lti::sffs Class Reference

Implemantation of the sequential floating forward search algorithm to select the best features from a data set. More...

#include <ltiSffs.h>

Inheritance diagram for lti::sffs:

[legend]

Collaboration diagram for lti::sffs:

[legend]

List of all members.

Classes
class	parameters
	the parameters for the class sffs More...
Public Member Functions
	sffs ()
	sffs (const sffs &other)
virtual	~sffs ()
virtual const char *	getTypeName () const
bool	apply (const dmatrix &src, const ivector &srcIds, dmatrix &dest) const
sffs &	copy (const sffs &other)
sffs &	operator= (const sffs &other)
virtual functor *	clone () const
const parameters &	getParameters () const

---

Detailed Description

Implemantation of the sequential floating forward search algorithm to select the best features from a data set.

This algorithm is implented from: P. Pudil, F.J. Ferri, J. Novovicova, J. Kittler: "Floating Search Methods for Feature Selection with nonmonotonic criterion Functions" Procedings of the IEEE Intl. Conf. on Pattern Recognition, 279-283, 1994; The original SFFS-Algorithm is discriped in P.Pudil,J.Novovicova,Kittler "Floating search methods in feature selection" Pattern Recogniton Letters 15, pages 1119-1125

---

Constructor & Destructor Documentation

lti::sffs::sffs

(

)

default constructor

lti::sffs::sffs

(

const sffs &

other

)

copy constructor

Parameters:

other

the object to be copied

virtual lti::sffs::~sffs

(

)

[virtual]

destructor

---

Member Function Documentation

bool lti::sffs::apply	(	const dmatrix &	src,
		const ivector &	srcIds,
		dmatrix &	dest
	)			const [virtual]

operates on the given parameter.

Parameters:

srcdest

dmatrix with the source data. The result will be left here too.

Returns:

true if apply successful or false otherwise. operates on a copy of the given parameters.

Parameters:

	src	dmatrix with the source data.
	dest	dmatrix where the result will be left.

Returns:

true if apply successful or false otherwise. extracts the most significant features from a source data set

Parameters:

	src	the src data
	srcIds	the cluster ids corresponding to the data points in src
	dest	the extracted features

Returns:

true if apply successful or false otherwise.

Implements lti::featureSelector.

virtual functor* lti::sffs::clone

(

)

const [virtual]

returns a pointer to a clone of this functor.

Implements lti::featureSelector.

sffs& lti::sffs::copy

(

const sffs &

other

)

copy data of "other" functor.

Parameters:

other

the functor to be copied

Returns:

a reference to this functor object

Reimplemented from lti::featureSelector.

const parameters& lti::sffs::getParameters

(

)

const

returns used parameters

Reimplemented from lti::featureSelector.

virtual const char* lti::sffs::getTypeName

(

)

const [virtual]

returns the name of this type ("sffs")

Reimplemented from lti::featureSelector.

sffs& lti::sffs::operator=

(

const sffs &

other

)

alias for copy member

Parameters:

other

the functor to be copied

Returns:

a reference to this functor object

Reimplemented from lti::featureSelector.

---

The documentation for this class was generated from the following file:

• ltiSffs.h