Search Results (546)

This study introduces a model-free reinforcement learning framework based on Q-Learning (QLA) for the multi-objective optimization of Selective Laser Melting (SLM) process parameters for Inconel 718. To efficiently handle the limited experimental dataset, a tabular Q-Learning approach was implemented, in which each parameter combination was treated as a discrete state and every possible transition as an action. Four key process variables laser power (P), scan speed (S), layer thickness (T), and hatch spacing (H) were optimized for two output responses: relative density (RD) and Vickers hardness (VH). The Q-Learning agent iteratively explored various parameter combinations, observed the resulting material properties, and continuously updated its policy to converge toward optimal conditions. The optimal parameter set identified by the framework was P = 270 W, S = 800 mm/s, H = 0.1 mm, and T = 0.08 mm. Despite relying on only 16 experimental trials, the model achieved exceptionally low prediction errors of 0.0503% for RD and 0.0857% for VH, demonstrating substantial reductions in both experimental effort and material consumption. The results confirm that reinforcement learning can autonomously and effectively identify optimal SLM parameter settings, highlighting its strong potential to enhance precision, efficiency, and overall quality in the additive manufacturing of metallic components. Full article

Enzyme engineering drives innovation in biotechnology, medicine, and industry, yet conventional approaches remain limited by labour-intensive workflows, high costs, and narrow sequence diversity. Artificial intelligence (AI) is revolutionising this field by enabling rapid, precise, and data-driven enzyme design. Machine learning and deep learning models such as AlphaFold2, RoseTTAFold, ProGen, and ESM-2 accurately predict enzyme structure, stability, and catalytic function, facilitating rational mutagenesis and optimisation. Generative models, including ProteinGAN and variational autoencoders, enable de novo sequence creation with customised activity, while reinforcement learning enhances mutation selection and functional prediction. Hybrid AI–experimental workflows combine predictive modelling with high-throughput screening, accelerating discovery and reducing experimental demand. These strategies have led to the development of synthetic “synzymes” capable of catalysing non-natural reactions, broadening applications in pharmaceuticals, biofuels, and environmental remediation. The integration of AI-based retrosynthesis and pathway modelling further advances metabolic and process optimisation. Together, these innovations signify a shift from empirical, trial-and-error methods to predictive, computationally guided design. The novelty of this work lies in presenting a unified synthesis of emerging AI methodologies that collectively define the next generation of enzyme engineering, enabling the creation of sustainable, efficient, and functionally versatile biocatalysts. Full article

River-training structures such as spur dikes are frequently used in the field of river engineering, which play a critical role in flow regulation and stabilization of the riverbank. However, previous studies lack a precise prediction of factors inducing scour and turbulence phenomena, such as tip velocity, for optimal design of the spur dikes. This study addresses a key gap in previous research by predicting tip velocity around spur dikes using advanced and interpretable machine learning models while simultaneously evaluating the influence of key geometric and hydraulic parameters. For this purpose, the current study utilized advanced artificial intelligence (AI) techniques like Gaussian Process Regression (GPR), Categorical Boosting (CatBoost), Random Forest (RF), and Extreme Gradient Boosting (XGBoost), optimized with Particle Swarm Optimization (PSO), to predict tip velocity in the vicinity of the spur dike. In this paper, a small dataset of 69 laboratory-scale experimental trials was collected; therefore, the chosen AI models were selected for their ability to handle such limited data points. In this study, the input parameters included Froude number (Fr), separation length to spur dike length ratio (L/l), and incidence angle (β), while the output parameter was tip velocity. The selected four AI models were trained on 70%, 15%, and 15% of the data for the training, testing, and validation phases, respectively. SHapley Additive exPlanations (SHAP) analysis was used to observe the influence of the critical parameters on the tip velocity. The results demonstrated the superior performance of GPR, followed by the CatBoost model, compared to other models. GPR and CatBoost show greater values of coefficient of determination (R²) (GPR R² = 0.972 and CatBoost R² = 0.970) and lower values of root mean square error (RMSE) (GPR RMSE = 0.0107 and CatBoost RMSE = 0.0236). The result of the heatmap and SHAP analysis indicated a greater influence of Fr and L/l and a lower impact of β on the tip velocity. The results of this study recommend the utilization of GPR and CatBoost for precise and robust performance of the hydrodynamic phenomenon around the spur dikes, supporting scour mitigation strategies in river engineering. Full article

The advancement of polymeric materials for orthopedic applications has enabled the development of lightweight, adaptable structures that support patient-specific solutions. This study focuses on the design, fabrication, and mechanical characterization of additively manufactured (AM) polymeric polylactic acid (PLA) components produced via Material Extrusion (MEX), commonly known as Fused Filament Fabrication (FFF). By optimizing geometric configurations and process parameters, these structures demonstrate enhanced flexibility, energy absorption, and load distribution, making them well-suited for orthopedic products and assistive devices. A comprehensive mechanical testing campaign was conducted to evaluate the elasticity, ductility, and strength of FFF-fabricated samples under tensile and three-point bending loads. Key process parameters, including nozzle diameter, layer thickness, and printing orientation, were systematically varied, and their influence on mechanical performance was recorded. The results reveal that these parameters affect mechanical properties in a complex, interdependent manner. To better understand these relationships, an automated routine was developed to calculate the experimental mechanical response, specifically, stiffness and strength. This methodology enables an automated evaluation of the output, considering parameter ranges for future applications. The outcome of the analysis of variance (ANOVA) of the experimental investigation reveals that the printing orientation has a strong impact on the mechanical anisotropy in FFF, while layer thickness and nozzle diameter demonstrate moderate-to-weak importance. Thereafter, the experimental findings were applied on an innovative orthopedic wrist splint design to be fabricated by means of FFF. The most suitable mechanical properties were selected to test the mechanical response of the designed components under operational bending loading by means of linear elastic finite element (FE) analysis. The computational results indicated the importance of employing the actual mechanical properties derived from the applied printing process parameters compared to data sheet values. Hereby, an additional parameter to adjust the mechanical response is the product’s design topology. Finally, this framework lays the foundation for future training of neural networks to optimize specific mechanical responses, reducing reliance on conventional trial-and-error processes and improving the balance between orthopedic product quality and manufacturing efficiency. Full article

Precision agriculture increasingly recognizes the transformative potential of unmanned aerial systems (UASs) for crop monitoring and field assessment, yet research consistently highlights significant usability barriers as the main constraints to widespread adoption. Complex mission planning processes, including detailed flight plan creation and way point management, pose substantial technical challenges that mainly affect non-expert operators. Farmers and their teams generally prefer user-friendly, straightforward tools, as evidenced by the rapid adoption of GPS guidance systems, which underscores the need for simpler mission planning in UAS operations. To enhance accessibility and safety in UAS control, especially for non-expert operators in agriculture and related fields, we propose a Secure UAS Control Framework (SAUCF): a comprehensive system for natural-language-driven UAS mission management with integrated dual-factor biometric authentication. The framework converts spoken user instructions into executable flight plans by leveraging a language-model-powered mission planner that interprets transcribed voice commands and generates context-aware operational directives, including takeoff, location monitoring, return-to-home, and landing operations. Mission orchestration is performed through a large language model (LLM) agent, coupled with a human-in-the-loop supervision mechanism that enables operators to review, adjust, or confirm mission plans before deployment. Additionally, SAUCF offers a manual override feature, allowing users to assume direct control or interrupt missions at any stage, ensuring safety and adaptability in dynamic environments. Proof-of-concept demonstrations on a UAS plat-form with on-board computing validated reliable speech-to-text transcription, biometric verification via voice matching and face authentication, and effective Sim2Real transfer of natural-language-driven mission plans from simulation environments to physical UAS operations. Initial evaluations showed that SAUCF reduced mission planning time, minimized command errors, and simplified complex multi-objective workflows compared to traditional waypoint-based tools, though comprehensive field validation remains necessary to confirm these preliminary findings. The integration of natural-language-based interaction, real-time identity verification, human-in-the-loop LLM orchestration, and manual override capabilities allows SAUCF to significantly lower the technical barrier to UAS operation while ensuring mission security, operational reliability, and operator agency in real-world conditions. These findings lay the groundwork for systematic field trials and suggest that prioritizing ease of operation in mission planning can drive broader deployment of UAS technologies. Full article

Background: Quantitative gait analysis is essential in both clinical and research contexts; however, traditional marker-based motion capture systems are costly and burdensome. Advances in three-dimensional markerless motion capture (3D-MMC) offer more accessible alternatives; however, they lack standardized protocols. Objectives: The present study aimed to establish a standardized protocol and procedures for 3D MMC-based gait analysis using OpenCap and to quantify the reliability and within-session precision of key spatiotemporal gait parameters. Methods: Fifty healthy university students (mean age = 22.15 ± 2.12 years) completed walking trials along a 10 m walkway under single-task (ST) and five dual-task (DT) conditions of varying cognitive complexity. Gait data were collected using a two-camera OpenCap 3D-MMC system, with standardized calibration, lighting, clothing, and trial segmentation. Spatiotemporal parameters were extracted, and within-session relative reliability was quantified using two-way mixed-effects intraclass correlation coefficients, and absolute reliability was quantified using general linear model–derived within-subject error (standard error of measurement, SEM) and minimal detectable change (MDC). Repeated-measures ANOVA with Bonferroni corrections were used to examine condition-related differences. Results: Of 500 trials, 491 (98.2%) were successfully processed. Within-subject test–retest reliability ranged from moderate to excellent for all variables, with gait speed, stride length, and cadence showing the highest ICCs and smallest SEM and MDC values, and step width and double support exhibiting larger measurement error. Conclusions: This study establishes a standardized 3D-MMC protocol for gait analysis using OpenCap and demonstrates good to excellent within-session relative and absolute reliability for most spatiotemporal gait parameters in healthy young adults. Dual-task walking is used here to illustrate how trial-averaged OpenCap measurements and their SEM/MDC can be used to determine which condition-related changes in gait exceed measurement error. Full article

Polyvinyl alcohol (PVA) is increasingly encountered in wastewater, yet reliable quantification and effective removal remain challenging. A colorimetric method for PVA quantification was validated, demonstrating excellent linearity and recoveries of 100.6 ± 2.8%. Limits were established at a limit of detection (LOD) of 1.28 mg/L and a limit of quantification (LOQ) of 1.8 mg/L. Accuracy was influenced by the PVA type, with errors reaching up to 42% due to variations in molecular weight and degree of hydrolyzation affecting the color complex. Consequently, polymer-specific calibration is advised. Analytical precision required strict temperature control and exact reaction times, and potential matrix interferences in wastewater should be assessed prior to application. PVA removal was evaluated using an AOP process based on hydrogen peroxide (H₂O₂) and UV-C irradiation. Increasing the H₂O₂/PVA ratio beyond 1:1 provided only marginal improvements, whereas increasing the UV-C dose was more impactful. A 1:1 H₂O₂/PVA ratio was sufficient even at PVA concentrations up to 5 g/L. Optimal UV-C doses were 7.5–12.5 kJ/m²; higher doses yielded only marginal additional removal. The colorimetric method was suitable for laboratory trials. A pilot-scale treatment of industrial wastewater applied microplastic agglomeration with organosilanes followed by granular activated carbon (GAC) treatment, which reduced PVA from an average of 24.2 mg/L to 7.4 mg/L, achieving ~65% removal, while microplastic removal reached 99.1%. Full article

The efficient pre-incubation selection of duck eggs is essential to ensuring stable hatchability, but most existing optoelectronic and machine vision systems have been calibrated for chicken eggs and cannot be directly used for duck eggs because of their larger size, stronger reflectivity and wider morphological variability. This study proposes an optoelectronic method specifically adapted to Adigel duck eggs that combines load cell weighing, infrared distance sensing and dual-projection image processing in a single stationary setup. A total of 300 eggs were measured manually and automatically, and the results were statistically compared. The developed algorithm uses adaptive Gaussian thresholding (51 × 51, C = 2) and a median 5 × 5 filter to stabilize contour extraction on glossy and spotted shells, followed by ellipsoid-based volume estimation with a breed-specific correction factor (K_v = 0.637). The automatic system showed high agreement with manual measurements (r > 0.95 for mass and linear dimensions) and a mean relative error below 2%. Density, the shape index (If) and the shape coefficient (K₁) were computed to classify eggs into “suitable”, “borderline” and “unsuitable” categories. A preliminary incubation trial (n = 60) of eggs classified as “suitable” resulted in 92% hatchability, thus confirming the predictive value of the proposed criteria. Unlike chicken-oriented systems, the presented solution provides breed-specific calibration and can be implemented in small and medium hatcheries for the reproducible, non-destructive sorting of hatching duck eggs. Full article

Membrane technologies play a vital role in sustainable development due to their efficiency in separation, purification, and chemical processing applications. However, the discovery and optimization of new membrane materials remain largely reliant on trial-and-error experimentation, limiting the pace of innovation. Artificial intelligence (AI) and machine learning (ML) are increasingly being applied to overcome these limitations by enabling data-driven insights, predictive modeling, and rapid material design. These computational approaches have shown significant promise in accelerating membrane fabrication, improving process simulation, detecting and mitigating fouling, and enhancing membrane characterization. This review provides a comprehensive overview of the recent advancements in the integration of AI and ML within membrane and material science. Fundamental AI and ML concepts relevant to membrane science are discussed, together with their applications in membrane fabrication, performance prediction, process modeling, fouling control, and membrane design. Challenges related to data quality, model interpretability, and the integration of domain-specific knowledge are also highlighted, along with potential future research directions. Compared with conventional empirical approaches, the advantages of AI and ML in handling complex, multivariate datasets and accelerating innovation are demonstrated. Overall, this review underscores the transformative potential of AI and ML in developing next-generation membranes with improved efficiency, selectivity, and sustainability across various industrial applications. Although several reviews have explored ML applications in membrane processes, comprehensive integration across material design, fabrication, fouling control, optimization, and process modeling remains limited. Full article

Advances in digital dental technologies have transformed implant therapy from analog, stepwise processes into advanced, data-driven workflows spanning diagnosis, planning, surgery, and prosthetic delivery. Contemporary digital implantology integrates multiple techniques, tools, and multimodal datasets into comprehensive diagnostic models and treatment workflows, enhancing implant placement accuracy, procedural efficiency, patient experience, and interdisciplinary coordination. However, integration remains constrained by fragmented datasets, diverse software platforms, and parallel surgical and prosthetic streams. These interfaces often require manual user intervention to convert, process, and align data, thereby increasing the risk of data loss, artifact generation, misalignment, and error accumulation, which may impact implant and prosthetic restorative outcomes. Similarly, implant and prosthetic planning steps continue to rely on subjective, non-standardized user input, requiring advanced experience and training. This narrative review synthesizes current evidence and technical developments in digital implant dentistry based on literature searches in PubMed, Scopus, and Web of Science, with emphasis on publications from 2010 onward, prioritizing systematic reviews, randomized clinical trials, and technical reports focusing on key technological innovations. It presents the current state of the art in digital implantology and identifies major workflow interfaces that constrain seamless, end-to-end integration. This part I summarizes contemporary tools and approaches in digital implant technology. In contrast, Part II of this series will address the emerging roles of artificial intelligence and robotics in overcoming these limitations and advancing toward fully integrated digital implant prosthodontic workflows. Overall, current digital implant workflows are clinically reliable and are equivalent to, or often superior to, conventional approaches in terms of efficiency and accuracy. Nevertheless, their full potential remains limited by persistent software, data, and process interface barriers. Full article

This research presents a novel, low-cost optical acquisition system based on infrared imaging for real-time weld bead geometry monitoring in Gas Metal Arc Welding (GMAW). The system uniquely employs a commercial CCD camera (1000–1150 nm) with tailored filters and lenses to isolate molten pool thermal radiation while mitigating arc interference. A single camera and a mirror-based setup simultaneously capture weld bead width and reinforcement. Acquired images are processed in real time (10 ms intervals) using MATLAB R2016b algorithms for edge segmentation and geometric parameter extraction. Dimensional accuracy under different welding parameters was ensured through camera calibration modeling. Validation across 35 experimental trials (over 6000 datapoints) using laser profilometry and manual measurements showed errors below 1%. The resulting dataset successfully trained a Support Vector Machine, highlighting the system’s potential for smart manufacturing and predictive modeling. This study demonstrates the viability of high-precision, low-cost weld monitoring for enhanced real-time control and automation in welding applications. Full article

The growing demand from the automotive industry for lightweight, high-performance, and advanced manufacturing techniques for efficient and cost-effective production has accelerated the adoption of fiber-reinforced polymer composites. However, considering the manufacturing complexity of these materials, design remains challenging due to the intricate and interdependent relationships between the process conditions, the part geometry, and the resulting microstructure and quality. This research utilized the Autodesk Moldflow Insight software to design an injection molding process for the manufacturing of discontinuous glass fiber-reinforced polymer parts through computer modeling. A geometrically complex car fender was used as a case study. The effects of various process parameters, particularly gate locations, on the injection-molded parts’ properties (such as the fiber orientation, volumetric shrinkage, and shear rate) were investigated. Multiple injection molding process configurations were designed and simulated, including three, four, and five gates at varying locations. Based on the optimal performance (i.e., low shrinkage, a consistent fiber orientation, and a controllable shear rate), an optimal configuration with four gates at appropriate locations (corresponding to the second gate location set) was identified based on multicriteria decision-making analysis, i.e., volumetric shrinkage of ${8.5}_{-2.2}^{+1.4}\%$, a fiber orientation tensor of 0.927 ± 0.011, and a stable shear rate < 74,324 (1/s). A reduced strain closure model (modified Folgar–Tucker model) was used to predict the glass fiber orientation. A multicriteria decision-making technique, based on similarity ranking with an ideal solution, was employed to optimize the gate location. The simulation results clearly demonstrate that the gate placement is crucial for material behavior during molding and for reducing common defects. The simulation-based injection molding process design for the manufacturing of discontinuous fiber-reinforced polymer parts proposed in this paper can improve the production efficiency, reduce trial-and-error rates, and improve part quality. Full article

Objectives: Kidneytumors, particularly renal cell carcinoma (RCC), represent a critical public health concern due to their prevalence and the severe consequences of late diagnosis. Traditional diagnostic techniques, though widely used, are often limited by human error, inter-observer variability, and delayed recognition of malignant subtypes, underscoring the urgent need for automated, accurate, and reproducible solutions. Methods: To address these challenges, this study introduces a hierarchical, AI-driven framework for early detection and precise classification of kidney tumors from CT scans. At its core, the framework uses a specialized encoder, RAD-DINO-MAIRA-2, to extract highly discriminative imaging features, which are subsequently processed through multiple machine learning classifiers tailored to distinct hierarchical levels of diagnosis. Results: Using benchmark kidney tumor datasets, the framework was rigorously validated across 25 independent trials. Performance was assessed using accuracy, reproducibility, and robustness metrics, with results revealing a maximum accuracy of 98.29% and a mean accuracy of 94.72%. Notably, the Gaussian Process classifier achieved perfect performance in tumor type classification, while the MLP classifier attained flawless results in malignant subtype differentiation. Comparative analyses demonstrate that our hierarchical approach outperforms conventional DL-based pipelines by reducing sensitivity to dataset variability and providing a clinically viable path for integration into diagnostic workflows. Combining state-of-the-art feature extraction with hierarchical classification, the proposed framework delivers a robust and interpretable tool with substantial promise for improving patient outcomes in real-world clinical practice. Full article

This study presents a deep learning–assisted integrated navigation scheme implemented on an autonomous underwater vehicle carrying a Chinese domestically developed strapdown inertial navigation system, designed for operation in surface and littoral environments. The system integrates measurements from SINS, the global positioning system, and a Doppler velocity log, while integrating a Decoder-based covariance estimator into the error state-extended Kalman filter. This hybrid architecture adaptively models time-varying processes and measurement noise from raw sensor inputs, greatly improving robustness for surface navigation in dynamic marine environments. To improve learning efficiency, we design a compact and informative feature representation that can be adapted to navigation error dynamics. The novel structure captures temporal dependencies and the evolution of nonlinear error more effectively than typical sequence models, achieving faster convergence and superior accuracy compared to GRU and Transformer baselines. The experimental results based on real sea trial data show that our method significantly outperforms model-based and learning-based methods in terms of navigation solution accuracy and stability, and the adaptive estimation of noise covariance. Specifically, it achieves the lowest RMSE of 0.0274, reducing errors by 94.6–34.6%, compared to conventional ES-EKF-integrated navigation, Transformer, GRU, and a DCE variant. These findings underscore the practical significance of integrating domain-informed filtering methodologies with deep noise modeling frameworks to achieve robust and accurate AUV surface navigation. Full article

Parents with cognitive difficulties are consistently overrepresented in child welfare proceedings, yet such difficulties in themselves are poor predictors of parenting capacity. Research shows that many parents succeed when provided with tailored support, making identification crucial for understanding parental capacity and whether interventions are adapted to individual needs. In this study, cognitive difficulties are understood broadly, encompassing challenges with memory, learning, information processing, and executive functioning, whether linked to formal diagnoses or arising from psychosocial strain. Families in contact with child welfare services often present with multiple and overlapping concerns, such as poverty, trauma, or diffuse forms of neglect, which can obscure or mimic cognitive difficulties. While previous studies have documented prevalence and outcomes, little is known about how professionals identify such difficulties in everyday practice. This study addresses this gap through qualitative interviews with 15 professionals from the Norwegian Child Welfare Service, which were analyzed thematically using an inductive approach. The analysis identified three themes: identification shaped by definitions, identification through relational insights, and identification through patterns of response. Identification rarely followed formal or standardized procedures. Instead, it unfolded gradually through accumulated observations, relational engagement, and professional reflection. The findings highlight how the absence of systematic routines and the delays that result from trial-and-error approaches shape opportunities for adequate support and influence assessments of both parental capacity and the child’s situation. Full article