Humbug Zooniverse: A Crowd-Sourced Acoustic Mosquito Dataset

Abstract

Mosquitoes are the only known vector of malaria, which leads to hundreds of thousands of deaths each year. Understanding the number and location of potential mosquito vectors is of paramount importance to aid the reduction of malaria transmission cases. In recent years, deep learning has become widely used for bioacoustic classification tasks. In order to enable further research applications in this field, we release a new dataset of mosquito audio recordings. With over a thousand contributors, we obtained 195,434 labels of two second duration, of which approximately 10 percent signify mosquito events. We present an example use of the dataset, in which we train a convolutional neural network on log-Mel features, showcasing the information content of the labels. We hope this will become a vital resource for those researching all aspects of malaria, and add to the existing audio datasets for bioacoustic detection and signal processing.

Emerging technologies revolutionise insect ecology and monitoring

“…Identification of species from their sounds is still limited by the size of the reference libraries, which are poorly developed for insects compared to those for vertebrates [40]. Currently, libraries are only sufficiently large in temperate regions for some terrestrial vocalising insect groups, and are largely lacking for other insect sounds (especially flight sounds) (but see [37]). Citizen science schemes could, however, help build these acoustic reference libraries [45].…”

“…Insect sounds may be sampled using stationary acoustic sensors or by mobile transects from cars or trains [33,34]. So far, these methods have mostly been applied to detect orthopterans and cicadas (Box 2), but have also been tested on freshwater insects [35,36] and bees, hornets, and mosquitoes based on their flight sounds [37,38].…”

HumBug – An Acoustic Mosquito Monitoring Tool for use on budget smartphones

“…(https://zenodo.org/record/4904800) (Kiskin 2021) . As acoustic data will be continually generated throughout this project, the database will continue to grow as we curate and add labelled flight tone…”

Detecting Aedes Aegypti Mosquitoes through Audio Classification with Convolutional Neural Networks

“…Staunton, Usher, Prachar, Ritchie, Snoad and Johnson (2019), in turn, collected wingbeat frequency data by measuring the Doppler shift of a reflected ultrasonic continuous wave signal. These investigations largely benefit from extensive datasets of mosquito wingbeat recording (Kiskin, Cobb, Wang and Roberts, 2020a), which often provide enough data for training artificial neural networks, or provide distinct audio features one can look for to identify mosquitoes.…”