The use of artificial neural networks for food enhancement in the food drying industry - A short review
The food drying industry is essential for maintaining different food products flavor, nutritional content, and shelf life. Traditionally used drying techniques sometimes rely on empirical data and heuristics, making optimizing drying procedures for various food products challenging. Low-temperature...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Proceedings |
| Language: | en |
| Published: |
American Institute of Physics Inc.
2025
|
| Subjects: | |
| Online Access: | https://eprints.ums.edu.my/id/eprint/45893/1/Fulltext.pdf https://eprints.ums.edu.my/id/eprint/45893/ https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105016486460&origin=inward |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The food drying industry is essential for maintaining different food products flavor, nutritional content, and shelf life. Traditionally used drying techniques sometimes rely on empirical data and heuristics, making optimizing drying procedures for various food products challenging. Low-temperature drying involves efficiently removing moisture from food products or other materials while minimizing the negative impact on their quality, nutritional content, and sensory attributes. Subsequently, a food processing component becomes more adaptable with machines, for example, able to differentiate between more complex tasks, such as low saturated fats from high unsaturated fats, and fundamental problems distinguishing between different fruits. As a result, introducing machine deep learning will improve and help the food sector since it may open opportunities for computer vision to increase its potential. Artificial neural networks (ANNs), which have the potential to improve process control, efficiency, and product quality, have recently become a formidable tool in the food drying business. The primary purpose of this study is to review the use of ANNs in food drying. This study also covers moisture content prediction using artificial neural networks and multiple linear regression. ANN can forecast and regulate crucial variables, including temperature, humidity, and air velocity, in the context of drying food. It shows that ANNs demonstrated incredible potential in the modeling and optimization of complicated, nonlinear systems. This approach paves the way for developing more precise and comprehensive drying models, facilitating the simulation, prediction, and optimization of food product drying performance without overly complex models. |
|---|