AutoClass
AutoClass is an approach to unsupervised classification based upon the
classical mixture model, supplemented by a Bayesian method for determining the
optimal classes. It is particularly useful for extracting information from databases.
Key features are:
- determines the number of classes automatically;
- can use mixed discrete and real valued data;
- can handle missing values;
- processing time is roughly linear in the amount of the data;
- cases have probabilistic class membership;
- allows correlation between attributes within a class;
- generates reports describing the classes found; and
- predicts "test" case class memberships from a "training" classification.
There are several implementations available for AutoClass, in Common Lisp and in ANSI C (called AutoClass C).
|
Current Version: 3.3.2 (AutoClass C)
License Type: Free
|
Home Site:
http://ic-www.arc.nasa.gov/ic/projects/bayes-group/group/autoclass/autoclass-c-program.html
Source Code Availability: Yes
Available Binary Packages:
- Debian Package: Yes
- RedHat RPM Package: No
- Other Packages: No
Targeted Platforms:
AutoClass C has been ported to and tested on: SunSparc with Solaris or SunOS, SGI IRIX5.2, Linux, HPUX.
Software/Hardware Requirements:
ANSI C compiler for AutoClass C
|
Other Links:
None
Mailing Lists/USENET News Groups:
None
User Comments:
See A Screen Shot?
|