You are on page 1of 2

Like us For Get More Latest Fast Genuiene Updates In Facebook:

www1b.com/jntukinfo www.jntufastupdates.com II
www.jntukfastupdates.com

56. Outliers can also be identified in____________step.:->Post processing


57. algorithm is more efficient and is less susceptible to initialization problems.:>Bisecting K Means
58. algorithm has difficulty for detecting the natural clusters, when the clusters have
-

non- spherical shapes or widely used different sizes or densities:->Agglomerative


59. Which of the following are not the choices for proximity function for K-Means algorithm?:>Euclidian distance
6 0 . _____________I n
technique, picking an initial solution and then repeating the two st
______________as
Computing the change to the solution, that best optimizes the objective function t h u p d a t e
61.
62.
63.
64.

The solution:->Agglomerative
algorithm also has trouble clustering data that contains outliers.:ns
Which algorithm is not suitable for all types of data?:->K-Means
Which of the following is the example for graph based clusters?:->Contigui
ased
In___________, a set of nodes in a graph that are completely connecte
a h other.:-

>Contiguity-based
6 5 . _____________I n
connected only if_irc with in a specified

clusters, where two objects arc

distance of each other.:->Contiguity-based


66. For data with categorical attributes, the prototype of a cluste >Medoid
67. Which of the following is not a additional issue in K-M
orithm.:->Increasing SSE
68. cluster is obtained, if no points are allocated
er during the assignment step:>Empty cluster
69. The cluster with the ____________is usually cho
splitting a cluster.:->Largest SSE
70. is accomplished by removing t
t a t at corresponds to the cluster and
reassigning the points to other clusters.:->D" i
a cluster
71. approach is to merge the two
rs that
results in the smallest increase in
total SSE by increasing the number of clusters:total
SSE.:->Merge two clusters
72. strategy is used for dec
>Split a cluster
73. To maximize the similarity of th
ents in a cluster to the cluster centroid, we use
____________quantity:->Cohesio
74. To measure the quality of
e g, we use the___________________:->SSE
7 5 . __________I n
clustering,
___________n only some of the points to a cluster.:->Partial clustering
76. In___________clusterg e sign every point to a cluster.:->Completc clustering
7 7 .
I n
cluster, e,
int is closer to center of its cluster than to any other cluster.:->Cen terbased
78. In ___________________r. ea point is closer to all of the points in its cluster than to any point in
another cluste
e 1 separated
79. For data wit vtinuous attributes, the prototype of a cluster is often a _____________: >Mean
80. In
luster, points in a cluster share some general property that derives from the
entire
points.: >Conceptual cluster
81. In
cluster, clusters are regions of high density separated by regions of low density.:
>Dens'
ased
82. In__________cluster, each point is closer to at least one point in its cluster than to any point in
-

another cluster.: >Contiguity based


In K-Means algorithm, K stands for number of_____________________: >Clusters
K-Means algorithm is also linear in the number of____________: >Data points
The time complexity of K-Means algorithm is_______________: >O (imkn)
The space complexity of K-Means algorithm is___________: >O ((m+k) n)
is simply a division of the set of data objects into non-overlapping subsets.:-

83.
84.
85.
86.
87.

>partitioning clustering

This Original online Bits Is Exclusively providing by


www.jntukfastupdates.com Only
www.jntukresult.com

II www.techpcworld.com II www.jfujobs.com

You might also like