Food Chemistry, Год журнала: 2024, Номер 464, С. 141567 - 141567
Опубликована: Окт. 9, 2024
Язык: Английский
Food Chemistry, Год журнала: 2024, Номер 464, С. 141567 - 141567
Опубликована: Окт. 9, 2024
Язык: Английский
Trends in Food Science & Technology, Год журнала: 2025, Номер unknown, С. 104918 - 104918
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
0Agriculture, Год журнала: 2025, Номер 15(4), С. 415 - 415
Опубликована: Фев. 16, 2025
Common bunt disease in wheat is a serious threat to crops and food security. Rapid assessments of its severity are essential for effective management. The electronic nose (e-nose) system used capture volatile organic compounds (VOCs), particularly trimethylamine (TMA), which serves as key marker common wheat. In this paper, the GFNN (gas feature neural network) model proposed detecting VOCs from e-nose system, providing lightweight efficient approach assessing severity. Multiscale convolution employed extract both global local features gas data, three attention mechanisms focus on important features. achieves 98.76% accuracy, 98.79% precision, 98.77% recall, an F1-score 98.75%, with only 0.04 million parameters 0.42 floating-point operations per second (FLOPS). Compared traditional current deep learning models, demonstrates superior performance, small-sample-size scenarios. It significantly improves performance extracting This study offers practical, rapid, cost-effective method monitoring managing wheat, enhancing crop protection
Язык: Английский
Процитировано
0Trends in Food Science & Technology, Год журнала: 2025, Номер unknown, С. 104977 - 104977
Опубликована: Март 1, 2025
Язык: Английский
Процитировано
0Food Chemistry, Год журнала: 2024, Номер 464, С. 141567 - 141567
Опубликована: Окт. 9, 2024
Язык: Английский
Процитировано
1