Our new paper at NeurIPS 2021!

HumBugDB: A Large-scale Acoustic Mosquito Dataset

We have reached a milestone publication to openly release research data of acoustic mosquito flight tones which we have been collecting with our collaborators for over five years. A preprint is available on https://arxiv.org/abs/2110.07607. Our paper has been accepted at the Thirty-fifth Conference on Neural Information Processing Systems 2021 with outstanding reviews. An oral presentation will be hosted at https://neurips.cc/ in December 2021. Stay tuned to our Twitter @OxHumBug for more details. 

You can access the entire database on https://zenodo.org/record/4904800.
State-of-the art Bayesian Neural Network code to a) detect mosquito events and b) classify mosquito species, based on this data is available on https://github.com/HumBug-Mosquito/HumBugDB.

This paper presents the first large-scale multi-species dataset of acoustic recordings of mosquitoes tracked continuously in free flight. We present 20 hours of audio recordings that we have expertly labelled and tagged precisely in time. Significantly, 18 hours of recordings contain annotations from 36 different species. A summary of the data collection sites is given below:

ivanmap