Statistical Learning Research Articles

Applying Gaussian Process Regression for Machine Learning-Assisted Reactor Simulations

Abstract This study explores the integration of machine learning, specifically Gaussian Process Regression (GPR), into traditional reactor core simulations. Building upon previous work on Boiling Water Reactors (BWR), GPR is implemented to predict and correct errors in lower-fidelity simulation outcomes. The findings demonstrate significant improvements in prediction accuracy when GPR is coupled with the diffusion-based core simulator, exhibiting remarkable reductions in both keff and nodal power errors. The comparison reveals that the GPR-enhanced core simulation model significantly outperforms both the standalone simulation and a combination of simulation with Multivariate Linear Regression. It also competes effectively with the performance of a Deep Neural Network-enhanced model. Importantly, this methodology enhances simulation accuracy while maintaining low computational costs. The research emphasizes the vast potential of machine learning, particularly GPR, in progressing nuclear reactor simulations, highlighting the immense value of combining traditional simulation methods with advanced statistical learning techniques.

Evaluation of statistical and machine learning models using satellite data to estimate aboveground biomass: A study in Vietnam Tropical Forests

The combination of machine learning models with satellite imagery is becoming a popular data-modeling tool for biomass prediction, supporting land cover management. This study aims to select the most suitable model to estimate tropical forest aboveground biomass in Vietnam, helping to manage and monitor changes in biomass at regional and local scales. The study identified the optimal model for estimating forest aboveground biomass and minimizing the number of input variables while achieving satisfactory model performance. A total of 59 input variables, including topography, texture features, and vegetation indices, from satellite data were used in four non-parametric algorithms and a conventional parametric model, Artificial Neural Networks (ANN), Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Multiple Linear Regression (MLR) to predict biomass and evaluate changes aboveground biomass over 10 years in two tropical forests in Vietnam. The results indicated that all models had good estimation performance with R2 ranging from 0.615 to 0.754. For RF, MLR, and XGBoost, vegetation indices contributed the highest model weights, occupying 77.71% – 92.48%. For ANN and SVM, textural and topographic features were the majority of the model weights (73.74 – 96.36%). The RF model performed the best using 59 variables (R2 = 0.754, MAE = 78.5 Mg·ha−1, and %RMSE = 13.57%) and ten variables (R2 = 0.745, MAE = 85.8 Mg·ha−1, and %RMSE = 16.17%). The biomass map using the RF and ten variables achieved a good degree of fitting of 0.76, so it was suitable for managing and monitoring forest biomass in Vietnam. The results indicated a sharp decrease in the areas of dense and very dense forests from 2013 to 2021 and a gradual increase in 2023.

Comparing Machine Learning Regression Models for Early-Age Compressive Strength Prediction of Recycled Aggregate Concrete

A branch of artificial intelligence called machine learning is well-positioned as a prediction method that can take into consideration several influencing factors and complex inter-factor connections. Without being specifically trained to do so, these machine learning models have the ability to generalize, predict, and learn from data. Regression theory is a key topic in statistical modelling and machine learning. The main goal of this study is to compare the performance of several popular machine learning regression models for predicting the early-age compressive strength of concretes made from recycled concrete aggregates from a structure that demolished following the Sivrice-Elazig earthquake on January 24, 2020. Early-age concrete compressive strength is even more crucial due to factors like the fact that there are thousands of newly built structures in the aftermath of the earthquake, the quick manufacturing of these structures, and the completion of the project in the lowest amount of time. Determining the early-age concrete strength with high accuracy and in a useful manner is crucial for this reason. Seven different classical machine learning algorithms were employed in this study to achieve all of these goals. Early-age concrete compressive strength values were considered for 1 and 3 days. The relationship between the experimental results and the predicted outcomes of the employed algorithms was investigated, and a thorough comparison of these intelligent regression algorithms was conducted. Within the scope of sustainable development and circular economy goals, it is thought that this article will make significant contributions to the literature in terms of utilizing these waste materials and determining the early-age compressive strengths of the concretes produced with high accuracy.

Application of multiparametric methods of data science for the classification of Russian subjects on the basis of subsidisation

The relevance of the study is justified by the importance of monitoring and forecasting the subsidisation of the Russian regions in order to identify the main criteria for classifying subjects on the basis of subsidisation. In a brief review of the literature, mathematical models used to model the subsidisation of the Russian regions are considered. They have mainly fixed socio-economic indicators that need to be given attention while applying, and also regression models are used, but mathematically sound recommendations for the withdrawal of regions from clusters of subsidisation are not provided. The paper analyses the socio-economic and demographic indicators of the Russian regions applying methods that identify patterns in a multiparametric dataset. The methods of traditional statistical analysis and machine learning, including the author’s ones, are used. Statistically significant patterns have been identified, reflecting the relationship of subsidisation with such indicators as investments in fixed capital, fixed assets, average per capita income and average size of assigned pensions, unemployment rate, etc. The performed logical and statistical analysis strongly supports the use of machine learning (Data Science) methods in identifying statistically significant relationships between various indicators characterising the development of the regions of the Russian Federation.

Active Inference in Psychology and Psychiatry: Progress to Date?

The free energy principle is a formal theory of adaptive self-organising systems that emerged from statistical thermodynamics, machine learning and theoretical neuroscience and has since been translated into biologically plausible 'process theories' of cognition and behaviour, which fall under the banner of 'active inference'. Despite the promise this theory holds for theorising, research and practical applications in psychology and psychiatry, its impact on these disciplines has only now begun to bear fruit. The aim of this treatment is to consider the extent to which active inference has informed theoretical progress in psychology, before exploring its contributions to our understanding and treatment of psychopathology. Despite facing persistent translational obstacles, progress suggests that active inference has the potential to become a new paradigm that promises to unite psychology's subdisciplines, while readily incorporating the traditionally competing paradigms of evolutionary and developmental psychology. To date, however, progress towards this end has been slow. Meanwhile, the main outstanding question is whether this theory will make a positive difference through applications in clinical psychology, and its sister discipline of psychiatry.

The impact of predictive analytics on financial risk management in businesses

This paper examines the impact of predictive analytics on financial risk management in businesses. Predictive analytics involves the use of statistical algorithms, machine learning, and data mining techniques to analyze historical data and predict future outcomes. In the context of financial risk management, predictive analytics plays a critical role in identifying, assessing, and mitigating potential financial risks. This paper explores various machine learning algorithms, including neural networks, decision trees, and support vector machines, and their applications in risk management. It also discusses data sources, preprocessing techniques, and the challenges associated with data privacy, model interpretability, and prediction accuracy. The review highlights successful implementations of predictive analytics in financial risk management and provides recommendations for future research and practical applications. As predictive analytics continues to advance, its integration with emerging technologies such as artificial intelligence and blockchain promises to enhance financial risk management practices.

Comparative analysis of the predictive power of statistical models of macroeconomic indicators in conditions of permanent crises

Subject. The article discusses prediction of the state of the economy, the accuracy of forecasts of traditional models during crises, the need to find more effective model specifications to predict macro indicators. Objectives. The purpose is to carry out a comparative analysis of the predictive ability of ensemble methods in comparison with a set of models, including traditional statistical algorithms and machine learning algorithms. Methods. The comparative analysis of predictive ability of the models and interpretation of results obtained were performed using a dynamic factor model (DFM), a neural network with long-term short-term memory (LSTM), and integrated gradient methods (IG). Results. We performed the analysis of predictive ability of the ensemble model to forecast GDP, which combines DFM and LSTM to account for both linear and nonlinear dependencies in the data; the analysis of predictive power of various indicators, which showed that an increase in forecast error is observed for all models except DFM, the ensemble model with an error correction structure, and ARMAX. The obtained results can be used to build models of macroeconomic indicators in order to make strategic decisions by enterprises of various industries operating in a highly uncertain environment. Conclusions. The combination of DFM and LSTM in the ensemble provides higher accuracy forecasts than LSTM and competitor models, however, with less predictive power than DFM.

Development of a machine learning model to support low cost real-time Legionella monitoring in premise plumbing systems

Legionella pneumophila (L. pneumophila) is a pathogenic bacterium primarily known for causing Legionnaires’ Disease which is known for high mortality rates, particularly in the elderly. With caseloads continuing to increase, further research is needed to improve our understanding of optimized sampling schema and safe limits of L. pneumophila, in part to target improved treatment options and realistic population-level risk modeling. Particularly in healthcare and other high-risk locations these become crucial and time sensitive needs. Therefore, we conceptualized this research as a means of incorporating easily measured physiochemical water quality parameters and generalization of the unique ecology of building water systems to build a computational model that can allow for more rapid and accurate decision making. This research uses the specific machine learning (ML) method called statistical learning theory to incorporate concentration of host cells, such as native amoeba, and physiochemical water quality parameters to estimate the probability of observing ranges of Legionella gene copy concentrations. Using data from previously published research on Legionella prevalence in a large building, our ML method trains the model on the relative impacts of physiochemical parameters on likely amoeba host cell occurrences. The model is expanded to estimate host cell concentrations using correlations and regressions operated through LASSO algorithms. After categorization variables from these results are then used to inform a logistic regression to provide an estimate of the probability of Legionella gene copy concentration ranges. In summary, conventional results generated by logistic regression and multiple linear regression quantified the associations among ecological conditions in the water and ability to predict a likely range of Legionella concentration in a management focused way. Further, two ML methods, PCA and LASSO, demonstrated feasibility in accurate real-time monitoring of Legionella through physiochemical indicators as evidenced with good accuracy of predictions based for validation results. Furthermore results demonstrate the vital need to account for the impact of water quality on building on host cells, and via their quantified water microbial ecology, not just Legionella concentrations.

COVID-19 from symptoms to prediction: A statistical and machine learning approach

During the COVID-19 pandemic, the analysis of patient data has become a cornerstone for developing effective public health strategies. This study leverages a dataset comprising over 10,000 anonymized patient records from various leading medical institutions to predict COVID-19 patient age groups using a suite of statistical and machine learning techniques. Initially, extensive statistical tests including ANOVA and t-tests were utilized to assess relationships among demographic and symptomatic variables. The study then employed machine learning models such as Decision Tree, Naïve Bayes, KNN, Gradient Boosted Trees, Support Vector Machine, and Random Forest, with rigorous data preprocessing to enhance model accuracy. Further improvements were sought through ensemble methods; bagging, boosting, and stacking. Our findings indicate strong associations between key symptoms and patient age groups, with ensemble methods significantly enhancing model accuracy. Specifically, stacking applied with random forest as a meta leaner exhibited the highest accuracy (0.7054). In addition, the implementation of stacking techniques notably improved the performance of K-Nearest Neighbors (from 0.529 to 0.63) and Naïve Bayes (from 0.554 to 0.622) and demonstrated the most successful prediction method. The study aimed to understand the number of symptoms identified in COVID-19 patients and their association with different age groups. The results can assist doctors and higher authorities in improving treatment strategies. Additionally, several decision-making techniques can be applied during pandemic, tailored to specific age groups, such as resource allocation, medicine availability, vaccine development, and treatment strategies. The integration of these predictive models into clinical settings could support real-time public health responses and targeted intervention strategies.

Temporal dynamics of uncertainty and prediction error in musical improvisation across different periods

Human improvisational acts contain an innate individuality, derived from one’s experiences based on epochal and cultural backgrounds. Musical improvisation, much like spontaneous speech, reveals intricate facets of the improviser’s state of mind and emotional character. However, the specific musical components that reveal such individuality remain largely unexplored. Within the framework of human statistical learning and predictive processing, this study examined the temporal dynamics of uncertainty and surprise (prediction error) in a piece of musical improvisation. This cognitive process reconciles the raw auditory cues, such as melody and rhythm, with the musical predictive models shaped by its prior experiences. This study employed the Hierarchical Bayesian Statistical Learning (HBSL) model to analyze a corpus of 456 Jazz improvisations, spanning 1905 to 2009, from 78 distinct Jazz musicians. The results indicated distinctive temporal patterns of surprise and uncertainty, especially in pitch and pitch-rhythm sequences, revealing era-specific features from the early 20th to the 21st centuries. Conversely, rhythm sequences exhibited a consistent degree of uncertainty across eras. Further, the acoustic properties remain unchanged across different periods. These findings highlight the importance of how temporal dynamics of surprise and uncertainty in improvisational music change over periods, profoundly influencing the distinctive methodologies artists adopt for improvisation in each era. Further, it is suggested that the development of improvisational music can be attributed to the adaptive statistical learning mechanisms. This study explores the period-specific characteristics in the temporal dynamics of improvisational music, emphasizing how artists adapt their methods to resonate with the cultural and emotional contexts of their times. Such shifts in improvisational ways offer a window into understanding how artists intuitively respond and adapt their craft to resonate with the cultural zeitgeist and the emotional landscapes of their respective times.

Understanding the Relationship Between Comorbidities, Medication Nonadherence, Activities of Daily Living, and Heart Condition Status Among Older Adults in the United States: A Regression Analysis and Machine Learning Approach.

Nonadherence to medication among patients with heart disease poses serious risks, including worsened heart failure and increased mortality rates. This study aims to explore the complex interplay between comorbidities, medication nonadherence, activities of daily living, and heart condition status in older American adults, using both traditional statistical methods and machine learning. Data from 326 older adults with heart conditions, drawn from the Health and Retirement Study, were analyzed. Descriptive statistics characterized demographic profiles and comorbidities, whereas logistic regression, multiple regression analyses, and decision tree models were used to address our research inquiries. In addition, a machine learning approach, specifically decision tree models, was integrated to enhance predictive accuracy. Our analysis showed that factors like age, gender, hypertension, and stroke history were significantly linked to worsening heart conditions. Notably, depression emerged as a robust predictor of medication nonadherence. Further adjusted analyses underscored significant correlations between stroke and challenges in basic activities such as dressing, bathing, and eating. Depression correlated significantly with difficulties in dressing, bed mobility, and toileting, whereas lung disease was associated with bathing hindrances. Intriguingly, our decision tree model revealed that patients experiencing dressing challenges, but not toileting difficulties, were more prone to report no improvement in heart condition status over the preceding 2 years. Blending traditional statistics with machine learning in this study reveals significant implications for crafting personalized interventions to improve patients' depression, leading to increased activities of daily living, medication adherence, reduced severity of comorbidities, and ultimately better management of heart conditions.

High-performance virtual sensors array based on a single-chip FBAR for volatile organic compounds (VOCs) detection and classification

The detection and classification of volatile organic compounds (VOCs) are of great significance in atmospheric environment monitoring and have garnered extensive attention in recent decades. This study proposes a virtual sensor array (VSA) for VOC detection and classification fabricating a single-chip high-Q-factor film bulk acoustic resonator (FBAR) functionalized with MIL-101(Cr) thin film, known for its porous crystal structure and high specific surface area. The sensing performance of five different VOCs was evaluated to characterize the VOCs, achieving high detection accuracy calibrated with the Langmuir adsorption model. The FBAR’s frequency response was utilized to determine the sensitivity and limit of detection (LOD), yielding sensitivity and LOD of 85.45 Hz/ppm and 51 ppm, respectively, for isopropanol. The identification and classification capabilities of the proposed VSA for VOCs and their mixtures were assessed using statistical methods and machine learning algorithms, realizing classification accuracies of 100 % for pure VOCs and 94.6 % for mixtures. The developed VSA demonstrates superior performances in VOC detection and classification, with potential applications across various domains.

Будущее уголовного правосудия: роль искусственного интеллекта в предиктивной аналитике

Introduction. This article focuses on the importance and prospects for the use of artificial intelligence in predictive analytics in the criminal justice context. The research is motivated by the significant development of artificial intelligence and machine learning technologies, which are being used in a multitude of fields, including criminal justice. The authors detail the theoretical and practical aspects of predictive analytics, which makes it possible to predict future events based on statistical data and machine learning algorithms. Special attention is paid to the difference between artificial intelligence and predictive analytics. The effectiveness of the application of predictive analytics in criminal justice, including optimising preliminary investigations, improving criminal prosecution and predicting the outcome of criminal cases, is highlighted. Methods. The basis of the research methodology is dialectical materialism, applied general scientific (system-structural and formallogical, inductive and deductive, analysis and synthesis) and special (formal-legal, comparativelegal) methods. Results. The authors conclude that artificial intelligence spans a wider range of tasks requiring human intelligence, while predictive analytics concentrates on making predictions. Advanced technologies that are already in active use in various countries, improving and optimising the allocation of law enforcement and judicial resources, are described. The prospect of integrating virtual and augmented reality technologies into criminal justice is considered, which can radically change approaches to predictive analytics and criminal procedure in general, enriching visualisation and interactive cooperation between participants of legal relations.

Comparative study of machine learning and statistical survival models for enhancing cervical cancer prognosis and risk factor assessment using SEER data.

Cervical cancer is a common malignant tumor of the female reproductive system and the leading cause of death among women worldwide. The survival prediction method can be used to effectively analyze the time to event, which is essential in any clinical study. This study aims to bridge the gap between traditional statistical methods and machine learning in survival analysis by revealing which techniques are most effective in predicting survival, with a particular emphasis on improving prediction accuracy and identifying key risk factors for cervical cancer. Women with cervical cancer diagnosed between 2013 and 2015 were included in our study using data from the Surveillance, Epidemiology, and End Results (SEER) database. Using this dataset, the study assesses the performance of Weibull, Cox proportional hazards models, and Random Survival Forests in terms of predictive accuracy and risk factor identification. The findings reveal that machine learning models, particularly Random Survival Forests (RSF), outperform traditional statistical methods in both predictive accuracy and the discernment of crucial prognostic factors, underscoring the advantages of machine learning in handling complex survival data. However, for a survival dataset with a small number of predictors, statistical models should be used first. The study finds that RSF models enhance survival analysis with more accurate predictions and insights into survival risk factors but highlights the need for larger datasets and further research on model interpretability and clinical applicability.

SpaTopic: A statistical learning framework for exploring tumor spatial architecture from spatially resolved transcriptomic data.

Tumor tissues exhibit a complex spatial architecture within the tumor microenvironment (TME). Spatially resolved transcriptomics (SRT) is promising for unveiling the spatial structures of the TME at both cellular and molecular levels, but identifying pathology-relevant spatial domains remains challenging. Here, we introduce SpaTopic, a statistical learning framework that harmonizes spot clustering and cell-type deconvolution by integrating single-cell transcriptomics and SRT data. Through topic modeling, SpaTopic stratifies the TME into spatial domains with coherent cellular organization, facilitating refined annotation of the spatial architecture with improved performance. We assess SpaTopic across various tumor types and show accurate prediction of tertiary lymphoid structures and tumor boundaries. Moreover, marker genes derived from SpaTopic are transferrable and can be applied to mark spatial domains in other datasets. In addition, SpaTopic enables quantitative comparison and functional characterization of spatial domains across SRT datasets. Overall, SpaTopic presents an innovative analytical framework for exploring, comparing, and interpreting tumor SRT data.

Development, study, and comparison of models of cross-immunity to the influenza virus using statistical methods and machine learning.

The World Health Organization considers the values of antibody titers in the hemagglutination inhibition assay as one of the most important criteria for assessing successful vaccination. Mathematical modeling of cross-immunity allows for identification on a real-time basis of new antigenic variants, which is of paramount importance for human health. This study uses statistical methods and machine learning techniques from simple to complex: logistic regression model, random forest method, and gradient boosting. The calculations used the AAindex matrices in parallel to the Hamming distance. The calculations were carried out with different types and values of antigenic escape thresholds, on four data sets. The results were compared using common binary classification metrics. Significant differentiation is shown depending on the data sets used. The best results were demonstrated by all three models for the forecast autumn season of 2022, which were preliminary trained on the February season of the same year (Auroc 0.934; 0.958; 0.956, respectively). The lowest results were obtained for the entire forecast year 2023, they were set up on data from two seasons of 2022 (Aucroc 0.614; 0.658; 0.775). The dependence of the results on the types of thresholds used and their values turned out to be insignificant. The additional use of AAindex matrices did not significantly improve the results of the models without introducing significant deterioration. More complex models show better results. When developing cross-immunity models, testing on a variety of data sets is important to make strong claims about their prognostic robustness.

The order of stimuli matters when learning second-order transitional probabilities.

The order of stimuli within sequences and the transitional probabilities (TPs) it generates are central information in sequence processing. However, less is known about what type of information and how it is extracted by general learning mechanisms. The present study focused on statistical learning of second-order TPs. Second-order TPs are involved when only the combination of two stimuli predicts the third. In a first experiment, TPs depended crucially on the order of presentation of a pair , which led to different predictions depending on the order of the stimuli (i.e., ABC vs.BAF). Eight visuomotor sequences governed by second-order TPs were used and response times (RTs) were recorded for each transition. The task included a learning phase followed by a switch phase during which the second-order TP were reversed (e.g., the sequences ABC and BAF became respectively ABF and BAC). A decrease of RTs between the second and the third stimulus during the learning phase and an increase of RTs during the switch phase suggested that variations of orders within second-order TPs could be learned. Further analyses, however, indicated that such learning was difficult for most participants. A second experiment showed that the difficulty of learning was not solely due to the difficulty to pick up the effect of order of presentation, but that learning second-order transitional probabilities in addition to order would be the main obstacle. These experiments suggest that statistical learning is capable of learning complex associations, even if this remains a challenge for human cognition.

Pengaruh Media Fun Learning Card Terhadap Hasil Belajar Peserta Didik Kelas XI SMAN 21 Surabaya

Education plays an important role in shaping learners' competencies, including cognitive, affective and psychomotor aspects to face the challenges of the times. In Indonesia, education should look at holistic aspects that include character development, life skills and social abilities as mandated in Law No. 20/2003. However, challenges in classroom management and learning boredom often become obstacles. For this reason, innovative approaches are needed, such as the use of interactive learning media. This study aims to examine the effect of using Fun Learning Card media on the learning outcomes of grade XI students at SMA Negeri 21 Surabaya. This media is expected to significantly increase student participation and understanding, overcome boredom, and create more meaningful learning. By using descriptive statistical analysis techniques, standard deviation, and learning outcome categories, the following results were found before using the learning media in cycle 1 with an average score of 49.6. The score was obtained from the lowest score of 35 and the highest score of 70, then also obtained a standard deviation score (P) of 10.2. In cycle 2 using Fun Learning Card media, the highest score was 97 while the lowest score was 76 with an average score of 85.4 and a standard deviation of 6.3.

Speaker variability, but not bilingualism, influences cross-situational word learning.

When learning new words, listeners must contend with multiple sources of ambiguity and variability. Research has revealed that learners can resolve referential ambiguity by tracking co-occurrence statistics between words and their referents across multiple exposures over time-a process termed cross-situational word learning (XSWL). However, the degree to which variability in the input, such as input from multiple speakers, and variability in learner experience, such as bilingual language experience, modulate XSWL remains unclear. In this study, we examined the effects of speaker variability in XSWL performance in monolingual adults and bilingual adults with a range of second language backgrounds and language acquisition histories. Results revealed above-chance word learning in both the single and the multiple-speaker conditions across language groups. An advantage for word learning was observed in the single-speaker condition, but the effects of bilingual language experience were null. This research adds to the limited body of work dedicated to extending theories of statistical learning to account for variations in both input and learner characteristics as well as their interactions.

Predicting time to cracking of concrete composites under restrained shrinkage: A review with insights from statistical analysis and ensemble machine learning approaches

Restrained shrinkage cracking significantly undermines the performance of reinforced concrete and shortens the structures' lifespan. Standard methods have been established to examine restrained shrinkage cracking of cementitious composites, i.e., ASTM C1581, AASHTO T 334, AASHTO T 363, and RILEM TC 119-TCE. Deficiencies in testing methods for accommodating and evaluating different cementitious composites have been recognized. Nevertheless, the significance of the restrained shrinkage cracking factors and cracking vulnerability based on the degree of restraint provided by different testing methods remain unexplored. This article provides a critical review of testing methods and studies on restrained shrinkage cracking in cementitious composites, highlighting the limitations, advantages, and further capabilities. Comprehensive experimental test datasets associated with standard restrained shrinkage cracking test methods are compiled. Advanced statistical analysis and machine learning (ML) techniques are utilized to predict time-to-cracking (TTC) of cementitious composites subjected to various testing methods based on the cracking factors. Robust and precise ML's bagging and boosting algorithms such as random forest, gradient boosting machine, extreme gradient boosting, adaptive boosting, categorical gradient boosting, and stacking ensemble models are utilized to merge predictions of the various approaches on TTC. Despite the satisfactory performance of statistical modeling, stacking demonstrates the highest precision in forecasting TTC, achieving an R2 of 0.92 for the ASTM dataset and 0.65 for the AASHTO dataset. The derived statistical and ML models reveal the significance of drying shrinkage, binder content, and moist curing as the most important factors in TTC based on ASTM C1581 and AASHTO T 334 standard testing methods. Equations are derived to predict cracking vulnerability and design concrete composites that offer delayed TTC and prolonged service life.