Chapter 10

Question 1

Cluster, potential class

Answer 1

a collection of data objects
similar to one another within the same group
dissimilar to the objects in other groups

Question 2

cluster analysis, clustering, data sementation…

Answer 2

finding simiularites between data according to the characteristics found in the data and grouping similar data objects into clusters.

Question 3

unsupervised learning

Answer 3

no predefined classes, i.e. learning by observarions vs. learning by examples, superives
a stand alone trool to get insight
preprocessing step for other algorithms

Question 4

Examples of clusteriong

Answer 4

biology: animal kingdom class order
economic science: market research

Question 5

summarization

Answer 5

preprocessing for regression, PCA, classification, and association analysis

Question 6

compression

Answer 6

image processing: vector quantization

Question 7

finding k-nearest neighbors

Answer 7

localizing search to one or a small number of clusters

Question 8

outlier detection

Answer 8

outliers are often viewed as those far away from any cluster

Question 9

KNN

Answer 9

simplest model, k=1 closeest value, k=2 the two closest entries
distance calculation: euclidean distance, manhattan distance
challenge: high dimensional data 3d 4d

Question 10

scalability

Answer 10

clustering all the data insread of onlt on samples which can lead to biased results

Question 11

abiltiy to deal with different types of attributes

Answer 11

numerical, binary, categorical, ordinal, linked, and mixture of these

Question 12

constraint based clustering

Answer 12

user may give inputs on constraints

use domain knowledge to determine input parameters

Question 13

partitioning crietria

Answer 13

single level vs hierarchical partitioning

Question 14

seperatrion of clusters

Answer 14

exclusive one customer belongs to one region vs non exlisov one document mauy belong to more than pone class

Question 15

similarity measure

Answer 15

distance based bs connectivity based

Question 16

clustering space

Answer 16

dull space vs subspaces

Question 17

good partitioning

Answer 17

objects in the same cluster are close to related to each other whereas objects in different clusters are far apart or very diofferent.

Question 18

typical methods

Answer 18

k means, kmedoid , work week for dinding spherical shaped slusters in samll to medium size databases

Question 19

hierarchical apaproch

Answer 19

create a hierarchical decomposition of data objects

Question 20

agglomerative bottom up approach

Answer 20

starts with each object forming a separate group successively merges into one or a ermination condition holds

Question 21

divisive top down approach

Answer 21

atarts wiht all objects in the same cluster, successively splits into smaller clusters intil each object is in one cluster or a termination condition holds

Question 22

density based approach

Answer 22

distance based clusterinfg methods can find spherical shaped cluster but encounter difficulty in discovering clusters of avitrary shapes
based on the notion of density
continue to grow a clsuter as long as the density in the neighborhood exceeds some thresholds

Question 23

centroi

Answer 23

the center of a cluster

Question 24

kmeans

Answer 24

eahc cluster is reoresebnted by thr enter of the cluster, the centroid of a cluster is the mean value of the points within the custer
iteratively improves the within cluster variation

Question 25

iterative relocation

Answer 25

the process iteratively reassigning objects to clusters to improve the partitioning

Question 26

kmeans algorithm four steps

Answer 26

1/partition objects into k nonemepty subsets 2. compute seed points as the entroid of the clusters of the current partitioning 3. assign each object to the cluster with the nearest seed point 4. iteratively improves the within cluster variant

Question 27

kmeans strength

Answer 27

efficient

Question 28

kmeans weakness

Answer 28

applicable only to objects in a continuouse n dimesional space need to specify k in advance sensitive to noisy data and outlires

Question 29

variations of the kimeans differ in

Answer 29

selection of the intial k means dissimilarity calculations strategies to calculate cluster means

Question 30

k modes

Answer 30

repalcing means of clusters with modes | using a frequency based method to update modes of clusters

Question 31

k medoids

Answer 31

insread of rtaing the mean vlkaue of the object in a cluster as a reference point, edoids can be used which h is the mont cneteally located object in a cluster

Question 32

hierarchial methods

Answer 32

grouping data objects into hierarchy or tree of clusters | hierarchy is useful for data summarization and visualization

Question 33

agglomerative

Answer 33

organized objects into a hierarchy using a bott up strategy start with individual objects as clusters, iterativelrt merged to form larger and larger cluster, the single cluster becomes the hierarchy root the merging step: find two lcuster that are cosese and comjine the two to form one cluster

Question 34

divisive

Answer 34

employs top down stratagy ler all the given objects form one cluster, iteratively spliot into smaller sub clusters and recursively partition those clusters into smaller ones intil each cluster at the lowest level contains only one object

Question 35

multiphased clsuetering

Answer 35

integrate hierarchical with other clusterting methods

Question 36

Agnes, agflomerative nesting

Answer 36

introduced in kaufmann and tousseeuw implemented in statistical packages merge nodes that have the least dissimilarity eventually all nodes belong to the same cluster

Question 37

diana civisive analysis

Answer 37

impleemented in statistical analysis packages inver order of AGNES eventually each node forms a cluster on its own.

Question 38

density based clustering methods

Answer 38

partitionign and hierarchical methods are sedigned to find spjerocal; shaped cluster

Question 39

main fetures

Answer 39

discover lcuster of srbritary hspe handle noise one scan need density parameters as termination condition

Question 40

dbscan: density based spatial clustering of applications with noise

Answer 40

the dnesity of and object o can be measured by the number of objects close to o it finds core objects, that have dense neighborhoods , connects core objects and their neighborhoods to form dense regions as clusters

Question 41

density reachable

Answer 41

a point is density reachable from a point if there is a chain of points

Question 42

density connects

Answer 42

a point p is sensity connected to a point if there is a point o such that both p an q are density reachable form

Question 43

dbscan algortrithm

Answer 43

arbritart select a point p retieve all point density reachable from p if p is a core point, a cluster is formed if p is a border point, no points are senity reachable from p and DBSCAN visits the next point of the database continue until; all points have been processed

Question 44

high intraclass imilarity

Answer 44

cohesive within clusters

Question 45

low interclass similarity

Answer 45

distinctive between clusters

Question 46

The quality of clusterig method depends on

Answer 46

the similarity measure used by the method its implementation its ability to discover some or all of the hidden patterns

Question 47

dissimilarity/similarity metric

Answer 47

simalarity is expressd in terms of a distance function, typically metric

Question 48

qualtiy of clustering

Answer 48

ther is usually a separate quality function that measures the goodness of a cluster it is hard to define similar enough or good enough, it is highly subjective

Question 49

extrinsic

Answer 49

supervise, i.e. the gorund truth is available | compare a clustering against the ground truth using certain clustering quality measure

Question 50

intrinsic: unserpervised

Answer 50

, i.e. the ground truth is unavalible evaluate the goodness of a clustering by considering how well the clusters are separated and how compact the clusters are