| Autor: |
Min-Shao Shih, Chao-Cheng Wu, Tsang-Sen Liu, Yen-Chieh Ouyang, Chia-Jui Wang |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
IGARSS |
| DOI: |
10.1109/igarss47720.2021.9555137 |
| Popis: |
Food safety and quality examination has received close attention from general public in recent years. One of examples is the freshness of pleurotus eryngii, which plays an important role in its economic values. The estimation of its freshness could not be based on the number of storage days because fungi could normally keep alive for a while after harvest depending on storage environment. With advances of hardware and software, hyperspectral technologies shed some light on prediction of its nonlinear decay trend. This paper proposed a spectral derivative analysis to improve the temporal accuracy of previous works [5] from weeks to days. Then, the long short-term memory neural network was utilized to predict the decay trend based on the data of beginning few days. The experimental studies demonstrated that the prediction trends were close to the real ones. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
