Intelligent Food Spoilage Detection System Using Machine Learning from AMTH Data

Food spoilage is a critical issue in the global food supply chain, leading to economic losses, increased food waste, and public health risks. This paper presents an intelligent food spoilage detection system using machine learning and AMTH-IoT sensor data, including temperature, humidity, carbon dioxide (CO₂) levels, and storage duration. A Multilayer Perceptron (MLP) classifier is trained to capture complex patterns associated with food deterioration. The model is deployed through a Flask-based web application that enables real-time prediction via a user-friendly interface. Experimental results demonstrate improved accuracy, precision, recall, and F1-score compared to conventional methods such as SVM. The system supports efficient decision-making in food storage and supply chain environments. The proposed framework provides a scalable, cost-effective solution for intelligent food quality monitoring, contributing to reduced food waste and enhanced food safety.