Loading...
Quality Degradation And Pricing of Perishable Food Products
Alastal, Haya
Alastal, Haya
Files
35.232-2024.64a Haya Alastal.pdf
Adobe PDF, 1.94 MB
- Embargoed until 2026-10-12
Description
A Master of Science thesis in Engineering Systems Management by Haya Alastal entitled, “Quality Degradation and Pricing of Perishable Food Products”, submitted in December 2024. Thesis advisor is Dr. Malick Ndiaye. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).
Abstract
Under ideal conditions, the cold supply chain for food products operates seamlessly, ensuring the preservation of quality from production to the point of sale. This ideal scenario involves maintaining precise temperature controls and consistent monitoring at every stage of the supply chain to prevent deviations that could compromise the product's freshness, nutritional value, or safety at any stage. However, the perishable food products industry faces significant challenges in maintaining optimal quality throughout the supply chain. Existing methods for capturing quality degradation often fall short, leading to potential risks such as temperature violations, loss of nutritional value, and pricing strategies that fail to adapt to the varying conditions of the cold supply chain. These misalignments frequently result in discrepancies between perceived value and pricing structures. To address these challenges, this thesis proposes an advanced quality monitoring system specifically designed for the cold supply chain of perishable and frozen food products. This system leverages existing technological advancements, such as smart indicator labels, integrated with Internet of Things (IoT) principles, and suggests an adaptive pricing model to the proposed system to dynamically adjust prices based on the perceived quality. To achieve this Gaussian Process Regression (GPR) was utilized for temperature and shelf-life predictions, combined with an innovative pricing algorithm using RGB values and Euclidean distance. Using GPR, the predictive models achieved high accuracy, with R-squared values of approximately 0.982 for temperature prediction and 0.981 for time estimation, indicating a strong correlation that improves efficiency and ensures the delivery of high-quality products while optimizing pricing structures to address the industry's unique challenges.