We were in EUSIPCO 2016 conference in Budapest to present our work on Blind Source Separation with Approximate Joint Diagonalization.
We shared the idea that using several data models simultaneously can improve the robustness of the data mining. Our composite model was used to discriminate Event-Related Potential sources from background brain activity with low resolution EEG which is known to be challenging.
I have presented a poster which is available (pdf).
The article will be available in conference the proceedings, meanwhile you can find a preprint on HALpage.
Last but not least, the code is available on GitHub with simulated data.