Early Detection of Grain Spoilage and Contamination Using Hybrid NIR-E-Nose Systems with Machine Learning

This project explores the feasibility of using a hybrid sensing system that combines Near-Infrared Spectroscopy (NIR) and Electronic Nose (E-Nose) technologies, enhanced by machine learning, to detect early signs of spoilage and contamination in stored grains. By analyzing changes in grain structure and gas emissions, the study contributes to ongoing research on reliable, non-destructive, and timely solutions for monitoring grain quality during storage. Such systems can help reduce post-harvest losses, support food safety and sustainability, and improve decision-making in grain handling and storage operations.

Faculty Supervisor:

Mohammad Nadimi

Student:

Partner:

University of Barcelona

Discipline:

Engineering

Sector:

Education

University:

University of Manitoba

Program: