当前位置: X-MOL 学术Constr. Build. Mater. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Assessment of importance-based machine learning feature selection methods for aggregate size distribution measurement in a 3D binocular vision system
Construction and Building Materials ( IF 7.4 ) Pub Date : 2021-09-17 , DOI: 10.1016/j.conbuildmat.2021.124894
Zhaoyun Sun 1 , Hanye Liu 1, 2 , Ju Huyan 3 , Wei Li 1 , Meng Guo 4 , Xueli Hao 1 , Lili Pei 1
Affiliation  

Aggregate size is usually measured by manual sampling and sieving. Machine vision techniques can provide fast, non-invasive measurement. However, the traditional imaging method using a single size descriptor to discriminate different sieve-size classes of coarse aggregates might not yield high-precision classification results. To determine the optimum supervised machine learning model for coarse aggregates sieve-size measurement, 17 methods were evaluated and compared. To train our model, a new dataset named MFCA27 (Multiple Features of Coarse Aggregate 27) was introduced, which contains 27 features of aggregates based on aggregate three-dimensional (3D) top-surface object. In addition, a feature selection approach for investigating how accuracy varied with the datasets under different feature sets was developed, where feature selection was performed according to the impurity-based feature importance score measured using an extremely randomized tree model. Experiments demonstrated that the Gaussian process classifier (GPC) was the best-performing method on the datasets with two- or three-dimensional (2D/3D) feature sets in terms of accuracy and robustness. The results also showed that, compared with the traditional aggregate sieve-size measurement method, which is based on a single size descriptor, GPC can achieve an accuracy of 95.06% on the test dataset of MFCA27 in the aggregate sieve-size class measurement task.



中文翻译:

评估基于重要性的机器学习特征选择方法,用于 3D 双目视觉系统中的聚合尺寸分布测量

骨料尺寸通常通过人工取样和筛分来测量。机器视觉技术可以提供快速、非侵入性的测量。然而,传统的成像方法使用单一尺寸描述符来区分不同筛分类别的粗骨料可能无法产生高精度的分类结果。为了确定粗骨料筛分测量的最佳监督机器学习模型,对 17 种方法进行了评估和比较。为了训练我们的模型,引入了一个名为 MFCA27(粗聚合 27 的多个特征)的新数据集,其中包含基于聚合三维(3D)顶面对象的聚合的 27 个特征。此外,还开发了一种特征选择方法,用于研究不同特征集下数据集的准确性如何变化,其中特征选择是根据使用极其随机化的树模型测量的基于杂质的特征重要性得分来执行的。实验表明,高斯过程分类器 (GPC) 是具有二维或三维 (2D/3D) 特征集的数据集在准确性和鲁棒性方面表现最佳的方法。结果还表明,与传统的基于单一粒度描述符的骨料筛分测量方法相比,GPC在MFCA27的测试数据集上在骨料筛分级测量任务中的准确率达到了95.06%。实验表明,高斯过程分类器 (GPC) 是具有二维或三维 (2D/3D) 特征集的数据集在准确性和鲁棒性方面表现最佳的方法。结果还表明,与传统的基于单一粒度描述符的骨料筛分测量方法相比,GPC在MFCA27的测试数据集上在骨料筛分级测量任务中的准确率达到了95.06%。实验表明,高斯过程分类器 (GPC) 是具有二维或三维 (2D/3D) 特征集的数据集在准确性和鲁棒性方面表现最佳的方法。结果还表明,与传统的基于单一粒度描述符的骨料筛分测量方法相比,GPC在MFCA27的测试数据集上在骨料筛分级测量任务中的准确率达到了95.06%。

更新日期:2021-09-17
down
wechat
bug