Monday, 28 April 2014

DecMeg2014 data analysis competition

Versione stampabile

Understanding how the human brain works is a primary goal in neuroscience research. Non-invasive functional neuroimaging techniques, such as magnetoencephalography (MEG), are able to capture the brain activity as multiple timeseries. When a subject is presented a stimulus and the concurrent brain activity is recorded, the relation between the pattern of recorded signal and the category of the stimulus may provide insights on the underlying mental process. Among the approaches to analyse the relation between brain activity and stimuli, the one based on predicting the stimulus from the concurrent brain recording is called brain decoding.

The goal of this competition is brain decoding across subjects: a large number of MEG recordings from multiple subjects, together with the respective category of stimulus, are available as train set, while the test set comprises MEG recordings from a different set of subjects. Because of the variability across subjects in brain anatomy and in the patterns of brain activity, a certain degree of difference is expected between the data of different subjects and thus between the train set and the test set. 

This competition is associated with the the 19th International Conference on Biomagnetism, Biomag 2014, Halifax (Canada), August 24-28, 2014. 

The competition begins: April 21st, 2014.
The competition ends: July 27th, 2014.

Prizes: 1st 3,000 USD,  2nd 1,500 USD, 3rd 500 USD. 

Organizers: Emanuele Olivetti, Seyed Mostafa Kia and Paolo Avesani (NeuroInformatics Lab, Bruno Kessler Foundation and University of Trento, IT), e-mail: decmeg2014 [at] list.fbk.eu.">decmeg2014 [at] list.fbk.eu.

The awards of this competition are funded by Elekta Oy, MEG International Services Ltd (MISL), Fondazione Bruno Kessler, and Besa. We would also like to thank Daniel Wakeman (Martinos Center, MGH, USA), Richard Henson (MRC/CBU, Cambridge, UK), Ole Jensen (Donders Institute, NL), Nathan Weisz (University of Trento, IT) and
Alexandre Gramfort (Telecom ParisTech, CNRS, CEA / Neurospin) for their contributions in preparing this competition.

Relevant links:
- competition website: https://www.kaggle.com/c/decoding-the-human-brain
- Biomag 2014: http://www.biomag2014.org
- NeuroInformatics Lab: http://nilab.fbk.eu
- Elekta Oy: http://www.elekta.com
- MISL (CTF MEG): http://www.ctfmeg.com
- Fondazione Bruno Kessler: http://www.fbk.eu
- Besa GmbH: http://www.besa.de