Implementing artificial intelligence to pest detection using a newly developed low-cost electronic nose (e-nose) and machine learning modelling
This project aims to test an artificial intelligence (AI) detection system to detect pests in different grain crops.
Technologies involve the use of a low-cost, wireless, and portable electronic nose to detect and identify the volatile compounds and specific gases produced by different pests (insects) validated using state of the art gas chromatography-mass spectrometers (GCMS) for calibration.
This integrated sensor system, along with the use of machine learning modelling (ML), will allow applying timely pest management techniques to avoid crop damages or major losses.
- Associate Professor Ranjith R Unnithan, Department of Electrical and Electronic Engineering, School of Engineering, University of Melbourne
- Funded by: GRDC - Australian Pest Innovation Program
- Grant number: 2062671
- Funding amount: $33,138
Associate Professor Sigfredo Fuentes