Jawaharlal Nehru Technological University Hyderabad 2011-3rd Year B.Tech Computer Science and Engineering (CCC) s- DATA WAREHOUSING AND MINING - Question Paper

Code No: C3CS06
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD
B.Tech (CCC) III Year exams February - 2011
DATA WAREHOUSING AND MINING
(Computer Science Engineering)

Time: three Hours Max.Marks:100

ans Any 5 ques.
All ques. Carry Equal Marks
- - -
1. Write short notes on the following:
a) Cluster analysis
b) Outlier analysis
c) Evolution analysis
d) Classification and prediction. [20]
2. Consider a few data to apply data smoothing techniques.
a) Smoothing by bin
b) Smoothing by bin median
c) Smoothing by bin boundaries
d) How might you determine outliers in the data? [20]

3.a) discuss different concept hierarchies with examples.
b) describe the following:
i. Simplicity
ii. Certainty
iii. Utility
iv. Novelty. [20]

4. Attribute oriented induction generates 1 or a set of generalized descriptions. How can
these descriptions be visualized? discuss in detail. [20]
5. How can you improve the efficiency of "apriori based mining" with the help of the
following:
a) Hash based technique.
b) Transaction reduction
c) Partitioning
d) Sampling

e) Dynamic item set counting. [20]

6.a) Compare the advantages and disadvantages of eager classification (eg: decision tree) versus
lazy classification ( eg: K-nearest neighbor).
b) What is case based learning? [15+5]

7.a) How is CLARANS various from CLARA? Illustrate this using a small example.
b) What is the main principle in partitioning methods of clustering? [12+8]

8.a) Which frequent item set mining is suitable for text mining?
b) elaborate the differences ranging from mining techniques of structured data and unstructured data
and semi structured data? [8+12]

Earning:   Approval pending.