DSFAS: EXPLORING A MACHINE LEARNING-DRIVEN APPROACH FOR MULTIPLEX DETECTION OF FOOD CONTAMINANTS BY SERS

The overall objectives of this multi-disciplinary project are to develop and integrate novel machine learning algorithms with surface-enhanced Raman spectroscopy (SERS) platform for multiplex detection and quantification of food contaminants in fresh produce with high accuracy. Specific objectives of this project are to synthesize SERS substrates; acquire SERS spectral data of different types and quantities of pesticides by SERS measurement; developattention-based deep networksfor qualitative and quantitative analysis of food contaminants; and validate the SERS coupled with deep learning methods for multiplex detection of pesticides in fresh produce.