首页|Reports from Zhejiang A&F University Highlight Recent Research in M achine Learning (A Monitoring Device and Grade Prediction System for Grain Milde w)
Reports from Zhejiang A&F University Highlight Recent Research in M achine Learning (A Monitoring Device and Grade Prediction System for Grain Milde w)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ar tificial intelligence. According to news originating from Hangzhou, People's Rep ublic of China, by NewsRx correspondents, research stated, "Mildew infestation i s a significant cause of loss during grain storage. The growth and metabolism of mildew leads to changes in gas composition and temperature within granaries." Financial supporters for this research include Ningbo Science And Technology Pla n Project; Key R&D Projects in Zhejiang Province; Research Developm ent Foundation of Zhejiang A&funiversity. Our news reporters obtained a quote from the research from Zhejiang A& F University: "Recent advances in sensor technology and machine learning enable the prediction of grain mildew during storage. Current research primarily focuse s on predicting mildew occurrence or grading using simple machine learning metho ds, without in-depth exploration of the time series characteristics of mildew pr ocess data. A monitoring device was designed and developed to capture high-quali ty microenvironment parameters and image data during a simulated mildew process experiment. Using the "Yongyou 15" rice varieties from Zhejiang Province, five s imulation experiments were conducted under varying temperature and humidity cond itions between January and May 2023. Mildew grades were defined through manual a nalysis to construct a multimodal dataset for the rice mildew process. This stud y proposes a combined model (CNN-LSTM-A) that integrates convolutional neural ne tworks (CNN), long short-term memory (LSTM) networks, and attention mechanisms t o predict the mildew grade of stored rice. The proposed model was compared with LSTM, CNN-LSTM, and LSTM-Attention models. The results indicate that the propose d model outperforms the others, achieving a prediction accuracy of 98% . The model demonstrates superior accuracy and more stable performance."
Zhejiang A&F UniversityHa ngzhouPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachin e Learning
NETL
NSTL
