HumBug: a new smartphone tool in fight against malaria using acoustic sounds and machine learning

Mosquitoes are responsible for over one billion cases of disease and over one million deaths each year. Malaria alone kills more than 400,000 people each year (WHO, 2019), and viruses carried by mosquitoes, such as yellow fever, dengue, chikungunya and more recently zika, are spreading and increasingly impacting on human health.

Traditional mosquito survey methods such as human landing catches (where the person conducting the survey uses themselves as bait to attract the mosquitoes) are time-consuming, expensive, spatially limited and put the surveyor at risk of catching the diseases they are trying to prevent. Consequently, many mosquito distribution models that map the range of these insects rely on small quantities of poorly distributed occurrence data. The data produced during mosquito surveillance are needed to identify emerging insecticide resistance, facilitate effective and evidence-led insecticide intervention programmes as well as model current and future vector-borne disease transmission. There is therefore an urgent need to develop new mosquito survey methods that can provide real-time species-specific occurrence and abundance data without human risk.

A multidisciplinary group of academics from the University of Oxford have developed HumBug, a novel mosquito survey tool that transforms a budget smartphone into a sensor that detects and identifies host-seeking mosquitoes using the acoustic signature of their flight tone.

HumBug 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 and can be used on other wearable smart devices as well as low-energy acoustic loggers. The sensor records the time and location, along with the mosquito flight tone and uploads the data to a central server where the species are identified using a suite of algorithms.

HumBug was originally funded via the Google Impact Award and Orchid  (in collaboration with Royal Botanic Gardens, Kew). We are now delighted to announce new funding awarded from the Bill and Melinda Gates Foundation allowing us to further develop and demonstrate this innovative system in selected field sites within Tanzania and the DRC.

Working with our established partners in Ifakara Health Institute (Tanzania) and the School of Public Health at the University of Kinshasa (Democratic Republic of Congo), we will test HumBug in rural communities to provide high quality, real-time data on the diversity, distribution and abundance of malaria transmitting mosquitoes. Combining these data with environmental variables from remote sensing satellite data, will also allow us to create dynamic real-time heat maps of their distribution, providing information to i) healthcare practitioners to better target mosquito control methods, ii) health policymakers to enhance more effective intervention policies and, iii) the academic community, providing unprecedented levels of occurrence, behavioural and ecological mosquito data.