Search in Publications
Found 6273 publications
Evaluating AI-driven credit scoring models versus traditional statistical techniques
Publication Name: Discover Artificial Intelligence
Publication Date: 2026-12-01
Volume: 6
Issue: 1
Page Range: Unknown
Description:
This study evaluates AI credit-scoring models against standard statistical models using a real-life data set with 1000 loan applications. The main research question is about whether machine-learning methods are more valuable in terms of predictive accuracy, interpretability and stability to changes in the process of macroeconomic deterioration as compared to traditional methods. The four model variants were developed: the logistic regression and decision tree as examples of the classical ones, and XGBoost gradient-boosting ensemble and multilayer perceptron neural networks as examples of AI-based alternatives. The methodological engine was R (v4.3.1), which established a 70:30 train-test strata union, inner cross-validation and harmony spatial search to tune the hyperparameter. The findings show that XGBoost produces an optimal balanced accuracy cumulative gain curve (cumulative gain, CGC: 0.89; area under the receiver operating characteristic, AUC: 0.89) that is trumped by the neural network (CGC: 0.87; AUC: 0.87) and succeeded by the logistic regression (CGC: 0.76; AUC: 0.76). The SHAP analysis shows that the amount of credit, duration of loan, and age are central predictors. During stress-test simulation, XGBoost is stable in making predictions (AUC = 0.83) compared to a severe decline in logistic-regression results (AUC = 0.68). The results therefore justify the claim that the state-of-the-art AI tools have better predictive potential and robust interpretability, thus rising as viable alternatives to the systems in vogue in modern finance organisations.
Open Access: Yes
MABAC model based on linguistic (p, q)-rung orthopair fuzzy Z-number and their application in green supply chain management
Publication Name: International Journal of Cognitive Computing in Engineering
Publication Date: 2026-12-01
Volume: 7
Issue: Unknown
Page Range: 247-267
Description:
The problem and complication arise from the growing environmental inefficiencies and concerns in traditional supply chains, for instance, poor accountability, excessive waste, and lack of transparency. The green supply chain practices aim to reduce or minimize the environmental impact of supply chain activities, but these efforts often face problems, for example, difficulty in monitoring sustainability performance, data manipulation, and limited traceability across numerous stakeholders. The main problem is that without effective techniques to verify and track eco-friendly practices, enterprises struggle to utilize and enforce green initiatives reliably. The blockchain technique is being derived as a solution because of its capability to give decentralized, transparent, and immutable records of processes and transactions. By integrating the blockchain into green supply chain practices, we aim to design the model of linguistic (p, q)-rung orthopair fuzzy Z-number sets with algebraic and Sugeno-Weber operational laws for the construction of the power weighted averaging operator and power weighted geometric operator. These operators can be used in the utilization of the multi-attributive border approximation area comparison model, which is also explained step-by-step with the help of examples to simplify the supremacy and validity of the invented model by comparing their ranking values with the ranking values of the existing approaches.
Open Access: Yes
Regression and statistical analysis of heat transfer enhancement in water/ethylene glycol (40/60) base molybdenum carbide (Mo2C) MXene nanofluid using a transient fractional model
Publication Name: Discover Nano
Publication Date: 2026-12-01
Volume: 21
Issue: 1
Page Range: Unknown
Description:
To investigate the effects of fractional order (), nanoparticle volume fraction (), magnetic field strength (), and Brinkman permeability () on both flow and heat transfer characteristics, a detailed parametric and statistical analysis is conducted. The statistical regression analysis shows that the volume fraction of nanoparticles and temperature have a strong positive correlation (coefficient = 0.94, p = 0.021) indicating that Mo2 C MXene is an excellent heat absorption. On the other hand, the fractional parameter α has a strong negative effect on temperature field (coefficient = − 0.086, p < 0.001), which emphasizes its importance in describing the effects of thermal memory. The findings also indicate that, although MXene nanoparticles significantly increase thermal transport, an augmentation in magnetic field strength and Brinkman resistance cause a resistive Lorentz force and frictional drag, respectively, to prevent fluid flow. These results are physically informative about non-Fourier heat transfer in MXene-based nanofluids as well as offer invaluable information to developing high-performance thermal management systems and solar-energy applications.
Open Access: Yes
Digital twin-based machine learning framework for predicting nonlinear seismic response of reinforced concrete shear walls using analytical data
Publication Name: Scientific Reports
Publication Date: 2026-12-01
Volume: 16
Issue: 1
Page Range: Unknown
Description:
This study proposes a digital twin (DT) and machine learning (ML) framework to predict nonlinear pushover responses of reinforced concrete (RC) shear walls using analytically derived data. Two hundred SAP2000 layered shell models were analyzed, and monotonic lateral capacity curves were processed via SPO2FRAG for bilinear parameter extraction. Key response features—initial stiffness (K0 ), yield displacement (), and post-yield stiffness ratio ()were identified. Ten input variables including wall geometry, material properties, reinforcement ratios, axial load, and opening ratio were used to train Random Forest regressors for predicting the pushover curve descriptors. Model accuracy was validated using nested cross-validation, yielding mean test R2 values of 0.996 for, 0.995 for, and 0.925 for, while uncertainty measures (Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), 95% confidence intervals) supported robustness. The DT surrogate reconstructs pushover curves in under 2 seconds per specimen, supporting rapid parametric analysis and seismic scenario assessments without the need for repetitive finite element simulations. The study also documents model limitations and outlines guidance for extending the approach to shear-dominated walls and experimental validation.
Open Access: Yes
Hybrid ML and metaheuristic optimization of slag-fly ash-gypsum modified solidified sludge for construction
Publication Name: Scientific Reports
Publication Date: 2026-12-01
Volume: 16
Issue: 1
Page Range: Unknown
Description:
Conventional sludge disposal, including incineration and landfilling, is unsustainable and can cause secondary pollution; thus, sludge solidification is emerging as a sustainable alternative. This study aims to combine machine learning (ML) and metaheuristic optimization to maximize the unconfined compressive strength (UCS) of municipal sludge modified with slag, desulfurized gypsum, and fly ash. A total of 190 specimens were tested, and predictive models based on Gradient Boosting Machine (GBM), Random Forest (RF), Support Vector Regression (SVR), LightGBM, XGBoost, CatBoost, K-Nearest Neighbors (KNN), and Histogram Gradient Boosting (HistGBoost) were coupled with the Whale Optimization Algorithm (WOA). In addition, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), Gazelle optimization algorithm (GOA), Octopus Optimization Algorithm (OOA), Hiking Optimization Algorithm (HOA), and Young’s double-slit experiment optimizer (YDSE) were applied for comparison. Sensitivity analysis identified optimal WOA–ML parameter settings. The results demonstrated that the WOA–RF model outperformed all metaheuristic and other WOA–ML approaches by achieving the highest predicted UCS (8.29851 MPa). The WOA-ML models yielded an average optimal mix comprising sludge (44.2%), gypsum (19%), slag (18.7%), fly ash (16%), and NaOH (2.1%). Among the metaheuristic algorithms, PSO, GOA, OOA, TJO, DOA, GA, and YDSE demonstrated competitive performance. GWO achieved the highest UCS (8.226109 MPa), while HOA yielded the lowest (5.15366 MPa). The optimal mix averaged 38.9% sludge, 23.7% gypsum, 21.6% fly ash, 13.4% slag, and 2.5% NaOH. Partial dependence analysis confirmed the nonlinear effects of these parameters, while SHAP sensitivity analysis validated the optimization results. RSM validation further confirmed that both WOA–ML and metaheuristic approaches reliably predict the optimal UCS of modified sludge.
Open Access: Yes
Role of centres in public transport networks
Publication Name: European Transport Studies
Publication Date: 2026-12-01
Volume: 3
Issue: Unknown
Page Range: Unknown
Description:
A well-functioning public transport network is the foundation of sustainable urban mobility. However, the term 'well working' is difficult to define and may be subjective. This paper introduces a network-analytical approach to show the correlation between usage, which reflects the quality of a public transport service, and the structure of its network. This approach is based on Barabási's definition of a scale-free network and physicists' observations of network structures. Ultimately, the paper will show that scale-free public transport networks are more efficient in terms of usage, as modelled by the modal split of the observed cities.
Open Access: Yes
Discovery of potential antiviral compounds and accelerating the therapeutic discovery against monkeypox virus
Publication Name: Scientific Reports
Publication Date: 2026-12-01
Volume: 16
Issue: 1
Page Range: Unknown
Description:
Monkeypox virus is a zoonotic virus of the genus Orthopox viruses. It can be transmitted through direct or indirect contact with animals or infected ones. Owing similarity of pathogenesis with smallpox, the same drugs can be used for both viruses, but they are not specific and only help to relieve the symptoms only. Therefore, the absence of antiviral treatment or licensed vaccine highlights an urgent need, especially due to its rapid prevalence. The study screened the library of compounds to retrieve drug-like molecules that can act against monkeypox virus. The highly virulent target gene B8R having uniport ID Q3I8J0 was chosen. Targeting B8R is substantial for global health and can align with SDG 3 and awareness of disease management. The B8R was modelled via Artificial intelligence (AI) AlphaFold method and then exposed to a library of compounds. Complementary interactions in the active site were shown by molecular docking. The Complex-1 had the greatest binding affinity (–8.4 kcal/mol), followed by Complex-2 (–8.1 kcal/mol) and Complex-3 (–7.7 kcal/mol). After 125 ns, Complex-1 reached equilibrium at 7.5 Å RMSD, according to MD simulations, exhibiting stable ligand retention and reliable interactions with crucial residues Gly135 and Lys136. Complex-3 shown intermediate protein stability (6 Å RMSD) but notable ligand fluctuation (48 Å RMSF), while Complex-2 displayed increased protein RMSD (8 Å RMSD) and delayed ligand stabilisation (16 Å RMSF). These results were corroborated by PCA analysis, which showed that Complex-1 exhibits coherent structural development whereas Complex-2 and Complex-3 show scattered and compact trajectories, respectively. Complex-1 promise for Mpox viral inhibition was highlighted by the fact that it was the most stable and dynamically favourable contender overall. The N-terminal follows the folding trend. The insilico analysis not only proposed a potent compound but also provides deep insight into the behavior of protein. The proposed potent compound against this zoonotic virus can be helpful to combat the monkeypox virus by subjecting it further towards experimental investigation.
Open Access: Yes
Examination of the Effect of Wind on Vehicle Drag Coefficient from Aerodynamics Point of View
Publication Name: Periodica Polytechnica Transportation Engineering
Publication Date: 2026-11-28
Volume: 54
Issue: 1
Page Range: 34-40
Description:
The aim of the paper is to investigate the wind effect on vehicle aerodynamic properties. Two-dimensional Ahmed body is examined with Computational Fluid Dynamics (CFD) method. During the analysis, two different studies were carried out. First, the simplified vehicle shape was examined in standing position, only the force from the wind velocity affected the body. The drag coefficient change was examined in case of different wind velocities and angles of attack. After that, the effect of wind while driving was investigated. The body was defined as a moving object and at another inlet the wind was defined. Different travelling and wind velocities with different angles of attack were studied. Based on the results of the simulations, a comprehensive impact of the wind can be measured on the drag coefficient. This proves that the wind has a measurable effect on vehicle aerodynamic properties and must be taken into account when investigating the effect of weather conditions on vehicle aerodynamic properties.
Open Access: Yes
DOI: 10.3311/PPtr.40035
Regulatory governance and AI innovation quality: A cross-country evaluation of technology, institutions, and ESG outcomes
Publication Name: Technological Forecasting and Social Change
Publication Date: 2026-09-01
Volume: 230
Issue: Unknown
Page Range: Unknown
Description:
This study examines how AI innovation quality shapes national ESG performance, including its governance dimensions, across 82 countries from 2000 to 2023. AI quality is measured as citation intensity per capita, reflecting scientific influence and technological sophistication validated in prior macro studies rather than patent volume, as citations better capture deployable impact for policy applications like regulatory compliance monitoring and transparent decision systems. Building on resource-resilient world theory, we assess direct AI effects and conditional interactions with financial institutions, globalization exposure, human capital, corruption, economic complexity, and clean-energy transitions using robust multi-model econometrics including IV-GMM to address endogeneity. The findings reveal advanced AI innovation quality significantly improves composite ESG performance, with stronger effects in developed economies where institutional capacity amplifies technological capabilities. AI citation intensity translates scientific breakthroughs into practical governance tools, enhancing regulatory transparency (G pillar), emissions tracking (E pillar), and social compliance (S pillar), though developing nations face implementation barriers. The findings imply that high-quality AI innovation serves as a critical technological shock absorber, enabling nations to enhance regulatory transparency and manage resources more resiliently against external shocks. However, the divergence between developed and developing nations suggests that technological sophistication must be paired with institutional reforms and human capital development to avoid value destruction. Ultimately, strategically governing AI innovation quality is essential for aligning global technological trajectories with long-term ESG performance and sustainable development goals.
Open Access: Yes
