AI-Assisted Cotton Grading: Active and Semi-Supervised Learning to Reduce the Image-Labelling Burden.
AI-Assisted Cotton Grading: Active and Semi-Supervised Learning to Reduce the Image-Labelling Burden.
复制标题
DOI：
10.3390/s23218671
复制
发表时间：
2023-10-24
期刊：
影响因子：
--
通讯作者：
Watson NJ
中科院分区：
文献类型：
--
作者：
Fisher OJ;Rady A;El-Banna AAA;Emaish HH;Watson NJ
收获期间对粮食和经济作物的评估对于确定质量和下游加工要求非常重要，这反过来又影响其市场价值。虽然已经为此目的开发了机器学习模型，但它们的部署受到标记作物图像以提供模型训练数据的高成本的阻碍。本研究考察了半监督和主动学习的能力，以最大限度地减少标记棉绒样品时的工作，同时保持高分类精度。随机森林分类模型的开发使用监督学习，半监督学习，主动学习，以确定埃及棉花等级。与监督学习（80.20-82.66%）和半监督学习（81.39-85.26%）相比，主动学习模型能够实现更高的准确率（82.85-85.33%），所需的标记数据量减少了46.4%。使用机器学习进行埃及棉花分级的主要障碍是标记棉绒样品所需的时间。然而，通过应用主动学习，这项研究成功地将所需的时间从422.5分钟减少到177.5分钟。这项研究的结果表明，主动学习是一种很有前途的方法，可以开发准确有效的机器学习模型，用于对粮食和经济作物进行分级。
The assessment of food and industrial crops during harvesting is important to determine the quality and downstream processing requirements, which in turn affect their market value. While machine learning models have been developed for this purpose, their deployment is hindered by the high cost of labelling the crop images to provide data for model training. This study examines the capabilities of semi-supervised and active learning to minimise effort when labelling cotton lint samples while maintaining high classification accuracy. Random forest classification models were developed using supervised learning, semi-supervised learning, and active learning to determine Egyptian cotton grade. Compared to supervised learning (80.20–82.66%) and semi-supervised learning (81.39–85.26%), active learning models were able to achieve higher accuracy (82.85–85.33%) with up to 46.4% reduction in the volume of labelled data required. The primary obstacle when using machine learning for Egyptian cotton grading is the time required for labelling cotton lint samples. However, by applying active learning, this study successfully decreased the time needed from 422.5 to 177.5 min. The findings of this study demonstrate that active learning is a promising approach for developing accurate and efficient machine learning models for grading food and industrial crops.
登录
查看更多内容
DOI：
10.3390/s17030518
发表时间：
2017-03-04
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Kuzy J;Li C
通讯作者：
Li C
DOI：
10.21608/ajs.2020.28192.1197
发表时间：
2020-01-01
影响因子：
--
作者：
Hussein, M. G.;El-Marakby, A. M.;Ebaido, I. A.
通讯作者：
Ebaido, I. A.
影响因子：
4.3
作者：
Charte, Francisco;Romero, Inmaculada;Castro, Eulogio
通讯作者：
Castro, Eulogio
影响因子：
2.3
作者：
Fisher, Oliver J.;Rady, Ahmed;Emaish, Haitham H.
通讯作者：
Emaish, Haitham H.
影响因子：
6.7
作者：
Ahmad, Muhammad Waseem;Mourshed, Monjur;Rezgui, Yacine
通讯作者：
Rezgui, Yacine