[Home]STLAlgorithmExtensions/ClusteringAlgorithms

BOOST WIKI | STLAlgorithmExtensions | RecentChanges | Preferences | Page List | Links List

Difference (from prior major revision) (author diff)

Added: 70a71,73
* p is a point instance of type Point
** get<N>(p) should be a valid expression that return the N'th element of the point.
** length< D >::value should be a valid expression that return the number of elements (arrity) of the type P.

Boost Clustering Algorithm

The overall objective of the Boost Clustering Library is to provide a modern and portable C++ clustering algorithm library suitable for wide use and eventual standardization.

What is clustering?

A loose definition of clustering could be “the process of organizing objects into groups whose members are similar in some way”. A cluster is therefore a collection of objects which are “similar” between them and are “dissimilar” to the objects belonging to other clusters.

Clustering algorithms can be applied in many fields, for instance:

Requirements

Action items

Algorithms

DBSCAN

K-Means

Concepts

The relevant concepts of the library are specified in the following sub sections.

Point

Distance Function

A Distance Function is a type that is callable (like a standard C++ function) with two arguments of types that model the Point concept. The Distance Function should return a distance of type Ret between the points (using some metric).

Supporting Objects

cluster_data


BOOST WIKI | STLAlgorithmExtensions | RecentChanges | Preferences | Page List | Links List
Edit text of this page | View other revisions
Last edited May 8, 2008 8:33 am (diff)
Search:
Disclaimer: This site not officially maintained by Boost Developers