The training dataset contains 80 labeled instances (54 non-meteors and 26
meteors
). The test dataset has 42 unlabeled instances (27 non-meteors and 15
meteors
). Meteors are labeled as 1 and non-meteors are labeled as 0 (the class is in the last column of the dataset). The train and test datasets contain all features extracted from the images, while the zip file DatasetPerFeature.zip contains the training and testing partitions separated according to each type of characteristic extracted from the images.
The evaluation metric for this competition is the log-loss. Therefore, the submissions must include probabilities for each class.
Deadline
The submissions will be closed on September 18th, 2017. Therefore, the final results will be based on the solutions posted until September 18th, 2017. Please note that the system will still be able to receive submissions after this deadline, but they will be not taken into account for computing the final results.
Award Session
As this competition is part of the joint activities of the 2017 editions of the Brazilian Conference on Intelligent Systems (BRACIS), the Brazilian Symposium on Databases (SBBD) and the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe), the top three teams will be invited to present their solutions at a competition award session, on October 3rd, 2017 (18-19 hs). The actual final positions of the ranking will be disclosed during the conference dinner.
Submission Format
Submission files should contain three columns: Id,
Prob1
and Prob2. Id should give the identification of the example (some Ids correspond to training examples and others are from the test examples), as indicated by the numbers in the first column of the training and testing datasets. Prob1 is the probability towards class
others
, while Prob2 is the probability towards class
meteor
. Therefore, two probabilities should be provided per example.
For easy of reference, the Ids of the training examples are: 1, 2, 5, 8, 10, 11, 12, 15, 17, 19, 22, 24-32, 34, 36 to 45, 47, 48, 49, 52, 54, 57-62, 64, 66, 68, 70, 73, 74, 76-85, 87-90, 93, 95, 96, 98, 99, 100, 102, 104-107, 109, 110, 114, 117-120 and 122.
The Ids of the test examples are: 3, 4, 6, 7, 9, 13, 14, 16, 18, 20, 21, 23, 33, 35, 38, 46, 50, 51, 53, 55, 56, 63, 65, 67, 69, 71, 72, 75, 86, 91, 92, 94, 97, 101, 103, 108, 111, 112, 113, 115, 116, 121.
The file should contain a header and have the following format :
Id,Prob1,Prob2
3,0.9,0.1
4,0.8,0.3
etc.