MDSTk Libraries  1.1.0
Medical Data Segmentation Toolkit
Enumerations | Variables
mds::math::MaxLikelihoodByEM Namespace Reference

Enumerations

enum  EOptions { LOGGING_ENABLED = 1 << 0, ADD_RAND_NOISE = 1 << 1, DEFAULT_FLAGS = LOGGING_ENABLED | ADD_RAND_NOISE }
 Flags which may be passed to the EM algorithm. More...

Variables

const tSize MAX_ITERS = 10
 Maximal allowed number of iterations.
const tSize MAX_ITERS2 = 10
 Maximal allowed number of internal iterations.
const double MIN_ADD_CHANGE = 0.001
 Minimal required change of the log-likelihood function which results in a new component addition.
const double MIN_CHANGE = 1.0e-6
 Minimal required change of the log-likelihood function while iterating.
const double RAND_NOISE_COEFF = 0.5
 Random noise.
const double SPLITTING_COEFF = 0.5
 Coefficient used to split a gaussian component.

Enumeration Type Documentation

Flags which may be passed to the EM algorithm.

Enumerator:
LOGGING_ENABLED 

Enables advanced logging.

ADD_RAND_NOISE 

Enables adding of random noise during iterations.

DEFAULT_FLAGS 

Default flags.


Variable Documentation

Maximal allowed number of iterations.

Maximal allowed number of internal iterations.

Minimal required change of the log-likelihood function which results in a new component addition.

Minimal required change of the log-likelihood function while iterating.

Random noise.

Coefficient used to split a gaussian component.