Performance evaluation of compressive strength of concrete using different machine learning algorithms

The combinations of chemical admixtures play a significant role in producing concrete. Understanding their mechanical properties is crucial for ensuring safety and durability. Among these properties, compressive strength (CS) stands out as the most critical attribute of concrete. This research introduced a distinct concrete mix utilizing a blend of superplasticizers, retarders, and air-entraining agents, designed to meet specific construction requirements for enhanced durability and workability. The study examines the long-term effects of combining various chemical admixtures on the compressive strength of concrete, utilizing advanced experimental data and machine learning models with a level of precision and detail that has been relatively underexplored.This investigation includes a substantial increase in samples (7845) compared to previous research. Samples were tested at different ages, ranging from 3 days to 3 years. To enhance the accuracy of machine learning (ML) models, a novel approach to data distribution simulation based on K-means clustering was employed for generating synthetic data. Various ML models, including Nonlinear Autoregressive with Exogenous Inputs (NARX), Support Vector Regression (SVR), Radial Basis Function (RBF), Multilayer Perceptron (MLP), Decision Tree (DT), and Random Forest (RF), were evaluated for predicting the compressive strength of concrete (CS). Results show the NARX model outperforms the other models, validated by experimental data and k-fold cross-validation. This model showed a coefficient of determination (R2 = 0.9932), normalized mean square error (NMSE = 18.97), normalized mean absolute error (NMAE = 2.49), and normalized root-mean-square error (NRMSE = 6.18). The findings revealed that in Mix - 1, the compressive strength increased from 450 (kg/cm2) at 28 days to 480 (kg/cm2)at 90 days, but then decreased to 420 (kg/cm2) after three years. This reduction in strength may lead to decreased load-bearing capacity and higher repair costs, highlighting the need to revise concrete design standards. This study emphasizes revising some current concrete structure design standards to accommodate the observed long-term reductions in compressive strength.

Raman spectroscopy (RS) is a promising tool for cancer diagnosis. In particular, in the last years several studies have demonstrated how the diagnostic performances of RS can be significantly improved by employing machine learning (ML) algorithms for the interpretation of Raman-based data. Recently, it has been demonstrated that RS can perform an accurate classification of chondrosarcoma tissues. Chondrosarcoma is a cancer of bones, that can occur in the soft tissues near the bones. It is normally characterized by three different malignant degrees and a benign counterpart, knows as enchondroma. In line with these findings, in this paper, we exploited ML algorithms to distinguish, as well as possible, between the three grades of chondrosarcoma and to distinguish between chondrosarcoma and enchondroma. We obtained a high level of accuracy of classification by analyzing a dataset composed of a relatively small number of Raman spectra, collected in a previous study by one of the authors of this paper. Such spectra were acquired from micrometric tissue sections with a confocal Raman microscope. We tested the classification performances of a support vector machine (SVM) and a random forest classifier (RFC), as representatives of ML algorithms, and two versions of the multi-layer perceptron (MLPC) as representatives of deep learning (DL). These models, especially RFC and MLPC, showed excellent classification performances, with accuracy reaching 99.7%. This outcome makes the aforementioned models a promising route for future improvements of diagnostic devices focused on detecting cancerous bone tissues. Alongside the diagnostic purpose, the aforementioned approach allowed us to identify characteristic molecules, i.e., amino acids, nucleic acids, and bioapatites, relevant for obtaining the final diagnostic response, through the use of a tool named by us Raman Band Identification (RBI). The method to evaluate RBI is the most important contribution of this paper, because RBI could represent a relevant parameter for the identification of biochemical processes on the basis of the tumor progression and associated malignant degree. In turn, the spectral bands highlighted by RBI could provide precious indicators in an attempt to restrict the spectral acquisition to specific Raman bands. This last objective could help to reduce the amount of experimental data needed to obtain an accurate final grading outcome, with a consequent reduction in the computational cost.

In the design of new structures, EN 1992‐1‐1 normatively regulates the correlation between the compressive strength and tensile strength of concrete, in accordance with EN 206‐1. However, as there are many time‐ and load‐dependent impacts on existing structures, the relationship described by EN 1992‐1‐1 cannot be assumed without any further observations for existing structures. At the moment, there is no comprehensive investigation on the influences of, for example, subsequent hardening and carbonation on the concrete compressive or tensile strength. The tensile strength of concrete defined in EN 1992‐1‐1 is based on a water storage and a testing age of 28 days. Furthermore, the in‐situ tensile strength is affected by micro‐crack formation cause of internal stresses due to outflow of hydration heat, for example. Generally, there is a different influence of micro‐crack formation on the tensile strength of concrete than on the compressive strength of concrete. The actual value of the in‐situ tensile strength of concrete affects the shear force resistance and the load‐bearing capacity of anchors with concrete cone failure as decisive failure mode. Within the framework of a research project (SWD‐10.08.18.7‐13.01), financed by “Forschungsinitiative Zukunft Bau”, an initiative of the Federal Institute for Research on Building, Urban Affairs and Spatial Development (BBR) structural investigations on the correlation between the compressive and tensile strength of old concretes have been performed. Below, the results of the research project are presented.

Self-compacting concrete (SCC) enhanced by the addition of a supplementary admixture of metakaolin and/or modifying agent rice husk ash has been the object of several types of research due to its display of different properties than normal vibrated concrete. This study aimed at utilizing machine learning approaches, viz, Support Vector Machine, Multilayer Perceptron, Gaussian Processes Regression, random tree, M5P tree, and Random Forest to develop models using seven input parameters, viz, cement (kg/m3), water (kg/m3), fine aggregates (kg/m3), coarse aggregates (kg/m3), superplasticizers (kg/m3), metakaolin (kg/m3), and rice husk ash (kg/m3) and one output parameter being the 28-day compressive strength (MPa) of SCC mix ratios derived from reliable literature. The dataset consisted of 159 mix ratios with their 28-day compressive strength. The results obtained for the dataset are subject to two different methodologies: the supplied test data method and the cross-validation method. The results obtained are compared and allowed users to make a reasonable prediction of compressive strength for mix ratios with the aid of models developed.

This study presents a prediction model for estimating the compressive strength of pervious concrete through the utilisation of machine learning techniques. The models were trained and tested using 437 datasets sourced from published literature. This work employed a collection of six machine learning algorithms as statistical evaluation tools to determine the optimal and dependable model for forecasting the compressive strength of pervious concrete. Out of all the models considered, the eXtreme Gradient Boosting model had greater performance in predicting the compressive strength. The coefficient of determination value for the train data is 0.99, indicating a strong correlation between the predicted and actual values. The root mean squared error for the train data is 0.86 MPa, representing the average deviation between the predicted and measured values. Similarly, the coefficient of determination value for the test datasets is determined to be 0.95, accompanied by a root mean squared error of 2.53 MPa. The eXtreme Gradient Boosting model's sensitivity analysis findings suggest that the aggregate size is the greatest parameter on forecasting the compressive strength of pervious concrete. This study delivers a systematic assessment of the compressive strength of pervious concrete, contributing to the current knowledge base and practical implementation in this field.

Recent advances in machine learning techniques have significantly influenced the development of early diabetes detection systems. In this paper, different machine learning (ML) algorithms are employed for diabetes detection based on hand movement. The spatial and temporal information for horizontal and vertical hand movement deviations for both diabetic and non-diabetic subjects are obtained using a data acquisition system. A dataset is constructed based on the obtained hand movement information along with other related attributes such as age, gender, weight and vision health. Binary classification of diabetic and non-diabetic subjects is achieved using several machine learning algorithms. These algorithms include Naïve Bayes (NB), Logistic Regression (LR), Linear Discriminate Analysis (LDA), Classification and Regression Tree (CART), k-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Multi-layer Perceptron (MLP). The considered ML algorithms are evaluated and ranked according to a set of key performance metrics that include accuracy, precision, recall and F-1 score. Algorithm ranking results demonstrate that LR, CART, KNN and MLP algorithms have achieved higher ranking positions as compared to other algorithms. The best ranked ML algorithms are then validated and thoroughly investigated to prove their ability to discriminate between diabetic and non-diabetic subjects. Validation results show that the best-ranked ML algorithms have achieved high classification accuracy, precision, recall and F-1 scores. Therefore, the considered machine learning algorithms can serve as efficient tools for diabetes detection based on the constructed dataset.

In the era of artificial intelligence, machine learning methods are successfully used in various fields. Machine learning has attracted extensive attention from investors in the financial market, especially in stock price prediction. However, one argument for the machine learning methods used in stock price prediction is that they are black-box models which are difficult to interpret. In this paper, we focus on the future stock price prediction with the historical stock price by machine learning and deep learning methods, such as support vector machine (SVM), random forest (RF), Bayesian classifier (BC), decision tree (DT), multilayer perceptron (MLP), convolutional neural network (CNN), bi-directional long-short term memory (BiLSTM), the embedded CNN, and the embedded BiLSTM. Firstly, we manually design several financial time series where the future price correlates with the historical stock prices in pre-designed modes, namely the curve-shape-feature (CSF) and the non-curve-shape-feature (NCSF) modes. In the CSF mode, the future prices can be extracted from the curve shapes of the historical stock prices. Conversely, in the NCSF mode, they can’t. Secondly, we apply various algorithms to those pre-designed and real financial time series. We find that the existing machine learning and deep learning algorithms fail in stock price prediction because in the real financial time series, less information of future prices is contained in the CSF mode, and perhaps more information is contained in the NCSF. Various machine learning and deep learning algorithms are good at handling the CSF in historical data, which are successfully applied in image recognition and natural language processing. However, they are inappropriate for stock price prediction on account of the NCSF. Therefore, accurate stock price prediction is the key to successful investment, and new machine learning algorithms handling the NCSF series are needed.

In this paper, an effort has been made to develop a recurrent type of neural network known as diagonal recurrent neural network (DRNN) to predict the compressive and flexural strengths of AOD steel slag-mixed concrete for pavements. The data used for modeling were attained from the laboratory experiments. The compressive and flexural strengths were experimentally analyzed for specimens containing 0%, 10%, 15%, 20%, and 25% of AOD steel slag as a partial replacement of cement at curing ages of 3, 7, 28, 90, 180, and 365 days. The developed model was trained using the backpropagation (BP) algorithm. The performance of the proposed model during the training and validation has been compared with the well-known prediction models such as multi-layer perceptron (MLP) and the radial basis function network (RBFN). The DRNN-based prediction model has given much better prediction results when compared to the other two models since the former provided comparatively smaller values of performance indicators such as average mean square error (AMSE) and mean average error (MAE). The reason for DRNN performing better than the other two models is that it contains feedback connections/weights which induce memory property in its structure. This helps DRNN to better model the complex mappings. Such feedback loops are not available in MLP and RBFN. The study conducted in this research concludes that the DRNN-based prediction model should be preferred over the MLP and RBFN models for predicting the compressive and flexural strengths of AOD steel slag added to concrete for pavements.

The objective of this study is to evaluate and compare the performance of different machine learning (ML) algorithms, viz., multi-layer perceptron (MLP), random forest (RF), extra trees regressor (ETR), CatBoost, and gradient boost (GB), considering the impact of variation in sample sizes for theprediction of soil nutrients. In this context, this study evaluates the impact of sample size on the prediction performance of five ML algorithms for mapping 14 soil properties, including key soil physico-chemical properties (soil organic carbon, pH, and electrical conductivity), and multiple macro (available nitrogen, phosphorus, potassium, calcium, magnesium, and sulfur) and micronutrients (available iron, manganese, copper, zinc, and boron) at a geographical extent of 8303 km2 located in eastern India. A total of 1024 surface soil samples were collected, of which 800 were used for model training, while the remaining 224 were reserved for independent validation (IV) of the resultant maps. The original training data set (800 samples) was reduced by random selection into six different sample sizes, i.e., 800, 400, 200, 100, 50, and 25. An exhaustive set of 574 environmental variables, derived from digital terrain derivatives and Sentinel-2 satellite imagery, was used as predictors. Popular statistical indicators, such as Lin's concordance correlation coefficient (CCC) and root mean squared error (RMSE) were employed to evaluate the predictive capability of the algorithms under different sample size scenarios. The results showed that prediction accuracy and reliability of prediction performance across multiple target variables improved with sample size. However, beyond a certain point, improvement in predictive performance became substantially negligible compared to the efforts in additional sampling. All the ML algorithms performed well (mean IV-CCC varied between 0.26 and 0.64 for different soil properties) to increase insample size, except MLP, which exhibited a poorer prediction performance(mean IV-CCC varied between 0.14 and 0.29 for different soil properties). Micronutrients in general responded well to the increase in sample sizes. The uncertainty analysis revealed that increasing sample size generally reduced prediction uncertainty, though the extent varied by soil property and ML algorithm. Concisely, the results presented herein showed an effective manner of selecting an appropriate sample size and a suitable ML algorithm to predict multiple soil nutrients accurately, which would be recommended to achieve optimal accuracy for a project.

This study compares single and hybrid soft computing models for estimating daily solar radiation flux for two scenarios. Scenario I developed single soft computing models, including multilayer perceptron (MLP), support vector machines (SVM), adaptive neuro-fuzzy inference system (ANFIS), and multivariate adaptive regression splines (MARS), for estimating daily solar radiation flux at two stations from the USA and South Korea. The MLP model was used to evaluate the effect of factors controlling daily solar radiation flux. Using different combinations of controlling factors as input, the MLP and SVM models, based on evaluation measures, were found to be superior to the ANFIS and MARS models at Big Bend station, USA. In addition, the MLP, SVM, and MARS models performed better than did the ANFIS model at Incheon station, South Korea. Scenario II combined the discrete wavelet transform (DWT) and single soft computing models (e.g., MLP and SVM) for improved performance using 4-input combination. The wavelet-based MLP (WMLP) and SVM (WSVM) models were superior to other single soft computing models (MLP, SVM, ANFIS, and MARS) at two stations. Taylor diagrams, violin plots and point density plots were also utilized to examine the similarity between the observed and estimated solar radiation flux values. Results showed that scenarios I and II can be alternatives for estimating daily solar radiation flux based on different meteorological information, such as peninsular and continental conditions.

Deep learning based concrete compressive strength prediction model with hybrid meta-heuristic approach

Several machine learning (ML) algorithms have been increasingly utilized for cardiovascular disease prediction. We aim to assess and summarize the overall predictive ability of ML algorithms in cardiovascular diseases. A comprehensive search strategy was designed and executed within the MEDLINE, Embase, and Scopus databases from database inception through March 15, 2019. The primary outcome was a composite of the predictive ability of ML algorithms of coronary artery disease, heart failure, stroke, and cardiac arrhythmias. Of 344 total studies identified, 103 cohorts, with a total of 3,377,318 individuals, met our inclusion criteria. For the prediction of coronary artery disease, boosting algorithms had a pooled area under the curve (AUC) of 0.88 (95% CI 0.84–0.91), and custom-built algorithms had a pooled AUC of 0.93 (95% CI 0.85–0.97). For the prediction of stroke, support vector machine (SVM) algorithms had a pooled AUC of 0.92 (95% CI 0.81–0.97), boosting algorithms had a pooled AUC of 0.91 (95% CI 0.81–0.96), and convolutional neural network (CNN) algorithms had a pooled AUC of 0.90 (95% CI 0.83–0.95). Although inadequate studies for each algorithm for meta-analytic methodology for both heart failure and cardiac arrhythmias because the confidence intervals overlap between different methods, showing no difference, SVM may outperform other algorithms in these areas. The predictive ability of ML algorithms in cardiovascular diseases is promising, particularly SVM and boosting algorithms. However, there is heterogeneity among ML algorithms in terms of multiple parameters. This information may assist clinicians in how to interpret data and implement optimal algorithms for their dataset.

To evaluate the value of a machine learning model using enhanced CT radiomics features in the prediction of lymphovascular invasion (LVI) of esophageal squamous cell carcinoma (ESCC) before treatment. We reviewed and analyzed the enhanced CT images of 258 ESCC patients from June 2017 to December 2019. We randomly assigned the patients in a ratio of 7:3 to a training set (182 cases) and a validation (76 cases) set. Clinical risk factors and CT image characteristics were recorded, and multifactor logistic regression was used to screen independent risk factors of LVI of ESCC patients. We extracted the CT radiomics features using the FAE software and screened radiomics features using maximum relevance and minimum redundancy (MRMR) and least absolute shrinkage and selection operator (LASSO) algorithms, and finally, the radiomics labels of each patient were established. Five machine learning algorithms, namely, support vector machine (SVM), K-nearest neighbor (KNN), logistic regression (LR), Gauss naive Bayes (GNB), and multilayer perceptron (MLP), were used to construct the model of radiomics labels, and its clinical features were screened. The predictive efficacy of the machine learning model for LVI of ESCC was evaluated using the receiver operating characteristic (ROC) curve. Tumor thickness [OR = 1.189, 95% confidence interval (CI) 1.060-1.351, P = 0.005], tumor-to-normal wall enhancement ratio (TNR) (OR = 2.966, 95% CI 1.174-7.894, P = 0.024), and clinical N stage (OR = 5.828, 95% CI 1.752-20.811, P= 0.005) were determined as independent risk factors of LVI. We extracted 1,316 features from preoperative enhanced CT images and selected 14 radiomics features using MRMR and LASSO to construct the radiomics labels. In the test set, SVM, KNN, LR, and GNB showed high predictive performance, while the MLP model had poor performance. In the training set, the area under the curve (AUC) values were 0.945 and 0.905 in the KNN and SVM models, but these decreased to 0.866 and 0.867 in the validation set, indicating significant overfitting. The GNB and LR models had AUC values of 0.905 and 0.911 in the training set and 0.900 and 0.893 in the validation set, with stable performance and good fitting and predictive ability. The MLP model had AUC values of 0.658 and 0.674 in the training and validation sets, indicating poor performance. A multiscale combined model constructed using multivariate logistic regression has an AUC of 0.911 (0.870-0.951) and 0.893 (0.840-0.962), accuracy of 84.4% and 79.7%, sensitivity of 90.8% and 87.1%, and specificity of 80.5% and 79.0% in the training and validation sets, respectively. Machine learning models can preoperatively predict the condition of LVI effectively in patients with ESCC based on enhanced CT radiomics features. The GNB and LR models exhibit good stability and may bring a new way for the non-invasive prediction of LVI condition in ESCC patients before treatment.

Slope stability prediction using integrated metaheuristic and machine learning approaches: A comparative study

This study presents a comparative analysis of the classification performance of facial and emotion recognition systems using Machine Learning (ML) and Deep Learning (DL) algorithms. The primary objective of this work is to evaluate the applicability of emotion recognition in fields such as psychotherapy and crime analysis, using the FER-2013 dataset.The study was conducted with ML algorithms such as Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Decision Trees, and Gradient Boosting, as well as the DL algorithm, Convolutional Neural Network (CNN). Supported by the application of feature selection, preprocessing, and feature extraction techniques, the model’s performance was measured using standard metrics such as accuracy, precision, F1-score, and AUC-ROC.The experimental results showed that the highest classification accuracy (46.61%) was achieved with the CNN model. While the ML models generally offered lower accuracy, they provided advantages in terms of computational efficiency in specific scenarios.This study aims to contribute to the literature by providing a comparative analysis of ML and DL algorithms and by highlighting the effect of data preprocessing on performance. The findings set targets for future work, such as real-time system integration and hybrid model development.