Humbug

Using smartphones to record and identify mosquitoes by their flight tones

Mosquitoes are notoriously dangerous, responsible for over one billion cases of disease and around a million deaths each year. Malaria alone kills more than 400,000 people each year and viruses carried by mosquitoes, such as yellow fever, dengue and zika, are emerging, spreading and increasingly impacting on human health.

To tackle these crippling global diseases requires targeted control of their vector, the mosquito. This in turn relies upon detailed knowledge of the distribution, diversity and abundance of mosquitos in space and time. Current mosquito survey methods are time consuming, expensive, spatially limited and can put those conducting them at risk of catching the vector borne diseases they are trying to prevent. Consequently, there is an urgent need to find new, automated and reliable survey methods.

HumBug is our response. We have developed a new system to detect and identify different species of mosquitoes using the acoustic signature (sound) of their flight tones captured on a smartphone. By using sound to identify different species, this new system can generate unprecedented levels of urgently needed high-quality, spatially accurate mosquito occurrence data without incurring any risk to those conducting the surveys. It is low cost, running on budget smartphones using our MozzWear app. The app captures and records the mosquito flight tones employing the inbuilt phone microphone as an acoustic sensor. The recordings, along with the time and location, are uploaded by the app to a central server where the species is identified using a suite of algorithms that distinguish between species according to their acoustic signature.

We deploy our sensor (a budget smartphone running our MozzWear App) into adapted bednets (HumBug Nets). The flight tone of the host-seeking mosquito is recorded as the mosquito tries to access the person inside the net. The acoustic data is uploaded to the HumBug server where it passes through an algorithm pipeline that detects mosquito flight tones from background, noise, removes sections of human speech and identifies the mosquito species. (The final steps are still under development): – the abundance and species information will be used in real time maps and all data passed back to the smartphone to the user.

Publications

Winifrida P. Mponzi​​​, Rinita Dam, ​​​​Dickson Msaky¹​​​​​, Yohana A. Mwalugelo, Marianne Sinka, Ivan Kiskin​​​​​​, Eva Herreros-Moya³​​​​​​, Stephen Roberts, “Fighting against malaria is everyone’s concern”: A randomized control trial assessing the role of incentives for encouraging local communities to record and upload mosquito sounds using the MozzWear application (2024). Preprint https://doi.org/10.21203/rs.3.rs-3897618/v1

Dam, R., Mponzi, W., Msaky, D., Mwandyala, T., Kaindoa, E.W., Sinka, M.E., Kiskin, I., Herreros-Moya, E., Messina, J., Shah, S.G.S., Roberts, S., Willis, K.J., 2023: What incentives encourage local communities to collect and upload mosquito sound data by using smartphones? A mixed methods study in Tanzania. Global Health Research and Policy 8, 18 (2023). https://doi.org/10.1186/s41256-023-00298-y

Kiskin I., Sinka M., Cobb A.D., Rafique W., Wang L., Zilli D., Gutteridge B., Dam R., Marinos T., Li Y., Msaky D., Kaindoa E., Killeen G., Herreros-Moya E., Willis K.J., Roberts S.J., 2021: HumBugDB: A Large-scale Acoustic Mosquito Dataset. Preprint available on https://arxiv.org/abs/2110.07607

Kiskin I., Cobb A.D., Wang L., Sinka M., Willis K., Roberts S, 2021: Automatic Acoustic Mosquito Tagging with Bayesian Neural Networks. In ECML PKDD 2021: Machine Learning and Knowledge Discovery in Databases. https://doi.org/10.1007/978-3-030-86514-6_22.

Sinka M.E., Zilli D., Li Y., Kiskin I., Kirkham D., Rafique W., Wang L., Chan H., Gutteridge B., Herreros-Moya E., Portwood H., Roberts S., Willis K.J., 2021: HumBug – An Acoustic Mosquito Monitoring Tool for use on budget smartphones. In Methods in Ecology and Evolution June 2021. https://doi.org/10.1111/2041-210X.13663