System and Method for the Analysis and Transmission of Data, Images, and Video Related to the Identification of Mosquito Specimens

Unmet Need
A number of governmental and non-governmental organizations closely monitor mosquito population dynamics due to the threat of mosquito-borne diseases, including malaria and viruses responsible for yellow fever, dengue fever, and Zika. Current mosquito surveillance generally involves the placement and collection of traps spread across a particular region. The insect samples are then tested in a laboratory to determine what types of mosquitoes were caught, the diseases associated with them, and if the insect population is expanding or shrinking. This type of work is remarkably resource and time intensive, as researchers need to physically place and collect each trap. Moreover, this manual sampling approach produces large temporal gaps in the population dynamics data and allows potentially dangerous changes to be overlooked or detected late.
 
Technology Overview
Johns Hopkins researchers have developed a mobile platform capable of capturing, analyzing, and transmitting data related to mosquito populations in a desired area. Once placed, this device lures mosquitoes into a trap where they are immobilized and a camera can image the insects. The researchers used machine-learning approaches to train the camera software to identify different types of mosquitoes. The platform wirelessly transmits data to allow for real-time analysis of mosquito populations. This approach saves countless hours and resources spent manually placing, checking, and replacing traps across a region and eliminates potentially dangerous time gaps in the data set.
 
Stage of development:
Prototype devices and software are under development.

Category(s):