Freshness Monitoring of Broccoli Using Intelligent Electronic Nose Systems for Sustainability in Food Supply Chains

Reducing food waste and enhancing sustainability in food supply chains have become increasingly critical in the global food industry. Broccoli, known for its nutrient richness, is particularly vulnerable to spoilage due to environmental factors, which results in considerable food loss. To address this issue, this paper proposes an innovative and sustainable approach to predicting broccoli freshness using an electronic nose (E-nose) system. The E-nose, equipped with gas sensors, detects volatile organic compounds (VOCs) emitted by broccoli during spoilage. The sensor data was first analyzed using unsupervised clustering algorithms such as K-Means, Gaussian Mixture Model (GMM), and Spectral Clustering, to group the broccoli samples based on freshness levels. Following this, advanced machine learning (ML) and deep learning (DL) techniques were applied to classify the samples into specific freshness categories: fresh, half-spoiled, and spoiled. K-means clustering combined with the Long Short-Term Memory (LSTM) model achieved an accuracy of 99.46%. Furthermore, hyperparameter tuning (HPT) was employed to optimize the performance of the LSTM models, improving classification accuracy to 100%. The results illustrate the effectiveness of integrating E-nose technology with AI-driven techniques for real-time, scalable freshness monitoring. This system offers a promising solution for reducing food waste and promoting sustainability in the management of perishable produce within food supply chains.