Mosquitoes communicate with the sound of their wingbeat. In many species, males and females mating try to match each other's tone, and if they are not able to do so—sometimes the female is considerably bigger than the male—they will meet at a common harmonic.
We can use this sound and its components, for example its strongest frequency and its temporal signature, to recognise the presence of a mosquito and determine to which species it belongs. This plot shows the spectral components of the wingbeat of 500 different specimens belonging to four different classes, four species plus one species with males and females considered separately.
In order to automate this process, we are developing a set of machine learning algorithms that take a mosquito recording, analyse its features and use these to classify the signal and determine the most likely species that may have generated it. Many challenges lie in the detection and classification of these sounds, in particular the fact that mosquitoes are inherently quiet and that the characteristics of their sounds largely vary with the size of the individual, its age, the temperature and humidity of the environment and many other factors.
These algorithms can then be deployed in a cheap, portable device that can record sounds and analyse them in real time. Smartphones are ideal platforms because they are equipped with a wide range of sensors, as well as being internet-connected, which enables continuous data transfer. Where a low-power device is required to maintain continuous operation, static loggers can be deployed, for example in high-risk places such as a bed-side table, where the presence of a person and a potentially a light source would act as an attractor for mosquitoes. For animals, these loggers can take the form of a cattle tag, a device attached to the animal and capable of continuous monitoring.