PSGLab is a Matlab toolbox for processing of polysomnographic (PSG) data.

PSG recording encompasses a set of heterogeneous biological signals recorded simultaneously. Electroencephalographic (EEG) signals, electrooculogram (EOG) and electromyogram (EMG) are important parts of this kind of recording. PSG recording may also include electrocardiogram (ECG), respiratory effort and respiratory airflow, blood oxygen saturation and temperature, as well as movement or body position.

This toolbox is released under the GNU General Public License. This is a copyleft license, which means you have the freedom to use, distribute and modify the code, but only on the condition that you must pass on this freedom.

PSGLab Features

PSGLab implements signal preprocessing, feature extraction, classification, cluster analysis and data visualization methods. PSGLab main features:

  1. Multiformat data importing/exporting
  2. Signal preprocessing (filtering, resampling, artifact rejection, isoline removing)
  3. Constant and adaptive segmentation
  4. Feature extraction (mainly EEG oriented features)
  5. Feature selection (mutual information approach, SFS)
  6. Correlation and coherence analysis
  7. Wavelet analysis
  8. Principal component analysis
  9. K-means clustering, Hierarchical clustering
  10. KNN and HMM classifiers
  11. Data visualization (2D EEG maps, hypnograms, spectrograms, clustering results visualization, etc.)

Extension planning:

  1. Extraction of other problem-oriented features
  2. Simple GUI
  3. Generality of used methods increasing
  4. Online processing support

Feedback instruments

We welcome all comments and suggestions. Comments can be sent via e-mail to

© 2010-2018 BioDat Research Group: All rights reserved | XHTML 1.0 Strict & CSS level 2.1