Search Results (69)

Automated waste classification is essential for improving recycling efficiency and supporting sustainable waste management systems. However, conventional convolutional neural network (CNN) approaches primarily focus on localized feature extraction, which may limit their ability to capture complex spatial relationships in heterogeneous waste materials. This study proposes DeepWasteSort-SI-SSO, a Vision Transformer (ViT)-based framework enhanced with a Self-Improved Sparrow Search Optimization (SI-SSO) strategy for hyperparameter tuning. The optimization process focuses on key training parameters, including learning rate, batch size, and dropout rate, to improve convergence stability and reduce the risk of suboptimal local minima. The framework was evaluated on a balanced four-class waste image dataset (paper, wood, food, and leaves; N = 4000) using a five-fold cross-validation protocol. Experimental results achieved an average accuracy of 95.5% (±0.007), a macro-averaged AUC-ROC of 0.975, and a Cohen’s Kappa coefficient of 0.938, indicating strong agreement between predicted and true labels. Comparative experiments against ResNet-50 and a baseline ViT configuration suggest that SI-SSO optimization improves performance stability with only a modest increase in computational cost. These findings highlight the potential of optimized Transformer-based approaches for automated waste image classification under controlled evaluation conditions. Full article

The integration of unmanned aerial vehicles (UAVs) and Federated Learning (FL) enables distributed model training while preserving data privacy. To overcome the challenges caused by centralized and synchronous model updates, we integrate Directed Acyclic Graph (DAG) blockchain-based FL into UAV networks. In this decentralized and asynchronous framework, UAVs can independently and autonomously participate in the FL process according to their own requirement. To achieve the high FL performance, it is essential for UAVs to actively contribute their computational and data resources to the FL process. However, it is challenging to ensure that UAVs consistently contribute their resources, as they may have a propensity to prioritize their own self-interest. Therefore, it is crucial to design effective incentive mechanisms that encourage UAVs to actively participate in the FL process and contribute their computational and data resources. Currently, research on effective incentive mechanisms for DAG blockchain-based FL framework in UAV networks remains limited. To address these challenges, this paper proposes a novel incentive mechanism that integrates both rewards and punishments to encourage UAVs to actively contribute to FL and to deter free riding under incomplete information. We formulate the interactions among UAVs as an evolutionary game, and the aspiration-driven rule is employed to imitate the UAV’s decision-making processes. We evaluate the proposed mechanism for UAVs within a DAG blockchain-based FL framework. Experimental results show that the proposed incentive mechanism substantially increases the average UAV contribution rate from $77.{04}_{\pm 0.84}\%$ (without incentive mechanism) to $97.{48}_{\pm 1.29}\%$. Furthermore, the higher contribution rate results in an approximate 2.23% improvement in FL performance. Additionally, we evaluate the impact of different parameter configurations to analyze how they affect the performance and efficiency of the FL system. Full article

Widely used in treating oil mist aerosols generated from metalworking processes, conventional gas–liquid coalescing filters face drawbacks such as increased energy consumption, performance limitations, and shortened service life due to high steady-state pressure drop. To address these issues, this study proposes an innovative design for a filter based on wettability-regulated gradient pore structure. Using glass fiber filter media with different pore size parameters as the substrate and incorporating an intermediate mesh layer, a three-layer filtration structure of “large-pore filtration layer—mesh layer—small-pore filtration layer” was constructed. The surface wettability of each layer was regulated by a self-developed surface modifier, producing gradient pore structure filters with different wettability configurations. The variations in key performance parameters, including steady-state pressure drop, filtration efficiency, saturation, and service life, were systematically evaluated for these configurations. Experimental results demonstrated that the configuration with an “oleophobic large-pore filtration layer—mesh layer—oleophilic small-pore filtration layer” yielded the best overall performance. Analysis based on the “jump-channel” model indicated that the gradient pore structure achieves progressive droplet filtration and optimizes droplet coalescence and capture through wettability differences. Consequently, while maintaining exceptional filtration efficiency (>99%), this configuration significantly reduces the steady-state pressure drop by over 34% and effectively extends the service life by more than 66%. This wettability-regulated gradient pore structure provides a novel technical pathway for addressing the challenges of balancing pressure drop and filtration efficiency, as well as extending the service life, in gas–liquid coalescing filters. Full article

The topological structure of fracture networks fundamentally controls the mechanical behavior and fluid-driven failure of brittle materials. However, a systematic understanding of how topology dictates hydraulic fracture propagation remains limited. This study conducted experimental investigations on granite specimens containing 10 different topological fracture structures using a self-developed visual hydraulic fracturing test system and an improved Digital Image Correlation (DIC) method. It systematically revealed the macroscopic control laws of topological nodes on crack initiation, propagation path, and peak pressure. The experimental results indicate that hydraulic crack initiation follows the “proximal-to-loading-end priority” rule. Macroscopically, the breakdown pressure shows a significant negative correlation with topological parameters (number of nodes, number of branches, normalized total fracture length). However, specific configurations (e.g., X-shaped nodes) can exhibit a configuration-strengthening effect due to dispersed stress concentration, leading to a higher breakdown pressure than simpler topological configurations. Discrete Element Method (DEM) simulations revealed the underlying mechanical essence at the meso-scale: the topological structure governs crack initiation behavior and initiation pressure by regulating the distribution of force chains and the mode of stress concentration within the rock mass. These findings advance the fundamental understanding of fracture–topology–property relationships in rock masses and provide insights for optimizing fluid-driven fracturing processes in engineered materials and reservoirs. Full article

This systematic review examined the use of building-integrated photovoltaics (BIPVs) in high-rise buildings, focusing on early-stage design strategies to enhance energy performance. With limited rooftop space in tall buildings, façades offer a promising alternative for solar energy generation. Using the PRISMA framework, 41 articles were synthesized to identify key parameters influencing the effectiveness of BIPV systems. This included environmental and urban contexts, building form and orientation, façade configuration, and typology-specific characteristics for residential, office, and mixed-use buildings. The findings highlight the importance of integrating BIPV from the earliest stages of the design process. Local climate and latitude guide optimal façade orientation and form, while module efficiency can be improved with ventilation, air gaps, and appropriate spacing. Urban density, site placement, and shading patterns also significantly affect overall energy output. Podiums and multifaceted building forms enhance solar exposure and reduce self-shading, while building height, orientation, and spacing further influence BIPV potential. Different building types require tailored strategies to balance energy generation, daylight, and architectural quality. Finally, the review identified research gaps and proposed future directions to support architects, designers, and urban planners in effectively incorporating photovoltaic systems into high-rise building design. Full article

As a process fluid in oil reservoirs, carbon dioxide plays a dominant role in enhanced oil recovery by increasing volume and decreasing interfacial tension. To study the volume expansion behavior of a CO₂–oil system under reservoir conditions, ten hydrocarbon components with carbon numbers ranging from 8 to 26 were selected to represent crude oil. Systems of CO₂ with normal alkanes, cycloalkanes, and aromatic hydrocarbons were measured using a self-assembled high-pressure visible cell, with a temperature range of 313.15 K to 353.15 K and a pressure up to 25 MPa. Experimental results demonstrate that pressure and temperature significantly influence the relative volumetric expansion behavior. The expansion rate exhibits a positive correlation with pressure, whereas it shows a negative correlation with temperature. Among different molecular configurations, normal alkanes exhibit the most pronounced swelling effect. This study establishes that the volumetric expansion behavior of crude oil under CO₂ exposure is predominantly governed by n-alkane components with carbon numbers less than 16. In the heavy hydrocarbon (carbon number > 16) and CO₂ system, the influence of hydrocarbon structure and carbon number on the expansion extent is considerably reduced. This paper delivers critical theoretical foundations for elucidating the microscopic interaction mechanisms in CO₂ enhanced oil recovery and optimizing injection parameter strategies. Full article

In maritime blurred image recognition, ship collision accidents frequently result from three primary blur types: (1) motion blur from vessel movement in complex sea conditions, (2) defocus blur due to water vapor refraction, and (3) scattering blur caused by sea fog interference. This paper proposes a dual-branch recognition method specifically designed for motion blur, which represents the most prevalent blur type in maritime scenarios. Conventional approaches exhibit constrained computational efficiency and limited adaptability across different modalities. To overcome these limitations, we propose a hybrid CNN–Transformer architecture: the CNN branch captures local blur characteristics, while the enhanced Transformer module models long-range dependencies via attention mechanisms. The CNN branch employs a lightweight ResNet variant, in which conventional residual blocks are substituted with Multi-Scale Gradient-Aware Residual Block (MSG-ARB). This architecture employs learnable gradient convolution for explicit local gradient feature extraction and utilizes gradient content gating to strengthen blur-sensitive region representation, significantly improving computational efficiency compared to conventional CNNs. The Transformer branch incorporates a Hierarchical Swin Transformer (HST) framework with Shifted Window-based Multi-head Self-Attention for global context modeling. The proposed method incorporates blur invariant Positional Encoding (PE) to enhance blur spectrum modeling capability, while employing DyT (Dynamic Tanh) module with learnable α parameters to replace traditional normalization layers. This architecture achieves a significant reduction in computational costs while preserving feature representation quality. Moreover, it efficiently computes long-range image dependencies using a compact 16 × 16 window configuration. The proposed feature fusion module synergistically integrates CNN-based local feature extraction with Transformer-enabled global representation learning, achieving comprehensive feature modeling across different scales. To evaluate the model’s performance and generalization ability, we conducted comprehensive experiments on four benchmark datasets: VAIS, GoPro, Mini-ImageNet, and Open Images V4. Experimental results show that our method achieves superior classification accuracy compared to state-of-the-art approaches, while simultaneously enhancing inference speed and reducing GPU memory consumption. Ablation studies confirm that the DyT module effectively suppresses outliers and improves computational efficiency, particularly when processing low-quality input data. Full article

By embedding optical fiber sensors into fiber preforms and utilizing liquid molding processes such as resin transfer molding (RTM), intelligent composite materials with self-sensing capabilities can be fabricated. In the liquid molding process of these intelligent composites, the quality of the final product is highly dependent on the resin flow and impregnation effects. The embedding of optical fibers can affect the microscopic flow and impregnation behavior of the resin; therefore, it is necessary to investigate the specific impact of optical fiber embedding on the resin flow and impregnation of fiber bundles. Due to the difficulty of directly observing this process at the microscopic scale through experiments, numerical simulation has become a key method for studying this issue. This paper focuses on the resin micro-flow in RTM processes for intelligent composites with embedded optical fibers. Firstly, a steady-state analysis of the resin flow and impregnation process was conducted using COMSOL 6.0 obtaining the velocity and pressure field distribution characteristics under different optical fiber embedding conditions. Secondly, the dynamic process of resin flow and impregnation of fiber bundles at the microscopic scale was simulated using Fluent 2022R2. This study comprehensively analyzes the impact of different optical fiber embedding configurations on resin flow and impregnation characteristics, determining the impregnation time and porosity after impregnation under different optical fiber embedding scenarios. Additionally, this study reveals the mechanisms of pore formation and their distribution patterns. The research findings provide important theoretical guidance for optimizing the RTM molding process parameters for intelligent composite materials. Full article

The Online Droplet Inspection system plays a vital role in closed-loop control for OLED inkjet printing. However, generating realistic synthetic droplet images for reliable restoration and precise measurement of droplet parameters remains challenging due to the complex, multi-factor degradation inherent to microscale droplet imaging. To address this, we propose a physics-informed degradation model, Diffraction–Gaussian–Motion–Noise (DGMN), that integrates Fraunhofer diffraction, defocus blur, motion blur, and adaptive noise to replicate real-world degradation in droplet images. To optimize the multi-parameter configuration of DGMN, we introduce the MISABO (Multi-strategy Improved Subtraction-Average-Based Optimizer), which incorporates Sobol sequence initialization for search diversity, lens opposition-based learning (LensOBL) for enhanced accuracy, and dimension learning-based hunting (DLH) for balanced global–local optimization. Benchmark function evaluations demonstrate that MISABO achieves superior convergence speed and accuracy. When applied to generate synthetic droplet images based on real droplet images captured from a self-developed OLED inkjet printer, the proposed MISABO-optimized DGMN framework significantly improves realism, enhancing synthesis quality by 37.7% over traditional manually configured models. This work lays a solid foundation for generating high-quality synthetic data to support droplet image restoration and downstream inkjet printing processes. Full article

In this study, a novel shape memory alloy actuated bearing active preload system (SMA-BAPS) was proposed and experimentally demonstrated. SMA actuators placed in a single or antagonistic configuration were employed to drive the screw pair and thus fulfill one-way or bidirectional preload adjustment. Moreover, the self-locking screw pair was used to maintain the bearing preload without external energy input. To determine the parameters of screw pair and SMA actuators, a detailed design process was conducted based on analytical models of the proposed system. Finally, a screw pair with a lead of 3 mm and SMA actuators with a diameter of 0.5 mm and a length of 130 mm were adopted. Prototype tests were conducted to validate and evaluate the performance of the preload adjustment with the SMA-BAPS. The resistive torque and the natural frequency of spindles were recorded to represent the preload level of the bearing. Through the performance tests, the SMA-BAPS induced a maximum 47% variation in the resistive torque and a 20% variation in the spindle’s natural frequency. The response time of the SMA-BAPS was less than 5 s when the heating current of 5 A was applied on the SMA actuator. This design highlighted the compact size, quick response, as well as the bidirectional preload adjustment, representing its potential use in aerospace mechanisms and advanced motors. Full article

To address the issue of surface glazing that occurs during prolonged polishing with gel tools, this study employs a triethanolamine (TEA)-based polishing fluid system to enhance the self-sharpening capability of the gel polishing disc. The inhibitory mechanism of TEA concentration on disc glazing is systematically analyzed, along with its impact on the gel disc’s frictional wear behaviour. Furthermore, the synergistic effects of process parameters on both surface quality and material removal rate (MRR) of SiC are examined. The results demonstrate that TEA concentration is a critical factor in regulating polishing performance. At an optimal concentration of 4 wt%, an ideal balance between chemical chelation and mechanical wear is achieved, effectively preventing glazing while avoiding excessive tool wear, thereby ensuring sustained self-sharpening capability and process stability. Through orthogonal experiment optimization, the best parameter combination for SiC polishing is determined: 4 wt% TEA concentration, 98 N polishing pressure, and 90 rpm rotational speed. This configuration delivers both superior surface quality and desirable MRR. Experimental data confirm that TEA significantly enhances the self-sharpening performance of gel discs through its unique complex reaction. During the rough polishing stage, the MRR increases by 34.9% to 0.85 μm/h, while the surface roughness S_a is reduced by 51.3% to 6.29 nm. After subsequent CMP fine polishing, an ultra-smooth surface with a final roughness of 2.33 nm is achieved. Full article

With the rapid advancement of urbanization in China, the demand for community-based elderly care facilities (CECFs) has been increasing. One pressing challenge is the question of how to provide CECFs that not only meet the health needs of the elderly but also make efficient use of limited urban land resources. This study addresses this issue by adopting an integrated multi-method research framework that combines multi-objective optimization (MOO) algorithms, Spearman rank correlation analysis, ensemble learning methods (Random Forest combined with SHapley Additive exPlanations (SHAP), where SHAP enhances the interpretability of ensemble models), and Self-Organizing Map (SOM) neural networks. This framework is employed to identify optimal building configurations and to examine how different architectural parameters influence key daylight performance indicators—Useful Daylight Illuminance (UDI) and Daylight Factor (DF). Results indicate that when UDI and DF meet the comfort thresholds for elderly users, the minimum building area can be controlled to as little as 351 m² and can achieve a balance between natural lighting and spatial efficiency. This ensures sufficient indoor daylight while mitigating excessive glare that could impair elderly vision. Significant correlations are observed between spatial form and daylight performance, with factors such as window-to-wall ratio (WWR) and wall thickness (WT) playing crucial roles. Specifically, wall thickness affects indoor daylight distribution by altering window depth and shading. Moreover, the ensemble learning models combined with SHAP analysis uncover nonlinear relationships between various architectural parameters and daylight performance. In addition, a decision support method based on SOM is proposed to replace the subjective decision-making process commonly found in traditional optimization frameworks. This method enables the visualization of a large Pareto solution set in a two-dimensional space, facilitating more informed and rational design decisions. Finally, the findings are translated into a set of practical design strategies for application in real-world projects. Full article

This paper investigates sustainable decision systems within green E-business models by analyzing how different O2O (online-to-offline) fulfillment structures affect emission-reduction efforts and pricing strategies in a two-tier supply chain consisting of a manufacturer and a new retailer. Three practical sales formats—package self-pickup, nearby delivery, and hybrid—are modeled using Stackelberg game frameworks that incorporate key factors such as inconvenience cost, logistics cost, processing fees, and emission-reduction coefficients. Results show that the manufacturer’s emission-reduction decisions and both parties’ pricing strategies are highly sensitive to cost conditions and consumer preferences. Specifically, higher inconvenience and abatement costs consistently reduce profitability and emission efforts; the hybrid model exhibits threshold-dependent advantages over single-mode strategies in terms of carbon efficiency and economic returns; and consumer green preference and distance sensitivity jointly shape optimal channel configurations. Robustness analysis confirms the model’s stability under varying parameter conditions. These insights provide theoretical and practical guidance for firms seeking to develop adaptive, low-carbon fulfillment strategies that align with sustainability goals and market demands. Full article

Unmanned ships, equipped with self-navigation and image processing capabilities, are progressively expanding their applications in fields such as mining, fisheries, and marine environments. Along with this development, issues concerning waterborne traffic safety are gradually emerging. To address the challenges of navigation and obstacle detection on the water’s surface, this paper presents CDS-YOLOv7, an enhanced obstacle-detection framework for aquatic environments, architecturally evolved from YOLOv7. The proposed system implements three key innovations: (1) Architectural optimization through replacement of the Spatial Pyramid Pooling Cross Stage Partial Connections (SPPCSPC) module with GhostSPPCSPC for expanded receptive field representation. (2) Integration of a parameter-free attention mechanism (SimAM) with refined pooling configurations to boost multi-scale detection sensitivity, and (3) Strategic deployment of depthwise separable convolutions (DSC) to reduce computational complexity while maintaining detection fidelity. Furthermore, we develop a Spatial–Channel Synergetic Attention (SCSA) mechanism to counteract feature degradation in convolutional operations, embedding this module within the Extended Effective Long-Range Aggregation Network (E-ELAN) network to enhance contextual awareness. Experimental results reveal the model’s superiority over baseline YOLOv7, achieving 4.9% mean average precision@0.5 (mAP@0.5), +4.3% precision (P), and +6.9% recall (R) alongside a 22.8% reduction in Giga Floating-point Operations Per Second (GFLOPS). Full article

Speaker verification (SV) is an exceptionally effective method of biometric authentication. However, its performance is heavily influenced by the effectiveness of the extracted speaker features and their suitability for use in resource-limited environments. Transformer models and convolutional neural networks (CNNs), leveraging self-attention mechanisms, have demonstrated state-of-the-art performance in most Natural Language Processing (NLP) and Image Recognition tasks. However, previous studies indicate that standalone Transformer and CNN architectures present distinct challenges in speaker verification. Specifically, while Transformer models deliver good results, they fail to meet the requirements of low-resource scenarios and computational efficiency. On the other hand, CNNs perform well in resource-constrained environments but suffer from significantly reduced recognition accuracy. Several existing approaches, such as Conformer, combine Transformers and CNNs but still face challenges related to high resource consumption and low computational efficiency. To address these issues, we propose a novel solution that enhances the Transformer model by introducing multi-scale convolutional attention and a Global Response Normalization (GRN)-based feed-forward network, resulting in a lightweight backbone architecture called the lightweight simple transformer (LST). We further improve LST by incorporating the Res2Net structure from CNN, yielding the Res2Former model—a low-parameter, high—precision SV model. In Res2Former, we design and implement a time-frequency adaptive feature fusion(TAFF) mechanism that enables fine-grained feature propagation by fusing features at different depths at the frame level. Additionally, holistic fusion is employed for global feature propagation across the model. To enhance performance, multiple convergence methods are introduced, improving the overall efficacy of the SV system. Experimental results on the VoxCeleb1-O, VoxCeleb1-E, VoxCeleb1-H, and Cn-Celeb(E) datasets demonstrate that Res2Former achieves excellent performance, with the Large configuration attaining Equal Error Rate (EER)/Minimum Detection Cost Function (minDCF) scores of 0.81%/0.08, 0.98%/0.11, 1.81%/0.17, and 8.39%/0.46, respectively. Notably, the Base configuration of Res2Former, with only 1.73M parameters, also delivers competitive results. Full article