Search Results (1,724)

Detecting steel defects is a vital process in industrial production, but traditional methods suffer from poor feature extraction and low detection accuracy. To address these issues, this research introduces an improved model, EB-YOLOv8, based on YOLOv8. First, the multi-scale attention mechanism EMA is integrated into the backbone and neck sections to reduce noise during gradient descent and enhance model stability by encoding global information and weighting model parameters. Second, the weighted fusion splicing module, Concat_BiFPN, is used in the neck network to facilitate multi-scale feature detection and fusion. This improves detection precision. The results show that the EB-YOLOv8 model increases detection accuracy on the NEU-DET dataset by 3.1%, reaching 80.2%, compared to YOLOv8. Additionally, the average precision on the Severstal steel defect dataset improves from 65.4% to 66.1%. Overall, the proposed model demonstrates superior recognition performance. Full article

Adulteration detection in medicinal plant powders remains a critical challenge in quality control. In this study, we propose a hyperspectral imaging (HSI)-based method combined with deep learning models to quantitatively analyze adulteration levels in Anoectochilus roxburghii powder. After preprocessing the spectral data using raw, first-order, and second-order Savitzky–Golay derivatives, we systematically evaluated the performance of traditional machine learning models (Random Forest, Support Vector Regression, Partial Least Squares Regression) and deep learning architectures. While traditional models achieved reasonable accuracy (R² up to 0.885), their performance was limited by feature extraction and generalization ability. A single-channel convolutional neural network (CNN) utilizing individual spectral representations improved performance marginally (maximum R² = 0.882), but still failed to fully capture the multi-scale spectral features. To overcome this, we developed a multi-channel CNN that simultaneously integrates raw, SG-1, and SG-2 spectra, effectively leveraging complementary spectral information. This architecture achieved a significantly higher prediction accuracy (R² = 0.964, MSE = 0.005), demonstrating superior robustness and generalization. The findings highlight the potential of multi-channel deep learning models in enhancing quantitative adulteration detection and ensuring the authenticity of herbal products. Full article

In marketing science, product categorization using cannibalization relationship data is an emerging but still underdeveloped area, where clustering using price effect information is a novel direction that is worth further exploration. In this study, by assuming a realistic modeling of the cross-price effect, we developed and experimentally validated with simulations an agglomerative clustering algorithm that outputs clustering results closer to the ground truth compared with other agglomerative algorithms based on traditional cluster linkages. Full article

Broth cooking is a traditional pretreatment and ripening strategy for high-commercial-value dehydrated marine food, effectively enhancing its texture and rehydration properties. In this work, we characterized the structural information of Maillard reaction products (MRPs) derived from beef scrap stock and investigated their effects on the texture and rehydration performance of dehydrated abalone. The optical and structural properties of the MRPs were analyzed using X-ray photoelectron spectroscopy (XPS), X-ray diffraction (XRD), transmission electron microscopy (TEM), and fluorescence spectroscopy. These MRPs showed osmosis in abalone processing including pretreatment and drying. Low-field nuclear magnetic resonance (LF-NMR) results revealed that MRP pretreatment improved the moisture migration and physicochemical properties of dehydrated abalone. These findings suggest that MRPs, owing to their high osmotic efficiency and nanoscale size, could serve as promising food additives and potential alternatives to traditional penetrating agents in the food industry, enhancing the rehydration performance of dried seafood and reducing quality deterioration. Full article

In this work, we introduce a novel method to extract correlations in diagonal quantum states in multi-particle quantum systems, addressing a significant limitation of traditional approaches that require prior knowledge of the density matrices of quantum states. Instead of relying on classical information processing, our method is based on weak couplings and ancillary systems, eliminating the need for classical communication, optimization, and complex calculations. The concept of mutually unbiased bases is intrinsically linked to symmetry, as it entails the uniform distribution of quantum states across distinct bases. Within the framework of our theoretical model, mutually unbiased bases are employed to facilitate weak measurements and to function as the post-selected states. To quantify the correlations in the initial state, we employ the trace distance between the initial state and the product of its marginal states, and illustrate the feasibility and effectiveness of our approach. We generalize the approach to accommodate high-dimensional multi-particle systems for potential applications in quantum information processing and quantum networks. Full article

The accurate identification of seismic faults, which serve as crucial fluid migration pathways in hydrocarbon reservoirs, is of paramount importance for reservoir characterization. Traditional interpretation is inefficient. It also struggles with complex geometries, failing to meet the current exploration demands. Deep learning boosts fault identification significantly but struggles with edge accuracy and noise robustness. To overcome these limitations, this research introduces SwiftSeis-AWNet, a novel lightweight and high-precision network. The network is based on an optimized MedNeXt architecture for better fault edge detection. To address the noise from simple feature fusion, a Semantics and Detail Infusion (SDI) module is integrated. Since the Hadamard product in SDI can cause information loss, we engineer an Attention-Weighted Semantics and Detail Infusion (AWSDI) module that uses dynamic multi-scale feature fusion to preserve details. Validation on field seismic datasets from the Netherlands F3 and New Zealand Kerry blocks shows that SwiftSeis-AWNet mitigates challenges like the loss of small-scale fault features and misidentification of fault intersection zones, enhancing the accuracy and geological reliability of automated fault identification. Full article

Grains and their derivatives play a crucial role as staple foods for the global population. Identifying grains in the food chain that are free from mycotoxin contamination is essential. Researchers have explored various traditional detection methods to address this concern. However, as grain consumption becomes increasingly time-sensitive and dynamic, traditional approaches face growing limitations. In recent years, emerging techniques—particularly molecular-based vibrational spectroscopy methods such as visible–near-infrared (Vis–NIR), near-infrared (NIR), Raman, mid-infrared (MIR) spectroscopy, and hyperspectral imaging (HSI)—have been applied to assess fungal contamination in grains and their products. This review summarizes research advances and applications of vibrational spectroscopy in detecting mycotoxins in grains from 2019 to 2025. The fundamentals of their work, information acquisition characteristics and their applicability in food matrices were outlined. The findings indicate that vibrational spectroscopy techniques can serve as valuable tools for identifying fungal contamination risks during the production, transportation, and storage of grains and related products, with each technique suited to specific applications. Given the close link between grain-based foods and humans, future efforts should further enhance the practicality of vibrational spectroscopy by simultaneously optimizing spectral analysis strategies across multiple aspects, including chemometrics, model transfer, and data-driven artificial intelligence. Full article

The architecture, engineering, and construction (AEC) industry faces challenges related to inefficiencies and fragmentation that highlight the need for advanced construction technologies and drive interest in innovative solutions such as the platform approach to design. This study assessed platform-based building design through (1) interviews with practitioners from China, Jordan, and the UK, which helped to define the platform approach in the AEC industry and the challenges involved, and (2) a residential building design simulation conducted to evaluate the potential of the platform approach. The simulated design’s materials costs, energy efficiency, and construction time were compared with those of the traditional building design. The results of the comparison corroborate the interview findings concerning practitioners’ perspectives on platform definition, benefits, challenges, and implementation. The findings also demonstrate the potential of the platform approach to enhance productivity and scalability through modularization, kit-of-parts configuration, and standardization. This research bridges the gap between theory and practice by supporting shareholder perspectives on building design and construction with the results of a simulated platform approach to a real-world design project. This research addresses the urgent need to better understand and test the platform approach to achieve material, energy, and construction time savings through collaborative and practice-informed design. Full article

In the industrial production of polytetrafluoroethylene (PTFE), accurately recognizing the liquid state within the coagulation vessel is critical to achieving better product quality and higher production efficiency. However, the complex and subtle changes in the coagulation process pose significant challenges for traditional sensing methods, calling for more reliable visual approaches that can handle varying scales and dynamic state changes. This study proposes a multi-branch deep learning framework for classifying the liquid state of PTFE emulsions based on high-resolution images captured in real-world factory conditions. The framework incorporates multi-scale feature extraction through a three-branch network and introduces a frequency–channel attention module to enhance feature discrimination. To address optimization challenges across branches, contrastive learning is employed for deep supervision, encouraging consistent and informative feature learning. The experimental results show that the proposed method significantly improves classification accuracy, achieving a mean F1-score of 94.3% across key production states. This work demonstrates the potential of deep learning-based visual classification methods for improving automation and reliability in industrial production. Full article

The accurate detection of surface defects in bamboo is critical to maintaining product quality. Traditional inspection methods rely heavily on manual labor, making the manufacturing process labor-intensive and error-prone. To overcome these limitations, TEB-YOLO is introduced in this paper, a lightweight and efficient defect detection model based on YOLOv5s. Firstly, EfficientViT replaces the original YOLOv5s backbone, reducing the computational cost while improving feature extraction. Secondly, BiFPN is adopted in place of PANet to enhance multi-scale feature fusion and preserve detailed information. Thirdly, an Efficient Local Attention (ELA) mechanism is embedded in the backbone to strengthen local feature representation. Lastly, the original CIoU loss is replaced with EIoU loss to enhance localization precision. The proposed model achieves a precision of 91.7% with only 10.5 million parameters, marking a 5.4% accuracy improvement and a 22.9% reduction in parameters compared to YOLOv5s. Compared with other mainstream models including YOLOv5n, YOLOv7, YOLOv8n, YOLOv9t, and YOLOv9s, TEB-YOLO achieves precision improvements of 11.8%, 1.66%, 2.0%, 2.8%, and 1.1%, respectively. The experiment results show that TEB-YOLO significantly improves detection precision and model lightweighting, offering a practical and effective solution for real-time bamboo surface defect detection. Full article

Background: The transition to renewable energy is intensifying demand for lithium-ion batteries (LIBs), thereby increasing the need for sustainable lithium sourcing. Traditional mining practices pose environmental and health risks, which can be mitigated through efficient end-of-life recycling systems. Methods: This study proposes a modified lithium reverse logistics network that decentralizes black-mass production at distributed facilities before centralized extraction, contrasting with conventional models that transport raw LIBs directly to central processing sites. Using the United States as a case study, two mathematical optimization (mixed-integer linear programming) models were developed to compare the traditional and modified networks in terms of cost efficiency and carbon emissions. Results: The model indicates that the proposed network significantly reduces both operational costs and emissions. Conclusions: This study highlights its potential to support a greener economy and inform policy development. Full article

The field of metal additive manufacturing has witnessed significant growth in recent years, with technology offering the ability to produce complex geometries that are challenging to manufacture using the traditional methods. In situ monitoring and control of the manufacturing process are crucial for increasing the production capacity and improving the quality of manufactured parts. This article provides a comparative analysis of computational, indirect, and direct methods for in situ temperature monitoring during additive manufacturing of metal alloy components. Furthermore, it discusses the current status, recent improvements, and perspectives for in situ temperature measurements. The basic principles of thermal imaging, two-color pyrometry, and millimeter-wave radiometry are explored, highlighting their limitations for addressing challenges related to material emissivity and rapid changes in building material composition. Overcoming the challenges related to the inaccessibility of the chamber where the parts are formed, direct temperature measurements would allow for the integration of collected information into big data systems. Within the framework of Industry 4.0, this approach offers a viable alternative to the conventional metal shaping processes, improving the production capacity and part quality. This research aims to contribute to ongoing advancements in metal additive manufacturing and its potential to completely replace traditional metal casting practices in the Industry 4.0 era. Full article

Throughout the generations, traditional academic writing skills development has taught students in socio-human programs to express their knowledge and thoughts with an evidence-based foundation, helping them make a special connection with their professional fields. However, a lack of digital learning and writing resources in this process has been identified. This study of the social work field connects digital academic writing, social protection functionality, and research innovations, identifying and exploring open-access (OA) educational and social resources for social work higher education (SWHE). Applying content analyses to online documents and websites, we identified key terms characteristic of social work, following a standard approach on formulating research questions, identifying categories, creating a code book, sampling, and measuring information. The research questions were as follows: How is digital academic writing being developed in social work education programs in Romanian universities? Where do researchers, students, teachers, and professionals gather OA digital information and data for academic innovation? What kind of OA information and data are contained in websites for academic writing? We also used OA socio-educational resource analysis to derive digital, evidence-based, and academic writing codes. The frequencies of these elements in documents and websites were examined. Professional samples of four OA documents and five academic and non-academic Romanian websites with extensions were processed. Furthermore, information from a non-academic official website concerning social protection functionality was observed, identified, and measured. We concluded that academic writing is not included as an independent course in the curricula of Romanian social work programs at universities; this topic is rarely researched. Digital and evidence-based education is also a marginalized topic in socio-human scientific resources. OA information, laws, reports, and statistics were identified. Information on scientific research, academic–non-academic partnerships, descriptions of good practices, and human resources information was lacking. In conclusion, this study contributes to increasing productivity and developing digital academic skills in social work education and research. Full article

Accurate regional-scale mapping of soil organic matter (SOM) is crucial for land productivity management and global carbon pool monitoring. Current remote sensing inversion of SOM faces challenges, including the underutilization of temporal information and low feature selection efficiency. To address these limitations, this study developed an integrated framework combining multi-temporal Landsat imagery, field-measured SOM data, intelligent feature optimization, and machine learning. The framework employs two novel image-processing strategies: the Maximum Annual Bare-Soil Composite (MABSC) method to extract background spectral information and the Multi-temporal Feature Optimization Composite (MFOC) method to capture seasonal and environmental dynamics. These features, along with topographic covariates, were processed using an improved Feature-Optimized and Interpretable XGBoost (FOI-XGB) model for key variable selection and spatial mapping. Validation across two subtropical coastal mountainous regions at different scales in southeastern China demonstrated the framework’s effectiveness and robustness. Key findings include the following: (1) Both the MABSC-derived spectral bands and the MFOC-optimized indices significantly outperformed traditional single-season approaches. Their combined use achieved a moderate SOM inversion accuracy (R² = 0.42–0.44). (2) The FOI-XGB model substantially outperformed traditional feature selection methods (Pearson, SHAP, and CorrSHAP), achieving significant regional R² improvements ranging from 9.72% to 88.89%. (3) The optimal model integrating the MABSC-derived features, MFOC-optimized indices, and topographic covariates attained the highest accuracy (R² up to 0.51). This represents major improvements compared with using topographic covariates alone (R² increase of up to 160.11%) or the combined spectral features (MABSC + MFOC) alone (R² increase of up to 15.91%). This study provides a robust, scalable, and practical technical solution for accurate SOM mapping in complex environments, with significant implications for sustainable land management and carbon monitoring. Full article

Endometrial carcinoma (EC) is the most common gynaecological malignancy in developed nations, exhibiting significant molecular heterogeneity that impacts prognosis and treatment response, particularly in advanced or recurrent settings. Traditional classification is increasingly supplemented by molecular subtyping (POLE-ultramutated, MSI-high/dMMR, NSMP, p53-mutated/CNH), which provides crucial prognostic information and predicts benefit from immunotherapy. This review summarizes the landscape of predictive biomarkers for immune checkpoint inhibitor (ICI) therapy in EC, emphasizing a new therapeutic scenario for advanced and recurrent EC. Mismatch repair deficiency (dMMR) or high microsatellite instability (MSI-H), leading to high tumor mutational burden (TMB) and increased neoantigen production, is the most established predictor, resulting in FDA approvals for pembrolizumab and dostarlimab in this subgroup. POLE mutations also confer hypermutation and high immunogenicity, predicting a favorable ICI response. Other biomarkers, including PD-L1 expression and TMB, show variable correlation with response and require further standardization. The tumor immune microenvironment, including tumor-infiltrating lymphocytes (TILs), also influences treatment outcomes. Clinical trials have demonstrated significant survival benefits for ICIs combined with chemotherapy (e.g., dostarlimab/pembrolizumab + carboplatin/paclitaxel) in first-line settings, especially for dMMR/MSI-H EC, and for ICI combinations with targeted agents (e.g., lenvatinib + pembrolizumab) in previously treated patients. Integrating molecular classification and validated biomarkers is essential for optimizing patient selection and developing personalized immunotherapy strategies for EC. Full article