Challenge

Les dates du congrès ont changé mais le challenge est toujours d'actualité. Vous pouvez donc toujours travailler sur vos approches jusqu'au 30 mai 2022 !

For the 2022 challenge, one parameter has to be predicted. The CALIBRATION and the VALIDATION sets contain 500 and 32000 spectra respectively. The CAL set contains spectra of wheat flours scanned in reflectance mode between 1100 and 2498 nm on a classical spectrometer. The VAL spectra have been extracted from hyperspectral images with blocks of 20 x 20 pixels for 80 samples. The Y values are in column A in the CAL sheet of the provided Excel file.

The goal is to predict accurately the Y values of the images using the CAL set.

The criterion to classify the results will be the R2 on the VAL set. 

The participants are invited to send their results (1 solution and 1 vector of 80 values in TXT or Excel) to Pierre Dardenne at dardennepaj@gmail.com  by the Monday 30th of May midnight. The participants will join a short PPT or DOC file with their methodology. The participants with the best results will be asked to present their results during the meeting in 5-10 minutes depending of the number of answers.

The data can be downloaded here : https://nextcloud.univ-lille.fr/index.php/s/9kyjKf45ADjePm4

Good luck.

P. Dardenne.

We thank CRAW (Vincent Baeten and Juan-Antonio Fernandez-Pierna) the provider of the data