Search Results (164)

A newly emerging disease affecting Schizolobium parahyba (commonly known as pachaco), termed “decline and dieback,” has been reported in association with the fungal pathogens Fusarium sp. and Botryodiplodia sp. This study assessed the antagonistic potential of two Trichoderma sp. isolates (CEP-01 and CEP-02) against these phytopathogens under controlled laboratory conditions. The effects of three temperature regimes (5 ± 2 °C, 24 ± 2 °C, and 30 ± 2 °C) on the growth and inhibitory activity of two Trichoderma spp. isolates were evaluated using a completely randomized design. The first experiment included six treatments with five replicates, while the second comprised twelve treatments, also with five replicates. All assays were conducted on PDA medium. No fungal growth was observed at 5 ± 2 °C. However, at 24 ± 2 °C and 30 ± 2 °C, both isolates reached maximum growth within 72 h. At 24 ± 2 °C, both Trichoderma spp. isolates exhibited inhibitory activity against Fusarium sp. FE07 and FE08, with radial growth inhibition percentages (RGIP) ranging from 37.6% to 44.4% and 52,8% to 54.6%, respectively. When combined, the isolates achieved up to 60% inhibition against Fusarium sp., while Botryodiplodia sp. was inhibited by 40%. At 30 ± 2 °C, the antagonistic activity of Trichoderma sp. CEP-01 declined (25.6–32.4% RGIP), whereas Trichoderma sp. CEP-02 showed increased inhibition (60.3%–67.2%). The combination of isolates exhibited the highest inhibitory effect against Fusarium sp. FE07 and FE08 (68.4%–69.3%). Nonetheless, the inhibitory effect on Botryodiplodia sp. BIOT was reduced under elevated temperatures across all treatments. These findings reinforce the potential of Trichoderma spp. isolates as a viable and eco-friendly alternative for the biological control of pathogens affecting S. parahyba, contributing to more sustainable disease management practices. The observed inhibitory capacity of Trichoderma sp., especially under optimal temperature conditions, highlights its potential for application in integrated disease management programs, contributing to forest health and reducing reliance on chemical products. Full article

This study presents a multi-modal investigation into the wear behavior of bio-based epoxy composites reinforced with multi-walled carbon nanotubes (MWCNTs) at 0–0.75 wt%. A Taguchi L16 orthogonal array was employed to systematically assess the influence of MWCNT content, load (20–50 N), and sliding speed (1–2.5 m/s) on wear rate (WR), coefficient of friction (COF), and surface roughness (Ra). Statistical analysis revealed that MWCNT content contributed up to 85.35% to wear reduction, with 0.5 wt% identified as the optimal reinforcement level, achieving the lowest WR (3.1 mm³/N·m) and Ra (0.7 µm). Complementary morphological characterization via SEM and AFM confirmed microstructural improvements at optimal loading and identified degradation features (ploughing, agglomeration) at 0 wt% and 0.75 wt%. Regression models (R² > 0.95) effectively captured the nonlinear wear response, while a Random Forest model trained on GLCM-derived image features (e.g., correlation, entropy) yielded WR prediction accuracy of R² ≈ 0.93. Key image-based predictors were found to correlate strongly with measured tribological metrics, validating the integration of surface texture analysis into predictive modeling. This integrated framework combining experimental design, mathematical modeling, and image-based machine learning offers a robust pathway for designing high-performance, sustainable nanocomposites with data-driven diagnostics for wear prediction. Full article

Software-defined networking (SDN) represents a transformative shift in network architecture by decoupling the control plane from the data plane, enabling centralized and flexible management of network resources. However, this architectural shift introduces significant security challenges, as SDN’s centralized control becomes an attractive target for various types of attacks. While the body of current research on attack detection in SDN has yielded important results, several critical gaps remain that require further exploration. Addressing challenges in feature selection, broadening the scope beyond Distributed Denial of Service (DDoS) attacks, strengthening attack decisions based on multi-flow analysis, and building models capable of detecting unseen attacks that they have not been explicitly trained on are essential steps toward advancing security measures in SDN environments. In this paper, we introduce a novel approach that leverages Natural Language Processing (NLP) and the pre-trained Bidirectional Encoder Representations from Transformers (BERT)-base-uncased model to enhance the detection of attacks in SDN environments. Our approach transforms network flow data into a format interpretable by language models, allowing BERT-base-uncased to capture intricate patterns and relationships within network traffic. By utilizing Random Forest for feature selection, we optimize model performance and reduce computational overhead, ensuring efficient and accurate detection. Attack decisions are made based on several flows, providing stronger and more reliable detection of malicious traffic. Furthermore, our proposed method is specifically designed to detect previously unseen attacks, offering a solution for identifying threats that the model was not explicitly trained on. To rigorously evaluate our approach, we conducted experiments in two scenarios: one focused on detecting known attacks, achieving an accuracy, precision, recall, and F1-score of 99.96%, and another on detecting previously unseen attacks, where our model achieved 99.96% in all metrics, demonstrating the robustness and precision of our framework in detecting evolving threats, and reinforcing its potential to improve the security and resilience of SDN networks. Full article

Accurate and interpretable prediction plays a vital role in natural language processing (NLP) tasks, particularly for enhancing user trust and model transparency. However, existing models often struggle with poor adaptability and limited interpretability when applied to dynamic language prediction tasks such as Wordle. To address these challenges, this study proposes an interpretable reinforcement learning framework based on an Enhanced Deep Deterministic Policy Gradient (Enhanced-DDPG) algorithm. By leveraging a custom simulation environment and integrating key linguistic features word frequency, letter frequency, and repeated letter patterns (rep) the model dynamically predicts the number of attempts needed to solve Wordle puzzles. Experimental results demonstrate that Enhanced-DDPG outperforms traditional methods such as Random Forest Regression (RFR), XGBoost, LightGBM, METRA, and SQIRL in terms of both prediction accuracy (MSE = 0.0134, R² = 0.8439) and robustness under noisy conditions. Furthermore, SHapley Additive exPlanations (SHAP) are employed to interpret the model’s decision process, revealing that repeated letter patterns significantly influence low-attempt predictions, while word and letter frequencies are more relevant for higher attempt scenarios. This research highlights the potential of combining interpretable artificial intelligence (I-AI) and reinforcement learning to develop robust, transparent, and high-performance NLP prediction systems for real-world applications. Full article

Reinforced concrete deep beams (RCDBs) provide significant strength and serviceability for building structures. However, a simple, general, and universally accepted procedure for predicting their shear strength (SS) has yet to be established. This study proposes a novel data-driven approach to predicting the SS of RCDBs using an enhanced CatBoost (CB) model. For this purpose, a newly comprehensive database of RCDBs with shear failure, including 950 experimental specimens, was established and adopted. The model was developed through a customized procedure including feature selection, data preprocessing, hyperparameter tuning, and model evaluation. The CB model was further evaluated against three data-driven models (e.g., Random Forest, Extra Trees, and AdaBoost) as well as three prominent mechanics-driven models (e.g., ACI 318, CSA A23.3, and EU2). Finally, the SHAP algorithm was employed for interpretation to increase the model’s reliability. The results revealed that the CB model yielded a superior accuracy and outperformed all other models. In addition, the interpretation results showed similar trends between the CB model and mechanics-driven models. The geometric dimensions and concrete properties are the most influential input features on the SS, followed by reinforcement properties. In which the SS can be significantly improved by increasing beam width and concert strength, and by reducing shear span-to-depth ratio. Thus, the proposed interpretable data-driven model has a high potential to be an alternative approach for design practice in structural engineering. Full article

Usher syndrome, a rare genetic disorder causing both hearing and vision loss, presents significant diagnostic and therapeutic challenges due to its complex genetic basis. The identification of reliable biomarkers for early detection and intervention is crucial for improving patient outcomes. In this study, we present a machine learning-based hybrid sequential feature selection approach to identify key mRNA biomarkers associated with Usher syndrome. Beginning with a dataset of 42,334 mRNA features, our approach successfully reduced dimensionality and identified 58 top mRNA biomarkers that distinguish Usher syndrome from control samples. We employed a combination of feature selection techniques, including variance thresholding, recursive feature elimination, and Lasso regression, integrated within a nested cross-validation framework. The selected biomarkers were further validated using multiple machine learning models, including Logistic Regression, Random Forest, and Support Vector Machines, demonstrating robust classification performance. To assess the biological relevance of the computationally identified mRNA biomarkers, we experimentally validated candidates from the top 10 selected mRNAs using droplet digital PCR (ddPCR). The ddPCR results were consistent with expression patterns observed in the integrated transcriptomic metadata, reinforcing the credibility of our machine learning-driven biomarker discovery framework. Our findings highlight the potential of machine learning-driven biomarker discovery to enhance the detection of Usher syndrome. Full article

The drilling and blasting method is commonly employed for the rapid demolition of outdated buildings by destroying key structural components and inducing progressive collapse. The residual bearing capacity of these components is governed by the deformation morphology of the longitudinal reinforcement, characterized by bending deflection and exposed height. This study develops and validates a finite element (FE) model of a reinforced concrete (RC) column subjected to demolition blasting. By varying concrete compressive strength, the yield strength of longitudinal reinforcement, the longitudinal reinforcement ratio, and the shear reinforcement ratio, 45 FE models are established to simulate the post-blast morphology of longitudinal reinforcement. Two databases are created: one containing 45 original simulation cases, and an augmented version with 225 cases generated through data augmentation. To predict bending deflection and the exposed height of longitudinal reinforcement, artificial neural network (ANN) and random forest (RF) models are optimized using the hunter–prey optimization (HPO) algorithm. Results show that the HPO-optimized RF model trained on the augmented database achieves the best performance, with MSE, MAE, and R² values of 0.004, 0.041, and 0.931 on the training set, and 0.007, 0.057, and 0.865 on the testing set, respectively. Sensitivity analysis reveals that the yield strength of longitudinal reinforcement has the most significant impact, while the shear reinforcement ratio has the least influence on both output variables. The partial dependence plot (PDP) analysis indicates that the ratio of shear reinforcement has the most significant impact on the deformation of longitudinal reinforcement. Full article

The dynamic thermomechanical properties of wood–plastic composites (WPCs) are influenced by various factors, such as the selection of raw materials and processing parameters. To investigate the effects of different wood fiber content ratios and temperature on the loss modulus of WPCs, seven different proportions of Masson pine (Pinus massoniana Lamb.) and Chinese fir [Cunninghamia lanceolata (Lamb.) Hook.] mixed-fiber-reinforced HDPE composites were prepared using the extrusion molding method. Their dynamic thermomechanical properties were tested and analyzed. The storage modulus of WPCs showed a decreasing trend with increasing temperature. A reduction in the mass ratio of Masson pine wood fibers to Chinese fir wood fibers resulted in an increase in the storage modulus of WPCs. The highest storage modulus was achieved when the mass ratio of Masson pine wood fibers to Chinese fir wood fibers was 1:5. In addition, the loss modulus of the composites increased as the content of Masson pine fiber decreased, with the lowest loss modulus observed in HDPE composites reinforced with Masson pine wood fibers. The loss tangent for all seven types of WPCs increased with rising temperatures, with the maximum loss tangent observed in WPCs reinforced with Masson pine wood fibers and HDPE. A prediction method based on the Extreme Learning Machine (ELM) model was introduced to predict the dynamic thermomechanical properties of WPCs. The prediction accuracy of the ELM model was compared comprehensively with that of other models, including Support Vector Machines (SVMs), Random Forest (RF), Back Propagation (BP) neural networks, and Particle Swarm Optimization-BP (PSO-BP) neural network models. Among these, the ELM model showed superior data fitting and prediction accuracy, with an R² value of 0.992, Mean Absolute Error (MAE) of 1.363, and Root Mean Square Error (RMSE) of 3.311. Compared to the other models, the ELM model demonstrated the best performance. This study provides a solid basis and reference for future research on the dynamic thermomechanical properties of WPCs. Full article

This study presents a protocol for applying Interpretable Machine Learning (IML) to enhance communication within Variety Registration Offices (VROs). Rather than focusing on a model comparison, we illustrate how two IML-compatible models—Random Forests and AMBARTI—can support a clearer interpretation of genotype-by-environment (G×E) interactions and variable importance. Using multi-environment wheat trial data from CREA-DC-Milano across Italian sites, we predicted the yield and protein content while visualizing the performance patterns. Genotype g25 ranked first in protein across both years, while g20 led in yield in Year 1. Tolentino consistently supported higher protein levels; Torino and Tolentino led in yield, varying by year. These insights, made accessible through intuitive IML visualizations, proved valuable in supporting VRO, reinforcing the role of IML as a practical communication tool in regulatory processes, agricultural innovation, and food security. Full article

Predicting the flexural behavior of fiber-reinforced ultra-high-performance concrete (UHPC) remains a significant challenge due to the complex interactions among numerous mix design parameters. This study presents a machine learning-based framework aimed at accurately estimating the modulus of rupture (MOR) of UHPC. A comprehensive dataset comprising 566 distinct mixtures, characterized by 41 compositional and fiber-related variables, was compiled. Seven regression models were trained and evaluated, with Random Forest, Extremely Randomized Trees, and XGBoost yielding coefficients of determination (R²) exceeding 0.84 on the test set. Feature importance was quantified using Shapley values, while partial dependence plots (PDPs) were employed to visualize both individual parameter effects and key interactions, notably between fiber factor, water-to-binder ratio, maximum aggregate size, and matrix compressive strength. To validate the predictive performance of the machine learning models, an independent experimental campaign was carried out comprising 26 UHPC mixtures designed with varying binder compositions—including supplementary cementitious materials such as fly ash, ground recycled glass, and calcium carbonate—and reinforced with mono-fiber (straight steel, hooked steel, and PVA) and hybrid-fiber systems. The best-performing models were integrated into a hybrid neural network, which achieved a validation accuracy of R² = 0.951 against this diverse experimental dataset, demonstrating robust generalizability across both material and reinforcement variations. The proposed framework offers a robust predictive tool to support the design of more sustainable UHPC formulations incorporating supplementary cementitious materials without compromising flexural performance. Full article

Acoustic emission (AE) signals exhibit a strong correlation with concrete damage. However, the relationship between column damage and AE signals under eccentric loading conditions, combined with the application of traditional RA-AF classification methods for crack characterization, demonstrates limitations. These approaches provide insufficient resolution to accurately identify damage types throughout the entire structural failure process. This study employed K-means clustering algorithm and Gaussian mixture models (GMMs) to analyze AE signal features from reinforced concrete (RC) columns undergoing failure under the eccentric compression loading of different eccentricity. Subsequently, a random forest model was used for automated damage stage classification. Experimental results demonstrate that the damage progression in eccentrically compressed columns comprises four distinct stages, each exhibiting unique AE signal characteristics. The integrated approach of clustering and random forest modeling demonstrates robust feasibility in identifying AE signal patterns associated with specific damage stages, achieving an 85% recognition rate for damage stage classification. These findings provide quantitatively validated evidence supporting the efficacy of machine learning-based methodologies for enabling stage-specific damage characterization in structural health monitoring applications. Full article

The strengthening of reinforced concrete (RC) beams with aluminum alloy was typically implemented in a symmetrical configuration. To evaluate the flexural performance of strengthened beams, four machine learning (ML)-based models, namely Random Forest (RF), Xtreme Gradient Boosting (XGBoost), Adaptive Boosting (Adaboost), and Light Gradient Boosting Machine (LightGBM), were developed for predicting the flexural bearing capacity of aluminum-alloy-strengthened RC beams. A total of 124 experimental samples were collected from the literature to establish a database for the prediction models, with 70% and 30% of the data allocated as the training and testing sets, respectively. The K-fold cross-validation method and random search method were used to adjust the hyperparameters of the algorithm, thereby improving the performance of the models. The effectiveness of the models was evaluated through statistical indicators, including the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). Additionally, absolute error boxplots and Taylor diagrams were used for statistical comparisons of the ML models. SHAP (Shapley Additive Explanations) was employed to analyze the importance of each input parameter in the predictive capability of the ML models and further examine the influence of feature variables on the model prediction results. The results showed that the predicted values of all models had a good correlation with the experimental values, especially the LightGBM model, which can effectively predict the flexural bearing capacity behavior of aluminum-alloy-strengthened RC beams. The research achievements provided a reliable prediction framework for optimizing aluminum-alloy-strengthened concrete structures and offered references for the design of future strengthened structures. Full article

The durability of reinforced concrete (RC) structures is strongly influenced by carbonation, a phenomenon governed by material and environmental interactions. This study applied machine learning (ML) techniques—Random Forest (RF), Support Vector Regression (SVR), and Artificial Neural Networks (ANNs)—to predict carbonation depth using a synthetic dataset of 20,000 instances generated from the validated Possan equation. Model performances were evaluated across multiple scenarios, with compressive strength and exposure time identified as the most influential features, while relative humidity and exposure conditions had intermediate effects. SVR consistently captured linear and nonlinear trends, the ANN achieved the highest R² values but showed minor overestimations, and RF exhibited lower adaptability to feature variations. The results highlight the applicability of ML models for durability assessments, particularly under complex conditions where traditional approaches are limited. Moreover, this study reinforces the strategic value of synthetic datasets in developing predictive models when experimental data collection is time-consuming or impractical. The methodologies developed here can be extended beyond carbonation modeling to other deterioration processes, supporting data-driven strategies for maintenance planning and resilience design in RC structures. Full article

Background/Objectives: Glycogen synthase kinase-3 beta (GSK3β) is a key enzyme involved in neurodegenerative diseases such as Alzheimer’s and Parkinson’s, contributing to tau hyperphosphorylation, amyloid-beta (Aβ) aggregation, and neuronal dysfunction. Methods: This study applied a machine learning-driven virtual screening approach to identify potent natural inhibitors of GSK3β. A dataset of 3092 natural compounds was analyzed using Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN), with feature selection focusing on key molecular descriptors, including lipophilicity (ALogP: −0.5 to 5.0), hydrogen bond acceptors (0–10), and McGowan volume (0.5–2.5). RF outperformed SVM and KNN, achieving the highest test accuracy (83.6%), specificity (87%), and lowest RMSE (0.3214). Results: Virtual screening using AutoDock Vina and molecular dynamics simulations (100 ns, GROMACS 2022) identified artemisinin as the top GSK3β inhibitor, with a binding affinity of −8.6 kcal/mol, interacting with key residues ASP200, CYS199, and LEU188. Dihydroartemisinin exhibited a binding affinity of −8.3 kcal/mol, reinforcing its neuroprotective potential. Pharmacokinetic predictions confirmed favorable drug-likeness (TPSA: 26.3–70.67 Ų) and non-toxicity. Conclusions: While these findings highlight artemisinin-based inhibitors as promising candidates, experimental validation and structural optimization are needed for clinical application. This study demonstrates the effectiveness of machine learning and computational screening in accelerating neurodegenerative drug discovery. Full article

Additive manufacturing (AM) is gaining widespread adoption in the manufacturing industry due to its capability to fabricate intricate and high-performance components. In parallel, the increasing emphasis on functional materials in AM has highlighted the critical need for accurate prediction of the mechanical behavior of composite systems. This study experimentally investigates the tensile strength and surface quality of carbon fiber-reinforced nylon composites (PA12-CF) fabricated via fused deposition modeling (FDM) and models their behavior using artificial neural networks (ANNs). A Taguchi L27 orthogonal array was employed to design experiments involving five critical printing parameters: layer thickness (100, 200, and 300 µm), infill pattern (gyroid, honeycomb, and triangles), nozzle temperature (250, 270, and 290 °C), printing speed (50, 100, and 150 mm/s), and infill density (30, 60, and 90%). An analysis of variance (ANOVA) revealed that the infill density had the most significant influence on the resulting tensile strength, contributing 53.47% of the variation, with the strength increasing substantially at higher densities. In contrast, the layer thickness was the dominant factor in determining surface roughness, accounting for 53.84% of the variation, with thinner layers yielding smoother surfaces. Mechanistically, a higher infill density enhances the internal structural integrity of the parts, leading to an improved load-bearing capacity, while thinner layers improve the interlayer adhesion and surface finish. The highest tensile strength achieved was 69.65 MPa, and the lowest surface roughness recorded was 9.18 µm. An ANN model was developed to predict both the tensile strength and surface roughness based on the input parameters. Its performance was compared with that of three other machine learning (ML) algorithms: support vector regression (SVR), random forest regression (RFR), and XGBoost. The ANN model exhibited superior predictive accuracy, with a coefficient of determination (R² > 0.9912) and a mean validation error below 0.41% for both outputs. These findings demonstrate the effectiveness of ANNs in modeling the complex relationships between FDM parameters and composite properties and highlight the significant potential of integrating ML and statistical analysis to optimize the design and manufacturing of high-performance AM fiber-reinforced composites. Full article