Sensor Circuits - The Electronic Nose Artificial Olfaction Technology - page 202

Fig. 7.24 Cluster analysis steps [ 15 ]

step until only one cluster is left. The clustering method uses the differences or
distances between objects when structure the clusters. A dendrogram is the
process represented on a diagram during execution of a hierarchical cluster
analysis. This diagram demonstrates which clusters have been joined at each
stage of the analysis and the distance between clusters at the time of joining.
• k-mean clustering:

k-mean clustering is the grouping of samples into a set number of classes and it
uses all variables to determine relative distances. This method of clustering is
dissimilar from the hierarchical clustering, which are applied when there is no
prior knowledge of how many clusters there may be or what they are characterized
by, so it is also called as non-hierarchical cluster analysis. K-means clustering is
used when proposition concerning the number of clusters in cases or variables. The
input required by the computer is to form exactly desired clusters that are to be as
distinct as possible. The k-means clustering algorithm addressed this type of
research question.
In general, the k-means method will produce the exact k different clusters
demanded of greatest possible distinction. Frequently, both the hierarchical and the
k-means techniques are used successively.