利用三层深度学习模型为环境更清洁的工厂生产
Zahraa Tarek1, Mohamed Elhoseny1,2, Mohamemd I Alghamdi3
1Faculty of Computers and Information Science, Mansoura University, Mansoura, Egypt.
Scientific reports
|November 9, 2023
概括
这项研究引入了使用物联网传感器和机器学习的早期植物疾病诊断框架. 拟议的模型实现了93.84%的准确性,改善了农业预测和粮食生产.
科学领域:
- 农业技术 农业技术
- 计算科学 计算科学
- 物联网 (IoT) 的物联网 (IoT) 的物联网.
背景情况:
- 到2050年全球人口增长到90亿,需要粮食生产增加70%.
- 挑战包括资源稀缺,气候变化和流行病,需要计算预测.
- 植物疾病从种子到生长阶段构成重大威胁.
研究的目的:
- 使用雾计算和边缘环境开发早期植物疾病诊断框架.
- 评估预训练的卷积神经网络 (CNN) 架构作为特征提取器的有效性.
- 提高植物疾病识别的准确性,以提高农业产量.
主要方法:
- 利用物联网传感器在雾和边缘计算环境中收集数据.
- 雇佣了预先训练有素的CNN模特 (AlexNet) 作为特征提取器.
- 应用了修订的灰狼优化 (GWO) 算法来进行特征选择,并训练了一个SVM分类器.
主要成果:
- 拟议的模型在十个不同的植物数据集中实现了93.84%的平均准确性.
- 这超过了标准的AlexNet (85.49%),GoogleNet (87.89%) 和SVM (87.04%) 的准确性.
- GWO算法有效地优化了特征选择,以改善分类.
结论:
- 拟议的框架为早期植物疾病诊断提供了一个高度准确的解决方案.
- 这有助于更可靠的农业预测和增加粮食生产.
- 物联网,雾计算和优化机器学习的整合在农业技术中显示出重大前景.
相关概念视频
02:16Light Acquisition
8.5K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.5K
00:46Bioremediation
18.6K
Bioremediation is the use of prokaryotes, fungi, or plants to remove pollutants from the environment. This process has been used to remove harmful toxins in groundwater as a byproduct of agricultural run-off and also to clean up oil spills.
18.6K