Anna University Previous Years Question Papers
Question paper code: 71356
B.E,B.TECH DEGREE EXAMINATION,APRIL/MAY-2015
Seventh semester
Computer science and Engineering
CS 2032/ CS 701/ 10144 CSE 32- DATA WAREHOUSING AND DATA MEANING
(Common to sixth semester information technology)
(Regulation 2008/2010)
(Common to PTCS 2032-Data warehousing and data meaning for B.E. (part-time) sixth semester-Computer science and Engineering-(Regulation 2008/2010)
Time- Three hour
Maximum mark-100
Answer all questions
PART A-10X2=20marks
1. Why data preprocessing is an important issues for both data warehousing and data mining?
2. What is data warehouse and data metadata?
3. Where a multidimensional data model is typically use?
4. What is multi-relation OLAP?
5. List out the data mining functionalities?
6. Why data cleaning routines are needed?
7. Distinguish between classification and clustering.
8. What is a decision tree?
9. Let x1=¬{1,2}and x¬2={3,5} represent two points. Calculate the Manhattan distance between the two points?
10. How outliers may be detected by clustering?
Part B-5x16=80 MARKS
11.(a)Explain the three tier architecture of a data warehouse with diagrammatic illustration.
(or)
(b)Explain star schema and snowflake schema with example and diagrammatic illustration.
12.(a) Highlight the features of cognos impromptu.
(or)
(b) List and explain the typical OLAP operations for multidimensional data with suitable example and diagrammatic illustration.
13.(a) List and explain about the primitives involved in specifying a data mining task.
(or)
(b)Explain with a diagrammatic illustration for the steps involved in the process of knowledge discovery from databases.
14.(a) Apply the Apriori algorithm for discovering frequent item sets to the following data set:
Trans ID Items purchased
101 Litchi, Hill banana, straw berry
102 Litchi, Passion Fruit
103 Passion Fruit, Tomato
104 Litchi, Hill banana, straw berry
105 Pears, straw berry
106 Pears
107 Pears, Passion Fruit
108 Litchi, Hill Banana, Water melon, straw berry
109 Water melon, Tomato
110 Litchi, Hill Banana
Use of 0.3 for the minimum support value .
(or)
(b)Explain the working of the naive Bayesian classifier with an example.
15.(a)(i) How agglomerative hierarchical clustering works? Explain with an example.
(ii) How divisible hierarchical clustering works? Explain with an example.
(or)
(b)Consider five points {X1,X2,X3,X4,X5} with the following coordinate as a two dimensional samples for clustering:
X1=(0,2),X2=(1,0),X3=(2,1)X4=(4,1)and X¬5=(5,3)
Illustrate the K-means algorithm on the above data set. The required number of clusters is two and initially, clusters are formed from random distribution of samples: C1{X1, X2, X4} and C1{X3, X5}.
Question paper code: 71356
B.E,B.TECH DEGREE EXAMINATION,APRIL/MAY-2015
Seventh semester
Computer science and Engineering
CS 2032/ CS 701/ 10144 CSE 32- DATA WAREHOUSING AND DATA MEANING
(Common to sixth semester information technology)
(Regulation 2008/2010)
(Common to PTCS 2032-Data warehousing and data meaning for B.E. (part-time) sixth semester-Computer science and Engineering-(Regulation 2008/2010)
Time- Three hour
Maximum mark-100
Answer all questions
PART A-10X2=20marks
1. Why data preprocessing is an important issues for both data warehousing and data mining?
2. What is data warehouse and data metadata?
3. Where a multidimensional data model is typically use?
4. What is multi-relation OLAP?
5. List out the data mining functionalities?
6. Why data cleaning routines are needed?
7. Distinguish between classification and clustering.
8. What is a decision tree?
9. Let x1=¬{1,2}and x¬2={3,5} represent two points. Calculate the Manhattan distance between the two points?
10. How outliers may be detected by clustering?
Part B-5x16=80 MARKS
11.(a)Explain the three tier architecture of a data warehouse with diagrammatic illustration.
(or)
(b)Explain star schema and snowflake schema with example and diagrammatic illustration.
12.(a) Highlight the features of cognos impromptu.
(or)
(b) List and explain the typical OLAP operations for multidimensional data with suitable example and diagrammatic illustration.
13.(a) List and explain about the primitives involved in specifying a data mining task.
(or)
(b)Explain with a diagrammatic illustration for the steps involved in the process of knowledge discovery from databases.
14.(a) Apply the Apriori algorithm for discovering frequent item sets to the following data set:
Trans ID Items purchased
101 Litchi, Hill banana, straw berry
102 Litchi, Passion Fruit
103 Passion Fruit, Tomato
104 Litchi, Hill banana, straw berry
105 Pears, straw berry
106 Pears
107 Pears, Passion Fruit
108 Litchi, Hill Banana, Water melon, straw berry
109 Water melon, Tomato
110 Litchi, Hill Banana
Use of 0.3 for the minimum support value .
(or)
(b)Explain the working of the naive Bayesian classifier with an example.
15.(a)(i) How agglomerative hierarchical clustering works? Explain with an example.
(ii) How divisible hierarchical clustering works? Explain with an example.
(or)
(b)Consider five points {X1,X2,X3,X4,X5} with the following coordinate as a two dimensional samples for clustering:
X1=(0,2),X2=(1,0),X3=(2,1)X4=(4,1)and X¬5=(5,3)
Illustrate the K-means algorithm on the above data set. The required number of clusters is two and initially, clusters are formed from random distribution of samples: C1{X1, X2, X4} and C1{X3, X5}.
0 comments:
Pen down your valuable important comments below