当前位置: X-MOL 学术Adv. Eng. Softw. › 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.)
Automatic recognition of concrete spall using image processing and metaheuristic optimized LogitBoost classification tree
Advances in Engineering Software ( IF 4.8 ) Pub Date : 2021-07-09 , DOI: 10.1016/j.advengsoft.2021.103031
Minh-Tu Cao , Ngoc-Mai Nguyen , Kuan-Tsung Chang , Xuan-Linh Tran , Nhat-Duc Hoang

This paper presents a novel artificial intelligence model to automatically recognize concrete spall appearing on building components. The model is constructed by integrating a metaheuristic optimization algorithm, advanced image processing techniques, and a powerful machine learning-based inference model. Kapur's entropy based image segmentation, statistical measurements of image color, gray level co-occurrence matrices, and local ternary pattern are used to extract numerical features presenting concrete surfaces on spall and non-spall samples. Subsequently, a LogitBoost based ensemble framework of classification and regression tree (CART) models (denoted as LBT) is employed to construct a decision boundary capable of recognizing spall/non-spall image samples. Moreover, in order to enhance the performance of the LogitBoost based ensemble framework, forensic-based investigation (FBI) metaheuristic is utilized to determine the most suitable set of the framework's hyper-parameters including the learning rate (μ), the learning cycle (Lc), the minimum number of leaves (Lmin), and the maximum number of splits (Smax). A data set including 486 image samples has been collected from field surveys at high-rise buildings in Da Nang city (Vietnam) to train and verify the proposed FBI optimized LBT model (denoted as F-LBT). Experimental results supported by statistical tests point out that the F-LBT is a capable method for concrete spall detection with a classification accuracy rate = 88.3%, precision = 0.889, recall = 0.874, F1 score = 0.881, and negative predictive value = 0.874. Hence, the proposed hybrid approach is a promising tool to support building maintenance agencies in the task of periodic structural inspection.



中文翻译:

使用图像处理和元启发式优化 LogitBoost 分类树自动识别混凝土剥落

本文提出了一种新颖的人工智能模型来自动识别出现在建筑构件上的混凝土剥落。该模型是通过集成元启发式优化算法、先进的图像处理技术和强大的基于机器学习的推理模型构建的。Kapur 基于熵的图像分割、图像颜色的统计测量、灰度共生矩阵和局部三元模式用于提取呈现混凝土表面剥落和非剥落样本的数值特征。随后,采用基于 LogitBoost 的分类和回归树(CART)模型(表示为 LBT)的集成框架来构建能够识别剥落/非剥落图像样本的决策边界。而且,μ)、学习周期(L c)、最小叶子数(L min)和最大分裂数(S max)。从岘港市(越南)高层建筑的现场调查中收集了包括 486 个图像样本的数据集,以训练和验证拟议的 FBI 优化 LBT 模型(表示为 F-LBT)。统计测试支持的实验结果表明,F-LBT 是一种有效的混凝土剥落检测方法,分类准确率 = 88.3%,精度 = 0.889,召回率 = 0.874,F1 分数 = 0.881,阴性预测值 = 0.874。因此,所提议的混合方法是支持建筑维护机构执行定期结构检查任务的有前途的工具。

更新日期:2021-07-09
down
wechat
bug