A novel optical sensor system for the automatic classification of mosquitoes by genus and sex with high levels of accuracy

Abstract

Background: Every year, more than 700,000 people die from vector-borne diseases, mainly transmitted by mosqui‑ toes. Vector surveillance plays a major role in the control of these diseases and requires accurate and rapid taxo‑ nomical identifcation. New approaches to mosquito surveillance include the use of acoustic and optical sensors in combination with machine learning techniques to provide an automatic classifcation of mosquitoes based on their fight characteristics, including wingbeat frequency. The development and application of these methods could enable the remote monitoring of mosquito populations in the feld, which could lead to signifcant improvements in vector surveillance. Methods: A novel optical sensor prototype coupled to a commercial mosquito trap was tested in laboratory conditions for the automatic classifcation of mosquitoes by genus and sex. Recordings of > 4300 laboratory-reared mosquitoes of Aedes and Culex genera were made using the sensor. The chosen genera include mosquito species that have a major impact on public health in many parts of the world. Five features were extracted from each recording to form balanced datasets and used for the training and evaluation of fve diferent machine learning algorithms to achieve the best model for mosquito classifcation. Results: The best accuracy results achieved using machine learning were: 94.2% for genus classifcation, 99.4% for sex classifcation of Aedes, and 100% for sex classifcation of Culex. The best algorithms and features were deep neural network with spectrogram for genus classifcation and gradient boosting with Mel Frequency Cepstrum Coefcients among others for sex classifcation of either genus. Conclusions: To our knowledge, this is the frst time that a sensor coupled to a standard mosquito suction trap has provided automatic classifcation of mosquito genus and sex with high accuracy using a large number of unique samples with class balance. This system represents an improvement of the state of the art in mosquito surveillance and encourages future use of the sensor for remote, real-time characterization of mosquito populations.