Hi @masorx ,
Thank you for the extension of round 2 !
However, the challenge page seems to be not properly parametrized:
- Team creation is frozen
- In your message, it is said that the required coverage is reduced to 70%. However, a recent submission with a 79% coverage from @sconfina was rejected with the message “Less than 90% coverage”.
Maybe @shivam and the aicrowd team can help fixing this.
Thank you for your help !
PS: I am not participating, I am just supervising a team of students.
timeAtServer is a date in seconds from 0 to 3600 as we are working with one hour of data, 0 being the first entry in the file. I do not know exactly how this date is computed.
The timestamps are the dates (in nanoseconds) at which different receivers receive the same message. We do not have the date at which the aircraft has emitted the message.
Calling it “overfitting challenge” is a bit strong. With a total of six submission one week ago, I already was at 25.635. So I do not believe that the whole challenge was about over-fitting.
That being said, if you use it to describe the last competition hours, I totally agree with you.
As a feedback, I think the limit of 100 submissions a day was way too high. On the last day of the competition, I was basically fine-tuning my algorithms using the online test set as a validation set. This might also be the case for the other top 3 participants who also made a lot of submissions during the last day.
This is not satisfactory:
_for the organizers, the fine-tuned algortihms might overfit the online test set;
_for the participants, this incentivize them to perform a boring task (fine-tune using the online test set as a validation set) till the very end of the competition. With a limit of only 5 submissions, I would have done my 5 submissions and do something else of my day. But, here, the possibility to submit as many files as I want pushed me to fully use this so I would regret nothing.
For the next round, I think a hidden test set would be the best, if not possible a limit of 5 submissions per day would be good.
This is just my humble opinion, this was my first competition and maybe other participants feel different about it.
PS: That being said, I enjoyed participating this competition and I would like to thank all the people organizing and participating this competition, the final was tense/exciting and I learned a lot about multi-lateration!
I doubt it. I comply with the rules of the competition. I am not affiliated with the OpenSky Network or the CYD Campus.
Working with ADS-B data is a very common thing. Just looking at the names on the leaderboard, I could point at least 7 persons who have experience with ADS-B data.
In addition, again, the nanoseconds timestamps from several receivers (which are central in this competition) are not included in usual ADS-B data.
Dear Sergei Markochev,
Concerning my results at the first attempt, we have 7 training/test sets, so plenty of ressources to tweak and tune our models. I started to have good results on these test sets two weeks ago but I did not make a submission. I felt like it would hint my opponents that a ~50m accuracy would be achievable. As the competition is soon ending, I made a submission just to know where I was.
Since 2018, I have been working with ADS-B data provided by OpenSky Network. As it was pure ADS-B data, these data did not contain any “nanosecond receiving date” from several receivers. Again, my research work was only on climbing data with consolidated ADS-B data, not nanoseconds timestamps from several receivers.
Concerning my links with OpenSky Network, I applied to get ADS-B data in 2017 on their website https://opensky-network.org/ like anyone can or could. I only exchanged a few emails with OpenSky staff, mostly regarding the exact meaning of the variables inside the data they shared with me. I think a lot of researchers are in such a case, dozens, maybe a hundred.
Concerning my eligibility, it is up to the organizers to decide. Should they rule I am not eligible, I would accept their decision but I worked dozens of hours on this competition like anyone participating in this competition.