We are pleased to announce the winners of the different tests of the landscape contest, which took place on Aug, 22 in Istanbul.

Champion of the Offline Test
The winner is… Joaquín Derrac, Salvador García, and Francisco Herrera

Champion of the Real-Time Test
The winner is… Joaquín Derrac, Salvador García, and Francisco Herrera

Champion of the Neighborhood Dominance Test
The winner is… Robert P.W. Duin, Marco Loog, Elzbieta Pekalska, and David M.J. Tax

In addition, we included two work awards:

Offline Training
for… Robert P.W. Duin, Marco Loog, Elzbieta Pekalska, and David M.J. Tax

Perseverance in Participation
for… Luiz Otavio Vilas Boas Oliveira and Isabela Neves Drummond

Many congratulations and thank you!

The deadline has been extended until June, 1.

Please note that there is a major change in the submission.
Due to a LNCS publication, contestants have to submit a 10 page paper explaining their method and results.

New templates are available at the submission section.

1. LNCS publication
Contestants should submit a paper (10-pages, LNCS format) explaining their method and results.

2. Oral and poster sessions
Oral and poster sessions will take place on 22 August Sunday prior to ICPR.

3. Registration fee
If contestants want to assure that their paper is included in the LNCS volume, at least one of the authors should be registered to the contests by paying full registration fee (not student fee) by 8 June.

Some more days! Deadline was extended until May, 26.

Good luck!

Icke points out that seems like the test arff files in S2 directory have a problem. I can not open them using WEKA.

Icke is right. You cannot open test data sets with Weka. We removed the labels because you have to give us the right labeling. We decided to maintain the Weka format just to indicate the labels that you have to use for each problem.

John and Tim ask for some benchmark results… Why not?

In the TrainingAccuracy.txt you will find some guiding results.

Thanks a lot for your interest!

Sulabh was wondering whether there is any sort of dependability between the Dn relations and the ‘pima_diabetes’ ones and…

Yes, Pima Indians diabetes was used to generate these data sets… BUT, it is not the only one. Actually we used a combination of data sets, that’s why we do not recommend using this problem to build any hypothesis.

We request participants to register by sending an e-mail to the contest organizers. Registered participants will be subscribed to the mailing-list to receive updated information. In the e-mail, please specify: team name, team members, members’ institution.

Contest participants are allowed to use any type of technique. However, we highly encourage and appreciate the use of novel algorithms.

We are planning to have a day workshop during the ICPR 2010, so that participants will be able to present and discuss their results. Hope to see you there!

Please contact the organizers for further information.

Classifier domains of competence: The landscape contest is a research competition aimed at finding out the relation between data complexity and the performance of learners. Comparing your techniques to those of other participants may contribute to enrich our understanding of the behavior of machine learning techniques and open further research lines.

The contest will take place on August 22, during the 20th International Conference on Pattern Recognition (ICPR 2010) at Istanbul, Turkey.

We encourage everyone to participate and share with us your work!

ICPR 2010 is the twentieth conference of the International Association for Pattern Recognition (IAPR).

ICPR 2010 will be an international forum for discussions on recent advances in the fields of Computer Vision; Pattern Recognition and Machine Learning; Signal, Speech, Image and Video Processing; Biometrics and Human Computer Interaction; Multimedia and Document Analysis, Processing and Retrieval; Medical Imaging and Visualization.

ICPR 2010 will be held during August 23-26, 2010 at the Istanbul Convention & Exhibition Centre (ICEC), Istanbul, Turkey.