Wovenware, Science Trust partner to build AI tech to detect Aedes Aegyptis mosquito
Editor’s Note: The information initially provided to News is my Business contained material errors that we are required to correct. Our apologies for the inconvenience.
The Puerto Rico Science, Technology & Research Trust has selected Wovenware Partners, a provider of Artificial Intelligence (AI)-based services and solutions, to develop a system to automate the identification and classification of the Aedes Aegyptis mosquito.
The project, supported by a $50 million grant from the Centers for Disease Control, is currently underway by the Trust’s Puerto Rico Vector Control Unit and seeks to gain an understanding of why many mosquitos have become immune to insecticides approved by the U.S. Food and Drug Administration.
“The talented research team within the PRVCU is committed to shedding light on the mosquito population and the impact of insecticides in preventing the outbreak of related diseases,” said Lucy Crespo, CEO of the Trust.
The purpose is to control the spread of the vector, or mosquito, that can infect people with diseases such as Zika, Dengue and Chikungunya across Puerto Rico, and ultimately nationwide. The other purpose of this labeling is to develop safe and more effective insecticides.
To achieve the goal, researchers have spread out across the island, capturing different mosquito species in traps; monitoring and testing them for viral presence and insecticide resistance; and labeling and classifying them.
To manually capture and classify thousands of mosquitos, across different areas in Puerto Rico is extremely time-intensive and requires specialized human resources, the nonprofit said.
Wovenware is creating an “advanced deep learning solution” to automate the time-consuming task.
Through its private crowd of data specialists, the company will identify and label thousands of images of mosquitos and data sets over the next three to six months and will use those images and data to train an algorithm to automatically identify and classify specific species.
By eliminating the manual classification process, the AI-based solution is projected to save the PRVCU months of work that can be used to more quickly analyze the findings and identify the root cause of resistance to insecticides, as well as disease spread and prevention routes.
“We support the valuable contributions of the Puerto Rico Science, Technology & Research Trust and its PRVCU, which is working tirelessly to address a serious mosquito problem in post-hurricane Puerto Rico,” said Christian González, CEO of Wovenware.
“This work has serious implications for controlling the spread of mosquito-borne illness across the nation. The project also underscores the impact AI-based technology can have when bright minds are augmented by smart technology to help solve some of the world’s most pressing challenges,” he said.
“Thanks to Wovenware’s support and deep expertise in AI technologies, we’re confident that our thorough field work and research will be bolstered by data-driven insights,” Crespo said.
In 2016, Puerto Rico registered 38,058 confirmed cases of Zika, Dengue and Chikungunya. Aedes Aegyptis is the vector, or mosquito type, that transmits those diseases.
These mosquitos need accumulated water to complete their lifecycle, so Hurricane María may have drastically increased their numbers, according to available data.
Since one of the easiest ways to reduce diseases carried by Aedes Aegyptis is by reducing mosquito breeding sites, their identification and classification is critical, project participants said.