Data Mining complete the table if you dont know the answer p

Algorithm

shapes of clusters that can be determined

input parameters that must be specified

limitations

BIRCH

• Better suited to find spherical clusters

• N d-dimensional data points

• Because a CF tree can hold only a limited number of entries due to its size, a CF tree does not always correspond to what a user may consider a natural cluster.

• data order sensitivity and inability to deal with non-spherical clusters of varying size because it uses the concept of diameter to control the boundary of a cluster

• Handles only numeric data, and sensitive to the order of the data Record

DBSCAN

• To identify clusters of any shape in data set (or)
• discover clusters of arbitrary shapes

• Maximum possible distance for a point to be considered density-reachable and minimum number of points in a cluster

• Quadratic time in the worst case

• fails to identify clusters if density varies and if the data set is too sparse

• difficulties in high dimensional spaces

CHAMELEON

• discovering arbitrary-shaped clusters of varying density

(or)

• Arbitrary shape

• N d-dimensional categorical points

• Quadratic time in the worst case

k-means

• finding spherical-shaped clusters (or) convex clusters

• The number of clusters must be specify   (K)

• Sensitive to noise and outliers. Works well on small data sets only

• Sensitive to noisy and outlier.

• K-Means cannot handle non-globular data of different sizes and densities
• K-Means will not identify outliers

k-medoids

• finding spherical-shaped clusters( or) convex clusters

• The number of clusters must be specify .it allow if presence of noisy and outlier

• Small data sets (not scalable)

• Processing more costly than k-mean.large data set cannot handle

CLARA

• finding spherical-shaped clusters

• The number of clusters must be specify

• Sensitive to the selection of initial samples

• Fixed sample at each stage .
• Does not find best cluster