Search Results (266)

Maritime transportation is the backbone of global trade, with ports acting as pivotal nodes for the efficient and resilient movement of goods in international supply chains. However, most existing studies lack a systematic and integrated framework for assessing port connectivity. To address this gap, this study develops an integrated Bayesian Network (BN) modeling approach that, for the first time, simultaneously incorporates international connectivity, port competitiveness, and hinterland connectivity within a unified probabilistic framework. Drawing on empirical data from 26 major coastal countries in Asia, the model quantifies the multi-layered and interdependent determinants of port connectivity. The results demonstrate that port competitiveness and hinterland connectivity are the dominant drivers, while the impact of international shipping links is comparatively limited in the current Asian context. Sensitivity analysis further highlights the critical roles of rail transport development and trade facilitation in enhancing port connectivity. The proposed BN framework supports comprehensive scenario analysis under uncertainty and offers targeted, practical policy recommendations for port authorities and regional planners. By systematically capturing the interactions among maritime, port, and inland factors, this study advances both the theoretical understanding and practical management of port connectivity. Full article

Two-dimensional (2D) hybrid organic–inorganic perovskites (HOIPs) have attracted considerable attention in optoelectronic applications, owing to their remarkable characteristics. Nevertheless, the application of 2D HOIPs encounters inherent challenges due to the presence of insulating organic spacers, which create barriers for efficient interlayer charge transport (CT). To tackle this issue, we propose a BA₂MAPb₂I₇/PEA₂MA₂Pb₃I₁₀ bilayer heterostructure, where efficient interlayer energy transfer (ET) facilitates compensation for the restricted charge transport across the organic spacer. Our findings reveal that under 532 nm light illumination, the BA₂MAPb₂I₇/PEA₂MA₂Pb₃I₁₀ heterostructure photodetector exhibits a significant photocurrent enhancement compared with that of the pure PEA₂MA₂Pb₃I₁₀ device, mainly due to the contribution of the ET process. In contrast, under 600 nm light illumination, where ET is absent, the enhancement is rather limited, emphasizing the critical role of ET in boosting device performance. The overlap of the PL emission peak of BA₂MAPb₂I₇ with the absorption spectra of PEA₂MA₂Pb₃I₁₀, alongside the PL quenching of BA₂MAPb₂I₇ and the enhanced emission of PEA₂MA₂Pb₃I₁₀ provide confirmation of the existence of ET in the BA₂MAPb₂I₇/PEA₂MA₂Pb₃I₁₀ heterostructure. Furthermore, the PL enhancement factor followed a 1/d² relationship with the thickness of the hBN layer, indicating that ET originates from 2D-to-2D dipole–dipole coupling. This study not only highlights the potential of leveraging ET mechanisms to overcome the limitations of interlayer CT, but also contributes to the fundamental understanding required for engineering advanced 2D HOIP optoelectronic systems. Full article

This study reported covalent organic frameworks (COFs) and their hybrid composites with two-dimensional materials, graphene oxide (GO), graphitic carbon nitride (g-C₃N₄), and boron nitride (BN), to examine their structural, textural, and gas adsorption properties. Material characterization confirmed the crystallinity of COF-1 and the preservation of framework integrity after integrating the 2D nanomaterials. FT-IR spectra exhibited pronounced vibrational fingerprints of imine linkages and validated the functional groups from the COF and the integrated nanomaterials. TEM images revealed the integration of the two components, porous, layered structures with indications of interfacial interactions between COF and 2D nanosheets. Nitrogen adsorption–desorption isotherms revealed the microporous characteristics of the COFs, with hysteresis loops evident, indicating the development of supplementary mesopores at the interface between COF-1 and the 2D materials. The BET surface area of pristine COF-1 was maximal at 437 m²/g, accompanied by significant micropore and Langmuir surface areas of 348 and 1290 m²/g, respectively, offering enhanced average pore widths and hierarchical porous strcuture. CO₂ adsorption tests were investigated showing maximum adsorption capacitiy of 1.47 mmol/g, for COF-1, closely followed by COF@BN at 1.40 mmol/g, underscoring the preserved sorption capabilities of these materials. These findings demonstrate the promise of designed COF-based hybrids for gas capture, separation, and environmental remediation applications. Full article

This paper proposes a mathematical description of nitriding atmospheres obtained from a one-component ammonia ingoing atmosphere and a two-component ammonia inlet nitrogen-diluted atmosphere. The Fe-N phase equilibrium diagrams of the nitriding atmosphere in the hydrogen content-temperature (Q-T) system for selected NH₃/N₂ atmosphere compositions are presented. The nitriding atmosphere obtained with different degrees of nitrogen dilution of the ingoing atmosphere was characterized. It has been shown that in processes carried out in nitriding atmospheres obtained from a two-component atmosphere with nitrogen, there is no direct relationship between the value of the nitrogen potential and the degree of dilution of the ingoing atmosphere with nitrogen. It has been shown analytically and confirmed experimentally that with changes in the degree of dilution of ammonia with nitrogen, the hydrogen content of the nitriding atmosphere and, consequently, the nitrogen availability of the nitriding atmosphere change. Using the example of nitriding AISI 52100 steel, it has been experimentally demonstrated that the change in nitrogen availability, caused by a change in the degree of dilution of the ingoing atmosphere with nitrogen, is not accompanied by a change in the value of the nitrogen potential. It has also been shown that the change in the nitrogen availability of the nitriding atmosphere, induced by the change in the composition of the aNH₃/bN₂ ingoing atmosphere, affects the kinetics of nitrogen mass gain in the nitrided layer and the distribution of nitrogen mass between the iron nitride layer and the solution zone. It has also been shown that with the change in nitrogen availability, what changes in addition to the thickness of the iron nitride layer is also the phase composition of the layer. Using gravimetric tests, the mass of nitrogen in the iron nitride layer and the solution zone has been determined. To describe the equilibrium between the NH₃/H₂ atmosphere and nitrogen in the different iron phases, a modified Lehrer diagram in the coordinate system of temperature and hydrogen content in the nitriding atmospheres (T-Q) has been proposed. Full article

The structural parameters and electronic structures of Sc- and Y-based nitride semiconductors that adopted hexagonal BN-like atomic sheets were investigated with calculations based on density functional theory (DFT). A hybrid exchange-correlation functional and spin–orbit coupling were employed for studies on the band structures. A strong variation in the band gap type, as well as the width, was revealed not only between the monolayer and bulk materials but also between the multilayer systems. An exceptionally wide range of band gaps from 1.39 (bulk) up to 3.59 eV (three layers) was obtained for two-dimensional materials based on ScN. This finding is related to two phenomena: significant contributions of subsurface ions into bands that formed a valence band maximum and pronounced shifts in conduction band positions with respect to the Fermi energy between the multilayer systems. The relatively low values of the work function (below 2.36 eV) predicted for the few-layer YN materials might be considered for applications in electron emission. In spite of the fact that the band gaps of two-dimensional materials predicted with hybrid DFT calculations may be overestimated to some extent, the electronic structure of homo- and heterostructures formed by rare earth nitride semiconductors seems to be an interesting subject for further experimental research. Full article

Batch normalization (BN) is crucial for achieving state-of-the-art binary neural networks (BNNs). Unlike full-precision neural networks, BNNs restrict activations to discrete values $\{-1,1\}$, which requires a renewed understanding and research of the role and significance of the BN layers in BNNs. Many studies notice this phenomenon and try to explain it. Inspired by these studies, we introduce the self-attention mechanism into BN and propose a novel Attention-Based Batch Normalization (ABN) for Binary Neural Networks. Also, we present an ablation study of parameter trade-offs in ABN, as well as an experimental analysis of the effect of ABN on BNNs. Experimental analyses show that our ABN method helps to capture image features, provide additional activation-like functions, and increase the imbalance of the activation distribution, and these features help to improve the performance of BNNs. Furthermore, we conduct image classification experiments over the CIFAR10, CIFAR100, and TinyImageNet datasets using BinaryNet and ResNet-18 network structures. The experimental results demonstrate that our ABN consistently outperforms the baseline BN across various benchmark datasets and models in terms of image classification accuracy. In addition, ABN exhibits less variance on the CIFAR datasets, which suggests that ABN can improve the stability and reliability of models. Full article

State evaluation of relay protection equipment constitutes a crucial component in ensuring the stable, secure, and symmetric operation of power systems. Current methodologies predominantly encompass fuzzy-rule-based control systems and data-driven machine learning approaches. The former relies on manual experience for designing fuzzy rules and membership functions and exhibits limitations in high-dimensional data integration and analysis. The latter predominantly formulates state evaluation as a classification task, which demonstrates its ineffectiveness in identifying equipment at boundary states and faces challenges in model parameter selection. To address these limitations, this paper proposes a quantitative state evaluation method for relay protection equipment based on a two-stage artificial protozoa optimizer (two-stage APO) optimized improved Conformer (two-stage APO-IConf) model. First, we modify the Conformer architecture by replacing pre-layer normalization (Pre-LN) in residual networks with post-batch normalization (post-BN) and introducing dynamic weighting coefficients to adaptively regulate the connection strengths between the first and second feed-forward network layers, thereby enhancing the capability of the model to fit relay protection state evaluation data. Subsequently, an improved APO algorithm with two-stage optimization is developed, integrating good point set initialization and elitism preservation strategies to achieve dynamic equilibrium between global exploration and local exploitation in the Conformer hyperparameter space. Experimental validation using operational data from a substation demonstrates that the proposed model achieves a RMSE of 0.5064 and a MAE of 0.2893, representing error reductions of 33.6% and 35.0% compared to the baseline Conformer, and 9.1% and 15.2% error reductions over the improved Conformer, respectively. This methodology can provide a quantitative state evaluation and guidance for developing maintenance strategies for substations. Full article

To improve the performance of superhard ceramic composites, this study aims to develop a dense, phase-pure, and uniform TiN coating on cubic boron nitride (cBN) particles with a target thickness of at least 150 nm. TiN coatings were applied using atomic layer deposition (ALD) alone, as well as a combined ALD/chemical vapor deposition (CVD) process. While ALD produced uniform and dense coatings, the thickness remained below 50 nm. The combined ALD/CVD approach achieved greater thicknesses up to 500 nm, though coating homogeneity remained a challenge. Optimization efforts, including increased ALD cycles and reduced CVD pressure, led to improved coating uniformity, with 25%–30% of particles coated to thicknesses ≥ 80 nm. Structural analysis confirmed dense, pore-free TiN_1−x layers for all synthesized powders. In contrast, the commercial reference powder showed a non-uniform, multiphase coating (α − Ti, Ti₂N, and TiN_0.53) with defects. While the ALD/CVD powders exhibited better phase purity than the commercial sample, further optimization is needed to achieve consistent coatings above 150 nm. These results suggest the ALD/CVD route is promising for producing coatings suitable for use in ceramic matrix composites. Full article

The development of Facial Expression Recognition (FER) technology has significantly enhanced the naturalness and intuitiveness of human-robot interaction. In the field of service robots, particularly in applications such as production assistance, caregiving, and daily service communication, efficient FER capabilities are crucial. However, existing Convolutional Neural Network (CNN) models still have limitations in terms of feature representation and recognition accuracy for facial expressions. To address these challenges, we propose CAGNet, a novel network that combines multiscale feature aggregation and attention mechanisms. CAGNet employs a deep learning-based hierarchical convolutional architecture, enhancing the extraction of features at multiple scales through stacked convolutional layers. The network integrates the Convolutional Block Attention Module (CBAM) and Global Average Pooling (GAP) modules to optimize the capture of both local and global features. Additionally, Batch Normalization (BN) layers and Dropout techniques are incorporated to improve model stability and generalization. CAGNet was evaluated on two standard datasets, FER2013 and CK+, and the experiment results demonstrate that the network achieves accuracies of 71.52% and 97.97%, respectively, in FER. These results not only validate the effectiveness and superiority of our approach but also provide a new technical solution for FER. Furthermore, CAGNet offers robust support for the intelligent upgrade of service robots. Full article

License plate recognition in sandstorm conditions faces challenges such as image blurriness, reduced contrast, and partial information loss, which result in significant limitations in the feature extraction and recognition accuracy of existing methods. To address these challenges, this study proposes a license plate recognition method based on an improved AlexNetBN network. By introducing Batch Normalization (BN) layers, the model achieves greater training stability and generalization in complex environments. A dedicated dataset tailored for license plate recognition in sandstorm conditions was constructed, and data augmentation techniques were used to simulate real-world scenarios for model training and testing. Experimental results demonstrate that, compared to the traditional AlexNet model, AlexNetBN achieves higher recognition accuracy and robustness in environments with frequent sandstorms and significant variations in lighting intensity. This study not only effectively enhances license plate recognition performance under sandstorm conditions but also offers new insights and references for applying CNN-based methods in low-visibility scenarios. Full article

Nuclear energy is a cornerstone of the global energy mix, delivering reliable, low-carbon power essential for sustainable energy systems. However, the safety of nuclear reactors is critical to maintaining operational reliability and public trust, particularly during accidents like a Loss of Coolant Accident (LOCA) or a Steam Line Break Inside Containment (SLBIC). This study introduces a Bayesian Network (BN) framework used to enhance nuclear energy safety by predicting accident severity and identifying key factors that ensure energy production stability. With the integration of simulation data and physical knowledge, the BN enables dynamic inference and remains robust under missing-data conditions—common in real-time energy monitoring. Its hierarchical structure organizes variables across layers, capturing initial conditions, intermediate dynamics, and system responses vital to energy safety management. Conditional Probability Tables (CPTs), trained via Maximum Likelihood Estimation, ensure accurate modeling of relationships. The model’s resilience to missing data, achieved through marginalization, sustains predictive reliability when critical energy system variables are unavailable. Achieving R² values of 0.98 and 0.96 for the LOCA and SLBIC, respectively, the BN demonstrates high accuracy, directly supporting safer nuclear energy production. Sensitivity analysis using mutual information pinpointed critical variables—such as high-pressure injection flow (WHPI) and pressurizer level (LVPZ)—that influence accident outcomes and energy system resilience. These findings offer actionable insights for the optimization of monitoring and intervention in nuclear power plants. This study positions Bayesian Networks as a robust tool for real-time energy safety assessment, advancing the reliability and sustainability of nuclear energy production. Full article

This study investigates the influence of hexagonal boron nitride (h-BN) particle size and concentration on the tribological performance of lithium and calcium greases. Formulations containing h-BN nanoparticles and microparticles at 1%, 3%, 5%, and 10% by weight were evaluated in ball-on-flat reciprocating tests under three load conditions. The tests were conducted using a steel ball and a steel plate. The most favorable results were obtained for greases with 3% h-BN, characterized by an average particle size of 130 nm and the highest nanoparticle content. In lithium grease, this formulation reduced friction by up to 9.7% and wear by up to 69.2% compared to the base grease. In calcium grease, the same additive concentration led to reductions of up to 18.2% in friction and 70.2% in wear. Tribological performance was significantly influenced by the type of base grease, which affected the dispersion of the additive and its ability to form protective surface layers. SEM/EDS analysis of the surfaces after testing revealed that the dominant lubrication mechanisms included shearing-sliding and surface-mending effects. This study confirms that h-BN—especially in nanoparticle form—is an effective additive for improving the performance of greases. Full article

The problem of the feature extraction and fusion classification of optical and SAR data remains challenging due to the differences in optical and synthetic aperture radar (SAR) imaging mechanisms. To this end, a statistical prediction interval-guided feature fusion network, SPIFFNet, is proposed for optical and SAR image classification. It consists of two modules, the feature propagation module (FPM) and the feature fusion module (FFM). Specifically, FPM imposes restrictions on the scale factor of the batch normalization (BN) layer by means of statistical prediction interval, and features exceeding the scale factor of the interval are considered redundant and are replaced by features from other modalities to improve the classification accuracy and enhance the information interaction. In the feature fusion stage, we combine channel attention (CA), spatial attention (SA), and multiscale squeeze enhanced axial attention (MSEA) to propose FFM to improve and fuse cross-modal features in a multiscale cross-learning manner. To counteract category imbalance, we also implement a weighted cross-entropy loss function. Extensive experiments on three optical–SAR datasets show that SPIFFNet exhibits excellent performance. Full article

Using convolutional neural networks (CNNs) to recognize forest fires in complex outdoor environments is a hot research direction in the field of intelligent forest fire recognition. Due to the storage-intensive and computing-intensive characteristics of CNN algorithms, it is difficult to implement them at edge terminals with limited memory and computing resources. This paper uses a FPGA (Field-Programmable Gate Array) to accelerate CNNs to realize forest fire recognition in the field environment and solves the problem of the difficulty in giving consideration to the accuracy and speed of a forest fire recognition network in the implementation of edge terminal equipment. First, a simple seven-layer lightweight network, LightFireNet, is designed. The network is compressed using a knowledge distillation method and the classical network ResNet50 is used as the teacher network to supervise the learning of LightFireNet so that its accuracy rate reaches 97.60%. Compared with ResNet50, the scale of LightFireNet is significantly reduced. Its model parameter amount is 24 K and its calculation amount is 9.11 M, which are 0.1% and 1.2% of ResNet50, respectively. Secondly, the hardware acceleration circuit of LightFireNet is designed and implemented based on the FPGA development board ZYNQ Z7-Lite 7020. In order to further compress the network and speed up the forest fire recognition circuit, the following three methods are used to optimize the circuit: (1) the network convolution layer adopts a depthwise separable convolution structure; (2) the BN (batch normalization) layer is fused with the upper layer (or full connection layer); (3) half float or ap_fixed<16,6>-type data is used to express feature data and model parameters. After the circuit function is realized, the LightFireNet terminal circuit is obtained through the circuit parallel optimization method of loop tiling, ping-pong operation, and multi-channel data transmission. Finally, it is verified on the test dataset that the accuracy of the forest fire recognition of the FPGA edge terminal of the LightFireNet model is 96.70%, the recognition speed is 64 ms per frame, and the power consumption is 2.23 W. The results show that this paper has realized a low-power-consumption, high-accuracy, and fast forest fire recognition terminal, which can thus be better applied to forest fire monitoring. Full article

Aiming at the model overfitting problem caused by limited datasets and visual complexity in succulent plant classification tasks, this study proposes a GoogLeNet classification method based on lightweighting and improving the Convolutional Block attention module (CBAM). Meanwhile, batch normalization (BN) operations are added after each convolutional layer to accelerate network convergence and improve model stability. In addition, the model’s ability to extract key features is enhanced by integrating the channel and spatial attention mechanisms of the CBAM attention module. Experimental results show that the improved lightweight GoogLeNet achieves 99.4% classification accuracy on the validation set, effectively mitigates the overfitting problem, and maintains high computational efficiency in resource-constrained environments. The model parameters and computational complexity are significantly reduced by streamlining the Inception modules from nine to seven and introducing depth-separable convolution. To further validate the model robustness, this study extends the dataset via data augmentation methods, and the experiments show that the improved model still maintains stable performance in small dataset environments, demonstrating its advantages in data-scarce scenarios. This study provides an effective solution for the task of succulent plant classification, which has significant application value. Future research will focus on further optimization of the model structure to continuously improve the classification accuracy and robustness. Full article