Search Results (5,759)

We propose an advanced electronic nose based on SE-RelationNet for COPD diagnosis with limited breath samples. The model integrates residual blocks, BiGRU layers, and squeeze–excitation attention mechanisms to enhance feature-extraction efficiency. Experimental results demonstrate exceptional performance with minimal samples: in 4-way 1-shot tasks, the model achieves 85.8% mean accuracy (F1-score = 0.852), scaling to 93.3% accuracy (F1-score = 0.931) with four samples per class. Ablation studies confirm that the 5-layer residual structure and single-hidden-layer BiGRU optimize stability (h_F1-score ≤ 0.011). Compared to SiameseNet and ProtoNet, SE-RelationNet shows superior accuracy (>15% improvement in 1-shot tasks). This technology enables COPD detection with as few as one breath sample, facilitating early intervention to mitigate lung cancer risks in COPD patients. Full article

Green innovation is a critical driver of sustainable development, yet it often faces efficiency challenges in rapidly industrializing economies. This study investigates the effect of China’s Circular Economy Demonstration Policy (CEDP) on urban green innovation efficiency (GIE) using city-level panel data from 2010 to 2021. Employing a difference-in-differences (DID) approach, we find that CEDP significantly enhances GIE, with the policy effect becoming statistically significant after a three-year lag and accumulating over time. Robustness tests, including placebo analyses, alternative dependent variables, and propensity score matching, confirm the validity of the results. Mechanism analysis reveals that the policy improves green innovation primarily by reducing capital distortion, promoting market integration, and enhancing resource allocation efficiency. Further heterogeneity analyses show that the positive effects are stronger in central cities, capital cities, and eastern regions, reflecting the role of local economic and institutional conditions. The study concludes with policy implications emphasizing regionally tailored implementation, capacity building, and long-term commitment to maximize green innovation outcomes. Full article

The construction industry has been troubled by a shortage of skilled labor and safety accidents in recent years. Therefore, more and more robots are introduced to undertake dangerous and repetitive jobs, so that human workers can concentrate on higher-value and creative problem-solving tasks. Nevertheless, although human–robot collaboration (HRC) shows great potential, most existing evaluation methods still focus on the single performance of either the human or robot, and systematic indicators for a whole HRC team remain insufficient. To fill this research gap, the present study constructs a comprehensive evaluation framework for HRC team performance in construction projects. Firstly, a detailed literature review is carried out, and three theories are integrated to build 33 indicators preliminarily. Afterwards, an expert questionnaire survey (N = 15) is adopted to revise and verify the model empirically. The survey yielded a Cronbach’s alpha of 0.916, indicating excellent internal consistency. The indicators rated highest in importance were task completion time (µ = 4.53) and dynamic separation distance (µ = 4.47) on a 5-point scale. Eight indicators were excluded due to mean importance ratings falling below the 3.0 threshold. The framework is formed with five main dimensions and 25 concrete indicators. Finally, an AHP-TOPSIS method is used to evaluate the HRC team performance. The AHP analysis reveals that Safety (weight = 0.2708) is prioritized over Productivity (weight = 0.2327) by experts, establishing a safety-first principle for successful HRC deployment. The framework is demonstrated through a case study of a human–robot plastering team, whose team performance scored as fair. This shows that the framework can help practitioners find out the advantages and disadvantages of HRC team performance and provide targeted improvement strategies. Furthermore, the framework offers construction managers a scientific basis for deciding robot deployment and team assignment, thus promoting safer, more efficient, and more creative HRC in construction projects. Full article

Stress in pigs poses significant challenges to animal welfare and productivity in modern pig farming, contributing to increased antimicrobial use and the rise of antimicrobial resistance (AMR). This study involves stress classification in pregnant sows by exploring five deep learning models: ConvNeXt, EfficientNet_V2, MobileNet_V3, RegNet, and Vision Transformer (ViT). These models are used for stress detection from facial images, leveraging an expanded dataset. A facial image dataset of sows was collected at Scotland’s Rural College (SRUC) and the images were categorized into primiparous Low-Stressed (LS) and High-Stress (HS) groups based on expert behavioural assessments and cortisol level analysis. The selected deep learning models were then trained on this enriched dataset and their performance was evaluated using cross-validation on unseen data. The Vision Transformer (ViT) model outperformed the others across the dataset of annotated facial images, achieving an average accuracy of 0.75, an F1 score of 0.78 for high-stress detection, and consistent batch-level performance (up to 0.88 F1 score). These findings highlight the efficacy of transformer-based models for automated stress detection in sows, supporting early intervention strategies to enhance welfare, optimize productivity, and mitigate AMR risks in livestock production. Full article

To address the inefficiency of traditional concrete crack detection methods and the heavy reliance of supervised learning on extensive labeled data, in this study, an intelligent assessment method of concrete damage based on pseudo-label semi-supervised learning and fractal geometry theory is proposed to solve two core tasks: one is binary classification of pixel-level cracks, and the other is multi-category assessment of damage state based on crack morphology. Using three-channel RGB images as input, a dual-path collaborative training framework based on U-Net encoder–decoder architecture is constructed, and a binary segmentation mask of the same size is output to achieve the accurate segmentation of cracks at the pixel level. By constructing a dual-path collaborative training framework and employing a dynamic pseudo-label refinement mechanism, the model achieves an F1-score of 0.883 using only 50% labeled data—a mere 1.3% decrease compared to the fully supervised benchmark DeepCrack (F1 = 0.896)—while reducing manual annotation costs by over 60%. Furthermore, a quantitative correlation model between crack fractal characteristics and structural damage severity is established by combining a U-Net segmentation network with the differential box-counting algorithm. The experimental results demonstrate that under a cyclic loading of 147.6–221.4 kN, the fractal dimension monotonically increases from 1.073 (moderate damage) to 1.189 (failure), with 100% accuracy in damage state identification, closely aligning with the degradation trend of macroscopic mechanical properties. In complex crack scenarios, the model attains a recall rate (Re = 0.882), surpassing U-Net by 13.9%, with significantly enhanced edge reconstruction precision. Compared with the mainstream models, this method effectively alleviates the problem of data annotation dependence through a semi-supervised strategy while maintaining high accuracy. It provides an efficient structural health monitoring solution for engineering practice, which is of great value to promote the application of intelligent detection technology in infrastructure operation and maintenance. Full article

Tea cultivation faces significant threats from red spider mite (RSM: Oligonychus coffeae) infestations, which reduce yields and economic viability in major tea-producing regions. Current automated detection methods rely on supervised deep learning models requiring extensive labeled data, limiting scalability for smallholder farmers. This article proposes AIM-Net (AI-based Infestation Mapping Network) by evaluating SwAV (Swapping Assignments between Views), a self-supervised learning framework, for classifying RSM infestation severity (Mild, Moderate, Severe) using a geo-referenced, field-acquired dataset of RSM infested tea-leaves, Cam-RSM. The methodology combines SwAV pre-training on unlabeled data with fine-tuning on labeled subsets, employing multi-crop augmentation and online clustering to learn discriminative features without full supervision. Comparative analysis against a fully supervised ResNet-50 baseline utilized 5-fold cross-validation, assessing accuracy, F1-scores, and computational efficiency. Results demonstrate SwAV’s superiority, achieving 98.7% overall accuracy (vs. 92.1% for ResNet-50) and macro-average F1-scores of 98.3% across classes, with a 62% reduction in labeled data requirements. The model showed particular strength in Mild_RSM-class detection (F1-score: 98.5%) and computational efficiency, enabling deployment on edge devices. Statistical validation confirmed significant improvements (p < 0.001) over baseline approaches. These findings establish self-supervised learning as a transformative tool for precision pest management, offering resource-efficient solutions for early infestation detection while maintaining high accuracy. Full article

Timely and accurate identification of surface damage in hydraulic structures is essential for maintaining structural integrity and ensuring operational safety. Traditional manual inspections are time-consuming, labor-intensive, and prone to subjectivity, especially for large-scale or inaccessible infrastructure. Leveraging advancements in aerial imaging, unmanned aerial vehicles (UAVs) enable efficient acquisition of high-resolution visual data across expansive hydraulic environments. However, existing deep learning (DL) models often lack architectural adaptations for the visual complexities of UAV imagery, including low-texture contrast, noise interference, and irregular crack patterns. To address these challenges, this study proposes a lightweight, robust, and high-precision segmentation framework, called LFPA-EAM-Fast-SCNN, specifically designed for pixel-level damage detection in UAV-captured images of hydraulic concrete surfaces. The developed DL-based model integrates an enhanced Fast-SCNN backbone for efficient feature extraction, a Lightweight Feature Pyramid Attention (LFPA) module for multi-scale context enhancement, and an Edge Attention Module (EAM) for refined boundary localization. The experimental results on a custom UAV-based dataset show that the proposed damage detection method achieves superior performance, with a precision of 0.949, a recall of 0.892, an F1 score of 0.906, and an IoU of 87.92%, outperforming U-Net, Attention U-Net, SegNet, DeepLab v3+, I-ST-UNet, and SegFormer. Additionally, it reaches a real-time inference speed of 56.31 FPS, significantly surpassing other models. The experimental results demonstrate the proposed framework’s strong generalization capability and robustness under varying noise levels and damage scenarios, underscoring its suitability for scalable, automated surface damage assessment in UAV-based remote sensing of civil infrastructure. Full article

Efficient and accurate panel assignment is critical in expert and peer review processes. Traditional methods—based on manual preferences or Heuristic rules—often introduce bias, inconsistency, and scalability challenges. We present an automated framework that combines transformer-based document similarity modeling with optimization-based reviewer assignment. Using the all-mpnet-base-v2 from model (version 3.4.1), our system computes semantic similarity between proposal texts and reviewer documents, including CVs and Google Scholar profiles, without requiring manual input from reviewers. These similarity scores are then converted into rankings and integrated into an Integer Linear Programming (ILP) formulation that accounts for workload balance, conflicts of interest, and role-specific reviewer assignments (lead, scribe, reviewer). The method was tested across 40 researchers in two distinct disciplines (Chemical Engineering and Philosophy), each with 10 proposal documents. Results showed high self-similarity scores (0.65–0.89), strong differentiation between unrelated fields (−0.21 to 0.08), and comparable performance between reviewer document types. The optimization consistently prioritized top matches while maintaining feasibility under assignment constraints. By eliminating the need for subjective preferences and leveraging deep semantic analysis, our framework offers a scalable, fair, and efficient alternative to manual or Heuristic assignment processes. This approach can support large-scale review workflows while enhancing transparency and alignment with reviewer expertise. Full article

Work-related musculoskeletal disorders (WMSDs) are a leading concern in industrial ergonomics, often stemming from sustained non-neutral postures and repetitive tasks. This paper presents a vision-based framework for real-time, frame-level ergonomic risk classification using a lightweight Vision Transformer (ViT). The proposed system operates directly on raw RGB images without requiring skeleton reconstruction, joint angle estimation, or image segmentation. A single ViT model simultaneously classifies eight anatomical regions, enabling efficient multi-label posture assessment. Training is supervised using a multimodal dataset acquired from synchronized RGB video and full-body inertial motion capture, with ergonomic risk labels derived from RULA scores computed on joint kinematics. The system is validated on realistic, simulated industrial tasks that include common challenges such as occlusion and posture variability. Experimental results show that the ViT model achieves state-of-the-art performance, with F1-scores exceeding 0.99 and AUC values above 0.996 across all regions. Compared to previous CNN-based system, the proposed model improves classification accuracy and generalizability while reducing complexity and enabling real-time inference on edge devices. These findings demonstrate the model’s potential for unobtrusive, scalable ergonomic risk monitoring in real-world manufacturing environments. Full article

Accurate cloud segmentation is critical for astronomical observations and solar forecasting. However, traditional threshold- and texture-based methods suffer from limited accuracy (65–80%) under complex conditions such as thin cirrus or twilight transitions. Although the deep-learning segmentation method based on U-Net effectively captures low-level and high-level features and achieves significant progress in accuracy, current methods still lack interpretability and multi-scale feature integration and usually produce fuzzy boundaries or fragmented predictions. In this paper, we propose multi-scale CAM, an explainable AI (XAI) framework that integrates class activation mapping (CAM) with hierarchical feature fusion to quantify pixel-level attention across hierarchical features, thereby enhancing the model’s discriminative capability. To achieve precise segmentation, we integrate CAM into an improved U-Net architecture, incorporating multi-scale CAM attention for adaptive feature fusion and dilated residual modules for large-scale context extraction. Experimental results on the SWINSEG dataset demonstrate that our method outperforms existing state-of-the-art methods, improving recall by 3.06%, F1 score by 1.49%, and MIoU by 2.21% over the best baseline. The proposed framework balances accuracy, interpretability, and computational efficiency, offering a trustworthy solution for cloud detection systems in operational settings. Full article

The Solar Agro Savior (SAS) is an innovative solution that is assisted by drones for the sustainable utilization of water and plant disease observation in the agriculture sector. This system integrates an alerting mechanism for humidity, moisture, and temperature variations, which affect the plants’ health and optimization in water utilization, which enhances plant yield productivity. A significant feature of the system is the efficient monitoring system in a larger region through drones’ high-resolution cameras, which enables real-time, efficient response and alerting for environmental fluctuations to the authorities. The machine learning algorithm, particularly recurrent neural networks, which is a pioneer with agriculture and pest control, is incorporated for intelligent monitoring systems. The proposed system incorporates a specialized form of a recurrent neural network, Long Short-Term Memory (LSTM), which effectively addresses the vanishing gradient problem. It also utilizes an attention-based mechanism that enables the model to assign meaningful weights to the most important parts of the data sequence. This algorithm not only enhances water utilization efficiency but also boosts plant yield and strengthens pest control mechanisms. This system also provides sustainability through the re-utilization of water and the elimination of electric energy through solar panel systems for powering the inbuilt irrigation system. A comparative analysis of variant algorithms in the agriculture sector with a machine learning approach was also illustrated, and the proposed system yielded 99% yield accuracy, a 97.8% precision value, 98.4% recall, and a 98.4% F1 score value. By encompassing solar irrigation and artificial intelligence-driven analysis, the proposed algorithm, Solar Argo Savior, established a sustainable framework in the latest agricultural sectors and promoted sustainability to protect our environment and community. Full article

Recent advancements in deep learning have significantly enhanced brain tumor segmentation from MRI data, providing valuable support for clinical diagnosis and treatment planning. However, challenges persist in effectively integrating prior medical knowledge, capturing global multimodal features, and accurately delineating tumor boundaries. To address these challenges, the Hybrid Network for Multimodal Brain Tumor Segmentation (HN-MBTS) is proposed, which incorporates prior medical knowledge to refine feature extraction and boundary precision. Key innovations include the Two-Branch, Two-Model Attention (TB-TMA) module for efficient multimodal feature fusion, the Linear Attention Mamba (LAM) module for robust multi-scale feature modeling, and the Residual Attention (RA) module for enhanced boundary refinement. Experimental results demonstrate that this method significantly outperforms existing approaches. On the BraT2020 and BraT2023 datasets, the method achieved average Dice scores of 87.66% and 88.07%, respectively. These results confirm the superior segmentation accuracy and efficiency of the approach, highlighting its potential to provide valuable assistance in clinical settings. Full article

Background: Lung cancer ranks as the leading cause of cancer-related mortality worldwide. The complexity of tumor delineation, crucial for radiation therapy, requires expertise often unavailable in resource-limited settings. Artificial Intelligence (AI), particularly with advancements in deep learning (DL) and natural language processing (NLP), offers potential solutions yet is challenged by high false positive rates. Purpose: The Oncology Contouring Copilot (OCC) system is developed to leverage oncologist expertise for precise tumor contouring using textual descriptions, aiming to increase the efficiency of oncological workflows by combining the strengths of AI with human oversight. Methods: Our OCC system initially identifies nodule candidates from CT scans. Employing Language Vision Models (LVMs) like GPT-4V, OCC then effectively reduces false positives with clinical descriptive texts, merging textual and visual data to automate tumor delineation, designed to elevate the quality of oncology care by incorporating knowledge from experienced domain experts. Results: The deployment of the OCC system resulted in a 35.0% reduction in the false discovery rate, a 72.4% decrease in false positives per scan, and an F1-score of 0.652 across our dataset for unbiased evaluation. Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs, improving contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation and reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVM hallucinations with ablation study; and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges. Full article

Carbon emissions from freshwater aquaculture can exacerbate the greenhouse effect, thereby impacting human life and health. Consequently, it is of great significance to explore the carbon peak process and the role of emission reduction data in China’s freshwater aquaculture industry. This study innovatively employs the Logarithmic Mean Divisia Index model (LMDI) and the Tapio decoupling model to conduct an in-depth analysis of the relationship between carbon emissions and output values in the freshwater aquaculture industry, accurately identifying the main driving factors. Meanwhile, the global and local Moran’s I indices are introduced to analyze its spatial correlation from a new perspective. The results indicate that from 2013 to 2023, carbon emissions from China’s freshwater aquaculture industry exhibited a quasi-“N”-shaped trend, reaching a peak of 38 million tons in 2015. East China was the primary contributor to carbon emissions, accounting for 46%, while South China, Central China, and Northeast China each had an average annual share of around 14%, with Southwest, North China, and Northwest China contributing relatively small proportions. The global Moran’s I index showed a decreasing trend, with a p-value ≤ 0.0010 and a z-score > 3.3, indicating a 99% significant spatial correlation. High-high clusters were concentrated in some provinces of East China, while low-low clusters were found in Northwest, North, and Southwest China. The level of fishery economic development positively drove carbon emissions, whereas freshwater aquaculture production efficiency, industrial structure, and the scale of the aquaculture population had negative effects on carbon emissions. During the study period, carbon emissions exhibited three states: weak decoupling, strong decoupling, and expansive negative decoupling, with alternating strong and weak decoupling occurring after 2015. Full article

Efficient plastic waste end-of-life management is a serious worldwide environmental issue motivated by growing waste production and negative effects of wrongful disposal. This study presents a comparative overview of plastic waste management regimes within the European Union (EU), the United States of America (USA), and Romania, ranked with circular economy goals. By using the United States Environmental Protection Agency (US EPA) Waste Reduction Model (WARM), version 16, the study provides a quantified score to greenhouse gas (GHG) emissions within three large options of management: recycling, energy recovery through combustion, and landfilling. The model setup utilizes region-specific information on legislation, base technology, and recycling efficiency. The outcomes show that recycling always entails net GHG emissions reductions, i.e., −4.49 kg CO_2e/capita/year for EU plastic waste and −20 kg CO_2e/capita/year for USA plastic waste. Combustion and landfilling have positive net emissions from 1.76 to 14.24 kg CO_2e/capita/year. Economic indicators derived from the model also show significant variation: salaries for PET management amounted to USD 2.87 billion in the EU and USD 377 million in the USA, and tax collection was USD 506 million and USD 2.01 billion, respectively. The conclusions highlight the wider environmental and socioeconomic benefits of recycling and reinforce its status as a cornerstone of circular-economy sustainable plastic waste management and a strategic element of national development agendas, with special reference to Romania’s national agenda. Full article