Search Results (1,850)

In the production of clad rolled plates from asymmetric sandwich-type slab for pipeline applications, achieving both target mechanical properties and high geometric flatness remains a critical challenge due to differential thermal stresses between the dissimilar steel layers during accelerated cooling. This study aims to develop an optimal cooling schedule for a 25 mm thick clad plate, comprising a X70-grade steel base layer and an AISI 316L cladding, to ensure required strength and minimal bending. A comprehensive approach was employed, integrating a 3D finite element model (Ansys) for simulating thermoelastic stresses with a CatBoost machine learning model trained on industrial data to predict heat transfer coefficients accurately. A parametric analysis of cooling strategies was conducted. Results showed that a standard cooling strategy caused unacceptable bending of plate after cooling exceeding 130 mm. An optimized strategy featuring delayed activation of the lower cooling headers (on the cladding side) created a compensating thermoelastic moment, successfully reducing bending to approximately 20 mm while maintaining the base layer’s requisite mechanical properties. The findings validate the efficacy of the combined FEM-machine learning methodology and propose a viable, industrially implementable cooling strategy for high-quality clad plate production. Full article

Background: The efficacy of real-time fMRI neurofeedback (NFB) depends critically on how feedback is presented and perceived by the participant. Although various visual feedback designs are used in practice, there is limited evidence on the impact of modality on learning and performance. We conducted a feasibility study to compare the effectiveness of different feedback modalities, and to evaluate the technical performance of NFB across two scanner field strengths. Methods: In a single-session study, nine healthy adults (6 men, 3 women) voluntarily adapted the activation level of the primary sensorimotor cortex (SMC) to reach three predefined activation levels. We contrasted a continuous, signal-proportional feedback (cFB; a thermometer-style bar) with an affect-based, categorical feedback (aFB; a smiling face). A no-feedback transfer condition (noFB) was included to probe regulation based on internal representations alone. To assess technical feasibility, three participants were scanned at 7T and six at 3T. Results: Participants achieved successful regulation in 44.4% of trials overall (cFB 46.9%, aFB 43.8%, noFB 42.6%). Overall success rates did not differ significantly between modalities and field strengths when averaged across the session; given the small feasibility sample, this null result is inconclusive and does not establish equivalence. Learning effects were modality-specific. Only cFB showed a significant within-session improvement (+14.8 percentage points from RUN1 to RUN2; p = 0.031; d_z = 0.94), whereas aFB and noFB showed no evidence of learning. Exploratory whole-brain contrasts (uncorrected) suggested increased recruitment of ipsilateral motor regions during noFB. The real-time pipeline demonstrated robust technical performance: transfer/reconstruction latency averaged 497.8 ms and workstation processing averaged 296.8 ms (≈795 ms end-to-end), with rare stochastic outliers occurring predominantly during 7T sessions. Conclusions: In this single-session motor rt-fMRI NFB paradigm, continuous signal-proportional feedback supported rapid within-session learning, whereas affect-based categorical cues did not yield comparable learning benefits. Stable low-latency operation was achievable at both 3T and 7T. Larger, balanced studies are warranted to confirm modality-by-learning effects and to better characterize transfer to feedback-free self-regulation. Full article

Cardiac rehabilitation (CR) improves functional capacity and reduces cardiovascular morbidity, yet clinical response remains highly heterogeneous and difficult to stratify using conventional assessment. This study presents a machine-learning framework for the early stratification of CR patients into responders and non-responders based exclusively on pre-intervention baseline characteristics. A total of 122 patients undergoing an 8-week CR program were evaluated using 56 clinical, physiological and metabolic predictors. Multiple classification models were trained under a stratified 10-fold cross-validation scheme. Among them, an SVM-RBF classifier achieved the best performance and retained high discriminative capacity after dimensionality reduction. The final reduced model, based on the ten most informative features identified through convergence between Random Forest and SHAP analyses, preserved >95% of the full-feature performance. The predictors were physiologically coherent, reflecting muscular strength, ventilatory efficiency, chronotropic modulation and metabolic burden. SHAP-based explainability enabled patient-level attribution of improvement likelihood, identifying modifiable variables associated with favorable or limited training response. In parallel, we developed a web-based clinical decision-support prototype that estimates improvement probability and highlights the most influential determinants for each patient, illustrating translational applicability for precision rehabilitation planning. These findings support a transition toward personalized CR strategies guided by explainable AI and baseline phenotyping. Full article

In this study, linear and nonlinear parametric models (M1–M6) were jointly evaluated alongside machine learning (ML)-based approaches to achieve reliable and interpretable prediction of the penetration rate (ROP) of tunnel boring machines (TBMs). The analyses incorporate key geomechanical and structural variables, including the brittleness index (BI), uniaxial compressive strength (UCS), mean spacing of weakness planes (DPW), the angle between the tunnel axis and weakness planes (α), and Brazilian tensile strength (BTS). The coefficients of the parametric models were optimized using the Differential Evolution (DE) algorithm. Variable effects were systematically examined through Jacobian-based elasticity analysis under both original and standardized data scenarios. The results indicate that the M6 model, which explicitly incorporates interaction terms, delivers superior predictive accuracy and a more balanced, physically meaningful representation of variable contributions compared to widely used parametric formulations reported in the literature. While the dominant influence of BI and UCS on ROP is consistently preserved across all models, the indirect contributions of variables such as DPW and BTS are more clearly revealed in M6 owing to its interaction-based structure. Model performance improves systematically with increasing complexity, with the coefficient of determination (R²) rising from 0.62 for M1 to 0.69 for M6. Relative to the linear model, M6 achieves a 9.07% reduction in RMSE and a 10.48% increase in R², while providing additional improvements of 2.47% in RMSE and 2.37% in R² compared with the closest competing model. ML-based variable importance analyses are largely consistent with the parametric findings, highlighting BI and α in tree-based models, and UCS and α in SVM and GAM frameworks. Notably, the GAM exhibits the highest predictive performance under both data scenarios. Overall, the integrated use of parametric and ML approaches establishes a robust hybrid modeling framework that enables highly accurate and engineering-interpretable prediction of TBM penetration rate. Full article

Emotion recognition in video (ERV) aims to infer human affect from visual, audio, and contextual signals and is increasingly important for interactive and intelligent systems. Over the past decade, ERV has evolved from handcrafted features and task-specific deep learning models toward transformer-based vision–language models and multimodal large language models (MLLMs). This review surveys this evolution, with an emphasis on engineering considerations relevant to real-world deployment. We analyze multimodal fusion strategies, dataset characteristics, and evaluation protocols, highlighting limitations in robustness, bias, and annotation quality under unconstrained conditions. Emerging MLLM-based approaches are examined in terms of performance, reasoning capability, computational cost, and interaction potential. By comparing task-specific models with foundation model approaches, we clarify their respective strengths for resource-constrained versus context-aware applications. Finally, we outline practical research directions toward building robust, efficient, and deployable ERV systems for applied scenarios such as assistive technologies and human–AI interaction. Full article

The multi-objective optimization of multicomponent superalloys has long been impeded by not only the complex interactions among multiple elements but also the low efficiency and high cost of traditional trial-and-error methods. To address this issue, this study proposed a thermodynamic calculation data-driven optimization framework that integrates machine learning (ML) and multi-objective screening based on domain knowledge. The core of this methodology involves introducing a commercial reference alloy and rapidly generating a large-scale thermodynamic dataset through ML models. After training, the ML models were verified to be more efficient at predicting phase transition temperatures and γ′ volume fractions than the CALPHAD methods. Focusing on the mechanical properties, critical strength indices, including solid solution strengthening, precipitation strengthening, and creep resistance based on the calculated γ/γ′ two-phase compositions, were compared with the reference alloy and set as the critical screen criteria. Optimal alloys were selected from the 388,000 candidates. Compared with the reference alloy, two new alloys were experimentally verified to have superior or comparable compressive yield strength and creep resistance at 900 °C at the expense of oxidation resistance and density, while maintaining comparable cost. This work demonstrates the significant potential of combining high-throughput thermodynamic data with intelligent multi-objective optimization to accelerate the development of new alloys with tailored property profiles. Full article

Reconstructing original cusp dimensions in worn molars represents a fundamental challenge across dentistry, anthropology, and paleontology, as dental wear obscures critical morphological information. In this proof-of-concept study, we present a standardized machine learning pipeline for predicting original cusp height, specifically the horn tips of the enamel–dentine junction (EDJ), in worn lower molars using three-dimensional morphometric data from micro-computed tomography (micro-CT). We analyzed 40 permanent lower first (M1) and second (M2) molars from four hominin groups, systematically evaluated across three wear stages: original, moderately worn (worn1), and severely worn (worn2). Morphometric variables including height, area, and volume were quantified for each cusp, with Random Forest and multiple linear regression models developed individually and combined through ensemble methods. To mimic realistic reconstruction scenarios while preserving a known ground truth, models were trained on unworn specimens (original EDJ morphology) and tested on other teeth after digitally simulated wear (worn1 and worn2). Predictive performance was evaluated using root mean square error (RMSE) and coefficient of determination (R²). Our results demonstrate that under moderate wear (worn1), the ensemble models achieved normalized RMSE values between 11% and 17%. Absolute errors typically below 0.25 mm for most cusps, with R² values up to ~0.69. Performance deteriorated under severe wear (worn2), particularly for morphologically variable cusps such as the hypoconid and entoconid, but generally remained within sub-millimetric error ranges for several structures. Random Forests and linear models showed complementary strengths, and the ensemble generally offered the most stable performance across cusps and wear states. To enhance transparency and accessibility, we provide a comprehensive, user-friendly software pipeline including pre-trained models, automated prediction scripts, standardized data templates, and detailed documentation. This implementation allows researchers without advanced machine learning expertise to explore EDJ-based reconstruction from standard morphometric measurements in new datasets, while explicitly acknowledging the limitations imposed by our modest and taxonomically unbalanced sample. More broadly, the framework represents an initial step toward predicting complete crown morphology, including enamel thickness, in worn or damaged teeth. As such, it offers a validated methodological foundation for future developments in cusp and crown reconstruction in both clinical and evolutionary dental research. Full article

This paper analyzes the implementation of the Geoportal SIG FESBAL–UPM, a Participatory Geographic Information System (PGIS) developed within the Master’s and Doctorate programs in Rural Development Project Planning and Sustainable Management at UPM. The study introduces a model integrated with Project-Based Learning (PBL), the Working With People (WWP) framework, and the CFS-RAI principles to address challenges in responsible food systems. The geoportal designed to be applied at the Food Bank–UPM Chair–FESBAL, acts as an innovative instrument for participation among the different stakeholders enabling the spatialization and analysis of data across social, environmental, and governance dimensions. Functionally, it offers a robust foundation for evidence-based decision-making, systematizes geographic information, and visualizes data via the web, supporting research, training, and community engagement actions. Furthermore, this study details the specific projects and activities developed under the three involved action lines: research, training, and community engagement, identifying strengths and weaknesses in each. The findings affirm that this participatory approach ensures that the proposed solutions are aligned with local needs and priorities, increasing the sustainability and long-term success of the projects implemented through the geoportal. Full article

A hybrid modeling framework for predicting the mechanical properties of Al-Mg-Si alloys, that blends physics-based and machine-learning models, is developed and tested. Motivated by a demand for post-consumer material (PCM) content in wrought aluminium applications, this work proposes, analyses, and discusses a parallel framework that applies an adaptive weighting coefficient derived from local observation density. Based on existing datasets from a range of Al-Mg-Si alloys, such a model is trained and tested in an iterative manner to study its robustness, by emulating a shift in observed alloy composition. The results indicate that the hybrid model is able to combine the interpolative strength of machine learning for cases similar to previous observations with the explorative strength of physics-based (Kampmann–Wagner Numerical) modeling for previously unobserved parameter combinations, as the hybrid model shows higher or similar accuracy than the best of its constituents across the majority of the sequence. The observed model characteristics are promising for predicting the effect of increased compositional variation inherent in PCM. Finally, possible future research is discussed. Full article

This systematic integrative review examines methodological frameworks used to evaluate educational technologies in biomedical higher education. We synthesize five complementary approaches frequently reported in the literature: the Technology Acceptance Model (TAM), the Unified Theory of Acceptance and Use of Technology (UTAUT), the System Usability Scale (SUS), Technology Readiness Levels (TRL), and the ARCS motivational model. Each framework addresses distinct but interrelated dimensions of evaluation, including technology acceptance and intention to use, perceived usability and user experience, technological maturity and implementation risk, and learner motivation. Drawing on representative studies in e-learning platforms, virtual and extended reality environments, and clinical simulation, we discuss the strengths, limitations, and common pitfalls of applying these models in isolation. Based on this synthesis, we propose a pragmatic, multi-phase evaluation workflow that aligns usability, acceptance, motivation, and technological maturity across different stages of educational technology development and adoption. Finally, we outline exploratory future perspectives on how existing evaluation models might need to evolve to address emerging AI-driven, immersive, and haptic technologies in biomedical education. This abstract was prepared in accordance with PRISMA 2020 for Abstracts, ensuring structured reporting and transparency. Full article

This study employed data-driven machine learning models to analyze the effects of filler material composition and other process parameters on mechanical properties during the crack repair of nickel-based superalloys such as K417G using wide-gap brazing technology. First, a linear regression model was used to analyze the influence of independent variables (filler material composition and other process parameters) on the dependent variables (tensile strength and elongation). The regression results indicated that temperature and filler composition significantly affected tensile strength and elongation. Subsequently, a TabNet machine learning model was applied to simulate the relationship between parameters such as composition and mechanical properties. The experimental results showed that when four parameters, namely, the filler composition, temperature, holding time, and pressure, were used as input features, the deviation between the actual and predicted values of elongation was minimal, with a value of only 1.5650. Full article

The dynamics of open quantum systems play a crucial role in quantum information science. However, obtaining numerically exact solutions for the Lindblad master equation is often computationally expensive. Recently, machine learning techniques have gained considerable attention for simulating open quantum system dynamics. In this paper, we propose a deep learning model based on time series prediction (TSP) to forecast the dynamical evolution of open quantum systems. We employ the positive operator-valued measure (POVM) approach to convert the density matrix of the system into a probability distribution and construct a TSP model based on Transformer neural networks. This model effectively captures the historical evolution patterns of the system and accurately predicts its future behavior. Our results show that the model achieves high-fidelity predictions of the system’s evolution trajectory in both short- and long-term scenarios, and exhibits robust generalization under varying initial states and coupling strengths. Moreover, we successfully predicted the steady-state behavior of the system, further proving the practicality and scalability of the method. Full article

Background: Iron ore tailings (IOTs) are a mine waste product used as road materials and suffer from a lack of sufficient strength, which should be improved through stabilization. Unconfined compressive strength (UCS) is a crucial parameter for determining the quality and mix design of stabilized soils, which is time-consuming, requires specialized equipment and professional operators, and is not affordable. Methods: In this study, six ensemble learning techniques, five-fold cross-validation, and the Fennec Fox Optimization metaheuristic algorithm were utilized to predict UCS. For this purpose, cement content, curing time, compaction energy, and moisture content were selected as independent variables. Results: The results suggested that XGBoost-FFO was the most accurate model, R² = 0.9505, MAE = 0.257, MSE = 0.118, and RMSE = 338. Two interpretation methods were employed to evaluate the model’s performance, and the results indicated that the most significant parameter was compaction energy. Conclusions: Moreover, to facilitate practical engineering applications, a graphical user interface (GUI) was also designed to predict the UCS of cement-stabilized IOTs. Full article

Reliable models for predicting the uniaxial compressive strength (UCS) of rocks are crucial for mining operations and rock engineering design. Empirical methods, including statistical methods, are often faced with many limitations when generalizing in a wide range of lithological types. To address this limitation, this study investigates the capability of grey wolf optimization (GWO)-optimized ensemble machine learning models, including decision tree (DT), extreme gradient boosting (XGBoost), and adaptive boosting (AdaBoost) for predicting UCS using a small dataset of easily measurable and non-destructive rock index properties. The study’s objective is to evaluate whether metaheuristic-based hyperparameter optimization can enhance model robustness and generalization performance under small-sample conditions. A unified experimental framework incorporating GWO-based optimization, three-fold cross-validation, sensitivity analysis, and multiple statistical performance indicators was implemented. The findings of this study confirm that although the GWO-XGBoost model achieves the highest training accuracy, it exhibits signs of mild overfitting. In contrast, the GWO-AdaBoost model outpaced with significant improvement in terms of coefficient of determination (R²) = 0.993, root mean square error (RMSE) = 2.2830, mean absolute error (MAE) = 1.6853, and mean absolute percentage error (MAPE) = 4.6974. Therefore, the GWO-AdaBoost has proven to be the most effective in terms of its prediction potential of UCS, with significant potential for adaptation due to its effectively learned parameters. From a theoretical perspective, this study highlights the non-equivalence between training accuracy and predictive reliability in UCS modeling. Practically, the findings support the use of GWO-AdaBoost as a reliable decision-support tool for preliminary rock strength assessment in mining and geotechnical engineering, particularly when comprehensive laboratory testing is not feasible. Full article

Modern engineering systems require reliable and timely Fault Detection and Diagnosis (FDD) to ensure operational safety and resilience. Traditional model-based and rule-based approaches, although interpretable, exhibit limited scalability and adaptability in complex, data-intensive environments. This survey provides a systematic overview of recent studies exploring Machine Learning (ML) and Artificial Intelligence (AI) techniques for FDD across industrial, energy, Cyber-Physical Systems (CPS)/Internet of Things (IoT), and cybersecurity domains. Deep architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformers, and Graph Neural Networks (GNNs) are compared with unsupervised, hybrid, and physics-informed frameworks, emphasizing their respective strengths in adaptability, robustness, and interpretability. Quantitative synthesis and radar-based assessments suggest that AI-driven FDD approaches offer increased adaptability, scalability, and early fault detection capabilities compared to classical methods, while also introducing new challenges related to interpretability, robustness, and deployment. Emerging research directions include the development of foundation and multimodal models, federated learning (FL), and privacy-preserving learning, as well as physics-guided trustworthy AI. These trends indicate a paradigm shift toward self-adaptive, interpretable, and collaborative FDD systems capable of sustaining reliability, transparency, and autonomy across critical infrastructures. Full article