<p>The proposed system utilizes an array of tin-oxide-based gas sensors and temperature &amp; humidity sensors to detect odors emitted by food items, capturing unique odor signatures associated with different stages of freshness and spoilage. The central data processing station pre-processes the sensor responses using signal pre-processing techniques like noise filtration, dimensionality reduction, and feature extraction to improve the quality of the data. The system then applies an artificial neural network model to classify food items into four freshness categories: fresh, may still be useful, not suitable for use, and completely spoiled. The system demonstrates high accuracy in distinguishing freshness levels across various perishable food types, including meat, fish, eggs, and dairy products, with 95%, 97%, 97% and 97% accuracy, respectively. The integration of machine learning with E-Nose technology offers a rapid, non-invasive, and scalable solution for real-time food quality assessment. By automating the assessment process, the framework minimizes human error, reduces operational costs, and enhances food safety compliance. This study demonstrates how intelligent sensing systems have the potential to revolutionize quality control within the food supply chain. This could have big effects on public health, reducing waste, and the long-term health of the industry. Future work includes optimizing sensor arrays for broader food categories and enhancing model explainability for better decision-making.</p>