations of data cube with suitable examples.
UNIT – II
4 (a) How are concept hierarchies useful in OLAP? Explain.
(b) Explain any four OLAP operations with appropriate examples.
OR
5 (a) Describe three tier data warehousing architecture.
(b) Construct lattice of cuboids given 4 dimensions: time, location, product and supplies.
UNIT – III
6 (a) Provide examples for frequent pattern mining based on following criteria:
(i) Levels of abstractions.
(ii) Number of data dimensions.
(iii) Types of value handled in rule.
(b) Explain support, confidence and lift measure with respect to association rule mining.
OR
7 (a) Explain the working of k-nearest neighbor classifier.
(b) What is confusion matrix? Given the confusion matrix, compute sensitivity and specificity.
C1 C2
C1 6,934 40
C2 412 2,568
Contd. in page 2

Page 1 of 2
Code: 15A05602 R15
UNIT – IV
8 (a) Describe the working of k-means clustering.
(b) Compare agglomerative and divisive hierarchical clustering.
OR
9 Briefly outline how to compute the dissimilarly between objects described by the following types of
attributes: (i) Interval scaled variable.
(ii) Binary variable.
(iii) Categorical variable.
(iv) Ordinal variable.
UNIT – V
10 What is a social network? How can we mine social network?
OR
11 Describe web usage mining in detail.

*****

Page 2 of 2

También podría gustarte