Search Results (389)

Inventory counting of logistics boxes in complex scenarios has always been a core task in intelligent logistics systems. To solve the problems of a high leakage rate and low computational efficiency caused by stacking, occlusion, and rotation in box detection against complex backgrounds in logistics environments, this paper proposes a lightweight, rotated object detection model: REW-YOLO (RepViT-Block YOLO with Efficient Local Attention and Wise-IoU). By integrating structural reparameterization techniques, the C2f-RVB module was designed to reduce computational redundancy in traditional convolutions. Additionally, the ELA-HSFPN multi-scale feature fusion network was constructed to enhance edge feature extraction for occluded boxes and improve detection accuracy in densely packed scenarios. A rotation angle regression branch and a dynamic Wise-IoU loss function were introduced to further refine localization and balance sample quality. Experimental results on the self-constructed BOX-data dataset demonstrate that the REW-YOLO achieves 90.2% mAP50 and 130.8 FPS, with a parameter count of only 2.18 M, surpassing YOLOv8n by 2.9% in accuracy while reducing computational cost by 28%. These improvements provide an efficient solution for automated box detection in logistics applications. Full article

In intelligent vehicular networks, the accuracy of semantic segmentation in road scenes is crucial for vehicle-mounted artificial intelligence to achieve environmental perception, decision support, and safety control. Although deep learning methods have made significant progress, two main challenges remain: first, the difficulty in balancing global and local features leads to blurred object boundaries and misclassification; second, conventional convolutions have limited ability to perceive irregular objects, causing information loss and affecting segmentation accuracy. To address these issues, this paper proposes a global–local collaborative attention module and a spider web convolution module. The former enhances feature representation through bidirectional feature interaction and dynamic weight allocation, reducing false positives and missed detections. The latter introduces an asymmetric sampling topology and six-directional receptive field paths to effectively improve the recognition of irregular objects. Experiments on the Cityscapes, CamVid, and BDD100K datasets, collected using vehicle-mounted cameras, demonstrate that the proposed method performs excellently across multiple evaluation metrics, including mIoU, mRecall, mPrecision, and mAccuracy. Comparative experiments with classical segmentation networks, attention mechanisms, and convolution modules validate the effectiveness of the proposed approach. The proposed method demonstrates outstanding performance in sensor-based semantic segmentation tasks and is well-suited for environmental perception systems in autonomous driving. Full article

Unexpected machine failures in industrial environments lead to high maintenance costs, unplanned downtime, and safety risks. This study proposes a proactive predictive model using a hybrid of eXtreme Gradient Boosting (XGBoost) and Neural Networks (NN) to forecast machine failures. A synthetic dataset capturing recent breakdown history and time since last failure was used to simulate industrial scenarios. To address class imbalance, SMOTE and class weighting were applied, alongside a focal loss function to emphasize difficult-to-classify failures. The XGBoost model was tuned via GridSearchCV, while the NN model utilized ReLU-activated hidden layers with dropout. Evaluation using stratified 5-fold cross-validation showed that the NN achieved an F1-score of 0.7199 and a recall of 0.9545 for the minority class. XGBoost attained a higher PR AUC of 0.7126 and a more balanced precision–recall trade-off. Sample predictions demonstrated strong recall (100%) for failures, but also a high false positive rate, with most prediction probabilities clustered between 0.50–0.55. Additional benchmarking against Logistic Regression, Random Forest, and SVM further confirmed the superiority of the proposed hybrid model. Model interpretability was enhanced using SHAP and LIME, confirming that recent breakdowns and time since last failure were key predictors. While the model effectively detects failures, further improvements in feature engineering and threshold tuning are recommended to reduce false alarms and boost decision confidence. Full article

To address the limitations in multi-scale feature processing and illumination sensitivity of existing steel surface defect detection algorithms, we proposed ADP-YOLOv8-n, enhancing accuracy and computational efficiency through advanced feature fusion and optimized network architecture. Firstly, an adaptive weighted down-sampling (ADSConv) module was proposed, which improves detector adaptability to diverse defects via the weighted fusion of down-sampled feature maps. Next, the C2f_DWR module was proposed, integrating optimized C2F architecture with a streamlined DWR design to enhance feature extraction efficiency while reducing computational complexity. Then, a Multi-Scale-Focus Diffusion Pyramid was designed to adaptively handle multi-scale object detection by dynamically adjusting feature fusion, thus reducing feature redundancy and information loss while maintaining a balance between detailed and global information. Experiments demonstrate that the proposed ADP-YOLOv8-n detection algorithm achieves superior performance, effectively balancing detection accuracy, inference speed, and model compactness. Full article

This study enhanced the self-healing performance of cherry wood furniture coatings by incorporating chitosan gum arabic-coated tung oil (CGA-T) microcapsules (types 1 and 2) into UV topcoats at 3%–15% concentrations. Multi-layer coated samples were systematically evaluated for optical, mechanical, and self-healing properties. Results demonstrated that microcapsules conferred self-healing ability, but concentrations >9% reduced reflectance (min 39.20%), increased color difference (max ΔE = 8.35), decreased gloss (max 35.25% loss at 60°), and raised roughness (max 1.79 μm). Mechanically, impact resistance improved (to grade 3), while adhesion declined (to grade 3) and hardness decreased (4H→2H). Self-healing performance peaked at 9% microcapsule 2 content (31.32% healing rate), with optimal overall performance at 6%. The 6% microcapsule 2 formulation (Sample 7) achieved the best overall balance among optical, mechanical, and self-healing properties, demonstrating its suitability for practical applications. Full article

Low-altitude drones, which are unimpeded by traffic congestion or urban terrain, have become a critical asset in emergency rescue missions. To address the current lack of emergency rescue data, UAV aerial videos were collected to create an experimental dataset for action classification and localization annotation. A total of 5082 keyframes were labeled with 1–5 targets each, and 14,412 instances of data were prepared (including flight altitude and camera angles) for action classification and position annotation. To mitigate the challenges posed by high-resolution drone footage with excessive redundant information, we propose the SlowFast-Traffic (SF-T) framework, a spatio-temporal sequence-based algorithm for recognizing traffic accident rescue actions. For more efficient extraction of target–background correlation features, we introduce the Actor-Centric Relation Network (ACRN) module, which employs temporal max pooling to enhance the time-dimensional features of static backgrounds, significantly reducing redundancy-induced interference. Additionally, smaller ROI feature map outputs are adopted to boost computational speed. To tackle class imbalance in incident samples, we integrate a Class-Balanced Focal Loss (CB-Focal Loss) function, effectively resolving rare-action recognition in specific rescue scenarios. We replace the original Faster R-CNN with YOLOX-s to improve the target detection rate. On our proposed dataset, the SF-T model achieves a mean average precision (mAP) of 83.9%, which is 8.5% higher than that of the standard SlowFast architecture while maintaining a processing speed of 34.9 tasks/s. Both accuracy-related metrics and computational efficiency are substantially improved. The proposed method demonstrates strong robustness and real-time analysis capabilities for modern traffic rescue action recognition. Full article

The accurate acquisition of agricultural parcels from remote sensing images is crucial for agricultural management and crop production monitoring. Most of the existing agricultural parcel extraction methods comprise semantic segmentation through remote sensing images, pixel-level classification, and then vectorized raster data. However, this approach faces challenges such as internal cavities, unclosed boundaries, and fuzzy edges, which hinder the accurate extraction of complete agricultural parcels. Therefore, this paper proposes a vector contour segmentation network based on the hybrid backbone and multiscale edge feature extraction module (HEVNet). We use the extraction of vector polygons of agricultural parcels by predicting the location of contour points, which avoids the above problems that may occur when raster data is converted to vector data. Simultaneously, this paper proposes a hybrid backbone for feature extraction. A hybrid backbone combines the respective advantages of the Resnet and Transformer backbone networks to balance local features and global features in feature extraction. In addition, we propose a multiscale edge feature extraction module, which can extract and enhance the edge features of different scales to prevent the possible loss of edge details in down sampling. This paper uses the datasets of Denmark, the Netherlands, iFLYTEK, and Hengyang in China to evaluate our model. The obtained IOU indexes were 67.92%, 81.35%, 78.02%, and 66.35%, which are higher than previous IOU indexes based on the optimal model (DBBANet). The results demonstrate that the proposed model significantly enhances the integrity and edge accuracy of agricultural parcel extraction. Full article

Single-image super-resolution (SISR) plays a critical role in enhancing visual quality for real-world applications, including industrial inspection and embedded vision systems. While deep learning-based approaches have made significant progress in SR, existing lightweight SR models often fail to accurately reconstruct high-frequency textures, especially under complex degradation scenarios, resulting in blurry edges and structural artifacts. To address this challenge, we propose a Dense Residual Fused Attention Network (DRFAN), a novel lightweight hybrid architecture designed to enhance high-frequency texture recovery in challenging degradation conditions. Moreover, by coupling convolutional layers and attention mechanisms through gated interaction modules, the DRFAN enhances local details and global dependencies with linear computational complexity, enabling the efficient utilization of multi-level spatial information while effectively alleviating the loss of high-frequency texture details. To evaluate its effectiveness, we conducted ×4 super-resolution experiments on five public benchmarks. The DRFAN achieves the best performance among all compared lightweight models. Visual comparisons show that the DRFAN restores more accurate geometric structures, with up to +1.2 dB/+0.0281 SSIM gain over SwinIR-S on Urban100 samples. Additionally, on a domain-specific rice grain dataset, the DRFAN outperforms SwinIR-S by +0.19 dB in PSNR and +0.0015 in SSIM, restoring clearer textures and grain boundaries essential for industrial quality inspection. The proposed method provides a compelling balance between model complexity and image reconstruction fidelity, making it well-suited for deployment in resource-constrained visual systems and industrial applications. Full article

Background: The gut microbiota is increasingly recognized as a key modulator in obesity management, influencing host energy balance, lipid metabolism, and inflammatory pathways. With obesity prevalence continuing to rise globally, dietary interventions that promote beneficial microbial shifts are essential for enhancing weight loss outcomes and long-term health. Objective: This study investigated the effects of the multicomponent Weight Loss Maintenance 3 Phases Program (WLM3P), which integrates caloric restriction, a high-protein low-carbohydrate diet, time-restricted eating (10h TRE), dietary supplementation (prebiotics and phytochemicals), and digital app-based support on gut microbiota composition compared to a standard low-carbohydrate diet (LCD) in adults with obesity. The analysis focused exclusively on the 6-month weight loss period corresponding to Phases 1 and 2 of the WLM3P intervention. Methods: In this sub-analysis of a randomized controlled trial (ClinicalTrials.gov Identifier: NCT04192357), 58 adults with obesity (BMI 30.0–39.9 kg/m²) were randomized to the WLM3P (n = 29) or LCD (n = 29) groups. Stool samples were collected at baseline and 6 months for 16S rRNA sequencing. Alpha and beta diversity were assessed, and genus-level differential abundance was determined using EdgeR and LEfSe. Associations between microbial taxa and clinical outcomes were evaluated using regression models. Results: After 6-month, the WLM3P group showed a significant increase in alpha diversity (p = 0.03) and a significant change in beta diversity (p < 0.01), while no significant changes were observed in the LCD group. Differential abundance analysis revealed specific microbial signatures in WLM3P participants, including increased levels of Faecalibacterium. Notably, higher Faecalibacterium abundance was associated with greater reductions in fat mass (kg, %) and visceral adiposity (cm²) in the WLM3P group compared to LCD (p < 0.01). Conclusions: These findings suggest a potential microbiota-mediated mechanism in weight loss, where Faecalibacterium may enhance fat reduction effectiveness in the context of the WLM3P intervention. Full article

Accurate and rapid aquatic organism recognition is a core technology for fisheries automation and aquatic organism statistical research. However, due to absorption and scattering effects, images of aquatic organisms often suffer from poor contrast and color distortion. Additionally, the clustering behavior of aquatic organisms often leads to occlusion, further complicating the identification task. This study proposes a lightweight object detection model, Mobile-YOLO, for the recognition of four representative aquatic organisms, namely holothurian, echinus, scallop, and starfish. Our model first utilizes the Mobile-Nano backbone network we proposed, which enhances feature perception while maintaining a lightweight design. Then, we propose a lightweight detection head, LDtect, which achieves a balance between lightweight structure and high accuracy. Additionally, we introduce Dysample (dynamic sampling) and HWD (Haar wavelet downsampling) modules, aiming to optimize the feature fusion structure and achieve lightweight goals by improving the processes of upsampling and downsampling. These modules also help compensate for the accuracy loss caused by the lightweight design of LDtect. Compared to the baseline model, our model reduces Params (parameters) by 32.2%, FLOPs (floating point operations) by 28.4%, and weights (model storage size) by 30.8%, while improving FPS (frames per second) by 95.2%. The improvement in mAP (mean average precision) can also lead to better accuracy in practical applications, such as marine species monitoring, conservation efforts, and biodiversity assessment. Furthermore, the model’s accuracy is enhanced, with the mAP increased by 1.6%, demonstrating the advanced nature of our approach. Compared with YOLO (You Only Look Once) series (YOLOv5-12), SSD (Single Shot MultiBox Detector), EfficientDet (Efficient Detection), RetinaNet, and RT-DETR (Real-Time Detection Transformer), our model achieves leading comprehensive performance in terms of both accuracy and lightweight design. The results indicate that our research provides technological support for precise and rapid aquatic organism recognition. Full article

Assessing building fire safety risks during the early design phase is vital for developing practical solutions to minimize loss of life and property. This study aims to identify research trends and provide a guiding framework for researchers by systematically reviewing the literature on integrating machine learning-based predictive methods into building fire safety design using bibliometric methods. This study evaluates machine learning applications in fire safety using a comprehensive approach that combines bibliometric and content analysis methods. For this purpose, as a result of the scan without any year limitation from the Web of Science Core Collection-Citation database, 250 publications, the first of which was published in 2001, and the number has increased since 2019, were reached, and sample analysis was performed. In order to evaluate the contribution of qualified publications to science more accurately, citation counts were analyzed using normalized citation counts that balanced differences in publication fields and publication years. Multiple regression analysis was applied to support this metric’s theoretical basis and determine the impact levels of variables affecting the metric’s value (such as total citation count, publication year, and number of articles). Thus, the statistical impact of factors influencing the formation of the normalized citation count was measured, and the validity of the approach used was tested. The research categories included evacuation and emergency management, fire detection, and early warning systems, fire dynamics and spread prediction, fire load, and material risk analysis, intelligent systems and cyber security, fire prediction, and risk assessment. Convolutional neural networks, artificial neural networks, support vector machines, deep neural networks, you only look once, deep learning, and decision trees were prominent as machine learning categories. As a result, detailed literature was presented to define the academic publication profile of the research area, determine research fronts, detect emerging trends, and reveal sub-themes. Full article

Virulence factors (VFs), produced by pathogens, facilitate pathogenic microorganisms to invade, colonize, and damage the host cells. Accurate VF identification advances pathogenic mechanism understanding and provides novel anti-virulence targets. Existing models primarily utilize protein sequence features while overlooking the systematic protein–protein interaction (PPI) information, despite pathogenesis typically resulting from coordinated protein–protein actions. Moreover, a severe imbalance exists between virulence and non-virulence proteins, which causes existing models trained on balanced datasets by sampling to fail in incorporating proteins’ inherent distributional characteristics, thus restricting generalization to real-world imbalanced data. To address these challenges, we propose a novel Generative and Contrastive self-supervised learning framework for Virulence Factor identification (GC-VF) that transforms VF identification into an imbalanced node classification task on graphs generated from PPI networks. The framework encompasses two core modules: the generative attribute reconstruction module learns attribute space representations via feature reconstruction, capturing intrinsic data patterns and reducing noise; the local contrastive learning module employs node-level contrastive learning to precisely capture local features and contextual information, avoiding global aggregation losses while ensuring node representations truly reflect inherent characteristics. Comprehensive benchmark experiments demonstrate that GC-VF outperforms baseline methods on naturally imbalanced datasets, exhibiting higher accuracy and stability, as well as providing a potential solution for accurate VF identification. Full article

Microscopic colitis (MC) is an idiopathic inflammatory bowel disease characterized by watery, non-bloody diarrhea and histopathological changes but normal endoscopic findings. Increasing evidence now suggests that alterations in the gut microbiota contribute to the pathogenesis of MC. In this narrative review, we summarize evidence from nine case-control studies examining microbial composition using sequencing technology. The research presented here illustrates reduced alpha diversity, high dysbiosis, and pro-inflammatory oral-associated taxa enrichment, such as Veillonella dispar, and loss of protective microbes such as Akkermansia muciniphila and Bacteroides stercoris. These microbial changes have the potential to be non-invasive diagnostic biomarkers that can differentiate MC from other etiologies. In addition, the characterization of gut microbiota in MC can guide personalized therapeutic strategies, such as directed probiotic therapy or fecal microbiota transplantation, to help restore microbial balance. These microbial patterns can be applied to guide the creation of diagnostic biomarkers and personalized therapy. Despite differences in sample types and sequencing methods, general microbial trends highlight the need for further longitudinal and standardized investigations. Full article

The increasing sophistication of cyberattacks on smart grid infrastructure demands advanced anomaly detection and recovery systems that balance high recall rates with acceptable precision while providing reliable data restoration capabilities. This study presents an optimized two-stage anomaly detection and recovery system combining an enhanced TimerXL detector with a DeBERTa-v3-based verification and recovery mechanism. The first stage employs an optimized increment-based detection algorithm achieving 95.0% for recall and 54.8% for precision through multidimensional analysis. The second stage leverages a modified DeBERTa-v3 architecture with comprehensive 25-dimensional feature engineering per variable to verify potential anomalies, improving the precision to 95.1% while maintaining 84.1% for recall. Key innovations include (1) a balanced loss function combining focal loss ($\alpha$ = 0.65, $\gamma$ = 1.2), Dice loss (weight = 0.5), and contrastive learning (weight = 0.03) to reduce over-rejection by 73.4%; (2) an ensemble verification strategy using multithreshold voting, achieving 91.2% accuracy; (3) optimized sample weighting prioritizing missed positives (weight = 10.0); (4) comprehensive feature extraction, including frequency domain and entropy features; and (5) integration of a generative time series model (TimER) for high-precision recovery of tampered data points. Experimental results on 2000 hourly smart grid measurements demonstrate an F1-score of 0.873 ± 0.114 for detection, representing a 51.4% improvement over ARIMA (0.576), 621% over LSTM-AE (0.121), 791% over standard Anomaly Transformer (0.098), and 904% over TimesNet (0.087). The recovery mechanism achieves remarkably precise restoration with a mean absolute error (MAE) of only 0.0055 kWh, representing a 99.91% improvement compared to traditional ARIMA models and 98.46% compared to standard Anomaly Transformer models. We also explore an alternative implementation using the Lag-LLaMA architecture, which achieves an MAE of 0.2598 kWh. The system maintains real-time capability with a 66.6 ± 7.2 ms inference time, making it suitable for operational deployment. Sensitivity analysis reveals robust performance across anomaly magnitudes (5–100 kWh), with the detection accuracy remaining above 88%. Full article

Hyperspectral image cross-scene classification (HSICC) tasks are confronted with tremendous challenges due to spectral shift phenomena across scenes and the tough work of obtaining labels. Unsupervised domain adaptation has proven its effectiveness in tackling this issue, but it has a fatal limitation of intending to narrow the disparity between source and target domains by utilizing fully labeled source data and unlabeled target data. However, it is costly even to attain labels from source domains in many cases, rendering sufficient labeling as used in prior work impractical. In this work, we investigate an extreme and realistic scenario where unsupervised domain adaptation methods encounter sparsely labeled source data when handling HSICC tasks, namely, few-shot unsupervised domain adaptation. We propose an end-to-end refined bi-directional prototypical contrastive learning (RBPCL) framework for overcoming the HSICC problem with only a few labeled samples in the source domain. RBPCL captures category-level semantic features of hyperspectral data and performs feature alignment through in-domain refined prototypical self-supervised learning and bi-directional cross-domain prototypical contrastive learning, respectively. Furthermore, our framework introduces the class-balanced multicentric dynamic prototype strategy to generate more robust and representative prototypes. To facilitate prototype contrastive learning, we employ a Siamese-style distance metric loss function to aggregate intra-class features while increasing the discrepancy of inter-class features. Finally, extensive experiments and ablation analysis implemented on two public cross-scene data pairs and three pairs of self-collected ultralow-altitude hyperspectral datasets under different illumination conditions verify the effectiveness of our method, which will further enhance the practicality of hyperspectral intelligent sensing technology. Full article