Boosting-based ensemble machine learning models for predicting unconfined compressive strength of geopolymer stabilized clayey soil.

The present research employs new boosting-based ensemble machine learning models i.e., gradient boosting (GB) and adaptive boosting (AdaBoost) to predict the unconfined compressive strength (UCS) of geopolymer stabilized clayey soil. The GB and AdaBoost models were developed and validated using 270 clayey soil samples stabilized with geopolymer, with ground-granulated blast-furnace slag and fly ash as source materials and sodium hydroxide solution as alkali activator. The database was randomly divided into training (80%) and testing (20%) sets for model development and validation. Several performance metrics, including coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), and mean squared error (MSE), were utilized to assess the accuracy and reliability of the developed models. The statistical results of this research showed that the GB and AdaBoost are reliable models based on the obtained values of R2 (= 0.980, 0.975), MAE (= 0.585, 0.655), RMSE (= 0.969, 1.088), and MSE (= 0.940, 1.185) for the testing dataset, respectively compared to the widely used artificial neural network, random forest, extreme gradient boosting, multivariable regression, and multi-gen genetic programming based models. Furthermore, the sensitivity analysis result shows that ground-granulated blast-furnace slag content was the key parameter affecting the UCS.

Evaluation of miRNA-146a, miRNA-34a, and pro-inflammatory cytokines as a potential early indicators for type 1 diabetes mellitus.

Background: Type I diabetes mellitus (T1DM) is one of the most common chronic autoimmune diseases worldwide. miRNAs are a class of small non-coding RNA molecules that have been linked to immune system functions, ß-cell metabolism, proliferation, and death, all of which contribute to pathogenesis of TIDM. Dysregulated miRNAs have been identified in Egyptian TIDM patients. Aim: Several miRNAs were profiled in Egyptian TIDM patients to determine whether they can be used as molecular biomarkers for T1DM. The relationship between the investigated miRNAs and pro-inflammatory cytokines (TNF-α and IL-6) has also been evaluated in the development of TIDM, in addition to the creation of a proposed model for TIDM prediction. Patients & methods: Case-control study included 177 Egyptian patients with confirmed type I diabetes mellitus and 177 healthy individuals. MiRNA-34 and miRNA-146 were detected in serum samples using real-time PCR, whereas TNF-α and IL-6 levels were assessed using ELIZA. Results: Patients with TIDM showed a significant decrease in the expression of miRNA-146, with a cut-off value ≤ 3.3, 48 % specificity, and 92.1 % sensitivity, whereas miRNA-34 had the highest sensitivity (95.5 %) and specificity (97.2 %) for differentiating diabetic patients from controls. Furthermore, other diagnostic proinflammatory markers showed lower sensitivity and specificity. Conclusion: Serum levels of miRNA-34a, miRNA-146, IL-6, and TNF-α provide new insights into T1DM pathogenesis and could be used for screening and diagnosis purposes. They can be also a potential therapeutic target, as well as allowing for more strategies to improve T1DM disease outcomes.