Mosquito Neural Netting: To identify the sound of a single mosquito

A complex new attack on mosquitoes, sort of, is outlined in this new study about identifying the sound of a single mosquito:

“Mosquito Detection with Neural Networks: The Buzz of Deep Learning,” Ivan Kiskin, Bernardo Pérez Orozco, Theo Windebank, Davide Zilli, Marianne Sinka, Kathy Willis, Stephen Roberts, arXiv:1705.05180, May 15, 2017.

The paper points out, especially, a limitation encountered in a previous attempt to enlist technology against mosquitoes:

“Chen et al. [6] attribute the stagnation of automated insect detection accuracy

to the mere use of acoustic devices, which are allegedly not capable of producing

a signal sufficiently clean to be classified correctly. As a consequence, they

replace microphones with pseudo-acoustic optical sensors, recording mosquito

wingbeat through a laser beam hitting a phototransistor array – a practice already

proposed by Moore et al. [22]. This technique however relies on the ability

to lure a mosquito through the laser beam.”

BONUS: A very different approach to battling mosquitoes is outlined in the NIH report “Novel insecticide blocks mosquitoes’ ability to urinate.”