Search Results (4,157)

In the field of deep learning, the design of optimization algorithms and neural network structures is crucial for improving model performance. Recent advances in medical image analysis have revealed that many pathological features exhibit fractal-like characteristics in their spatial distribution and morphological patterns. This observation has opened new possibilities for developing fractal-inspired deep learning approaches. In this study, we propose the following: (1) a novel Region-Module Adam (RMA) optimizer that incorporates fractal-inspired region-weighting to prioritize areas with higher fractal dimensionality, and (2) an ECA-Enhanced Shuffle MobileNet (ESM) architecture designed to capture multi-scale fractal patterns through its enhanced feature extraction modules. Our experiments demonstrate that this fractal-informed approach significantly improves classification accuracy compared to conventional methods. On gastrointestinal image datasets, the RMA algorithm achieved accuracies of 83.60%, 81.60%, and 87.30% with MobileNetV2, ShuffleNetV2, and ESM networks, respectively. For glaucoma fundus images, the corresponding accuracies reached 84.90%, 83.60%, and 92.73%. These results suggest that explicitly considering fractal properties in medical image analysis can lead to more effective diagnostic tools. Full article

This study proposes a novel Deep Reinforcement Learning (DRL) policy network structure for portfolio management called PortRSMs. PortRSMs employs stacked State-Space Models (SSMs) for the modeling of multi-scale continuous regime shifts in financial time series, striking a balance between exploring consistent distribution properties over short periods and maintaining sensitivity to sudden shocks in price sequences. PortRSMs also performs cross-asset regime fusion through hypergraph attention mechanisms, providing a more comprehensive state space for describing changes in asset correlations and co-integration. Experiments conducted on two different trading frequencies in the stock markets of the United States and Hong Kong show the superiority of PortRSMs compared to other approaches in terms of profitability, risk–return balancing, robustness, and the ability to handle sudden market shocks. Specifically, PortRSMs achieves up to a 0.03 improvement in the annual Sharpe ratio in the U.S. market, and up to a 0.12 improvement for the Hong Kong market compared to baseline methods. Full article

This work investigates spectrum sensing in cognitive radio networks, where multi-antenna secondary users aim to detect the spectral occupancy of noncircular signals transmitted by primary users. Specifically, we propose a deep-learning-based spectrum sensing approach using an augmented covariance-matrix-aware convolutional neural network (CNN). The core innovation of our approach lies in employing an augmented sample covariance matrix, which integrates both a standard covariance matrix and complementary covariance matrix, thereby fully exploiting the statistical properties of noncircular signals. By feeding augmented sample covariance matrices into the designed CNN architecture, the proposed approach effectively learns discriminative patterns from the underlying data structure, without stringent model constraints. Meanwhile, our approach eliminates the need for restrictive model assumptions and significantly enhances the detection performance by fully exploiting noncircular signal characteristics. Various experimental results demonstrate the significant performance improvement and generalization capability of the proposed approach compared to existing benchmark methods. Full article

To study the mechanical properties and modification mechanism of thermosetting polyurethane (PU)-modified asphalt, the effects of polyurethane dosage on the workability of polyurethane-modified asphalt were analyzed by means of rotational viscosity tests. The mechanical properties of polyurethane-modified asphalt with different polyurethane dosages were explored using tensile tests and dynamic mechanical analysis (DMA). In addition, the thermodynamic behavior and micromorphology of polyurethane-modified asphalt were also thoroughly investigated using the test results of differential scanning calorimetry (DSC) and scanning electron microscopy (SEM). The results showed that PU obtained the optimum workability when the polyurethane dose was 50%: at 120 min, its rotational viscosity was 1005 cp, which was lower than 2800 cp (40% PU) and 760 cp (60% PU). Additionally, the results of fracture elongation and fracture strength indicated that the PU-modified asphalt had good flexibility and strength. Compared with base asphalt, the tensile strength of 50% PU-modified asphalt increased by 509%, which was significantly higher than 157% (40% PU) and more balanced than 897% (60% PU) in terms of strength and flexibility. Added PU can significantly improve the elasticity of asphalt at high temperatures, while increasing the proportion of asphalt adhesive components, enhancing the deformation ability and temperature stability of asphalt. As the dose of PU increases, the interface between asphalt and PU blended more fully, and the surface became smoother. When the dose of PU was 50% or more, the interface between asphalt and PU was well integrated with a smooth and flat surface, forming a more uniform and stable cross-linked network structure. Full article

This study aimed to develop a functional powder using whey and milk matrices, leveraging the protective capacity of chia–alginate hydrogels and the advantages of electrohydrodynamic spraying (EHDA), a non-thermal technique suitable for encapsulating probiotic cells under stress conditions commonly encountered in food processing. A hydrogel matrix composed of chia seed mucilage and sodium alginate was used to form a biopolymeric network that protected probiotic cells during processing. The encapsulation efficiency reached 99.0 ± 0.01%, and bacterial viability remained above 9.9 log₁₀ CFU/mL after lyophilization, demonstrating the excellent protective capacity of the hydrogel matrix. Microstructural analysis using confocal laser scanning microscopy (CLSM) revealed well-retained cell morphology and homogeneous distribution within the hydrogel matrix while, in contrast, scanning electron microscopy (SEM) showed spherical, porous microcapsules with distinct surface characteristics influenced by the encapsulation method. Encapsulates were incorporated into beverages flavored with red fruits and pear and subsequently freeze-dried. The resulting powders were analyzed for moisture, protein, lipids, carbohydrates, fiber, and color determinations. The results were statistically analyzed using ANOVA and response surface methodology, highlighting the impact of ingredient ratios on nutritional composition. Raman spectroscopy identified molecular features associated with casein, lactose, pectins, anthocyanins, and other functional compounds, confirming the contribution of both matrix and encapsulants maintaining the structural characteristics of the product. The presence of antioxidant bands supported the functional potential of the powder formulations. Chia–alginate hydrogels effectively encapsulated L. reuteri, maintaining cell viability and enabling their incorporation into freeze-dried beverage powders. This approach offers a promising strategy for the development of next-generation functional food gels with enhanced probiotic stability, nutritional properties, and potential application in health-promoting dairy systems. Full article

Prolonged drought and soil degradation severely affect soil fertility and limit crop productivity. Superabsorbent hydrogels offer an effective solution for improving water retention in soil and supporting plant growth. In this work, we examined the performance of superabsorbent hydrogels based on sodium alginate, acrylic acid (AA), and poly (ethylene oxide) (PEO) cross-linked with 12.5 kGy using e-beam irradiation. The hydrogels were assessed in various aqueous environments by examining network characteristics, swelling capacity, and swelling kinetics to evaluate the impact of water’s electrical conductivity (which ranges from 0.05 to 321 μS/cm). Morphological and chemical structure changes were evaluated using SEM and FTIR techniques. The results demonstrated that water conductivity significantly affected the physicochemical properties of the hydrogels. Swelling behavior showed notable sensitivity to electrical conductivity variations, with swelling degrees reaching 28,400% at 5 μS/cm and 14,000% at 321 μS/cm, following first-order and second-order kinetics. FTIR analysis confirmed that structural modifications correlated with water conductivity, particularly affecting the O–H, C–H, and COOH groups sensitive to the ionic environment. SEM characterization revealed a porous morphology with an interconnected microporous network that facilitates efficient water diffusion. These hydrogels show exceptional swelling capacity and are promising candidates for sustainable agriculture applications. Full article

Hydrogels, characterized by their high water content, tunable mechanical properties, and excellent biocompatibility, have emerged as a promising material platform for the preservation of cultural heritage. Their unique physicochemical features enable non-invasive and adaptable solutions for environmental regulation, structural stabilization, and antifungal protection. This review provides a comprehensive overview of recent progress in hydrogel-based strategies specifically developed for the conservation of cultural relics, with a particular focus on antifungal performance—an essential factor in preventing biodeterioration. Current hydrogel systems, composed of natural or synthetic polymer networks integrated with antifungal agents, demonstrate the ability to suppress fungal growth, regulate humidity, alleviate mechanical stress, and ensure minimal damage to artifacts during application. This review also highlights future research directions, such as the application prospects of novel materials, including stimuli-responsive hydrogels and self-dissolving hydrogels. As an early exploration of the use of hydrogels in antifungal protection and broader cultural heritage conservation, this work is expected to promote the wider application of this emerging technology, contributing to the effective preservation and long-term transmission of cultural heritage worldwide. Full article

The incorporation of waste polyethylene terephthalate (PET) as a modifier for asphalt presents a promising approach to addressing the environmental pollution associated with waste plastics while simultaneously extending the service life of road surfaces. This study investigates the fundamental physical properties and rheological properties of asphalt modified with waste PET at both high and low temperatures. Utilizing the theory of fractional derivatives, performance evaluation indicators, such as the deformation factor and viscoelasticity factor, have been developed for the assessment of waste PET-modified asphalt. The underlying mechanism of this modification was examined through scanning electron microscopy and Fourier transform infrared spectroscopy. The results indicate that the addition of waste PET enhances the high-temperature stability of the base asphalt but reduces its resistance to cracking at low temperatures. The fractional derivative model effectively describes the dynamic shear rheological properties of waste PET-modified asphalt, achieving a maximum correlation coefficient of 0.99991. Considering the performance of modified asphalt at both high and low temperatures, the optimal concentration of waste PET was determined to be 6%. At this concentration, the minimum creep stiffness of the PET-modified asphalt was approximately 155 MPa at −6 °C. Additionally, the rutting factor of the waste PET-modified asphalt achieved a maximum value of 527.12 KPa at 52 °C. The interaction between waste PET and base asphalt was primarily physical, with mutual adsorption leading to the formation of a spatial network structure that enhanced the deformation resistance of the asphalt. This study provides a theoretical foundation and technical support for the engineering application of waste PET as a modifier in asphalt. Full article

To address the inefficiency of traditional concrete crack detection methods and the heavy reliance of supervised learning on extensive labeled data, in this study, an intelligent assessment method of concrete damage based on pseudo-label semi-supervised learning and fractal geometry theory is proposed to solve two core tasks: one is binary classification of pixel-level cracks, and the other is multi-category assessment of damage state based on crack morphology. Using three-channel RGB images as input, a dual-path collaborative training framework based on U-Net encoder–decoder architecture is constructed, and a binary segmentation mask of the same size is output to achieve the accurate segmentation of cracks at the pixel level. By constructing a dual-path collaborative training framework and employing a dynamic pseudo-label refinement mechanism, the model achieves an F1-score of 0.883 using only 50% labeled data—a mere 1.3% decrease compared to the fully supervised benchmark DeepCrack (F1 = 0.896)—while reducing manual annotation costs by over 60%. Furthermore, a quantitative correlation model between crack fractal characteristics and structural damage severity is established by combining a U-Net segmentation network with the differential box-counting algorithm. The experimental results demonstrate that under a cyclic loading of 147.6–221.4 kN, the fractal dimension monotonically increases from 1.073 (moderate damage) to 1.189 (failure), with 100% accuracy in damage state identification, closely aligning with the degradation trend of macroscopic mechanical properties. In complex crack scenarios, the model attains a recall rate (Re = 0.882), surpassing U-Net by 13.9%, with significantly enhanced edge reconstruction precision. Compared with the mainstream models, this method effectively alleviates the problem of data annotation dependence through a semi-supervised strategy while maintaining high accuracy. It provides an efficient structural health monitoring solution for engineering practice, which is of great value to promote the application of intelligent detection technology in infrastructure operation and maintenance. Full article

The cross-sectional dimensions of structural elements in a structure are design elements that need to be carefully designed and are related to the stiffness of the structure. Various optimization processes are applied to determine the optimum cross-sectional dimensions of beams or columns in structures. By repeating the optimization processes for multiple load scenarios, it is possible to create a data set that shows the optimum design section properties. However, this step means repeating the same processes to produce the optimum cross-sectional dimensions. Artificial intelligence technology offers a short-cut solution to this by providing the opportunity to train itself with previously generated optimum cross-sectional dimensions and infer new cross-sectional dimensions. By processing the data, the artificial neural network can generate models that predict the cross-section for a new structural element. In this study, an optimization process is applied to a simple tubular column and an I-section beam, and the results are compiled to create a data set that presents the optimum section dimensions as a class. The harmony search (HS) algorithm, which is a metaheuristic method, was used in optimization. An artificial neural network (ANN) was created to predict the cross-sectional dimensions of the sample structural elements. The neural architecture search (NAS) method, which incorporates many metaheuristic algorithms designed to search for the best artificial neural network architecture, was applied. In this method, the best values of various parameters of the neural network, such as activation function, number of layers, and neurons, are searched for in the model with a tool called HyperNetExplorer. Model metrics were calculated to evaluate the prediction success of the developed model. An effective neural network architecture for column and beam elements is obtained. Full article

Functional foods like flax (Linum usitatissimum L.) are rich sources of specialized metabolites that contribute to their nutritional and health-promoting properties. Understanding the biosynthesis of these compounds is essential for improving their quality and potential applications. However, dissecting complex metabolic networks in plants remains challenging due to the dynamic nature and interconnectedness of biosynthetic pathways. In this study, we present a synergistic approach combining stable isotopic labeling (SIL), Candidate Substrate–Product Pair (CSPP) networks, and a time-course study with high temporal resolution to reveal the biosynthetic fluxes shaping phenylpropanoid metabolism in young flax seedlings. By feeding the seedlings with ¹³C₃-p-coumaric acid and isolating isotopically labeled metabolization products prior to the construction of CSPP networks, the biochemical validity of the connections in the network was supported by SIL, independent of spectral similarity or abundance correlation. This method, in combination with multistage mass spectrometry (MSⁿ), allowed confident structural proposals of lignans, neolignans, and hydroxycinnamic acid conjugates, including the presence of newly identified chicoric acid and related tartaric acid esters in flax. High-resolution time-course analyses revealed successive waves of metabolite formation, providing insights into distinct biosynthetic fluxes toward lignans and early lignification intermediates. No evidence was found here for the involvement of chlorogenic or caftaric acid intermediates in chicoric acid biosynthesis in flax, as has been described in other species. Instead, our findings suggest that in flax seedlings, chicoric acid is synthesized through successive hydroxylation steps of p-coumaroyl tartaric acid esters. This work demonstrates the power of combining SIL and CSPP strategies to uncover novel metabolic routes and highlights the nutritional potential of flax sprouts rich in chicoric acid. Full article

Flocculants are indispensable in water and wastewater treatment, enabling the aggregation and removal of suspended particles, colloids, and emulsions. However, the conventional development and application of flocculants rely heavily on empirical methods, which are time-consuming, resource-intensive, and environmentally problematic due to issues such as sludge production and chemical residues. Recent advances in machine learning (ML) have opened transformative avenues for the design, optimization, and intelligent application of flocculants. This review systematically examines the integration of ML into flocculant research, covering algorithmic approaches, data-driven structure–property modeling, high-throughput formulation screening, and smart process control. ML models—including random forests, neural networks, and Gaussian processes—have successfully predicted flocculation performance, guided synthesis optimization, and enabled real-time dosing control. Applications extend to both synthetic and bioflocculants, with ML facilitating strain engineering, fermentation yield prediction, and polymer degradability assessments. Furthermore, the convergence of ML with IoT, digital twins, and life cycle assessment tools has accelerated the transition toward sustainable, adaptive, and low-impact treatment technologies. Despite its potential, challenges remain in data standardization, model interpretability, and real-world implementation. This review concludes by outlining strategic pathways for future research, including the development of open datasets, hybrid physics–ML frameworks, and interdisciplinary collaborations. By leveraging ML, the next generation of flocculant systems can be more effective, environmentally benign, and intelligently controlled, contributing to global water sustainability goals. Full article

Hydrogels, especially Polyvinyl alcohols, have received extensive attention as alternative materials for articular cartilage. Aiming at the problems such as low strength and poor toughness of polyvinyl alcohol hydrogels in practical applications, an enhancement and modification strategy is proposed. Sodium alginate fibers were introduced into polyvinyl alcohol hydrogel network through physical blending and freezing/thawing methods. The prepared composite hydrogels exhibited a three-dimensional porous network structure similar to that of human articular cartilage. The mechanical and tribological properties of hydrogels have been significantly improved, due to the multiple hydrogen bonding interaction between sodium alginate fibers and polyvinyl alcohol. Most importantly, under a load of 2 N, the friction coefficient of the PVA/0.4SA hydrogel can remain stable at 0.02 when lubricated in PBS buffer for 1 h. This work provides a novel design strategy for the development of high-performance polyvinyl alcohol hydrogels. Full article

Developing multifunctional wound dressings with excellent mechanical properties, strong tissue adhesion, and efficient antibacterial activity is crucial for promoting wound healing. This study prepared a novel nanocomposite hydrogel dressing based on sodium alginate-polyacrylic acid dual crosslinking networks, incorporating tannic acid-coated cellulose nanocrystals (TA@CNC) and in-situ reduced silver nanoparticles for multifunctional enhancement. The rigid CNC framework significantly improved mechanical properties (elastic modulus of 146 kPa at 1 wt%), while TA catechol groups provided excellent adhesion (36.4 kPa to pigskin, 122% improvement over pure system) through dynamic hydrogen bonding and coordination interactions. TA served as a green reducing agent for uniform AgNPs loading, with CNC negative charges preventing particle aggregation. Antibacterial studies revealed synergistic effects between TA-induced membrane disruption and Ag⁺-triggered reactive oxygen species generation, achieving >99.5% inhibition against Staphylococcus aureus and Escherichia coli. The TA@CNC-regulated porous structure balanced swelling performance and water vapor transmission, facilitating wound exudate management and moist healing. This composite hydrogel successfully integrates mechanical toughness, tissue adhesion, antibacterial activity, and biocompatibility, providing a novel strategy for advanced wound dressing development. Full article

The growing complexity of modern manufacturing has intensified the need for precise control of residual stresses to ensure structural reliability, dimensional stability, and material performance. This study conducts a bibliometric review using data from Scopus and Web of Science, covering publications from 2019 to 2024. Residual stress research in metal manufacturing has gained prominence, particularly in relation to welding, additive manufacturing, and machining—processes that induce significant stress gradients affecting mechanical behavior and service life. Emerging trends focus on simulation-based prediction methods, such as the finite element method, heat treatment optimization, and stress-induced defect prevention. Key thematic clusters include process-induced microstructural changes, mechanical property enhancement, and the integration of modeling with experimental validation. By analyzing the evolution of research output, global collaboration networks, and process-specific contributions, this review provides a comprehensive overview of current challenges and identifies strategic directions for future research in residual stress management in advanced metal manufacturing. Full article