This repository contains the supplementary material for the Time frequency Image article in the journal Knowledge based systems
The following reference should be cited whenever these scripts or functions are used: B. Boashash, H. Barki, S. Ouelha, Performance evaluation of time-frequency image feature sets for improved classification and Analysis of non-stationary signals: Application to Newborn EEG Seizure Detection, Knowledge-Based Systems, 2017.
This study was funded by grants from the ARC and QNRF NPRP 6-885-2-364.
The description of each file is inside the function itself. To reproduce the results in the aforementioned paper please run the script:
main_TFImageClassif_NewbornEEG
Please note that you can enable or disable the feature selection script as it is time-consuming. However all the algorithms are available and can be used to reproduce the results are in other applications.
Please note also that the TFDs are pre-computed to save time, they are in the folder called EEG.
Note also that the TFD can be computed using the TFSAP Toolbox. TFSAP Toolbox can be found using the following link: