
Code reproducing the experiments of the paper 'Joint time-vertex stationary
signal processing".

There are two main MATLAB scripts included.


1. experiment_JPSD_estimation.m
The code tests the accuracy of JPSD estimation methods (mode 'accuracy') shown
in Fig. 1 of the paper, as well as their computational complexity in machine
time (mode 'complexity') shown in Fig. 2.

2. experiment_recovery.m
The code tests recovery accuracy and generates the figures in Section VI B of
the paper. It is possible to choose the dataset (choices: molene, pems,
epidemic). In addition, the variable xaxis (miss, train) controls whether the
x-axis of the figure will be the percentage of signal entries hidden from the
algorithm, or the percentage of the total data used in training.


Note also: 
* The home directory should be at the same folder as this file
(with subdirectories /results, /utils, /data). 
* The first part of the code
takes a long time since it repeats all experiments. To just see the results,
set the variable replay to 1. In this latter case, you will need to have the
(bulky) mat files in your results/ folder.


Requirements: 
1. The latest version of the GSPBox, LTFAT, and UNLocBoX MATLAB toolboxes.
2. To save the figures you will need the export_fig matlab package.

 
Andreas Loukas and Nathanael Perraudin 
10 May 2017
