Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning

Lyngdoh, Gideon A.; Zaki, Mohd; Krishnan, N. M. Anoop; Das, Sumanta

doi:10.1016/j.cemconcomp.2022.104414

Cited by 104 publications

(19 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although our method is a purely data-driven imputation model on the basis of optimization, it has good model interpretability, which is a noteworthy topic of imputation model recently (Lyngdoh et al, 2022). To better reveal the mechanism of truncation operation and the effects of model components, in this subsection we give further interpretations and discussions about the proposed method.…”

Section: Further Interpretationmentioning

confidence: 99%

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns

Nie,

Qin,

Sun

2022

Preprint

View full text Add to dashboard Cite

Rapid advances in sensor, wireless communication, cloud computing and data science have brought unprecedented amount of data to assist transportation engineers and researchers in making better decisions. However, traffic data in reality often has corrupted or incomplete values due to detector and communication malfunctions. Data imputation is thus required to ensure the effectiveness of downstream data-driven applications. To this end, numerous tensor-based methods treating the imputation problem as the low-rank tensor completion (LRTC) have been attempted in previous works. To tackle rank minimization, which is at the core of the LRTC, most of aforementioned methods utilize the tensor nuclear norm (NN) as a convex surrogate for the minimization. However, the over-relaxation issue in NN refrains it from desirable performance in practice. In this paper, we define an innovative nonconvex truncated Schatten p-norm for tensors (TSpN) to approximate tensor rank and impute missing spatiotemporal traffic data under the LRTC framework. We model traffic data into a thirdorder tensor structure of time intervals×locations (sensors)×days and introduce four complicated missing patterns, including random missing and three fiber-like missing cases according to the tensor mode-n fibers. Despite nonconvexity of the objective function in our model, we derive the global optimal solutions by integrating the alternating direction method of multipliers (ADMM) with generalized soft-thresholding (GST). In addition, we design a truncation rate decay strategy to deal with varying missing rate scenarios. Comprehensive experiments are finally conducted using four different types of real-world spatiotemporal traffic datasets, which demonstrate that the proposed LRTC-TSpN method performs well under various missing cases even with high rates of data loss, meanwhile outperforming other state-of-the-art tensor-based imputation models in almost all scenarios. In general, the performance of the proposed method achieves up to a 52% improvement in mean absolute error (MAE) compared to baseline methods even when the missing ratio is as high as 90%. Moreover, both theoretical and empirical evidences indicate that our method has robust and efficient convergence performances.

show abstract

Section: Further Interpretationmentioning

confidence: 99%

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns

Nie,

Qin,

Sun

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Remarkably, in civil engineering, ML methods have improved the safety, productivity, quality, and maintenance of construction [17,18] and have been used to model and predict the mechanical properties of SCC [16,[19][20][21][22]. Therefore, the prediction of these properties through ML saves on the following: laboratory time, waste of concrete components, energy, and cost [3,14,16,20,23,24].…”

Section: Introductionmentioning

confidence: 99%

“…Among the most widely used ML methods to predict these concrete properties are: decision tree regressor (DTR) [1,[25][26][27], random forest (RF) [24,25,28], eXtreme gradient boosting (XG Boost) [29,30], support vector regressor (SVR) [14,21,31], artificial neural network (ANN) [1,22,27,[32][33][34][35], and gradient boosting regressor (GBR) [25,29,30]. For example, Lyngdoh et al [19] employed K-nearest neighbor (KNN), support vector machine (SVM), XG Boost, neural network (NN), least absolute shrinkage, random forest (RF), and selection operator (LASSO) to predict the splitting tensile strength and compressive strength of concrete. Meanwhile, Bui et al [36] established an expert system based on an artificial neural network (ANN) model and supported by a modified firefly algorithm (MFA) to predict the splitting tensile strength and compressive strength of high-performance concrete.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, splitting tensile strength is one of the mechanical properties of importance in the design of concrete structures [38,39] because cracking in concrete is generally due to tensile stresses that occur under load or due to environmental changes [40]. Machine learning methods have been employed to predict the splitting tensile strength of concrete, with the most widely used being neural networks (ANN) [32,36,[41][42][43][44][45][46], support vector machine (SVM) [16,19,37,38,42,44,45,[47][48][49], eXtreme gradient boosting (XG Boost) [19,37,44], random forest (RF) [16,19,49], decision tree regressor (DTR) [16,27], gradient boosting regressor (GBR) [16,37], and finally multilayer perceptron (MLPs) [37,49].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparison of Machine Learning Tools That Model the Splitting Tensile Strength of Self-Compacting Recycled Aggregate Concrete

de‐Prado‐Gil

Palencia

Jagadesh³

et al. 2022

Materials

View full text Add to dashboard Cite

Several types of research currently use machine learning (ML) methods to estimate the mechanical characteristics of concrete. This study aimed to compare the capacities of four ML methods: eXtreme gradient boosting (XG Boost), gradient boosting (GB), Cat boosting (CB), and extra trees regressor (ETR), to predict the splitting tensile strength of 28-day-old self-compacting concrete (SCC) made from recycled aggregates (RA), using data obtained from the literature. A database of 381 samples from literature published in scientific journals was used to develop the models. The samples were randomly divided into three sets: training, validation, and test, with each having 267 (70%), 57 (15%), and 57 (15%) samples, respectively. The coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) metrics were used to evaluate the models. For the training data set, the results showed that all four models could predict the splitting tensile strength of SCC made with RA because the R2 values for each model had significance higher than 0.75. XG Boost was the model with the best performance, showing the highest R2 value of R2 = 0.8423, as well as the lowest values of RMSE (=0.0581) and MAE (=0.0443), when compared with the GB, CB, and ETR models. Therefore, XG Boost was considered the best model for predicting the splitting tensile strength of 28-day-old SCC made with RA. Sensitivity analysis revealed that the variable contributing the most to the split tensile strength of this material after 28 days was cement.

show abstract

“…Due to the complex heterogeneous nature of concrete, phase separation remains a challenging task. The last advances in machine learning led to a better understanding of concrete properties, from strength 8 to shrinkage 9 or micromechanical properties, 10 and, more specifically, deep learning segmentation techniques have been fruitful in different fields 11 . For visual imagery, a convolutional neural network (CNN) might be used, combined with other techniques, to increase observation precision classifying or detecting objects of low contrast with a completely automated procedure.…”

Section: Introductionmentioning

confidence: 99%

Open‐source deep learning‐based air‐void detection algorithm for concrete microscopic images

Hilloulin

Bekrine

Schmitt³

et al. 2022

Journal of Microscopy

View full text Add to dashboard Cite

Analysing concrete microscopic images is difficult because of its highly heterogeneous composition and the different scales involved. This article presents an open‐source deep learning‐based algorithm dedicated to air‐void detection in concrete microscopic images. The model, whose strategy is presented alongside concrete compositions information, is built using the Mask R‐CNN model. Model performances are then discussed and compared to the manual air‐void enhancement technique. Finally, the selected open‐source strategy is exposed. Overall, the model shows a good precision (mAP = 0.6452), and the predicted air void percentage agrees with experimental measurements highlighting the model's potential to assess concrete durability in the future.

show abstract

Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning

Cited by 104 publications

References 54 publications

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns

A Comparison of Machine Learning Tools That Model the Splitting Tensile Strength of Self-Compacting Recycled Aggregate Concrete

Open‐source deep learning‐based air‐void detection algorithm for concrete microscopic images

Contact Info

Product

Resources

About