Search Results (3,780)

Lung cancer is one of the most common causes of death from cancer around the world, and catching it early through computed tomography (CT) scans can drastically improve survival. However, automated classification of pulmonary nodule candidates is hard because images do not all have the same intensity across scanners and protocols, resulting in inconsistent performance, more false positives (FP), and a ceiling on how much deep learning models work in an average clinic. In this work, we tackle this by introducing a preprocessing step that corrects intensity differences before feeding images into classification models. We use Contrast-Limited Adaptive Histogram Equalization (CLAHE), but with its key parameters tuned automatically via a modified version of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). This helps to boost local contrast adaptively, keeps important anatomical details intact, and cuts down on noise. We tested the approach on the public LUNA16 dataset, first checking image quality (Peak Signal-to-Noise Ratio (PSNR) around 53 dB and Structural Similarity Index (SSIM) of 0.9, better than standard methods), then training three popular deep models—namely, ResNet-50, EfficientNet-B0, and InceptionV3—with CutMix augmentation for better generalization. On the enhanced images, ResNet-50 achieved up to 99.0% classification accuracy with substantially less FP than when using the raw scans. Taken together, these results demonstrate that intelligent and optimized preprocessing can effectively mitigate intensity variations via deep learning for lung nodule detection, thus coming closer to realizing the practical toolbox of computer-aided diagnosis in routine clinical practice. Full article

The primary goal of manufacturing technologies in the metalworking industry is to provide products with specified quality characteristics, while maximizing time and cost efficiency. The total manufacturing cost in turning depends on a number of factors. The analysis of their effects and the estimation of the total manufacturing cost are of practical importance in process planning. Therefore, in the present study, the relationship between four inputs (depth of cut, feed rate, cutting speed and volume of material to be removed) and the total manufacturing cost in medium turning of C45E steel was modeled by using an artificial neural network (ANN). The developed ANN model was used for the analysis of the main and interaction effects of the aforementioned inputs on the total manufacturing cost. Verification of the observed effects was also carried out by applying the connection weight approach. The total manufacturing cost was mostly affected by depth of cut, while the effect of cutting speed was least pronounced. In addition, the results also revealed the presence of two-way interactions associated with cutting speed. For the given case study (with defined volume of material to be removed and specified machine tool), an optimized cutting regime was determined by developing and solving a single-objective turning optimization problem with three constraints related to chip slenderness, cutting power and depth of cut. Cutting force, needed for the estimation of cutting power, was estimated by using the dimensional analysis-based prediction model. Full article

Zinc-based coatings are insufficient as surface coatings; they corrode rapidly and can cause long-term damage to subsea pipelines and other instruments. Therefore, this research was undertaken by manufacturing a sacrificial nano-reinforced Zn coating combined with additives via electrodeposition onto a mild steel S235 substrate, which provides excellent corrosion resistance under severe marine conditions. The electrodeposited coatings were characterized using SEM/EDS and XRD, revealing the effective incorporation of cerium oxide nanoparticles and high-quality graphene (Gr) in the zinc matrix. Vickers microhardness measurements, mechanical resilience, and surface roughness of the Zn-CeO₂-Gr coating showed an inverse correlation between improved microhardness (+65.85%) and mechanical resilience (+31.49%), while surface roughness decreased (−81.48%) compared to pure zinc electrodeposited coatings. These characteristics indicate grain refinement and greater reliability under mechanical stress. Electrochemical impedance spectroscopy (EIS) and DC polarization measurements indicate a significant improvement in corrosion resistance compared to pure zinc, due to the synergistic effect between graphene and cerium oxide nanoparticles, which reduces the cathodic activity of the surface. These findings offer promising applications for cutting-edge materials in saline environments. Full article

This study investigates the factors affecting surface integrity during the machining of near-β Ti-5553, a critical material in the aerospace and defense industries. Considering this alloy as a difficult-to-machine material, the turning process was examined by analyzing the effects of cutting speed, feed rate, and cooling strategy (dry, conventional, and 30 MPa/High-Pressure cooling) on cutting force, temperature, surface roughness, and residual stress. The primary novelty of this research lies in its integrated approach: rather than evaluating surface integrity metrics in isolation, it simultaneously models interrelated responses to residual stress, cutting temperature, cutting force, and surface roughness under high-pressure coolant (HPC) conditions. Furthermore, it introduces a robust machine learning framework that uniquely applies data augmentation (Gaussian jittering and interpolation) to overcome the conventional constraints of limited experimental machining data, providing a highly accurate predictive tool. The experimental data were expanded using data augmentation methods (Gaussian jittering and interpolation) and modeled using five different machine learning algorithms (Extra Trees, Random Forest, Gradient Boosting, KNN, and AdaBoost). The results revealed that cooling pressure plays a dominant role, particularly in residual stress (importance score: 0.926) and cutting temperature (0.657). It was observed that high-pressure cooling (HPC) reduces thermal gradients, thereby lowering tensile stresses and improving surface integrity. When algorithm performances were compared, the Extra Trees and Random Forest models achieved the most accurate predictions after hyperparameter optimization. Specifically, the optimized Extra Trees regressor demonstrated exceptional predictive capability for residual stress, achieving an accuracy of 98.47%, a remarkably high coefficient of determination (R² = 0.9997), and a minimal Mean Squared Error (MSE = 6.8289). These quantitative results confirm that the proposed machine learning framework provides a highly reliable and precise tool for controlling surface quality in HPC- assisted machining. Full article

This study proposes a useful multi-criteria optimization approach for defining the proper fabrication factors for the CNC milling process on the inclined surfaces of SKD 11 material. The method is to be used in mold fabrication technology within the field of mechanical engineering. A combination technique of the Taguchi technique (TM), response surface method (RSM), and Lichtenberg optimization algorithm (LA) was proposed to optimize the fabrication factors for enriching the superiority attributes. In the first stage, several initial experiments of the fabricating parameters were generated by the TM. Secondly, the mathematical equations among the main fabricating parameters, the surface roughness, the flatness, and the CNC milling time were then established by the RSM. Significant influences of fabrication elements on surface roughness, flatness, and CNC milling time were evaluated by variance analysis and sensitivity analysis based on three distinct CNC milling toolpath strategies. Finally, the Lichtenberg optimization algorithm was carried out based on regression equations to define the optimized factors for three cutting strategies. The optimized results showed that the reverse CNC milling toolpath strategy was the best for achieving the three quality responses. Furthermore, the results demonstrated that the inaccuracies among optimized as well as experiment confirmations for the surface roughness, flatness and CNC milling time were 6.54%, 18.182% and 11.972%, respectively. The verifications of experiment results were relatively suitable with the anticipated consequences. The outcomes reveal that an integration optimization methodology is a successful approach to tackling the multi-objective optimal problem of determining the best CNC milling parameters for the cartwheel specimen made of SKD11 material in injection mold technology. It can also be expanded to apply to complicated multi-criteria optimization problems. Full article

Dynamic beam shaping opens new possibilities for improving the quality and productivity of industrial laser material processing applications such as welding and cutting. However, dynamic beam shaping involves time constants and frequencies that must be selected correctly to successfully modify a given laser process. This paper proposes a standardized nomenclature for the possible types of dynamic beam shaping and the resulting dynamic process modifications, and relates these to characteristic time constants and frequencies at which the process modifications have a particularly strong influence on the process. These characteristic frequencies define three process regimes that have distinctly different effects on the process. An overview of typical time constants and frequencies in laser processes aids in understanding the occurrence of characteristic frequencies. Knowledge of the process regimes allows for a systematic selection of frequencies in dynamic beam shaping to achieve targeted dynamic process modifications, e.g., for pore reduction. Using a laser system capable of dynamic beam shaping at frequencies of up to 80 MHz, the influence of the three process zones on the porosity of the weld was demonstrated using deep welds in cast aluminum as an example. Full article

Aramid fiber reinforced polymers (AFRPs) are widely used in aerospace and defense structures because of their high specific strength, impact resistance, and damage tolerance. However, severe burr formation during machining remains a major obstacle to achieving high surface integrity and dimensional accuracy. In particular, the mechanism by which tool edge radius affects burr formation in AFRP cutting has not yet been clarified quantitatively. To address this issue, this study develops an analytical model for the orthogonal cutting of AFRPs to reveal the burr formation mechanism associated with tool edge radius. The model, established on the basis of contact mechanics and fracture theory, predicts fiber deflection, cutting force evolution, fracture behavior, and burr length under different contact and boundary conditions. The results show that tool edge radius governs burr formation through a contact–state transition mechanism. When the edge radius is below a critical threshold, localized point-contact-like interaction promotes stress concentration and fiber fracture, leading to relatively clean material removal. When the edge radius exceeds this threshold, the interaction evolves toward extended contact and sliding, which suppresses complete fiber fracture and results in pronounced burr retention. Experimentally, increasing the edge radius from 5.6 μm to 110.3 μm increased the maximum burr height from 3.19 μm to 83.58 μm, corresponding to an increase of approximately 2520%. The predicted burr evolution agrees well with the experimental observations in both trend and characteristic magnitude. This study provides a mechanistic and predictive understanding of burr formation in AFRP machining and offers practical guidance for cutting edge preparation, tool wear control, and process optimization in high-quality composite machining. Full article

Research on ChatGPT GPT-4 and GPT-5 in higher education has focused on quantitative adoption models (intention to use and predictors) and fragmented effects (writing, performance, well-being, dependence, or ethics). However, this approach keeps the debate stuck in an outdated phase of debate about the tool’s acceptance, even though ChatGPT is part of the academic ecosystem. The objective of the study is to understand, from students’ voices, how the quality of academic interaction with ChatGPT is configured, and to identify patterns of decision-making, validation, ethical regulation, and communication (transparency/concealment) in university contexts. An interpretive qualitative approach was followed. A total of 418 university students participated, all of whom provided qualitative data through semi-structured virtual interviews. The data were analyzed using reflective thematic analysis in six phases, with the support of ATLAS.ti software for rooting and density calculations. The results revealed ten categories that structure the phenomenon (adoption, attitudes, writing, translation, performance, cross-cutting skills, integrity, well-being, disciplinary use, and institutional integration). A continuum was observed between high-quality interaction (verification, rewriting, appropriation, and responsible authorship) and low-quality interaction (cognitive delegation, overconfidence, dependence, and concealment). The quality of student interaction with ChatGPT requires critical, ethical, and institutional regulation to guide and legitimize the academic process. Full article

Background: The Magnetic Resonance Imaging (MRI)-based tumor segmentation remains a challenging problem in medical imaging due to tumor heterogeneity, unpredictable morphological features, and the high complexity of calculations needed to implement it in clinical practice, putting it out of the scope of real-time applications. Although neural networks have significantly improved segmentation performance, they still struggle to capture morphological tumor features while maintaining computational efficiency. This work introduces Hybrid Adaptive Attention U-Net (HAAU-Net) framework, combining context-aware morphologically stable features and spatial channel attention to achieve high-quality tumor segmentation with less computational cost. Methods: The proposed HAAU-Net framework integrates multi-scale Adaptive Attention Blocks (AAB), Context-Aware Morphological Feature Module (CAMFM) and Spatial-Channel Hybrid Attention Mechanism (SCHAM). CAMFM is used to maintain the stability of morphological features by hierarchical aggregation and dynamic normalization of features. SCHAM enhances feature representation by modelling channels and spatial regions where the strongest feature are determined to use in segmentation. On the BRaTS 2022/2023 data, the proposed HAAU-Net is evaluated using four modalities including T1, T1GD, T2 and T2-FLAIR sequences. Results: The proposed model able to obtain 96.8% segmentation accuracy with a Dice coefficient of 0.89 on the entire tumor region, outperforming the alternative U-Net (0.83) and conventional CNN methods of segmentation (0.81). The proposed HAAU-Net architecture cuts the computational complexity of the standard deep learning models by 43% and still achieve real-time inference (28 FPS on a regular GPU). The hybrid model used to predict survival has a C-Index of 0.91 which is higher than the traditional SVM-based methods (0.72). Conclusions: Spatial-channel attention, combined with morphologically stable features, can be combined to allow clinically significant interpretability in attention maps. The proposed framework significantly improves segmentation performance while maintaining computational effeciency. This broad system has a serious potential of AI-enabled clinical decision support system and early prognostic diagnosis in neuro-oncology with practical deployment capability. Full article

Sustainable nanotechnologies derived from renewable resources are increasingly being positioned at the interface of green chemistry, advanced drug delivery, and translational pharmaceutics. Over the past decade, lignocellulosic nanomaterials, chitin/chitosan platforms, polysaccharide-based nanogels and nano-enabled hydrogels, lignin- and polyphenol-derived nanostructures, and bio-based lipid nanocarriers have been engineered through progressively eco-efficient routes, including solvent-minimized self-assembly, nanoprecipitation, spray drying, hot-melt extrusion, and microfluidic-assisted fabrication. This work provides a structured evidence map of nano-enabled drug delivery and therapeutic platforms derived from renewable biological resources. Specifically, we aim to (i) identify and classify nanoplatform classes and renewable feedstocks; (ii) summarize reported pharmaceutical critical quality attributes (CQAs) and performance and safety endpoints; and (iii) appraise how “renewability” and “green” claims are evidenced (feedstock origin vs. process sustainability) and how frequently translational readiness factors (scalability, quality control, regulatory alignment) are addressed. We critically compare renewable and conventional nanomaterial platforms across key translational dimensions, including carbon footprint, batch consistency, biodegradability, functional tunability, safety/persistence, and scale-up maturity. Finally, we delineate a practical translational pathway—from biomass sourcing and fractionation to nanoformulation, characterization/stability, and GMP scale-up—highlighting cross-cutting enablers such as lifecycle assessment, EHS/toxicology risk assessment, quality-by-design, and regulatory alignment. Collectively, the evidence supports renewable nanomaterials as viable, scalable candidates for next-generation therapeutics, provided that variability control, standardized characterization, and safety-by-design principles are embedded early in development. Full article

This study investigates the influence of selected technical and technological parameters on cutting forces and power consumption during the milling of medium-density fibreboards. Unlike previous studies that focus primarily on force measurement, this work integrates experimental analysis with machine learning-based predictive modelling to improve process understanding and prediction accuracy. The main objective was to experimentally measure orthogonal cutting force components (F_x, F_y, F_z) and electrical power consumption under varying spindle speeds (14,000, 16,000 and 18,000 rpm), feed speed (6, 8 and 10 m/min), and milling strategies (conventional and climb), and to evaluate the suitability of the obtained data for predictive modelling. Cutting forces were measured using a Kistler 9257B piezoelectric dynamometer, and power consumption was recorded by a three-phase power quality analyser. Statistical analysis confirmed significant effects of machining parameters on force components, total cutting force, and power consumption. Spindle speed showed the strongest influence on total cutting force and power consumption, while milling strategy predominantly affected F_x and F_y components. Power consumption increased with increasing spindle speed. Based on the measured data, several machine learning models were developed to predict the total cutting force. The Fine Tree algorithm demonstrated the best performance, achieving validation metrics of R² = 0.9 and RMSE = 0.60 (MSE = 0.36, MAE = 0.48), and improved testing performance with R² = 0.95 and RMSE = 0.44 (MSE = 0.20, MAE = 0.36). After model comparison using RMSE, R², training time, and model size, a Fine Tree model was identified as the most suitable, achieving high prediction accuracy without signs of overfitting. The results confirm that experimentally obtained data on cutting force and electrical energy consumption are suitable for reliable predictive modelling in CNC milling of MDF boards. However, it is necessary to work with those components that have the greatest dependence on speed, feed, or type of milling, and these are the force components measured on the x and y axes. Full article

To address rapid tool wear and unstable hole surface quality during roughing and semi-finishing operations using indexable shallow-hole drills, an optimization study on the spatial mounting posture of the insert is conducted, aiming to improve tool life and machined surface quality. Considering that tool life and surface quality are significantly influenced by cutting force and cutting temperature, radial cutting force and cutting temperature are selected as the multi-objective optimization criteria. A mapping model between the insert mounting posture parameters and cutting performance metrics is established. An improved LO-NSGA-II algorithm is employed to perform multi-objective optimization, yielding a Pareto-optimal solution set, and the entropy weighted-TOPSIS method is subsequently applied to determine the optimal insert mounting posture. Experimental results demonstrate that the optimized spatial mounting posture significantly enhances the overall cutting performance of the tool. Compared with the non-optimized tool, the optimized configuration exhibits a significant extension in tool life and a notable improvement in machined hole surface quality. This study provides an effective methodology for the structural optimization design of indexable shallow-hole drills. Full article

Plywood has emerged as a key sustainable material in modern building. Yet, ensuring its consistent performance requires rigorous quality control of the rotary-cut veneers used in its manufacture. This task is complicated by the high-speed nature of industrial conveyors, where motion blur and the complex, varying textures of eucalyptus wood drastically reduce the effectiveness of real-time surface inspection. This study proposes an intelligent, real-time defect detection system specifically optimized for the diverse defect morphology of eucalyptus veneers. A lightweight model, YOLOv11-DMS-Veneers, was developed by integrating MobileNetV4 as the backbone, a Dynamic Head for multi-scale feature extraction, and a Shape-IoU loss function to precisely localize irregular defects like cracks and knots. Additionally, an ERD video enhancement framework (combining ESRGAN, RIFE, and DnCNN) was implemented to mitigate motion blur in dynamic environments. Experimental results demonstrate that the proposed model achieves a mean Average Precision (mAP@50) of 96.0% and a Precision of 95.7% with a low computational cost of only 4.5 GFlops, significantly outperforming traditional algorithms. Notably, the detection precision for challenging linear cracks reached 93.9%. In dynamic tests at conveyor speeds up to 24 m/min, the video enhancement strategy increased the average detection confidence by 0.288, maintaining a maximum confidence of 0.890. This technology offers a robust solution for the automated quality control of eucalyptus veneers, facilitating the production of high-performance plywood and advancing the efficient application of engineered wood in the building industry. Full article

Silicon carbide (SiC), owing to its excellent physical and chemical properties, has emerged as a leading third-generation semiconductor material. Conventional diamond wire cutting faces challenges in producing ultra-large, ultra-thin wafers. In contrast, the femtosecond laser has attracted significant attention in recent years due to its low kerf loss and high slicing speed. However, during femtosecond laser stealth slicing, spherical aberration induced by the refractive index mismatch between air and the SiC crystal severely degrades the slicing quality. Based on the analysis and calculation of wavefront aberration at a specific focal depth of 175 μm, we designed and implemented a static aberration correction method to reduce the thickness of the modified layer and improve the slicing quality. This method effectively mitigates focus elongation caused by refractive index mismatch, thereby reducing the modified layer thickness and the tensile stress required for wafer separation, while improving the surface quality of the separated wafers. Furthermore, this method eliminates the need for active optical components in aberration correction, simplifying the system and avoiding errors associated with the limited response speed of active optics. The technique demonstrates potential for practical application in industrial wafer slicing. Full article

Painho de Porco Preto is a traditional product of the Alentejo region, made with cuts of Alentejano autochthonous breed pigs. The objective of this study was to evaluate how different storage temperatures (4 °C and room temperature (20 ± 2 °C)) could influence the quality and safety of the sliced vacuum-packed Painho de Porco Preto, throughout 6 months of storage. Analyses included physicochemical parameters, microbiological, and sensory analysis. Throughout storage, the product showed low TBARS values (<3 MDA/kg) and stable tocopherol levels under both storage conditions, although the samples at room temperature performed slightly better. a_w and pH values were higher for samples stored at 4 °C, which influenced the results of some parameters. Color coordinate b* had an increase in values by the end of storage for the fat portion of the slices, but the rest of the parameters stayed stable. Nitrate/nitrite contents remained within expected ranges for dry-cured sausages. Microbiological analyses confirmed the absence of major pathogens during the study period, while variations in growth were observed depending on storage temperature. In sum, the results indicate that sliced vacuum-packaged Painho de Porco Preto can maintain acceptable quality and safety for 6 months at room temperature. These findings provide useful information for the meat industry by supporting the optimization of storage strategies and shelf-life management for sliced traditional dry-cured sausages. Full article