Parkinson's disease (PD) is one of major diseases for people over the age of 60, and causes disorders of body motions due to the affected motor system. It is important to tackle PD because there are more than 6 million patients and 100k death in a year globally. Many neuroscience research works have been done by using mice as a model animal for investigating and understanding PD of humans. In this challenge, your task is to classify mice trajectories into normal or PD, provided training mice trajectories.
A normal or PD mouse moves freely in a box surrounded by black walls. A camera mounted above the box takes top-view movies in 30 fps. 2D coordinates of three points on the mouse (the tip of the nose, the point between the ears, the root of the tail) are tracked and recorded as trajectories using DeepLabCut.
The first video is a normal mouse, and the second is a PD mouse. Three points on the mouses are shown. These videos are not included in the dataset and this challenge is based on trajectory (i.e., 2D coordinates).
Grant-in-Aid for Scientific Research on Innovative Areas from 2016 to 2021
Navigation is a fundamental behavior of animals including human. In navigation, the following three functions are required: the acquisition of dynamically-changing information from external and internal environment, the choice of route and destination based on the information, and the behavioral regulation to reach the destination. We aim for systems science of bio-navigation to understand the "algorithms" for the navigation of animals. To this end, we bring together experts from control engineering, data science, animal ecology, and neuroscience, and jointly work on how to measure, analyze, understand, and verify bio-navigation.
By hosting a series of competitions "Animal Behavior Challenge (ABC2018)" "Human Behavior Challenge (HBC2018)" "Mouse Behavior Challenge (MBC2020)", we hope to boost our understanding the algorithms for animal navigation.
Please visit our website.
This challenge is governed by the general ChaLearn contest rules.
You may submit 5 submissions every day and 50 in total in the test-dev phase.
Submitted results are evaluated by the accuracy, widely used for binary classification problems.
It is 0 if all predictions are wrong, while 1 if perfect.
There are 1538 test trajectory, and classification results should be a 1538-line text file, which contains 0 (normal) or 1 (PD) for each of test trajectory.
Each line has the label of the corresponding test trajectory; that is, line 0 is the label of the test trajectory 0000.csv. There is no header line.
Predicted label is binary (character):
Here is an example:
================= 1 1 1 0 1 0 0 ... =================
The file name should be "test_prediction.csv", which should be zipped as a single zip file.
The zip file can have any name, but should contain a single file named "test_prediction.csv" without any folders.
You can create and check your submission zip file by using zip and unzip as follows:
$ zip yoursubmission.zip test_prediction.csv updating: test_prediction.csv (deflated 79%) $ unzip -l yoursubmission.zip Archive: yoursubmission.zip Length Date Time Name --------- ---------- ----- ---- 357417 03-22-2019 10:17 test_prediction.csv --------- ------- 357417 1 file
Classifying trajectories of mice into normal or PD
A single CSV file (0000.csv, 0001.csv, ...) contains a trajectory. The first line is a header, and following lines represent the information of the location of a mouse.
Float values are of the format %.01f, and fields are separated by a single comma.
Here is an example:
frame,top_x,top_y,ear_x,ear_y,tail_x,tail_y 0,342.0,402.3,342.4,374.3,324.4,305.4 1,325.4,407.3,331.9,379.3,326.0,320.8 2,321.4,409.1,327.7,379.3,328.2,321.9 3,314.3,410.7,324.0,379.0,329.9,323.7 ...
The training and test trajectories are different in length; training is long (15min) and unprocessed, while test is short (4 to 8 sec) and post-processed.
UPDATE 2020/Sep/1: Due to the pandemic of COVID-19, the following symposium has been cancelled. We are very sorry but the travel grant will not be given to winners, and we will PDF certificates to winners as a prize.
UPDATE: Due to the pandemic of COVID-19, the following symposium MAY be cancelled in future. In such case, unfortunately the travel grant will not be given to winners and we will PDF certificates to winners as a prize.
The winner will receive the following travel grant in addition to the winner certificate.
The first winner will receive
Note that
This challenge is governed by the general ChaLearn contest rules.
Mouse Behavior Challenge at github
Start: Dec. 1, 2019, 3 p.m.
Description: Submit your results on the test set. Show one of results to the leaderboard, which is used for the test-challenge phase.
Start: Aug. 31, 2020, 2:59 p.m.
Description: Final phase. you don't submit any results. Instead, the result shown in the leaderboard of the test-dev phase is used for the final evaluataion.
Sept. 1, 2020, 2:59 p.m.
You must be logged in to participate in competitions.
Sign In