Discrete HMM model

o background_distributions
o state
o model
o model_direct
o hmm_check_t
o model_ipow
binary algorithm to compute powers of integers efficiently see Knuth, TAOCP, Vol 2, 463 uses if appropiate lookup table from struct model
o model_free
Frees the memory of a model.
o model_read
Reads in ASCII data to initialize an array of models.
o model_direct_read
Reads in a model, where the model parameters are explicit given in matrix form.
o model_from_sequence_ascii
Produces simple left-right models given sequences.
o model_from_sequence
Produces simple left-right models given sequences.
o model_copy
Copies a given model.
o model_check
Tests if all standardization requirements of model are fulfilled.
o model_check_compatibility
Tests if number of states and number of outputs in the models match.
o model_check_compatibel_models
Test if to models are compatible.
o model_generate_from_sequence
Produces a model, which generates the given sequence with probability 1.
o model_generate_sequences
Produces sequences to a given model.
o model_likelihood
Calculates the sum log( P( O | lambda ) ).
o model_set_transition
Set transition from state 'i' to state 'j' to value 'prob'.
o model_print
Writes a model in matrix format.
o model_A_print
Writes transition matrix of a model.
o model_B_print
Writes output matrix of a model.
o model_Pi_print
Writes initial allocation vector of a matrix.
o model_fix_print
Writes fix vector of a matrix.
o model_A_print_transp
Writes transposed transition matrix of a model.
o model_B_print_transp
Writes transposed output matrix of a model.
o model_Pi_print_transp
Writes transposed initial allocation vector of a matrix.
o model_direct_print
Writes a HMM in matrix format.
o model_states_print
Writes the parameters of a model sorted by states.
o model_direct_clean
Frees all memory from a model, sets the pointers to NULL and variables to zero.
o model_direct_check_data
Tests compatibility of the model components.
o model_prob_distance
Computes probabilistic distance of two models
o state_clean
Frees all memory from a state, sets the pointers to NULL and variables to zero.
o get_emission_index
Calculates the right index for emission array b of state j in model mo given an observation obs and taking the state order into account, returns -1 if state order exceeds number of so far emitted characters
o update_emission_history
Updates emission history of model mo, discarding the oldest and 'adding' the new observation by using modulo and multiplication
o update_emission_history_front
Updates emission history of model mo for backward algorithm by 'adding' observation obs to the left, (example: obs = 3 2 0 0 1 --> 3 2 0 0 )
o model_normalize
Uses vector_normalize in vectorh Normalizes the transition and output probs for each state in the given model
o model_add_noise
Add a specific level of noise to the model parameters
o model_apply_duration
Allocates a new background_distributions struct and assigs the arguments to the respective fields.
o model_apply_background
Apply the background distributions to the emission probabilities of states of the model which have one specified (background_id[state_id] != kNoBackgroundDistribution).
o model_alloc_background_distributions
Allocates a new background_distributions struct and assigs the arguments to the respective fields.
o model_get_uniform_background
Calculates the background distribution for a sequence_t the calculated distribution is uniform, every state with the same order has the same background distribution.
o model_distance
Calculates the squared distance between two compatible models.
o state_copy
Copies a given state.
o state_copy_to
Copies a given state to a given destination.

Alphabetic index


This page was generated with the help of DOC++.