Skip to Content

ByteSight: A Novel Handheld Field Tool that Rapidly Identifies Disease-carrying Mosquitoes

Team Members:
  • Lindsay Pierle
  • Amara Aarif
  • Rebecca Rosenberg
  • Robert Breidenstein
  • Zachary Zarubin
  • Dr. Soumyadipta Acharya MD, MSE, PhD
  • Monet Slinowsky, MSE


Malaria is a vector-borne disease, in which the malaria parasite is transmitted to humans through the bite of a female Anopheles mosquito. Despite investments of $2 billion per year, there were still 228 million cases of malaria in 2018, resulting in over 400,000 deaths. The most effective way to fight malaria is to eliminate malaria-carrying mosquitos. To accomplish this, vector control programs must know exactly what types of mosquitos are in a local area to effectively limit mosquito populations each species has its own behaviors, biting preferences, and insecticide resistance. Vector surveillance involves monitoring the density and distribution of malaria-carrying mosquitoes and is crucial for efficient distribution of limited species-specific control methods.

Species are currently identified from their discrete morphological characteristics which can take up to 20 minutes for each mosquito. Due to a lack of qualified entomologists, 34-55% of mosquitoes are misidentified. Thus, results are slow and inaccurate. This can prevent decision-makers from having reliable real-time data to inform their vector control decisions.

Our solution is a handheld field tool that uses a computer vision algorithm to identify mosquito species. The solution consists of two parts: a Cloud-based classification algorithm and a hardware setup to standardize optics and lighting.

Read the Johns Hopkins University privacy statement here.