MAFAT WiFi Challenge has recently ended. This was the third competition in the MAFAT Challenge series. The competition focused on detecting and counting human presence with WiFi RSSI data.
We've had more than 450 registered participants in and more than 2,000 submissions. During the competition, participants have received a training data set containing WiFi RSSI segments, labeled as either empty or occupied room. Participants trained their machine learning predictive models based on the training data, and were asked to make predictions for this classification task on untagged data (the test set).
After the private test phase has come to its conclusion, the participants' submissions were evaluated against the true labels of the private test set (labels that were unknown to the participants). Results are available under the results tab.
Since the competition ended, we have been evaluating the submissions of the leaders and verifying their prize-winning eligibility.
Track 1 Leaderboard:
Track 2 Leaderboard:
Track 1 first place & Track 2 second place prize winner – Harel Rom
We are delighted to formally announce Harel Rom as the track 1 competition first place winner and track 2 second place winner! He has put a lot of effort and creativity into this challenge, and has passed all our formal and technical eligibility tests. If you want to study his technical approach in this challenge, take a look at this blog post.
Track 2 first place & Track 1 second place prize winner – TrueFit
We would like to congratulate TrueFit and formally announce him as the track 2 competition first place winner and track 1 second place winner! He has shown a lot of great skill and has passed all our formal and technical eligibility tests. His technical approach to this challenge is described in the following blog post.