The projects
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.
Figure 1: HumBug project workflow
We have now received funding from the Bill and Melinda Gates Foundation to take this project a step further and test the HumBug system in rural communities in Tanzania and the Democratic Republic of Congo. Working in collaboration with the Ifakara Health Institute and the Kinshasa School of Public Health we aim to:
- Conduct extensive field trials to compare and evaluate our methodology with other vector monitoring methods
- Establish the feasibility of using our system to monitor mosquitoes in data poor areas where it is difficult to conduct traditional surveys
- Integrate cell phone-based airtime or cash payments into the MozzWear app to facilitate community involvement in HumBug mosquito surveys
- Develop a web-based platform with vector occurrence and abundance data
Our ultimate goal is to provide high quality, real-time data on the diversity, distribution and abundance of mosquitoes for:
- Health care practitioners to better target mosquito control methods
- Health policymakers to enhance more effective intervention policies
- The academic community, providing unprecedented levels of occurrence, behavioural and ecological mosquito data
On these pages you can find more about this project, its people and our outputs. If you are interested in working with us, if you have data that you can share, or if you would like to know more about this research, please don't hesitate to contact us.
Enabling large-scale acoustic monitoring for invasive insect species in the UK
Invasive insect species have the potential to outcompete or predate native species and bring disease. As mobile devices increasingly support biodiversity monitoring, acoustic detection and identification of insects opens up a new avenue to expand the coverage of biodiversity monitoring in the UK. Such technology is ideally suited for surveillance of invasive species, where the species density is initially low, meaning surveillance effort can be costly and uncertain but still has to be balanced against the potential economic cost of successful invasion.
The Biodiversity Intactness Index (BII) ranks the United Kingdom in the lowest 12% of global countries [1] and the most recent “State of Nature” report shows the decline in biodiversity is ongoing, with birds, amphibians, reptiles and terrestrial mammals all showing significant decline. Habitat loss, intensive farming and climate change are cited as the biggest drivers but there are other risks as the world becomes more connected. Invasive species have the potential to outcompete or predate native species (e.g. the Asian Hornet, Vespa vetulina, Harlequin ladybird, Harmonia axyridis), expand their range unchecked by natural predators (e.g. Box tree moth, Cydalima perspectalis), and bring disease (e.g. the Asian tiger mosquito, Aedes albopictus)
Aims and objectives
Working with nationally and internationally recognised biodiversity experts and mosquito control experts (UK Centre for Ecology & Hydrology and Mosquito Control Service - Catalan Government), stakeholder representatives (the British Bee Keepers Association), and commercial partners (Mind Foundry, Aioi R&D Lab), the aim of this project is to create and demonstrate the effectiveness and efficiency of a mobile acoustic sensing system suitable for monitoring invasive species that threaten the UK’s biodiversity. We will leverage our experience in developing and deploying a mosquito species acoustic monitoring system in the HumBug project, to develop a general-purpose acoustic sensing system which can be tuned to specific invading species including the Asian tiger mosquito and Asian Hornet.
As a whole, the project embodies key technology advances including i) unified on-device machine learning model integration on smartphones across mobile operating systems; ii) improved data/model interoperability between the sensing system (i.e. the smartphone) and the cloud; and iii) trustworthy post-acquisition processing techniques with crowdsourced noisy acoustic data. The project will deliver new collaborations with stakeholders to understand their needs and test the capabilities of the system to increase its uptake, with demonstration through innovative pilot applications of acoustic sensing of invasive insect species (Asian tiger mosquitoes, Asian hornets).
Potential applications and benefits
The system will enhance the capabilities of environmental monitoring organisations in efficiently mapping the distribution of concerned species, facilitating the evaluation of the effectiveness of interventions for improving biodiversity. We envision that the project’s use cases will expand beyond the two pilot applications to significantly improve our ability to assess habitat connectivity and collective understanding of species distribution and movement at regional and national scales.