FEDformer-Based Paddy Quality Assessment Model Affected by Toxin Change in Different Storage Environments
Zihan Li1, Qingchuan Zhang1, Wei Dong1
1National Engineering Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China.
Foods (Basel, Switzerland)
|April 28, 2023
Summary
Monitoring paddy storage environments is crucial for food safety. Five key factors and advanced AI models accurately predict quality changes, ensuring healthier grain.
Area of Science:
- Agricultural Science
- Food Science
- Artificial Intelligence
Background:
- Paddy quality is essential for human health and is significantly impacted by storage conditions.
- Fungal growth due to improper storage degrades grain quality and poses health risks.
- Effective monitoring of storage environments is needed to maintain grain integrity.
Purpose of the Study:
- To identify critical factors influencing paddy quality changes during storage.
- To develop an accurate predictive model for paddy quality.
- To establish a grading evaluation model for stored paddy.
Main Methods:
- Analysis of grain storage monitoring data from over 20 regions.
- Identification of five essential factors for predicting quality changes.
- Integration of these factors with the FEDformer (Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting) model and k-medoids algorithm.
- Construction of a paddy quality change prediction and grading evaluation model.
Main Results:
- Five factors were identified as essential for predicting paddy quality changes.
- The developed model demonstrated the highest accuracy and lowest error in predicting quality changes.
- The study successfully created a robust paddy quality assessment tool.
Conclusions:
- Monitoring and controlling the storage environment are critical for preserving paddy quality.
- The developed AI-driven model offers a reliable solution for ensuring food safety.
- Implementing these findings can help maintain high standards for stored grain.
