About PSGLab
Examples
Downloads
Install
Using
Documentation
PSGLab citation
Publications
Hardware module
Links
Contacts

Documentation

1. About PSGLab
2. Installing the Toolbox
3. Definition of global variables
4. Definition of used methods
5. Additional definition files for PSGLab
6. Examples of final visualization
7. PSGLab citation

1. Main routine (example of using)
2. Additional definition files (example of using)

List of functions currently implemented in PSGlab

function[X] = psglab_2d_map(data, options, global_vars)
%PSGLAB_2D_MAP creates the 2D brain image form EEG signals
%
% function[X] = psglab_2d_map(data, ch_pos_path, show_text, color_map, grid_precision, global_vars)
%
% data: input data matrix
% options: input parameters definition
% global_vars: global variables definition
%
% Additional:
% options.ch_pos_path: path to channels-position definiton file
% options.color_map: used colormap
% options.grid_precision: grid precision

function [] = psglab_2d_maps_to_avi(path_active, number_of_frames, add_frames_num, codec_type, video_fps)
%PSGLAB_2D_MAPS_TO_AVI converts time-series 2D map images into one avi file
%
% function [] = psglab_2d_maps_to_avi(path_active, number_of_frames, add_frames_num, codec_type, video_fps)
%
% path_active: path for PSG data directory
% number_of_frames: number of frames for avi (default is 50)
% codec_type: definion of avi codec (default is 'Cinepak')
% video_fps: fps (default is 25)

function[] = psglab_artefact_detection(path_active, options, global_vars)
%PSGLAB_ARTEFACT_DETECTION is used for detection of muscular artefacts
%
% function[] = psglab_artefact_detection(path_active, channels, interp_type, interp_points, interp_mcoef, baseline_type, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition
%
% Additional:
% options.interp_type: type of interpolation (cubic, nearest, linear , spline, pchip, cubic, v5cubic)
% options.interp_mcoef: multiplication coef. for thresholding
% options.baseline_type: method for computing of baseline (std, mean, median, std, min, max)

%function[] = psglab_artefact_remove()
%PSGLAB_ARTEFACT_REMOVE is used for removing of muscular artefacts
%
% function[] = psglab_artefact_remove()

function[] = psglab_averaging_signals(path_active, options, global_vars),
%PSGLAB_AVERAGING_SIGNALS returns mean signal computed from psg signals
%
% function [] = psglab_2d_maps_to_avi(path_active, number_of_frames, add_frames_num, codec_type, video_fps)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_classification_filter(path_active, options, global_vars)
%PSGLAB_CLASSIFICATION_FILTER includes moving filter algorithm for classification results
%
% function[] = psglab_classification_filter(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[cp, class] = psglab_classification_knn(path_active, options, global_vars)
%PSGLAB_CLASSIFICATION_KNN is k-nn classifier
%
% function[cp, class] = psglab_classification_knn(path_active, data_path, crossfolds_path, k_const, global_vars)
%
% path_active: path for PSG data directory
% data_path: path for input data loading
% crossfolds_path: path for final cross folds saving
% global_vars: global variables definition

function[] = psglab_clustering_hierarchical(path_active, options, global_vars)
%PSGLAB_CLUSTERING_HIERARCHICAL - hierarchical clustering
%
% function[] = psglab_clustering_hierarchical(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_clustering_kmeans(path_active, options, global_vars)
%PSGLAB_CLUSTERING_KMEANS - kmeans clustering
%
% function[] = psglab_clustering_hierarchical(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_coherence_or_correlation(path_active, options, global_vars)
%PSGLAB_COHERENCE_OR_CORRELATION - computes intrahemispheric and interhemispheric coherence or correlation between two psg channels
%
% function[] = psglab_coherence_or_correlation(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% options.compute_type: 1 = coherence, 2 = correlation
% global_vars: global variables definition

function[] = psglab_corr_coef(path_active, options, global_vars)
%PSGLAB_CORR_COEF -correlation coefficients
%
% function[] = psglab_corr_coef(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

psglab_create_dir_structure:
%PSGLAB_CREATE_DIR_STRUCTURE - main dir structure creating

function[] = psglab_cross_validation(path_active, options, k_const)
%PSGLAB_CROSS_VALIDATION defined creates cross validation folds for classifiers
%
% function[] = psglab_cross_validation(path_active, options, k_const)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_cut_data(options, global_vars)
%PSGLAB_CUT_DATA - preparing psg data to one format (the same length of recordings for each of subject)
%
% function[] = psglab_cut_data(options, global_vars)
%
% options: input parameters definition
% global_vars: global variables definition

function d = psglab_distance(X, Y)
%PSGLAB_DISTANCE - distance between two vectors
%
% function d = psglab_distance(X, Y)
%
% X, Y: input vectors
% d: distance between X and Y

function[] = psglab_expert_classification_covert(path_active, options, global_vars)
%PSGLAB_EXPERT_CLASSIFICATION_CONVERT - convert expert classification to different time-resolution
%
% function[] = psglab_expert_classification_covert(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_expert_classification_new(path_active, options, global_vars)
%PSGLAB_EXPERT_CLASSIFICATION_NEW - creates new expert classification
%
% function[] = psglab_expert_classification_new(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition
%

function[] = psglab_export_to_weka(path_active, options, global_vars)
%PSGLAB_EXPORT_TO_WEKA exports features and expert classification to ARFF format
%
% function[] = psglab_export_to_weka(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[average_features_results] = psglab_feature_average(path_active, options, global_vars)
%PSGLAB_FEATURE_AVERAGE Average values of features for all used classes
%
% function[] = psglab_feature_pc(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_feature_pca(path_active, options, global_vars)
%PSGLAB_FEATURE_PCA Principal Component Analysis (for reduction of features)
%
% function[] = psglab_feature_pc(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_feature_selection(path_active, options, global_vars)
%PSGLAB_FEATURE_SELECTION feature selection (class reduction by corrcoef method)
%
% function[] = psglab_feature_selection(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_feature_selection_combine(options, global_vars)
%PSGLAB_FEATURE_SELECTION_COMBINE combines the features after feature selection process
%
% function[] = psglab_feature_selection_combine(options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_feature_selection_sfs(options, global_vars)
%PSGLAB_FEATURE_SELECTION feature selection (class reduction by Sequential Forward Selection method)
%
% function[] = psglab_feature_selection_sfs(options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[findex,features] = psglab_features_default(data, compute_all_features, selected_features, fsamp, fft_size, br_nivoa, talasic,divide_low_bands, freq_min, freq_max, global_vars),
%PSGLAB_FEATURES_DEFAULT - file for psglab_features_extraction.m
%
% function[findex,features] = psglab_features_default(data,
% compute_all_features, selected_features, fsamp, fft_size, br_nivoa, talasic),
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[findex,features] = psglab_features_extraction(path, options, global_vars)
%PSGLAB_FEATURES_EXTRACTION - computation of predefined features
%
% function[findex,features] = psglab_features_extraction(path, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_features_normalization(path_active, options, global_vars);
%PSGLAB_FEATURES_NORMALIZATION - normalization of features
%
% function[] = psglab_features_normalization(path_active, options, global_vars);
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

% function[] = psglab_features_statistics()
%PSGLAB_FEATURES_STATISTICS - various statistics
%
% % function[] = psglab_features_statistics()

function[] = psglab_firpm_bandpass_filters(path_active, options, global_vars)
%PSGLAB_FIRPM_BANDPASS_FILTERS - equiripple bandpass filters designed using the FIRPM function
%
% function[] = psglab_firpm_bandpass_filters(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function model = psglab_hmm_em(X, options)
%psglab_hmm_em - EM algorithm for conditionally independent model
%
% function model = psglab_hmm_em(X, options)
%
% options: input parameters definition

function[model_1, model_2, model_3, model_4, model_5, model_6] = psglab_hmm_em_algorithm(signs_trained, expert_matrix_trained, em_maxy),
%PSGLAB_HMM_EM_ALGORITHM - EM algorithmn
%
% function[model_1, model_2, model_3, model_4, model_5, model_6] = psglab_hmm_em_algorithm(signs_trained, expert_matrix_trained, em_maxy),

function[emission_matrix] = psglab_hmm_emission_probability(signs_tested, model_1, model_2, model_3, model_4, model_5, model_6),
%PSGLAB_HMM_EMMISION_PROBABILITY - emission probability computing
%
% function[emission_matrix] = psglab_hmm_emission_probability(signs_tested, model_1, model_2, model_3, model_4, model_5, model_6),

function[expert_matrix_markov, transition_matrix, emission_matrix] = psglab_hmm_model(signs_trained, expert_matrix_trained, signs_test)
%PSGLAB_HMM_MODEL - HMM model creating
%
% function[expert_matrix_markov, transition_matrix, emission_matrix] = psglab_hmm_model(signs_trained, expert_matrix_trained, signs_test)

function [signs] = psglab_hmm_normalize_signs(signs, normalize_level_coef, max_values, min_values)
%PSGLAB_NORMALIZE_SIGNS - normalization algorithm for HMM
%
% function [signs] = psglab_hmm_normalize_signs(signs, normalize_level_coef, max_values, min_values),

function p = psglab_hmm_model(X,model),
%PSGLAB_HMM_MODEL - file for psglab_hmm_em_algorithm.m
%
% function p = psglab_hmm_model(X,model),

function [transition_matrix] = psglab_hmm_states_probability(expert_matrix)
%PSGLAB_STATES_PROBABILITY - states probability computing
%
% function [transition_matrix] = psglab_hmm_states_probability(expert_matrix)

function[expert_matrix] = psglab_hmm_viterbi_algorithm(prior_state, transition_matrix, emission_matrix)
%PSGLAB_HMM_VITERBI_ALGORITHM - viterbi algorithm for HMM
%
% function[expert_matrix] = psglab_hmm_viterbi_algorithm(prior_state, transition_matrix, emission_matrix)

function[] = psglab_change_amplitude(path_active, options, global_vars)
%PSGLAB_CHANGE_AMPLITUDE - change amplitude scaling
%
% function[] = psglab_change_amplitude(path_active, options, global_vars)

function[] = psglab_isoline_remove(path_active, options, global_vars)
%PSGLAB_ISOLINE_REMOVE - isoline removing
%
% function[] = psglab_isoline_remove(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_join_arff_files(options, global_vars)
%PSGLAB_JOIN_ARFF_FILES - join arff files (arff means weka format)
%
% function[] = psglab_join_arff_files(path_arff, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_join_spectrogram(global_vars)
%PSGLAB_JOIN_SPECTROGRAM - spectrograms joining
%
% function[] = psglab_join_spectrogram(global_vars)
%
% global_vars: global variables definition

%function[] = psglab_join_two_asc_file()
%PSGLAB_JOIN_ASC_FILE joins two asci files
%
% function[] = psglab_join_two_asc_file()
%

function[] = psglab_joint_and_export_to_weka_A(path_active, options, global_vars)
%PSGLAB_JOINT_AND_EXPORT_TO_WEKA_A - algorithm for arff file joining
%
% function[] = psglab_joint_and_export_to_weka_A(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_joint_and_export_to_weka_B(path_active, options, global_vars)
%PSGLAB_JOINT_AND_EXPORT_TO_WEKA_B - algorithm for arff file joining
%
% function[] = psglab_joint_and_export_to_weka_B(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_load_asc(filename, path_active, options, global_vars)
%PSGLAB_LOAD_ASC load PSG data (convert asci file to PSGLAB format file)
%
% function[] = psglab_load_asc(filename, path_active, options, global_vars)
%
% filename: filename definiton
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_load_dfile(dfile_name, path_active, options, global_vars)
%PSGLAB_LOAD_DFILE load PSG data (convert d.file to PSGLab format file)
%
% function[] = psglab_load_dfile(dfile_name, path_active, options, global_vars)
%
% dfile_name: filename definiton
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function [channel,tag_pos,tag_type,channel_name,fsamp,nchan,nsamp,time_abs] = psglab_load_dfile_one_channel
(name_file, channel_number)
%PSGLAB_LOAD_DFILE_ONE_CHANNEL converts BrainScope file format (one channel) to matlab matrix representation
%
% function [channel,tag_pos,tag_type,channel_name,fsamp,nchan,nsamp,time_abs]=psglab_load_dfile_one_channel
(name_file, channel_number)

function [] = psglab_load_grf()
%PSGLAB_LOAD_GRF load PSG data (convert grf file to PSGLab format file)
%
% function [] = psglab_load_grf()

function[] = psglab_read_gsr(filename_gsr, path_active, global_vars)
%PSGLAB_LOAD_GSR load PSG data (convert GSR file to PSGLab format file)
%
% function[] = psglab_read_gsr(filename_gsr, path_active, global_vars)
%
% filename_gsr: filename definiton
% path_active: path for PSG data directory
% global_vars: global variables definition

function[] = psglab_load_int(filename, path_active)
%PSGLAB_LOAD_INT load PSG data (convert binary file format to PSGLab format file)
%
% function[] = psglab_load_int(filename, path_active)
%
% filename: filename definiton
% path_active: path for PSG data directory

function[] = psglab_load_timecodes(path_active, options, global_vars)
%PSGLAB_LOAD_TIMECODES load time-codes definition (convert it to PSGLab format file)
%
% function[] = psglab_load_timecodes(path_active, options, global_vars)
%
% filename_gsr: filename definiton
% path_active: path for PSG data directory
% global_vars: global variables definition

function[] = psglab_load_vk(path)
%PSGLAB_LOAD_VK load PSG data (convert specific data from V.K. to PSGLAB format file)
%
% function[] = psglab_load_vk(path)

function[data] = psglab_moving_filter(data, filter_type, window_lenght)
%PSGLAB_MOVING_FILTER - moving average filter
%
% function[data] = psglab_moving_filter(data, filter_type, window_lenght)
%
% data: input data
% filter_type: filter type (mean, std,...)
% window_lenght: lennght of window for computing

function[] = psglab_change_amplitude(path_active, channels, mcoef, global_vars)
%PSGLAB_CHANGE_AMPLITUDE - change amplitude scale
%
% function[] = psglab_change_amplitude(path_active, channels, mcoef, global_vars)
%
% path_active: path for PSG data directory
% channels: active channels indexes
% mcoef: amplitude coef (1 means no change)
% global_vars: global variables definition

function T_CT = psglab_mutual_information(M)
%PSGLAB_MUTUAL_INFORMATION - mutual information approach
%
% function T_CT = psglab_mutual_information(M)
%
% M: input vextors
% T_CT: mutual information coef.

function[filtered_signal] = psglab_notch_filter_50_hz(path_active, options)
%PSGLAB_NOTCH_FILTER - notch filter (50Hz)
%
% function[filtered_signal] = psglab_notch_filter_50_hz(path_active, options)
%
% path_active: path for PSG data directory
% options: input parameters definition

function [coordV] = psglab_pca(X)
%PSGLAB_PCA - Principal Component Analysis
%
% function [coordV] = psglab_pca(X)
%
% X: input vectors (features)
% coordV: output vectors (principal components)

function [Y reconErr] = psglab_pca_back(X, d)
%PSGLAB_PCA_BACK - Principal Component Analysis (backward projection)
%
% function [Y reconErr] = psglab_pca_back(X, d)
%
% X: input vectors (features)
% Y: output vectors (features)
% d: number of components
% reconErr: error

function[] = psglab_resample(path_active, options, global_vars);
%PSGLAB_RESAMPLE - PSG signals resampling
%
% function[] = function[] = psglab_resample(path_active, options, global_vars);
%
% path_active: path for PSG data directory
% options: input parameters definition
% options.channels: [X X X]; [] for all channels
% global_vars: global variables definition

% function[] = psglab_RL_powers_compute()
%PSGLAB_RL_POWER_COMPUTE - compute specific features: (R-L)/(R+L) powers
%
% % function[] = psglab_RL_powers_compute()

function[] = psglab_save_ascii(file_path, data, precision)
%PSGLAB_SAVE_ASCII - export data to asci format
%
% function[] = psglab_save_ascii(file_path, data, precision)
%
% path_active: path for PSG data directory
% data: data for saving
% precision: precision definition (e.g. '%2.2f')

function[] = psglab_segmentation_adaptive(path, options, channel, global_vars)
%PSGLAB_SEGMENTATION_ADAPTIVE - adaptive segmnentation
%
% function[] = function[] = psglab_segmentation_adaptive(path, options, channel, global_vars)
%
% path: path for PSG data directory
% options: input parameters definition
% options.lengt [s]: (options.lengt == -1) -> whole signal processing
% channel: active channel ('channel' = 0) -> all available channels
% global_vars: global variables definition

function[] = psglab_segmentation_constant(path, options, channel, global_vars)
%PSGLAB_SEGMENTATION_CONSTANT - constant segmnentation
%
% function[] = psglab_segmentation_constant(path, options, channel, global_vars)
%
% path: path for PSG data directory
% options: input parameters definition
% options.lengt [s]: (options.lengt == -1) -> whole signal processing
% channel: active channel ('channel' = 0) -> all available channels
% global_vars: global variables definition

function[] = psglab_segmentation_from_tags(path, options, channel, global_vars)
%PSGLAB_SEGMENTATION_FROM_TAGS - segmnentation derived from position of tags
%
% function[] = psglab_segmentation_from_tags(path, options, channel, global_vars)
%
% path: path for PSG data directory
% options: input parameters definition
% channel: active channel ('channel' = 0) -> all available channels
% global_vars: global variables definition

%function[] = psglab_set_marks(path)
%PSGLAB_SET_MARKS - marks setting (file for psglab_run.m)
%
% %function[] = psglab_set_marks(path)
%
% path: path for PSG data directory

function[] = psglab_show_2d_maps(path_active, options, global_vars);
%PSGLAB_SHOW_2D_MAPS - visualization of 2D EEG mapping results
%
% function[] = psglab_show_2d_maps(path_active, options, global_vars);
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function [] = psglab_show_classification(path_active, options, global_vars)
%PSGLAB_SHOW_CLASSIFICATION - visualization of classification results
%
% function [] = psglab_show_classification(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_show_clusters_final(path_active, options, global_vars)
%PSGLAB_SHOW_CLUSTERS_FINAL - visualization of clustering results
%
% function[] = psglab_show_clusters_final(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_show_clusters_individual(path_active, options, global_vars)
%PSGLAB_SHOW_CLUSTERS_INDIVIDUAL - visualization of clustering results
%
% function[] = psglab_show_clusters_individual(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_show_clusters_type(path_active, options, global_vars)
%PSGLAB_SHOW_CLUSTERS_TYPE - visualization of clustering results
%
% function[] = psglab_show_clusters_type(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_show_coherence_or_correlation(path_active, options, global_vars)
%PSGLAB_SHOW_COHERENCE_OR_CORRELATION - visualization of coherence/correlation results
%
% function[] = psglab_show_coherence_or_correlation(path_active, options,
% global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_show_expert_classification(options, global_vars)
%PSGLAB_SHOW_EXPERT_CLASSIFICATION
%
% function[] = psglab_show_expert_classification(options, global_vars)
%
% options: input parameters definition
% global_vars: global variables definition

function[] = psglab_show_features(path_active, options, global_vars)
%PSGLAB_SHOW_FEATURES - visualization of final features
%
% function[] = psglab_show_features(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

psglab_show_notch_filter_param:
%PSGLAB_SHOW_NOTCH_FILTER_PARAM - show notch filter param

psglab_show_pca_component:
%PSGLAB_SHOW_PCA_COMPONENT - show results f PCA

function[] = psglab_show_signal(path, options, global_vars)
%PSGLAB_SHOW_SIGNAL - show PSG signals
%
% function[] = psglab_show_signal(path, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function [main_matrix] = skoci(c,l,broj,talasic,divide_low_bands)
%PSGLAB_ file for psglab_features_default.m
%
% function [main_matrix] = skoci(c,l,broj,talasic)

function[] = psglab_spectrogram(path_active, options, global_vars)
%PSGLAB_SPECTROGRAM - spectrogram computing
%
% function[] = psglab_spectrogram(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition

function[string_equal] = psglab_string_equal(str1, str2)
%PSGLAB_SRING_EQUAL - two strings comparing
%
% function[string_equal] = psglab_string_equal(str1, str2)
%
% str1, str2: input two strings

function[time_num] = psglab_time_to_sample(time_str, fsamp)
%PSGLAB_TIME_TO_SAMPLES convert string to number of samples
%
% function[time_num] = psglab_time_to_sample(time_str, fsamp)
%
% USING:
% psglab_time_to_sample('03', 128) // means 00:00:03
% psglab_time_to_sample('02:03', 128) // means 00:02:03
% psglab_time_to_sample('01:02:03', 128)

function[] = psglab_verify_expert_classification(path_active, options, global_vars)
%PSGLAB_VERIFY_EXPERT_CLASSIFICATION PSG (verify expert classification file)
%
% function[] = psglab_verify_expert_classification(path_active, options, global_vars)
%
% path_active: path for PSG data directory
% options: input parameters definition
% global_vars: global variables definition