Event Title

Identification of Vector Mosquitoes: A Field Implementation of Novel Hardware and AI Algorithm

Presenter Information

Brandon Wolfram
Estelle Toto Lobe

Loading...

Media is loading
 

Comments

Poster Presentation

Please select your campus affiliation

Tampa

Mentor Information

Dr. Sriram Chellappan

Description

Mosquito-borne diseases continue to be one of the leading causes of death globally. They arise from vector mosquitoes which can transmit various diseases such as malaria, yellow fever, dengue, etc. Vector-borne diseases account for 17% of all infectious diseases and affect millions of people around the world causing almost 3 million deaths annually as recorded by NASA. Critically, only a few hundred mosquito species (<1%) can transmit diseases to humans. Consequently, real-time identification of these species is essential to pest control agencies which have the goal of reducing and eventually eradicating such pernicious diseases. Therefore, an Artificial Intelligence (AI) algorithm integrated with novel trapping hardware has been developed to effectively identify vector mosquito species in real-time and enable targeted mosquito control. To create an environment for the AI system, a trap was developed which consists of an infrared sensor, an audio sensor, environmental sensors to record the surrounding environment, as well as a digital imaging chamber to capture the images required for the AI system. Mosquitoes are drawn to the trap using attractants, where the infrared sensors detect the presence of a mosquito. The mosquitoes' flight is then recorded using the audio sensor and infrared sensors, after which the insect is suctioned down the trap using an impeller fan to the cameras. The images of the mosquitoes are captured; genus and species are classified automatically via patented and patent-pending AI algorithms.

This document is currently not available here.

Share

COinS
 

Identification of Vector Mosquitoes: A Field Implementation of Novel Hardware and AI Algorithm

Mosquito-borne diseases continue to be one of the leading causes of death globally. They arise from vector mosquitoes which can transmit various diseases such as malaria, yellow fever, dengue, etc. Vector-borne diseases account for 17% of all infectious diseases and affect millions of people around the world causing almost 3 million deaths annually as recorded by NASA. Critically, only a few hundred mosquito species (<1%) can transmit diseases to humans. Consequently, real-time identification of these species is essential to pest control agencies which have the goal of reducing and eventually eradicating such pernicious diseases. Therefore, an Artificial Intelligence (AI) algorithm integrated with novel trapping hardware has been developed to effectively identify vector mosquito species in real-time and enable targeted mosquito control. To create an environment for the AI system, a trap was developed which consists of an infrared sensor, an audio sensor, environmental sensors to record the surrounding environment, as well as a digital imaging chamber to capture the images required for the AI system. Mosquitoes are drawn to the trap using attractants, where the infrared sensors detect the presence of a mosquito. The mosquitoes' flight is then recorded using the audio sensor and infrared sensors, after which the insect is suctioned down the trap using an impeller fan to the cameras. The images of the mosquitoes are captured; genus and species are classified automatically via patented and patent-pending AI algorithms.