Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (1,572)

Search Parameters:
Keywords = layer transfer process

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
30 pages, 6035 KB  
Article
Bio-Inspired Optimization of Transfer Learning Models for Diabetic Macular Edema Classification
by A. M. Mutawa, Khalid Sabti, Bibin Shalini Sundaram Thankaleela and Seemant Raizada
AI 2025, 6(10), 269; https://doi.org/10.3390/ai6100269 - 17 Oct 2025
Viewed by 106
Abstract
Diabetic Macular Edema (DME) poses a significant threat to vision, often leading to permanent blindness if not detected and addressed swiftly. Existing manual diagnostic methods are arduous and inconsistent, highlighting the pressing necessity for automated, accurate, and personalized solutions. This study presents a [...] Read more.
Diabetic Macular Edema (DME) poses a significant threat to vision, often leading to permanent blindness if not detected and addressed swiftly. Existing manual diagnostic methods are arduous and inconsistent, highlighting the pressing necessity for automated, accurate, and personalized solutions. This study presents a novel methodology for diagnosing DME and categorizing choroidal neovascularization (CNV), drusen, and normal conditions from fundus images through the application of transfer learning models and bio-inspired optimization methodologies. The methodology utilizes advanced transfer learning architectures, including VGG16, VGG19, ResNet50, EfficientNetB7, EfficientNetV2-S, InceptionV3, and InceptionResNetV2, for analyzing both binary and multi-class Optical Coherence Tomography (OCT) datasets. We combined the OCT datasets OCT2017 and OCTC8 to create a new dataset for our study. The parameters, including learning rate, batch size, and dropout layer of the fully connected network, are further adjusted using the bio-inspired Particle Swarm Optimization (PSO) method, in conjunction with thorough preprocessing. Explainable AI approaches, especially Shapley additive explanations (SHAP), provide transparent insights into the model’s decision-making processes. Experimental findings demonstrate that our bio-inspired optimized transfer learning Inception V3 significantly surpasses conventional deep learning techniques for DME classification, as evidenced by enhanced metrics including the accuracy, precision, recall, F1-score, misclassification rate, Matthew’s correlation coefficient, intersection over union, and kappa coefficient for both binary and multi-class scenarios. The accuracy achieved is approximately 98% in binary classification and roughly 90% in multi-class classification with the Inception V3 model. The integration of contemporary transfer learning architectures with nature-inspired PSO enhances diagnostic precision to approximately 95% in multi-class classification, while also improving interpretability and reliability, which are crucial for clinical implementation. This research promotes the advancement of more precise, personalized, and timely diagnostic and therapeutic strategies for Diabetic Macular Edema, aiming to avert vision loss and improve patient outcomes. Full article
Show Figures

Figure 1

25 pages, 3111 KB  
Article
Intrusion Detection in Industrial Control Systems Using Transfer Learning Guided by Reinforcement Learning
by Jokha Ali, Saqib Ali, Taiseera Al Balushi and Zia Nadir
Information 2025, 16(10), 910; https://doi.org/10.3390/info16100910 - 17 Oct 2025
Viewed by 163
Abstract
Securing Industrial Control Systems (ICSs) is critical, but it is made challenging by the constant evolution of cyber threats and the scarcity of labeled attack data in these specialized environments. Standard intrusion detection systems (IDSs) often fail to adapt when transferred to new [...] Read more.
Securing Industrial Control Systems (ICSs) is critical, but it is made challenging by the constant evolution of cyber threats and the scarcity of labeled attack data in these specialized environments. Standard intrusion detection systems (IDSs) often fail to adapt when transferred to new networks with limited data. To address this, this paper introduces an adaptive intrusion detection framework that combines a hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) model with a novel transfer learning strategy. We employ a Reinforcement Learning (RL) agent to intelligently guide the fine-tuning process, which allows the IDS to dynamically adjust its parameters such as layer freezing and learning rates in real-time based on performance feedback. We evaluated our system in a realistic data-scarce scenario using only 50 labeled training samples. Our RL-Guided model achieved a final F1-score of 0.9825, significantly outperforming a standard neural fine-tuning model (0.861) and a target baseline model (0.759). Analysis of the RL agent’s behavior confirmed that it learned a balanced and effective policy for adapting the model to the target domain. We conclude that the proposed RL-guided approach creates a highly accurate and adaptive IDS that overcomes the limitations of static transfer learning methods. This dynamic fine-tuning strategy is a powerful and promising direction for building resilient cybersecurity defenses for critical infrastructure. Full article
(This article belongs to the Section Information Systems)
Show Figures

Figure 1

49 pages, 7997 KB  
Article
Investigation of Thermo-Mechanical Characteristics in Friction Stir Processing of AZ91 Surface Composite: Novel Study Through SPH Analysis
by Roshan Vijay Marode, Tamiru Alemu Lemma, Srinivasa Rao Pedapati, Sambhaji Kusekar, Vyankatesh Dhanraj Birajdar and Adeel Hassan
Lubricants 2025, 13(10), 450; https://doi.org/10.3390/lubricants13100450 - 16 Oct 2025
Viewed by 157
Abstract
The current study examines the influence of tool rotational speed (TRS) and reinforcement volume fraction (%vol.) of SiC on particle distribution in the stir zone (SZ) of AZ91 Mg alloy. Two parameter sets were analyzed: S1 (500 rpm TRS, 13% vol.) and S2 [...] Read more.
The current study examines the influence of tool rotational speed (TRS) and reinforcement volume fraction (%vol.) of SiC on particle distribution in the stir zone (SZ) of AZ91 Mg alloy. Two parameter sets were analyzed: S1 (500 rpm TRS, 13% vol.) and S2 (1500 rpm TRS, 10% vol.), with a constant tool traverse speed (TTS) of 60 mm/min. SPH simulations revealed that in S1, lower TRS resulted in limited SiC displacement, leading to significant agglomeration zones, particularly along the advancing side (AS) and beneath the tool pin. Cross-sectional observations at 15 mm and 20 mm from the plunging phase indicated the formation of reinforcement clusters along the tool path, with inadequate SiC transference to the retreating side (RS). The reduced stirring force in S1 caused poor reinforcement dispersion, with most SiC nodes settling at the SZ bottom due to insufficient upward movement. In contrast, S2 demonstrated enhanced particle mobility due to higher TRS, improving reinforcement homogeneity. Intense stirring facilitated lateral and upward SiC movement, forming an interconnected reinforcement network. SPH nodes exhibited improved dispersion, with particles across the SZ and more evenly deposited on the RS. A comparative assessment of experimental and simulated reinforcement distributions confirmed a strong correlation. Results highlight the pivotal role of TRS in reinforcement movement and agglomeration control. Higher TRS enhances stirring and promotes uniform SiC dispersion, whereas an excessive reinforcement fraction increases matrix viscosity and restricts particle mobility. Thus, optimizing TRS and reinforcement content through numerical analysis using SPH is essential for producing a homogeneous, well-reinforced composite layer with improved surface properties. The findings of this study have significant practical applications, particularly in industrial material selection, improving manufacturing processes, and developing more efficient surface composites, thereby enhancing the overall performance and reliability of Mg alloys in engineering applications. Full article
(This article belongs to the Special Issue Surface Machining and Tribology)
Show Figures

Figure 1

21 pages, 2630 KB  
Article
Hierarchical Markov Chain Monte Carlo Framework for Spatiotemporal EV Charging Load Forecasting
by Xuehan Zheng, Yalun Zhu, Ming Wang, Bo Lv and Yisheng Lv
Appl. Sci. 2025, 15(20), 11094; https://doi.org/10.3390/app152011094 - 16 Oct 2025
Viewed by 100
Abstract
With the advancement of battery technology and the promotion of the “dual carbon” policy, electric vehicles (EVs) have been widely used in industrial, commercial, and civil fields, and the charging infrastructure of highway service areas across the country has also shown a rapid [...] Read more.
With the advancement of battery technology and the promotion of the “dual carbon” policy, electric vehicles (EVs) have been widely used in industrial, commercial, and civil fields, and the charging infrastructure of highway service areas across the country has also shown a rapid development trend. However, the charging load of electric vehicles in highway scenarios exhibits strong randomness and uncertainty. It is affected by multiple factors such as traffic flow, state of charge (SOC), and user charging behavior, and it is difficult to accurately model it through traditional mathematical models. This paper proposes a hierarchical Markov chain Monte Carlo (HMMC) simulation method to construct a charging load prediction model with spatiotemporal coupling characteristics. The model hierarchically models features such as traffic flow, SOC, and charging behavior through a hierarchical structure to reduce interference between dimensions; by constructing a Markov chain that converges to the target distribution and an inter-layer transfer mechanism, the load change process is deduced layer by layer, thereby achieving a more accurate charging load prediction. Comparative experiments with mainstream methods such as ARIMA, BP neural networks, random forests, and LSTM show that the HMMC model has higher prediction accuracy in highway scenarios, significantly reduces prediction errors, and improves model stability and interpretability. Full article
Show Figures

Figure 1

15 pages, 2013 KB  
Article
Influence of Bubble Shape on Mass Transfer in Multiphase Media: CFD Analysis of Concentration Gradients
by Irina Nizovtseva, Pavel Mikushin, Ilya Starodumov, Ksenia Makhaeva, Margarita Nikishina, Sergey Vikharev, Olga Averkova, Dmitri Alexandrov, Dmitrii Chernushkin and Sergey Lezhnin
Fluids 2025, 10(10), 269; https://doi.org/10.3390/fluids10100269 - 16 Oct 2025
Viewed by 141
Abstract
Our study investigates how non-spherical bubble shapes influence gas–liquid mass transfer across the bubble interface. An analytical shape descriptor, namely Superformula, is used to parametrically define the bubble interface, enabling efficient CFD simulations over a range of Reynolds (Re) and [...] Read more.
Our study investigates how non-spherical bubble shapes influence gas–liquid mass transfer across the bubble interface. An analytical shape descriptor, namely Superformula, is used to parametrically define the bubble interface, enabling efficient CFD simulations over a range of Reynolds (Re) and Eötvös (Eo) numbers. By prescribing the bubble geometry analytically, we avoid expensive interface-capturing simulations and directly compute the concentration field without transient boundary shape pre-equilibration. The represented approach is computationally efficient and captures the impact of bubble shape and flow parameters on the dissolved gas concentration gradients in the surrounding liquid. Results show that bubble deformation alters the distribution of dissolved gas around the bubble and the overall mass transfer rate, with higher Re enhancing convective transport and higher Eo (more deformed bubbles), leading to anisotropic concentration boundary layers. The developed framework not only advances a fundamental understanding of bubble-driven mass transfer mechanisms but also directly addresses industrial needs, particularly in optimizing oxygen delivery within bioreactors contour and similar aerated processes. The proposed efficient modeling strategy provides a basis for developing fast surrogate tools in hybrid modeling frameworks, where high-fidelity CFD insights are incorporated into larger-scale multiphase process simulations. Full article
(This article belongs to the Special Issue Advances in Multiphase Flow Science and Technology, 2nd Edition)
Show Figures

Figure 1

22 pages, 9565 KB  
Article
Directed Self-Assembly of an Acid-Responsive Block Copolymer for Hole-Shrink Process and Pattern Transfer
by Jianghao Zhan, Jiacheng Luo, Zixin Zhuo, Caiwei Shang, Zili Li and Shisheng Xiong
Nanomaterials 2025, 15(20), 1571; https://doi.org/10.3390/nano15201571 - 16 Oct 2025
Viewed by 219
Abstract
Directed self-assembly (DSA) of polystyrene-block-poly (methyl methacrylate) (PS-b-PMMA) has garnered substantial interest for semiconductor manufacturing, particularly for fabricating contact holes and vias. However, its application is limited by the low etch selectivity between the PS and PMMA domains. Here, we report [...] Read more.
Directed self-assembly (DSA) of polystyrene-block-poly (methyl methacrylate) (PS-b-PMMA) has garnered substantial interest for semiconductor manufacturing, particularly for fabricating contact holes and vias. However, its application is limited by the low etch selectivity between the PS and PMMA domains. Here, we report an acid-responsive block copolymer, PS-N=CH-PMMA, incorporating a Schiff base (-N=CH-) linkage between the two blocks to impart acid sensitivity. The copolymer is synthesized via aldehyde-terminated PMMA (PMMA-CHO) precursors and is fully compatible with conventional thermal annealing workflows used for PS-b-PMMA. Uniform thin films with vertically oriented cylindrical domains were obtained, which could be directly converted into high-fidelity PS masks through acetic acid immersion without UV exposure. Graphoepitaxial DSA in 193i pre-patterned templates produced shrink-hole patterns with reduced critical dimension (CD) and improved local CD uniformity (LCDU). The shrink-hole CD was tunable by varying PMMA-CHO molecular weights. XPS confirmed selective cleavage of Schiff base linkages at the PS/PMMA interface under acidic conditions, while Ohta–Kawasaki simulations indicated interfacial wetting asymmetry governs etch fidelity and residual layer formation. Pattern transfer into TEOS layers was achieved with minimal CD loss. Overall, the acid-cleavable BCP enables scalable, high-fidelity nanopatterning with improved etch contrast, tunable process windows, and seamless integration into existing PS-b-PMMA lithography platforms. Full article
Show Figures

Figure 1

14 pages, 2892 KB  
Article
Boosting Green Hydrogen Production—Energy Savings in Alkaline Water Electrolysis Using Synergy of Magnetic Field and In Situ Activation of Electrodes
by Milica P. Marceta Kaninski, Sladjana Lj. Maslovara, Jovana G. Protic, Dejana P. Popovic, Danilo Lj. Vujosevic, Zeljka M. Nikolic and Vladimir M. Nikolic
Catalysts 2025, 15(10), 985; https://doi.org/10.3390/catal15100985 - 15 Oct 2025
Viewed by 400
Abstract
This study focuses on enhancing the efficiency of alkaline water electrolysis technology, a key process in green hydrogen production, by leveraging the synergy of magnetic fields and in situ electrode activation. Optimizing AWE efficiency is essential to meet increasing demands for sustainable energy [...] Read more.
This study focuses on enhancing the efficiency of alkaline water electrolysis technology, a key process in green hydrogen production, by leveraging the synergy of magnetic fields and in situ electrode activation. Optimizing AWE efficiency is essential to meet increasing demands for sustainable energy solutions. In this research, nickel mesh electrodes were modified through the application of magnetic fields and the addition of hypo-hyper d-metal (cobalt complexes and molybdenum salt) to the electrolyte. These enhancements improve mass transfer, facilitate bubble detachment, and create a high-surface-area catalytic layer on the electrodes, all of which lead to improved hydrogen evolution rates. The integration of magnetic fields and in situ activation achieved over 35% energy savings, offering a cost-effective and scalable pathway for industrial green hydrogen production. Full article
(This article belongs to the Section Electrocatalysis)
Show Figures

Graphical abstract

20 pages, 4070 KB  
Article
Study on Meta-Learning-Improved Operational Characteristic Model of Central Air-Conditioning Systems
by Shuai Guo, Guiping Peng, Shiheng Chai, Jiwei Jia, Zhenhui Deng and Zhenqian Chen
Energies 2025, 18(20), 5405; https://doi.org/10.3390/en18205405 - 14 Oct 2025
Viewed by 186
Abstract
Establishing accurate models for central air-conditioning systems is an indispensable part of energy-saving optimization research. This paper focuses on large commercial buildings and conducts research on improving the energy efficiency model of chillers in central air-conditioning systems based on meta-learning. Taking the Model-Agnostic [...] Read more.
Establishing accurate models for central air-conditioning systems is an indispensable part of energy-saving optimization research. This paper focuses on large commercial buildings and conducts research on improving the energy efficiency model of chillers in central air-conditioning systems based on meta-learning. Taking the Model-Agnostic Meta-Learning (MAML) framework as the core, the study systematically addresses the energy efficiency prediction problem of chillers under different operating conditions and across different equipment. It constructs a comprehensive research process including data preparation, meta-model training, fine-tuning and evaluation, cross-device transfer, and energy efficiency analysis. Through its bi-level optimization mechanism, MAML significantly enhances the model’s rapid adaptability to new tasks. Experimental validation demonstrates that: under varying operating conditions on the same device, only 5 data points are required to achieve a relative error (RE) within 3%; under similar operating conditions across different devices, 4 data points achieve a RE within 5%. This represents a reduction in data requirements by 50% and 73%, respectively, compared to standard Multi-Layer Perceptron (MLP) models. This method effectively addresses modeling challenges in complex operating scenarios and offers an efficient solution for intelligent management. It significantly enhances the model’s rapid adaptation capability to new tasks, particularly its generalization performance in data-scarce scenarios. Full article
Show Figures

Figure 1

15 pages, 8005 KB  
Article
Effect of the Activator B(OCH3)3 on the Microstructure and Mechanical Properties of Cu-Mn-Al Alloy Coating via CMT Cladding
by Jin Peng, Shihua Xie, Junhai Xia, Xingxing Wang, Zenglei Ni, Pei Wang and Nannan Chen
Crystals 2025, 15(10), 881; https://doi.org/10.3390/cryst15100881 - 13 Oct 2025
Viewed by 175
Abstract
This study investigates the fabrication of a Cu-Mn-Al alloy coating on 27SiMn steel using Cold Metal Transfer (CMT) technology with an innovative Ar-B(OCH3)3 mixed shielding gas, focusing on the effect of the gas flow rate (5–20 L/min). The addition of [...] Read more.
This study investigates the fabrication of a Cu-Mn-Al alloy coating on 27SiMn steel using Cold Metal Transfer (CMT) technology with an innovative Ar-B(OCH3)3 mixed shielding gas, focusing on the effect of the gas flow rate (5–20 L/min). The addition of B(OCH3)3 was found to significantly enhance process stability by improving molten pool wettability, resulting in a wider cladding layer (6.565 mm) and smaller wetting angles compared to pure Ar. Macro-morphology analysis identified 10 L/min as the optimal flow rate for achieving a uniform and defect-free coating, while deviations led to oxidation (at low flow) or spatter and turbulence (at high flow). Microstructural characterization revealed that the flow rate critically governs phase evolution, with the primary κI phase transforming from dendritic/granular to petal-like/rod-like morphologies. At higher flow rates (≥15 L/min), increased stirring promoted Fe dilution from the substrate, leading to the formation of Fe-rich intermetallic compounds and distinct spherical Fe phases. Consequently, the cladding layer obtained at 10 L/min exhibited balanced and superior properties, achieving a maximum shear strength of 303.22 MPa and optimal corrosion resistance with a minimum corrosion rate of 0.02935 mm/y. All shear fractures occurred within the cladding layer, demonstrating superior interfacial bonding strength and ductile fracture characteristics. This work provides a systematic guideline for optimizing shielding gas parameters in the CMT cladding of high-performance Cu-Mn-Al alloy coatings. Full article
(This article belongs to the Section Crystalline Metals and Alloys)
Show Figures

Figure 1

24 pages, 943 KB  
Review
A Review on AI Miniaturization: Trends and Challenges
by Bin Tang, Shengzhi Du and Antonie Johan Smith
Appl. Sci. 2025, 15(20), 10958; https://doi.org/10.3390/app152010958 - 12 Oct 2025
Viewed by 479
Abstract
Artificial intelligence (AI) often suffers from high energy consumption and complex deployment in resource-constrained environments, leading to a structural mismatch between capability and deployability. This review takes two representative scenarios—energy-first and performance-first—as the main thread, systematically comparing cloud, edge, and fog/cloudlet/mobile edge computing [...] Read more.
Artificial intelligence (AI) often suffers from high energy consumption and complex deployment in resource-constrained environments, leading to a structural mismatch between capability and deployability. This review takes two representative scenarios—energy-first and performance-first—as the main thread, systematically comparing cloud, edge, and fog/cloudlet/mobile edge computing (MEC)/micro data center (MDC) architectures. Based on a standardized literature search and screening process, three categories of miniaturization strategies are distilled: redundancy compression (e.g., pruning, quantization, and distillation), knowledge transfer (e.g., distillation and parameter-efficient fine-tuning), and hardware–software co-design (e.g., neural architecture search (NAS), compiler-level, and operator-level optimization). The purposes of this review are threefold: (1) to unify the “architecture–strategy–implementation pathway” from a system-level perspective; (2) to establish technology–budget mapping with verifiable quantitative indicators; and (3) to summarize representative pathways for energy- and performance-prioritized scenarios, while highlighting current deficiencies in data disclosure and device-side validation. The findings indicate that, compared with single techniques, cross-layer combined optimization better balances accuracy, latency, and power consumption. Therefore, AI miniaturization should be regarded as a proactive method of structural reconfiguration for large-scale deployment. Future efforts should advance cross-scenario empirical validation and standardized benchmarking, while reinforcing hardware–software co-design. Compared with existing reviews that mostly focus on a single dimension, this review proposes a cross-level framework and design checklist, systematizing scattered optimization methods into reusable engineering pathways. Full article
Show Figures

Figure 1

19 pages, 7242 KB  
Article
Influence of Fe Vacancy on the Bonding Properties of γ-Fe (111)/α-Al2O3 (0001) Interfaces: A Theoretical Study
by Xiaofeng Zhang, Renwei Li, Qicheng Chen, Dehao Kong and Haifeng Yang
Materials 2025, 18(20), 4666; https://doi.org/10.3390/ma18204666 - 11 Oct 2025
Viewed by 359
Abstract
Here, the effects of Fe vacancy defects on the bonding properties of γ-Fe (111)/α-Al2O3 (0001) interfaces are studied in depth at the atomic and electronic levels using first-principles calculations. The first (V1), second (V2), third (V [...] Read more.
Here, the effects of Fe vacancy defects on the bonding properties of γ-Fe (111)/α-Al2O3 (0001) interfaces are studied in depth at the atomic and electronic levels using first-principles calculations. The first (V1), second (V2), third (V3), and fourth (V4) layers of vacancy structures within the Fe substrate, as well as the ideal Fe/Al2O3 interface structure, are proposed and contrasted, including their thermodynamic parameters and atomic/electronic properties. The results demonstrate that the presence of vacancies in the first atomic layer of Fe deteriorates the interfacial bonding strength, whereas vacancies situated in the third layer enhance the interfacial bonding strength. The effect of vacancy beyond the third layer becomes negligible. This occurs mainly because vacancy defects at different positions induce the relaxation behavior of atoms, resulting in bond-breaking and bond-forming reactions at the interface. Following that, the formation process of vacancies can cause the transfer and rearrangement of the electrons at the interface. This process leads to significant changes in the charge concentration of the interfaces, where V3 is the largest and V1 is the smallest, indicating that the greater the charge concentration, the stronger the bonding strength of the interface. Furthermore, it is discovered that vacancy defects can induce new electronic orbital hybridization between Fe and O at the interface, which is the fundamental reason for changes in the properties of the interface. Interestingly, it is also found that more electronic orbital hybridization will strengthen the bonding performance of the interface. It seems, then, that the existence of vacancy defects not only changes the electronic environment of the Fe/Al2O3 interface but also directly affects the bonding properties of the interface. Full article
(This article belongs to the Section Materials Simulation and Design)
Show Figures

Figure 1

29 pages, 7442 KB  
Article
Vulnerability Analysis of the Sea–Railway Cross-Border Intermodal Logistics Network Considering Inter-Layer Transshipment Under Cascading Failures
by Hairui Wei and Huixin Qi
Systems 2025, 13(10), 890; https://doi.org/10.3390/systems13100890 - 10 Oct 2025
Viewed by 396
Abstract
Maritime logistics and railway logistics are crucial in cross-border logistics, and their integration forms a sea-rail cross-border intermodal logistics network. Against the backdrop of frequent unexpected events in today’s world, the normal operation of the sea-rail cross-border intermodal logistics network is under considerable [...] Read more.
Maritime logistics and railway logistics are crucial in cross-border logistics, and their integration forms a sea-rail cross-border intermodal logistics network. Against the backdrop of frequent unexpected events in today’s world, the normal operation of the sea-rail cross-border intermodal logistics network is under considerable threat. Therefore, researching the vulnerability of the intermodal network is extremely urgent. To this end, this paper first constructs a topological model of the sea-rail cross-border intermodal logistics network, designed to reflect the crucial process of “inter-layer transshipment” via transshipment nodes. Subsequently, a cascading failure model is developed to evaluate network vulnerability, featuring a load redistribution process that distinguishes between transshipment and non-transshipment nodes. The paper yields three primary findings. First, it identifies the optimal values for the capacity factor, overload factor, and inter-layer load transfer rate that most effectively mitigate the network’s vulnerability. Second, compared to a single sub-network (such as a maritime logistics network or a railway logistics network), the sea-rail cross-border intermodal network exhibits lower vulnerability when facing attacks. Third, it highlights the critical role of transshipment nodes, confirming that their failure will make the entire sea-rail cross-border intermodal logistics network more vulnerable. Full article
(This article belongs to the Section Supply Chain Management)
Show Figures

Figure 1

21 pages, 8249 KB  
Article
Short-Term Passenger Flow Forecasting for Rail Transit Inte-Grating Multi-Scale Decomposition and Deep Attention Mechanism
by Youpeng Lu and Jiming Wang
Sustainability 2025, 17(19), 8880; https://doi.org/10.3390/su17198880 - 6 Oct 2025
Viewed by 449
Abstract
Short-term passenger flow prediction provides critical data-driven support for optimizing resource allocation, guiding passenger mobility, and enhancing risk response capabilities in urban rail transit systems. To further improve prediction accuracy, this study proposes a hybrid SMA-VMD-Informer-BiLSTM prediction model. Addressing the challenge of error [...] Read more.
Short-term passenger flow prediction provides critical data-driven support for optimizing resource allocation, guiding passenger mobility, and enhancing risk response capabilities in urban rail transit systems. To further improve prediction accuracy, this study proposes a hybrid SMA-VMD-Informer-BiLSTM prediction model. Addressing the challenge of error propagation caused by non-stationary components (e.g., noise and abrupt fluctuations) in conventional passenger flow signals, the Variational Mode Decomposition (VMD) method is introduced to decompose raw flow data into multiple intrinsic mode functions (IMFs). A Slime Mould Algorithm (SMA)-based optimization mechanism is designed to adaptively tune VMD parameters, effectively mitigating mode redundancy and information loss. Furthermore, to circumvent error accumulation inherent in serial modeling frameworks, a parallel prediction architecture is developed: the Informer branch captures long-term dependencies through its ProbSparse self-attention mechanism, while the Bidirectional Long Short-Term Memory (BiLSTM) network extracts localized short-term temporal patterns. The outputs of both branches are fused via a fully connected layer, balancing global trend adherence and local fluctuation characterization. Experimental validation using historical entry flow data from Weihouzhuang Station on Xi’an Metro demonstrated the superior performance of the SMA-VMD-Informer-BiLSTM model. Compared to benchmark models (CNN-BiLSTM, CNN-BiGRU, Transformer-LSTM, ARIMA-LSTM), the proposed model achieved reductions of 7.14–53.33% in fmse, 3.81–31.14% in frmse, and 8.87–38.08% in fmae, alongside a 4.11–5.48% improvement in R2. Cross-station validation across multiple Xi’an Metro hubs further confirmed robust spatial generalizability, with prediction errors bounded within fmse: 0.0009–0.01, frmse: 0.0303–0.1, fmae: 0.0196–0.0697, and R2: 0.9011–0.9971. Furthermore, the model demonstrated favorable predictive performance when applied to forecasting passenger inflows at multiple stations in Nanjing and Zhengzhou, showcasing its excellent spatial transferability. By integrating multi-level, multi-scale data processing and adaptive feature extraction mechanisms, the proposed model significantly mitigates error accumulation observed in traditional approaches. These findings collectively indicate its potential as a scientific foundation for refined operational decision-making in urban rail transit management, thereby significantly promoting the sustainable development and long-term stable operation of urban rail transit systems. Full article
Show Figures

Figure 1

29 pages, 3520 KB  
Article
Thermal Entropy Generation in Magnetized Radiative Flow Through Porous Media over a Stretching Cylinder: An RSM-Based Study
by Shobha Visweswara, Baskar Palani, Fatemah H. H. Al Mukahal, S. Suresh Kumar Raju, Basma Souayeh and Sibyala Vijayakumar Varma
Mathematics 2025, 13(19), 3189; https://doi.org/10.3390/math13193189 - 5 Oct 2025
Viewed by 232
Abstract
Magnetohydrodynamic (MHD) flow and heat transfer in porous media are central to many engineering applications, including heat exchangers, MHD generators, and polymer processing. This study examines the boundary layer flow and thermal behavior of an electrically conducting viscous fluid over a porous stretching [...] Read more.
Magnetohydrodynamic (MHD) flow and heat transfer in porous media are central to many engineering applications, including heat exchangers, MHD generators, and polymer processing. This study examines the boundary layer flow and thermal behavior of an electrically conducting viscous fluid over a porous stretching tube. The model accounts for nonlinear thermal radiation, internal heat generation/absorption, and Darcy–Forchheimer drag to capture porous medium resistance. Similarity transformations reduce the governing equations to a system of coupled nonlinear ordinary differential equations, which are solved numerically using the BVP4C technique with Response Surface Methodology (RSM) and sensitivity analysis. The effects of dimensionless parameters magnetic field strength (M), Reynolds number (Re), Darcy–Forchheimer parameter (Df), Brinkman number (Br), Prandtl number (Pr), nonlinear radiation parameter (Rd), wall-to-ambient temperature ratio (rw), and heat source/sink parameter (Q) are investigated. Results show that increasing M, Df, and Q suppresses velocity and enhances temperature due to Lorentz and porous drag effects. Higher Re raises pressure but reduces near-wall velocity, while rw, Rd, and internal heating intensify thermal layers. The entropy generation analysis highlights the competing roles of viscous, magnetic, and thermal irreversibility, while the Bejan number trends distinctly indicate which mechanism dominates under different parameter conditions. The RSM findings highlight that rw and Rd consistently reduce the Nusselt number (Nu), lowering thermal efficiency. These results provide practical guidance for optimizing energy efficiency and thermal management in MHD and porous media-based systems.: Full article
(This article belongs to the Special Issue Advances and Applications in Computational Fluid Dynamics)
Show Figures

Figure 1

13 pages, 3165 KB  
Article
Thermal Conductivity of Suspended Graphene at High Temperature Based on Raman Spectroscopy
by Junyi Wang, Zhiyu Guo, Zhilong Shang and Fang Luo
Nanomaterials 2025, 15(19), 1520; https://doi.org/10.3390/nano15191520 - 5 Oct 2025
Viewed by 369
Abstract
With the development of technology, many fields have put forward higher requirements for the thermal conductivity of materials in high-temperature environments, for instance, in fields such as heat dissipation of electronic devices, high-temperature sensors, and thermal management. As a potential high-performance thermal management [...] Read more.
With the development of technology, many fields have put forward higher requirements for the thermal conductivity of materials in high-temperature environments, for instance, in fields such as heat dissipation of electronic devices, high-temperature sensors, and thermal management. As a potential high-performance thermal management material, studying the thermal conductivity of graphene at high temperatures is of great significance for expanding its application range. In this study, high-quality suspended graphene was prepared through PDMS dry transfer, which can effectively avoid the binding and influence of the substrate. Based on the calculation model of the thermal conductivity of suspended graphene, the model was modified accordingly by measuring the attenuation coefficient of laser power. Combined with the temperature variation coefficient of suspended graphene measured experimentally and the influence of laser power on the Raman characteristic peak positions of graphene, the thermal conductance of suspended graphene with different layers under high-temperature conditions was calculated. It is conducive to a further in-depth understanding of the phonon scattering mechanism and heat conduction process of graphene at high temperatures. Full article
(This article belongs to the Section 2D and Carbon Nanomaterials)
Show Figures

Figure 1

Back to TopTop