Effect of transportation conditions and pre-storage treatments on the quality and shelf-life of fresh tomatoes in selected South African supply chains

Cherono, K.; Workneh, Tilahun Seyoum

doi:10.17660/actahortic.2019.1258.8

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The existing research on temperature prediction approaches for cold SC focuses on the cargo's temperature approximation with relatively stable or unstable environmental temperatures for a long time span and does not address the immediate predictions [27][28][29]. For decisionmaking, unstable environmental temperature conditions are required for predicting temperatures.…”

Section: Introductionmentioning

confidence: 99%

IoT- Enabled Firmness Grades of Tomato in Cold Supply Chain Using Fusion of Whale Optimization Algorithm and Extreme Learning Machine

Haider,

Kazmi,

Alam

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The firmness of tomatoes is a considerable parameter for the evaluation of harvest time, shelf life, and ripeness. The firmness of tomatoes provides guidance in the distribution and transportation of tomatoes. In the post harvest procedure, the tomato starts losing its firmness and transforming into a rotten state during transportation in the supply chain due to variations in environmental conditions. The cold supply chain for the transportation of tomatoes reduces the loss and maintains the quality of the tomatoes by controlling the environmental conditions. The monitoring of the cold supply chain is crucial for maintaining the quality of tomatoes and overcoming the effect of ambient temperature on tomatoes during logistics. In this study, an IoT and Whale Optimization Algorithm based temperature prediction system for the cold supply chain is presented. The ambient and tomato's temperatures were collected, as well the stable temperature under the variation conditions computed with the Whale Optimization Algorithm for performance improvement. The Extreme Learning Machine of Artificial Intelligence was applied for the predictions. The performance evaluation is done by using precision, recall, and f-measure accuracy metrics. The results of the study show the outstanding performance of the proposed approach rather than the Decision Tree, Linear Model, Naïve Bays, Random Forest, and Support Vector Machine models.

show abstract

Section: Introductionmentioning

confidence: 99%