Machine Learning Algorithm Detects and Identifies Mosquitoes from Their Buzz

Updated: Sep 16, 2018

As you know, computer science and artificial intelligent is changing the world, so as the world of mosquito control: researchers at Oxford University have developed a mosquito early warning system that raises the alarm when the insects are near by detecting the whine of their wing beats. What's even more interesting, the app is able to identify the species of the mosquitoes based on the buzzing sound's audio signature, which helps to prevent mosquito-borne diseases since certain mosquito species carry certain kinds of diseases.

Audio Signature of Different Mosquito species
Audio Signature of Different Mosquito Species, from

To build the early warning system, the Oxford team recorded mosquitoes in the lab and gathered more audio signatures from the US Centers for Disease Control and Prevention, an army research unit in Kenya and scientists working in the forests of Thailand. Beyond detecting mosquitoes and identifying their species, the early warning system could build up real-time maps of mosquito populations, and scientists in the field could identify mosquitoes more easily.

Now, you can help this project by participating in the the Humbug project. To improve the machine learning algorithms, the research team needs huge amounts of flight tone data to train and refine the algorithm. When a flying mosquito is recorded, the sound of its beating wings is relatively quiet and can be lost within any background noise. As such, help is needed to identify the snippet containing the actual mosquito buzz. To participate, all you need to do is to listen to short audio clips and report whether you hear a mosquito sound. See the video below for details.

Click here to read the original post from The Guardian Journal.