Search Results (43,271)

To solve the problem of limited generalization ability that is widely existing in lightweight models used for leaf disease detection, this paper puts forward a lightweight detection model named CE-Fusion Botanic, which is based on the adaptive control of local–global information fusion. Therefore, this model includes a globally guided dynamic gating fusion mechanism that dynamically adjusts fusion weights between local features, such as spot lesions, and global semantic features, such as symptoms of systemic infection, thus realizing adaptive perception of the dual characteristics of plant diseases. Hence, the local information extraction branch combines an improved MobileNetV3-Small structure and a CBAM attention mechanism, while the global information extraction branch uses a lightweight Vision Transformer (ViT) design called EffiViT. Comprehensive contrast experiments were carried out by using seven mainstream lightweight models on the PlantVillage tomato disease subset, the full-category PlantVillage leaf disease dataset, and the Grapevine leaf disease dataset. Models were divided into large-scale, medium-scale, and small-scale groups according to the number of parameters. The results show that CE-Fusion Botanic is significantly better than comparative methods in both detection accuracy and generalization performance, and at the same time, it keeps a lightweight profile, which demonstrates superior cross-dataset adaptation capabilities. Full article

In view of the complex seabed response and pipeline force characteristics induced by wave loading and long-term cross-shore profile evolution on shoreward submarine pipelines, this study investigates the coupled effects of profile evolution, burial depth, and pipeline angle on the surrounding seabed and resulting wave-induced forces. Physical model experiments were conducted in a wave flume under irregular wave conditions. A controlled variable design was adopted, dividing the experiments into five main groups and 17 subgroups based on the pipeline angle, initial burial depth, and seabed topography at different evolution stages. Pore pressure around the pipeline and wave height were measured synchronously, and seabed topography was scanned using a laser system. The results show that increasing the initial burial depth reduces both pore pressure and forces on the pipeline. Under cross-shore profile evolution, pore pressure and forces in sedimentation zones are lower and decrease further with continued evolution, whereas the opposite trend is observed in erosion zones. Changes in pipeline angle induce an asymmetric pore pressure distribution around the pipeline, with the resultant force first decreasing and then increasing. The direction of the resultant force shows greater rotation amplitude in sedimentation zones while, in erosion zones, the direction remains more concentrated. In sedimentation zones, pore pressure decreases and force changes are relatively gradual; in erosion zones, pore pressure increases and force changes are more pronounced. Overall, the variations in force direction and magnitude exhibit distinct characteristics depending on the zone type. These findings provide a scientific basis for the rational design of shoreward pipelines, enabling stability and safety optimization through integration with cross-shore profile evolution patterns, reducing engineering risks, and enhancing the economic viability and reliability of nearshore pipeline projects. Full article

Low-salinity water flooding (LSWF) has been widely investigated as an enhanced oil recovery (EOR) method for carbonate reservoirs; however, the relative contributions of wettability alteration and oil–brine interfacial tension (IFT) reduction remain poorly understood, particularly under strongly oil-wet conditions. This study systematically investigates the physicochemical mechanisms governing oil recovery during hybrid LSWF–surfactant flooding in oil-wet carbonate systems. Oil-wet Indiana limestone cores were used as representative carbonate reservoir rocks. Seawater and its diluted analogs were employed as base brines and combined with anionic and cationic surfactants at varying concentrations. Zeta potential and pH measurements were conducted to characterize electrostatic interactions at the rock–brine and oil–brine interfaces, while dynamic contact angle and pendant-drop IFT measurements were used to quantify wettability evolution and fluid–fluid interactions. Core flooding experiments were subsequently performed to link interfacial phenomena to macroscopic oil recovery behavior. The results demonstrate that brine dilution induces more negative surface charges at both interfaces, promoting double-layer expansion and electrostatic repulsion, which stabilizes the aqueous film and drives wettability alteration toward a water-wet state. The addition of anionic surfactants further amplifies this effect by increasing surface charge negativity, whereas cationic surfactants preferentially adsorb onto the negatively charged rock surface, limiting wettability alteration despite producing greater IFT reduction. Sulfate ions enhance wettability alteration by facilitating divalent cation interactions with adsorbed oil components; however, excessive sulfate concentrations lead to precipitation-induced flow impairment. Core flooding results reveal that diluted seawater combined with an anionic surfactant yields the highest incremental oil recovery. Our findings conclusively demonstrate that wettability alteration—rather than IFT reduction—is the more dominant recovery mechanism in oil-wet carbonate reservoirs under the investigated conditions. These results provide mechanistic guidance for optimized brine and surfactant design in hybrid LSWF–chemical EOR applications. Full article

Low-light image enhancement (LLIE) remains challenging due to severe degradation of high-frequency structures and semantic ambiguity under extreme darkness. Although existing methods achieve satisfactory brightness recovery, they often suffer from structural inconsistency and semantic drift, as diverse scenes are typically processed with uniform enhancement strategies or static text prompts. To address these issues, we propose a Multi-Modal Structural and Semantic-Adaptive Network (MSSA-Net) under a structure-anchored paradigm. First, we design a Multi-Scale Self-Refinement Block (MSRB) to enhance degraded visible representations through multi-scale feature extraction and progressive refinement. Meanwhile, a pseudo-infrared structural prior derived from the input image is introduced to provide noise-insensitive geometric cues. These cues are extracted via a Structure-Guided Cross-Attention (SGCA) module to produce structure-dominant features. The refined visible features and structural features are then adaptively integrated through an adaptive residual fusion (ARF) module to achieve balanced restoration. Furthermore, we develop a Large Multi-modal Model (LMM)-Driven Scene-Adaptive Attention mechanism that generates instance-aware scene tags from a coarse preview and injects semantic embeddings into visual features. Extensive experiments demonstrate that MSSA-Net improves structural fidelity, brightness recovery, and semantic naturalness across multiple benchmarks. Full article

Accurate crop classification is critical for optimizing agricultural resource use and informing production decisions. Deep learning, with its robust feature extraction ability, has become a prevalent technique for remote sensing-based crop classification. However, agricultural landscape complexity poses three key challenges: background noise interference, class confusion from inter-crop spectral similarity, and blurred small-area crop boundaries due to class imbalance. This paper proposes FCR-TransUNet, a TransUNet-based enhanced model integrating three modules: Feature Enhancement Module (FEM) for noise filtering, Class-Attention (CAExperimental results on the Youyi Farm and barley datasets validate the superiority of the proposed model. On the Youyi Farm dataset, FCR-TransUNet achieves an MIoU of 92.2%, representing an improvement of 1.8% over SAM2-UNet and 2.9% over the baseline TransUNet. On the barley dataset, it yields an MIoU of 89.9%. Ablation studies further verify the effectiveness of each designed module. To comprehensively evaluate the classification performance of FCR-TransUNet across the full crop growth cycle, experiments were conducted using remote sensing images from May, July, and August, respectively. The results demonstrate that FCR-TransUNet exhibits strong stability and adaptability at different crop growth stages, providing a reliable solution for precision agriculture and intelligent agricultural production. Full article

The automatic reading recognition of digital instruments is crucial for achieving metering automation and intelligent inspection. However, in non-standardized industrial environments, the masking effect caused by the coupling of non-uniform low-light conditions and the reflective surfaces of instrument panels severely degrades the displayed information, significantly limiting the recognition performance. Conventional image processing methods, while aiming to restore the imaging quality of instrument panels through low-light enhancement, inevitably introduce overexposure and indiscriminately amplify background noise during this process. To address the two key challenges of illumination recovery and noise suppression in the process of restoring panel image quality under non-uniform low-light conditions, this paper proposes a coarse-to-fine cascaded perception framework (CFCP). First, a lightweight YOLOv10 detector is employed to coarsely localize the meter reading region under non-uniform illumination conditions. Second, an Adaptive Illumination Correction Module (AICM) is designed to decouple and correct the illumination component at the pixel level, effectively restoring details in dark areas. Then, an Illumination-invariant Feature Perception Module (IFPM) is embedded at the feature level to dynamically perceive illumination-invariant features and filter out noise interference. Finally, the refined detection results are fed into a lightweight sequence recognition network to obtain the final meter readings. Experiments on a self-built industrial digital instrument dataset show that the proposed method achieves 93.2% recognition accuracy, with 17.1 ms latency and only 7.9 M parameters. Full article

Compared to traditional offline collaboration, current online collaboration often lacks nonverbal social cues, resulting in lower efficiency and a reduced emotional connection between teammates. To address this issue, this study used a two-player collaborative puzzle game as the experimental setting to explore the impact of two nonverbal social cues, emotion and gaze, on collaborative experience and performance. Specifically, this study designed four collaborative modes: with and without teammates’ facial expressions, and with and without teammates’ gaze points. Sixty-two participants took part in the experiment, and each pair was required to complete these four patterns. Subsequently, we analyzed their collaborative experience through subjective questionnaires, objective facial expressions, and gaze overlap rates. The experimental results revealed that teammates’ gaze could effectively enhance collaborative efficiency, while facial expression is key to optimizing subjective experience. Combining both cues further acquires advantages in cognitive and emotional dimensions, leading to improved performance outcomes. The study also indicated that facial expressions could alleviate the social pressure triggered by shared gaze from teammates. Additionally, the study also examined how personality differences influenced collaborative experiences and performance. The results indicated that individuals with high agreeableness actively seek social cues, leading to more positive collaborative experiences. This study provides empirical evidence for understanding the interactive mechanisms of cognitive and emotional processes during online collaboration, and points the way toward designing adaptive, personalized intelligent collaborative systems. Full article

A methodology was developed to evaluate the behavior of reinforced concrete slabs used in temporary traffic bridge systems installed over uncured cement concrete pavement sections using highly scaled-down experimental reinforced concrete slabs. A full-scale reinforced concrete slab was first designed and its behavior, such as strain and deflection, was numerically analyzed. A small-scale reinforced concrete slab was then designed considering a dimensional reduction ratio of 1/6. When using this reduction ratio, there is no actual reduced size steel bar, so the smallest size steel bar available must be used for placement. Therefore, numerical analyses were performed to design the steel bar arrangement of the small-scale slab so that the same behavior as that of the full-scale slab occurred. To conduct experiments, small-scale experimental slabs were fabricated according to the design. Since the size of coarse aggregates must be reduced in concrete used for small-scale slabs, specimens using the concrete mix design for full-scale slabs were also produced and the compressive strengths were compared to confirm that the strengths were the same. Next, a study was conducted on the selection of strain gauges that can be used in small-scale slab experiments, and a method for installing displacement gauges to accurately measure slab deflection was also designed. Based on this series of basic studies, load tests were performed to measure the strains and deflections of small-scale slabs. Comparing the measured behavior of the small-scale slab with the numerical analysis results, it was confirmed that the same behavior was observed. Therefore, the experimental results and numerical analysis results of the small-scale slab were consistent, and the numerical analysis results of the small-scale slab and the full-scale slab were identical, proving that the experimental results of the full-scale slab can be inferred through experiments using the small-scale slab. This study confirmed that if small-scale slabs are designed and manufactured to appropriately reflect the characteristics of full-scale slabs, even though the process is challenging, the behavior of full-scale slabs can be approximately determined through experiments using small-scale slabs. Full article

Modern deep convolutional neural networks achieve remarkable performance but require substantial computational resources due to their large parameter counts, limiting their suitability for resource-constrained environments. We propose Tiny Recursive ResNet-50, a parameter-efficient architecture that reduces model complexity through recursive feature refinement with weight sharing across reasoning cycles. The proposed design combines lightweight bottleneck blocks, iterative latent state accumulation, and deep supervision to enhance representation quality without increasing parameter count. Extensive experiments are conducted on melanoma classification using the HAM10000 dataset as the primary training and evaluation benchmark. Results demonstrate that the proposed recursive architecture maintains competitive accuracy while reducing parameters by approximately 49%, confirming its efficiency under constrained settings. To assess robustness under limited data and acquisition variability, we additionally validate on the PH2 dataset (200 images). Due to the small dataset size and class imbalance, evaluation is performed using 5-fold stratified cross-validation, and performance metrics are reported as mean ± standard deviation. This validation confirms that recursive refinement with moderate cycle depth improves stability and generalization in small-data regimes. Full article

Potato is one of the most important food crops worldwide, playing a critical role in global food security and agricultural production. The broken and impurity rates are important indicators for evaluating the harvesting quality of potato combine harvesting operations. To address the difficulty of achieving continuous and online detection using traditional methods, this study investigates an online monitoring approach for potato combine harvesting based on machine vision. Considering the characteristics of large material volume, severe overlap, and similar appearance features under field operating conditions, an online monitoring device suitable for potato combine harvesters was designed, along with a corresponding image acquisition and processing workflow. For the online monitoring device, an improved You Only Look Once version 11 (YOLOv11) detection model, was proposed to meet the requirements of multi-object detection in complex operating scenarios. The model incorporates Multi-Scale Depthwise Convolution (MSDConv), C2PSA_DCA (with Directional Context Attention, DCA), and Directional Selective Attention (DSA) modules, and introduces the Efficient Intersection over Union (EIoU) loss function to enhance recognition capability for broken potatoes and multiple types of impurity targets. While maintaining lightweight characteristics, the improved model demonstrates favorable detection accuracy. Field experiment results show that when the combine harvester operates at a forward speed of 3 km/h, the relative errors for broken and impurity rates are measured as 3.78% and 3.67%, respectively. Under extreme operating conditions with a speed of 4 km/h, the corresponding average relative errors rise to 8.30% and 8.72%, respectively. Overall, the online detection results exhibit satisfactory consistency with manual measurements, providing effective technical support for real-time monitoring of harvesting quality in potato combine harvesting operations. Future research will focus on expanding multi-scenario datasets under diverse soil and illumination conditions, as well as integrating detection results with adaptive control strategies to further enhance intelligent harvesting performance. Full article

Remote sensing object detection is severely hindered by background clutter and uneven object spatial distribution, limiting the performance of traditional algorithms and the original RT-DETR. To address these issues, this paper proposes an improved RT-DETR-based algorithm, CB-DETR. First, a symmetry-guided Density-Adaptive Attention (DAA) module is designed to tackle insufficient intra-scale feature interaction and poor adaptability to uneven density regions in RT-DETR. Centered on a density estimation network, it predicts target density, generates normalized weights via temperature scaling and softmax, and dynamically adjusts receptive fields through a multi-branch structure to symmetrically adapt to high- and low-density regions, outperforming RT-DETR’s fixed receptive field design. Second, a cross-attention-fused Posterior Dynamic Query Decoder (PDQD) is constructed to overcome fixed query interaction and weak small/occluded object detection in the original decoder. A dynamic query update mechanism optimizes vectors via multi-round iterations, breaking fixed-layer limitations and mining detailed features in complex scenarios, thus improving small/occluded target detection accuracy. Comparative experiments on RSOD, DIOR, and DOTA datasets show that CB-DETR outperforms the original RT-DETR comprehensively: ${\mathrm{mAP}}_{50}$/${\mathrm{mAP}}_{50:95}$ improve by 2.8%/2.1% and Precision (P)/Recall (R) by 4%/2.4% on RSOD; ${\mathrm{mAP}}_{50}$ improves by 1.3% on DIOR and 3% on DOTA. All core metrics surpass the original model and mainstream improved algorithms, verifying the effectiveness and innovation of the proposed improvements. Full article

Volatile organic compounds (VOCs, dominated by xylene, toluene, and benzene) and paint mist emissions from ship painting represent a major environmental and health concern, posing a critical bottleneck to the green transformation of the shipbuilding industry. To tackle this challenge, this study presents an integrated recovery system designed specifically for ship automatic-spraying robots. Guided by the synergistic principle of “air-curtain containment, multi-stage adsorption, and negative-pressure recovery,” the system features a modular design that ensures full compatibility with the robots’ spraying trajectory without operational interference. Core adsorption materials, namely glass fiber filter cotton and honeycomb activated carbon fiber, were selected to suit the high-humidity and high-pollutant-concentration environment typical of ship painting. An appropriately matched axial flow fan maintains stable negative pressure throughout the system. Furthermore, the design integrates an air curtain isolation subsystem and an automated control subsystem, enabling coordinated operation and real-time adjustment. Using ANSYS Fluent, geometric and flow field simulation models were established to analyze airflow distribution and pollutant adsorption behavior, which led to the optimization of key structural and material parameters. Field experiments conducted in shipyard environments demonstrated the system’s superior performance: it achieved a VOC removal efficiency of 88.4% and a paint mist capture efficiency of 85.7% under optimal working conditions, with a maximum simulated paint mist capture efficiency of 86.2%. The system maintained stable performance under complex vertical and overhead spraying conditions, with an efficiency attenuation of less than 1.5%, and its outlet emissions fully complied with the mandatory limits specified in the Emission Standard of Air Pollutants for the Shipbuilding Industry (GB 30981.2-2025). The relative error between experimental data and simulation results is less than 2%, confirming the reliability and practicality of the proposed system. This research provides an efficient and adaptable pollution control solution for green shipbuilding and offers valuable technical insights for the sustainable upgrading of automated painting processes in heavy industries. Full article

Underwater images often suffer from color distortion and low contrast, severely limiting the reliability of visual perception systems. Existing methods struggle to balance enhancement quality and computational efficiency. To address this issue, we propose PCF-Net (Perception-driven Color Fusion Network), a lightweight dual-branch network for underwater image enhancement based on a stable HSV-CS (Hue-Saturation-Value with sine–cosine transformation) color-space representation. Specifically, a sine–cosine transformation is introduced to construct a stable HSV-CS color space, effectively avoiding hue discontinuities at boundary regions in conventional HSV representations. To compensate for underwater degradation, a Color-Bias-Aware module and a Value-Confidence module are designed to adaptively correct color distortion and luminance degradation. Furthermore, a lightweight Channel-Spatial Adaptive Gated Fusion module dynamically aggregates features from the RGB and HSV-CS branches in a perception-driven manner. The overall architecture incorporates multi-branch re-parameterizable convolutions, significantly reducing computational cost while preserving strong representational capacity. Extensive experiments on underwater image enhancement benchmarks, including UIEB and RUIE, demonstrate that PCF-Net achieves state-of-the-art performance in terms of PSNR, SSIM, and UIQM, along with visually superior color correction and contrast enhancement. With only 0.17 M parameters, the proposed model runs at 118.6 FPS on an RTX 3090 and 35.3 FPS on a Jetson Orin Nano at a resolution of 512 × 512, making it well suited for resource-constrained real-time underwater vision applications. Full article

(1) Background: The scarcity and imbalance of real fault data significantly limit the development of data-driven fault diagnosis methods for liquid rocket engines (LREs), especially under few-shot conditions. (2) Methods: To address this issue, this study proposes a GAN-based fault data augmentation framework for multivariate LRE time-series signals and a hybrid diagnostic classifier combining convolutional neural networks (CNNs), bidirectional long short-term memory (BiLSTM), and multi-head attention (MHA). The GAN component is introduced to alleviate fault-data scarcity and class imbalance by generating additional fault-like samples, while the classifier is designed to capture local features, long-range temporal dependencies, and diagnostically informative temporal regions. (3) Results: A multidimensional evaluation based on temporal similarity, statistical consistency, and global distribution discrepancy indicates that the generated samples preserve important characteristics of the original signals under the current evaluation protocol. On the augmented LRE dataset, the proposed classifier achieved strong diagnostic performance. In addition, supplementary experiments on the public HIT aero-engine dataset further support the effectiveness of the classifier architecture, its component-wise contribution, and its behavior under imbalanced few-shot settings, while also demonstrating the value of uncertainty-aware prediction. (4) Conclusions: The results provide encouraging evidence that the proposed framework can improve LRE fault diagnosis under data-scarce conditions. However, the present findings should be interpreted within the scope of the available data and evaluation setting. More comprehensive generator-side ablation, broader external validation, and physics-oriented assessment of the generated signals are still needed before stronger conclusions can be made. Full article

Massive Open Online Courses (MOOCs) serve as catalysts for sustainable education by democratizing access to lifelong learning. While this potentially positions them as a key driver of the United Nations Sustainable Development Goal 4 (SDG 4), their long-term impact depends heavily on the implementation of inclusive design and ethical governance. This study evaluates the social sustainability of the AKADEMA platform—defined through equity of access, institutional trust, and long-term learner retention—using Badrul Khan’s e-learning framework. Employing a multi-layered mixed-methods design, the study triangulates subjective user perceptions—gathered via quantitative surveys (N = 209; a convenience sample of 6140 contacted users) and qualitative insights (n = 122)—with objective structural evidence from a technical accessibility audit. Although the results indicate high satisfaction with pedagogical quality, the findings reveal specific structural nuances regarding platform inclusivity and user diversity. Specifically, data triangulation highlights a notable ‘privacy awareness gap’—where working professionals demonstrate higher sensitivity regarding data governance than learners—alongside structural barriers hindering ‘Universal Design’ for learners with disabilities. Consequently, to strengthen the sustainability of open education models, future strategies should emphasize digital equity and institutional trust, ensuring that technical environments align with the promise of inclusive quality education. Full article