Automatic recognition of concrete spall using image processing and metaheuristic optimized LogitBoost classification tree. (September 2021)

• Record Type: Journal Article
• Authors: Cao, Minh-Tu; Nguyen, Ngoc-Mai; Chang, Kuan-Tsung; Tran, Xuan-Linh; Hoang, Nhat-Duc
• Is Part Of: Advances in engineering software. Volume 159(2021)
• Publication Date: 2021-09
• Subjects: Concrete spall detection -- Building maintenance -- Image processing -- Forensic-based investigation -- Classification tree -- Ensemble learning; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2021.103031
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: Propose a novel artificial intelligence model to recognize concrete spall. Combine metaheuristic, image processing, and machine learning approaches. Kapur's entropy criterion is employed for image segmentation. Image texture analysis is used as feature extractor. Metaheusitic optimized LogitBoost ensemble is used for pattern classification. Abstract: 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.