Question Bank

Year & Semester: III & V

Subject Code & Subject Name: U15CSE05 & Data Warehousing and Data Mining
Unit – V

MCQS

1. Of the following clustering algorithm what is the method which initially creates a hierarchical
decomposition of the given set of data objects?
a. Partitioning Method
b. Hierarchical Method
c. Density-based method
d. Grid-based Method
2. The goal of _____ is to discover both the dense and sparse regions of a data set.
a. Association rule. c. Clustering.
b. Classification. d. Genetic Algorithm.
3. Which of the following is a clustering algorithm?
a. A priori. c. Pincer-Search.
b. CLARA. d. FP-growth.
4. From the following clustering technique start with as many clusters as there are records, with
each cluster having only one record.
a. Agglomerative. c. Partition.
b. divisive. d. Numeric.
5. Which of the following clustering techniques starts with all records in one cluster and then try to
split that cluster into small pieces?
a. Agglomerative. c. Partition.
b. Divisive. d. Numeric.
6. In which algorithm each cluster is represented by the center of gravity of the cluster.
a. k-medoid. c. STIRR.
b. k-means. d. ROCK.
7. Which tree structure is used to represent the process of hierarchical clustering?
a. CF tree c. Dendrogram
b. FP tree d. None of the above
8. In ___________ each cluster is represented by one of the objects of the cluster located near the
center.
a. k-medoid. c. STIRR.
b. k-means. d. ROCK.
9. The data matrix is called as,
a. Two mode matrix c. n-by –n matrix
b. One mode matrix d. None of the above
10. Pick out a k-medoid algoithm.
a. DBSCAN c. PAM.
b. BIRCH. d. CURE.
11. Pick out a hierarchical clustering algorithm.
a. DBSCAN c. PAM.
b. BIRCH. d. CURE.
12. SOMs are used to cluster a specific _____________ dataset containing information about the
patient's drugs etc.

A. physical. C. medical.
B. logical. D. technical.
13. CLARANS stands for,
A. CLARA Net Server.
B. Clustering Large Application RAnge Network Search.
 C. Clustering Large Applications based on RANdomized Search.
D. CLustering Application Randomized Search.
14. BIRCH is a,
A. agglomerative clustering algorithm.
B. hierarchical algorithm.
C. hierarchical-agglomerative algorithm.
D. divisive.
15. The cluster features of different subclusters are maintained in a tree called?

A. CF tree. C. FP growth tree.

B. FP tree. D. B tree.
16. The partition algorithm uses _______ scans of the databases to discover all frequent sets.

A. two. C. six.
B. four. D. eight.
17. Which of following is a highly simplified model of biological neurons?
A. Artificial neurons.
B. Computational neurons.
C. Biological neurons.
D. Technological neurons
18. SOM is an acronym of,
A. self-organizing map.
B. self origin map.
C. single organizing map.
D. simple origin map.
19. Distance between clusters can be measured using:
a. Single link c. Centroid
b. Average link d. Mediod
20. K-modes method for data clustering is,
a. Similar to K
b. A variant of K
c. A an efficient version of K-means in terms of convergence
d. None of the above
21. Machine learning techniques differ from statistical techniques in that machine learning methods,
a. typically assume an underlying distribution for the data
b. are better able to deal with missing and noisy data
c. are not able to explain their behavior
d. have trouble with large-sized datasets

22. If the similarity between two transactions, Ti and Tj, then the Jaccard coefficient is?

a. =

b. =

c. Both a & b d. None of these

23. How to calculate the mean absolute deviation,

 a.

b.

c.
d. None of the above

24. The entire data is a mixture of parametric probability distributions, where each individual
distribution is typically referred to as a component distribution referred as,
a. Conceptual clustering
b. A neural network approach
c. Expectation-Maximization
d. High –dimension data

25. The three dimensional vector information of CF can be represented by,

a. (N, LS, SS)
b. (Pi+1, Pn)
c. (Eps, MinPts)
d. O(n2)
26. How to find dissimilarity between the two objects i & j,

a.

b.

c.

d.
27. Which of the following techniques are used to partition the database,
a. CLARA & CLARANS
b. ROCK & BIRCH
c. k-means & k-medoids
d. All of above
28. The meaning of the threshold parameter in CF tree is,
a. Max diameter of sub-cluster stored in leaf node
b. Min diameter of sub-cluster stored in non -leaf node
c. Max diameter of cluster stored in leaf node
d. Min diameter of sub-cluster stored in leaf node
29. What is the computational complexity of DBSCAN?
a. O(n log n) c. O(log n)
2
b. O(n ) d. O(log n2)
30. In outlier analysis the working hypothesis, H is denoted as,
a. Statement of data set n
b. Distribution of data set n
c. Slippage distribution of data set n
d. None of the above