Search Results (4,829)

Rural landscape character assessment (LCA) is significant for identifying and understanding rural landscapes and maintaining the cultural connotations of the rural vernacular. Taking the rural area of Songzi City as an example, this study identifies the landscape character (LC) and analyzes the coupling between the current state of its LC and a construction project based on the depth of rural landscape planning in the county and combining the ecology, arable land, and water body protection boundary as constraints. Thus, we obtain the “point, line, and surface” site selection suggestions for the construction activities of leisure agriculture, power grid, and energy facilities, and the zoning classification and layout control strategies for LC are subsequently proposed. The results show the following: (1) The county LC factor is a combination of natural and human factors used to obtain 165 LC areas in Songzi City. (2) The current state of rural LC is used to determine LCs from shallow to deep and to provide the basis for index selection and judgment for evaluation. (3) The coupling relationship between rural LC and construction projects varies and must be judged using subjective and objective methods, desktop research combined with field analyses, and multi-stakeholder participation. Based on the perspective of coupling and coordinating human and landscape, this study applies local-scale LCA to practice, strengthens the interface with rural construction planning, and provides research ideas and methodological references for the sustainable control of rural LC. Full article

Background: Systematic reviewers face a growing body of biomedical literature, making early-stage article screening increasingly time-consuming. In this study, we assessed six large language models (LLMs)—OpenHermes, Flan T5, GPT-2, Claude 3 Haiku, GPT-3.5 Turbo, and GPT-4o—for their ability to identify randomized controlled trials (RCTs) in datasets of increasing difficulty. Methods: We first retrieved articles from PubMed and used all-mpnet-base-v2 to measure semantic similarity to known target RCTs, stratifying the collection into quartiles of descending relevance. Each LLM then received either verbose or concise prompts to classify articles as “Accepted” or “Rejected”. Results: Claude 3 Haiku, GPT-3.5 Turbo, and GPT-4o consistently achieved high recall, though their precision varied in the quartile with the highest similarity, where false positives increased. By contrast, smaller or older models struggled to balance sensitivity and specificity, with some over-including irrelevant studies or missing key articles. Importantly, multi-stage prompts did not guarantee performance gains for weaker models, whereas single-prompt approaches proved effective for advanced LLMs. Conclusions: These findings underscore that both model capability and prompt design strongly affect classification outcomes, suggesting that newer LLMs, if properly guided, can substantially expedite systematic reviews. Full article

This study explores existing research on neural networks, fuzzy logic-based models, and genetic algorithms applied to brain tumor classification. A systematic review of 53 studies was conducted following PRISMA guidelines, covering search strategy, selection criteria, quality assessment, and data extraction. Articles were collected from three scientific databases: Web of Science, Scopus, and IEEE. The review primarily focuses on practical contributions, with most studies emphasizing applications over conceptual insights. Key methods in the field demonstrate significant impact and innovation. Commonly used training and testing mechanisms include dataset splitting, augmentation, and validation techniques, highlighting their widespread adoption for performance evaluation. The analysis of evaluation metrics shows that accuracy and the DICE score are the most frequently used, alongside sensitivity, specificity, recall, and other domain-specific measures. The variety of metrics underscores the need for tailored approaches based on dataset characteristics and research objectives. By highlighting trends, challenges, and research gaps, this review provides actionable insights for advancing BTC research. It offers a comprehensive overview of techniques and evaluation methods to guide future developments in this critical domain. Full article

Sea ice plays a critical role in the global climate system and maritime operations, making timely and accurate classification essential. However, traditional manual methods are time-consuming, costly, and have inherent biases. Automating sea-ice type classification addresses these challenges by enabling faster, more consistent, and scalable analysis. While both traditional and deep-learning approaches have been explored, deep-learning models offer a promising direction for improving efficiency and consistency in sea-ice classification. However, the absence of a standardized benchmark and comparative study prevents a clear consensus on the best-performing models. To bridge this gap, we introduce IceBench, a comprehensive benchmarking framework for sea-ice type classification. Our key contributions are three-fold: First, we establish the IceBench benchmarking framework, which leverages the existing AI4Arctic Sea Ice Challenge Dataset as a standardized dataset, incorporates a comprehensive set of evaluation metrics, and includes representative models from the entire spectrum of sea-ice type-classification methods categorized in two distinct groups, namely pixel-based classification methods and patch-based classification methods. IceBench is open-source and allows for convenient integration and evaluation of other sea-ice type-classification methods, hence facilitating comparative evaluation of new methods and improving reproducibility in the field. Second, we conduct an in-depth comparative study on representative models to assess their strengths and limitations, providing insights for both practitioners and researchers. Third, we leverage IceBench for systematic experiments addressing key research questions on model transferability across seasons (time) and locations (space), data downsampling, and preprocessing strategies. By identifying the best-performing models under different conditions, IceBench serves as a valuable reference for future research and a robust benchmarking framework for the field. Full article

Precision agriculture is an approach that uses information technologies to improve and optimize agricultural production. It is based on the collection and analysis of agricultural data to support decision making in agricultural processes. In recent years, Artificial Neural Networks (ANNs) have demonstrated significant benefits in addressing precision agriculture needs, such as pest detection, disease classification, crop state assessment, and soil quality evaluation. This article aims to perform a systematic literature review on how ANNs with an emphasis on image processing can assess if fruits such as mango, apple, lemon, and coffee are ready for harvest. These specific crops were selected due to their diversity in color and size, providing a representative sample for analyzing the most commonly employed ANN methods in agriculture, especially for fruit ripening, damage, pest detection, and harvest prediction. This review identifies Convolutional Neural Networks (CNNs), including commonly employed architectures such as VGG16 and ResNet50, as highly effective, achieving accuracies ranging between 83% and 99%. Additionally, it discusses the integration of hardware and software, image preprocessing methods, and evaluation metrics commonly employed. The results reveal the notable underuse of vegetation indices and infrared imaging techniques for detailed fruit quality assessment, indicating valuable opportunities for future research. Full article

Pain assessment is a challenging task for clinicians due to its subjective nature, particularly in individuals with communication difficulties, cognitive impairments, or severe disabilities. Traditional methods such as the Visual Analogue Scale (VAS), Numerical Rating Scale (NRS), and Verbal Rating Scale (VRS) rely heavily on patient feedback, which can be inconsistent and subjective. To address these limitations, developing objective and reliable pain assessment tools that incorporate advanced technologies, such as multimodal data integration from video and fNIRS, is important for improving clinical outcomes. However, challenges such as noise susceptibility in fNIRS signals must be carefully addressed to realize their full potential. Recent studies have explored automatic pain assessment using machine learning and deep learning techniques, which require high-quality data that can accurately represent pain categories. In response to the introduction of a new dataset in the AI4Pain Challenge, we proposed a multimodal neural network model utilizing attention-based fusion to improve overall accuracy (MMAPA). Our model leverages video and fNIRS modalities as well as manually extracted statistical features. We also implemented fNIRS signal preprocessing and artifact noise filtering, which significantly improved performance on both the fNIRS and statistical feature branches. On the hidden test set, our model achieved an accuracy of 51.33%, outperforming the official baseline of 43.33%. To evaluate generalizability, we further tested our method on the BioVid Heat Pain Database, where our fusion model achieved the highest accuracy in the 10-fold cross-validation setting, outperforming PainAttNet and unimodal variants. These results highlight the effectiveness of our multimodal attention-based approach in improving pain classification performance across datasets. Full article

Benggangs, a type of soil erosion widely distributed in the hilly and mountainous regions of South China, pose significant challenges to land management and ecological conservation. Accurate identification and assessment of their location and scale are essential for effective Benggang control. With advancements in technology, deep learning has emerged as a critical tool for Benggang classification. However, selecting suitable feature extraction and fusion methods for multi-source image data remains a significant challenge. This study proposes a Benggang classification method based on multiscale features and a two-stream fusion network (MS-TSFN). Key features of targeted Benggang areas, such as slope, aspect, curvature, hill shade, and edge, were extracted from Digital Orthophotography Map (DOM) and Digital Surface Model (DSM) data collected by drones. The two-stream fusion network, with ResNeSt as the backbone, extracted multiscale features from multi-source images and an attention-based feature fusion block was developed to explore complementary associations among features and achieve deep fusion of information across data types. A decision fusion block was employed for global prediction to classify areas as Benggang or non-Benggang. Experimental comparisons of different data inputs and network models revealed that the proposed method outperformed current state-of-the-art approaches in extracting spatial features and textures of Benggangs. The best results were obtained using a combination of DOM data, Canny edge detection, and DSM features in multi-source images. Specifically, the proposed model achieved an accuracy of 92.76%, a precision of 85.00%, a recall of 77.27%, and an F1-score of 0.8059, demonstrating its adaptability and high identification accuracy under complex terrain conditions. Full article

Machine learning (ML) has emerged as a powerful tool in transformer condition assessment, enabling more accurate diagnostics by leveraging historical test data. However, imbalanced datasets, often characterized by limited samples in poor transformer conditions, pose significant challenges to model performance. This study investigates the application of oversampling techniques to enhance ML model accuracy in predicting the Health Index of transformers. A dataset comprising 3850 transformer tests collected from utilities across Indonesia was used. Key parameters, including oil quality, dissolved gas analysis, and paper condition factors, were employed as inputs for ML modeling. To address the class imbalance, various oversampling methods, such as the Synthetic Minority Oversampling Technique (SMOTE), Borderline-SMOTE, SMOTE-Tomek, and SMOTE-ENN, were implemented and compared. This study explores the impact of these techniques on model performance, focusing on classification accuracy, precision, recall, and F1-score. The results reveal that all SMOTE-based methods improved model performance, with SMOTE-ENN yielding the best outcomes. It significantly reduced classification errors, particularly for minority classes, ensuring better predictive reliability. These findings underscore the importance of advanced oversampling techniques in improving transformer diagnostics. By effectively addressing the challenges posed by imbalanced datasets, this research provides a robust framework for applying ML in transformer condition monitoring and other domains with similar data constraints. Full article

Background/Objectives: The overuse and misuse of antibiotics has contributed significatively to the growing problem of the emergence and spread of antibiotic resistance genes among bacteria, posing a serious global challenge to the treatment of bacterial infectious diseases. For these reasons, there is a current and growing interest in the development of effective alternative or complementary strategies to antibiotic therapy for the prevention of fish diseases, which are mainly based on the use of probiotics—in particular, those belonging to the Lactic Acid Bacteria (LAB) group. In this context, the aim of the present study was to characterise, evaluate the genetic diversity and assess the safety of candidate probiotic LAB strains for aquaculture isolated from faeces and intestines of European hakes (Merluccius merluccius, L.) caught in the Northeast Atlantic Ocean (Ireland). Methods: The direct antimicrobial activity of the LAB isolates was tested by the Stab-On-Agar method against key ichthyopathogens. Subsequently, their taxonomic classification and genetic diversity were determined by 16SrDNA sequencing and Enterobacterial Repetitive Intergenic Consensus-PCR (ERIC-PCR), respectively. To ensure the in vitro safety of the LAB isolates, their biofilm-forming ability was assessed by a microtiter plate assay; their sensitivity to major antibiotics used in aquaculture, human and veterinary medicine by a broth microdilution method and their haemolytic and gelatinase activity by microbiological assays. Results: All LAB isolates were biofilm producers and susceptible to chloramphenicol, oxytetracycline, flumequine and amoxicillin. A total of 30 isolates (85.7%) were resistant to at least one of the tested antibiotics. None of the 35 LAB isolates showed haemolytic or proteolytic activity. Conclusions: Among the isolated strains, five LAB strains exhibiting the highest antimicrobial activity against aquaculture-relevant ichthyopathogens, taxonomically identified as Streptococcus salivarius, Enterococcus avium and Latilactobacillus sakei, were selected for further characterisation as potential probiotic candidates to promote sustainable aquaculture. To our knowledge, this is the first study to report that hake intestines and faeces represent viable ecological niches for the isolation of LAB strains with antimicrobial activity. Full article

The scarcity of information on agricultural development in the semi-arid region of Alagoas limits the spatial understanding of this activity. Government data are generally numerical and lack spatial detail. Remote sensing emerges as an efficient alternative, providing accessible visualization of agricultural areas. This study evaluates the performance of MapBiomas in monitoring agricultural areas in the semi-arid region of Alagoas, comparing it to a Random Forest model adjusted for the region using higher-resolution images. The first methodology is based on land use and land cover (LULC) data from MapBiomas, an initiative that provides information on land use and land cover in Brazil. The second method employs the Random Forest model, calibrated for the region’s dry season, addressing cloud cover issues and allowing for the identification of irrigated agriculture. LULC data were subjected to a precision analysis using 200 points generated within the study areas, extracting LULC information for each coordinate. These points were overlaid on high-resolution images to assess model accuracy. Additionally, field visits were conducted to validate the identification of agriculture. The irrigated area data from the Random Forest model were correlated with irrigation records from SEMARH. MapBiomas presented a Kappa index of 0.74, with precision exceeding 90% for classes such as forest, natural pasture, non-vegetated area, and water bodies. However, the agriculture class obtained an F1 score of 0.56. The Random Forest model achieved a Kappa index of 0.82, with an F1 score of 0.79 for agriculture. The correlation between the total annual irrigated area data from Random Forest and SEMARH records was high (R = 0.85). The Random Forest model yielded better results in classifying agriculture in the semi-arid region of Alagoas compared to MapBiomas. However, classification limitations were observed in lowland areas due to spectral confusion caused by soil moisture accumulation. Full article

Background: In recent years, there has been an exponential growth in global anti-cancer drug research, prompting the necessity for comprehensive analyses of publication output and thematic shifts. Methods: This study utilized a comprehensive set of PubMed records from 1962 to 2024 and examined growth patterns, content classification, and co-occurrence of key pharmacological and molecular terms. Results: Our results highlight an exponential rise in publications, with an annual compound growth rate of over 14%, influenced by advancements in digital knowledge sharing and novel therapeutic breakthroughs. A pronounced surge occurred during the COVID-19 pandemic, suggesting a sustained shift in research dynamics. The content analyses revealed a strong emphasis on classical chemotherapeutic agents—often studied in combination with targeted therapies or immunotherapies—and a growing focus on immune checkpoint inhibitors and vaccine platforms. Furthermore, co-occurrence networks indicated robust links between chemotherapy and supportive care, as well as emerging synergies between immuno-oncology, precision medicine approaches. Conclusions: Our study suggests that while novel modalities are reshaping treatment paradigms, chemotherapy remains central, underscoring the value of integrative regimens. This trend toward personalized, combination-based strategies indicates a transformative era in oncology research, where multidimensional data assessment is instrumental in guiding future therapeutic innovations. Full article

Background/Objectives: A missed periprosthetic joint infection (PJI) diagnosis can lead to implant failure. However, to date, no gold standard for PJI diagnosis exists, although several classification scores have been developed in the past years. The primary objective of the study was the evaluation of inter-rater reliability between five PJI classification systems when defining a patient who is infected. Two secondary outcomes were further examined: the inter-rater reliability assessed by comparing the classifications in pairs, and the evaluation of each classification system within the subcategories defined by the World Association against Infection in Orthopaedics and Trauma (WAIOT) definition. Methods: Retrospectively collected data on patients with knee and hip PJIs were used to assess the agreement among five PJI scoring systems: the Musculoskeletal Infection Society (MSIS) 2013 definition, the Infection Consensus Group (ICG) 2018 definition, the European Bones and Joints Infection Society (EBJIS) 2018 definition, the WAIOT definition, and the EBJIS 2021 definition. Results: In total, 203 patients with PJI were included in the study, and the agreement among the examined scores was 0.90 (Krippendorff’s alpha = 0.81; p-value < 0.001), with the MSIS 2013 and ICG 2018 classification systems showing the highest agreement (Cohen’s Kappa = 0.91; p-value < 0.001). Conclusions: There is a strong agreement between the major PJI classification systems. However, a subset of patients (n = 11, 5.42%) still falls into a diagnostic grey zone, especially in cases of low-grade infections. This highlights the need for enhanced diagnostic criteria that incorporate tools that are available even with limited resources, and the potential of artificial intelligence-based techniques in improving early detection and management of PJIs. Full article

With the rapid advancement of the civil aviation sector and the concurrent expansion of pilot training programs, a pressing need arises for more efficient assessment methodologies during the pilot training process. Traditional written evaluations conducted by flight instructors are often marred by subjectivity and inefficiency, rendering them inadequate to satisfy the stringent demands of Competency-Based Training and Assessment (CBTA) frameworks. To address this challenge, this study presents a novel multi-label classification model that seamlessly integrates RoBERTa, a robust language model, with Graph Convolutional Networks (GCNs). By simultaneously modeling text features and label interdependencies, this model enables the automated, multi-dimensional classification of instructor evaluations. It incorporates a dynamic weight fusion strategy, which intelligently adjusts the output weights of RoBERTa and GCNs based on label correlations. Additionally, it introduces a label co-occurrence graph convolution layer, designed to capture intricate higher-order dependencies among labels. This study is based on a real-world dataset comprising 1078 evaluations and 158 labels, covering six major dimensions, including operational capabilities and communication skills. To provide context for the improvement, the proposed RoBERTa + GCN model is compared with key baseline models, such as BERT and LSTM. The results show that the RoBERTa + GCN model achieves an F1 score of 0.9737, representing an average improvement of 4.73% over these traditional methods. This approach enhances the consistency and efficiency of flight training assessments and provides new insights into integrating natural language processing and graph neural networks, demonstrating broad application prospects. Full article

Transport networks are crucial for economic growth, yet their sustainability is increasingly threatened by natural hazards. Recent floods in Italy have highlighted the vulnerability of rail and road infrastructure, causing severe damage and economic losses. The Gargano Promontory in northern Apulia has experienced frequent hydrogeological disruptions over the past decade, significantly affecting bridges and the railway network managed by Ferrovie del Gargano s.r.l. (FdG). However, structural interventions are complex, time-consuming, costly, and involve certain risks. To enhance sustainability and comply with railway safety regulations, FdG has adopted non-structural measures to improve hydrogeological risk classification and management. Despite the prevalence of flood events, the existing literature often overlooks crucial technical aspects, which this study addresses. The HYD.RAIL (HYDraulic Risk Assessment for Infrastructure and Lane) research project aims to improve transport infrastructure resilience by refining hydraulic risk assessments and introducing new classification parameters. HYD.RAIL employs a multicriteria approach, integrating parameters defined in collaboration with railway professionals. This paper presents the initial framework, offering a methodology to identify, classify, and manage hydrogeological risks in transportation infrastructure. Compared to standard methods, which lack detailed risk classification, HYD.RAIL enables more precise flood risk mapping. For example, high-risk points were reduced from 37 to 6 locations on Line 1 and from 134 to 50 on Line 2 using HYD.RAIL. This approach enhances flood risk management efficiency, providing railway operators with a more accurate understanding of infrastructure vulnerabilities. Full article

Background/Objectives: Chronic obstructive pulmonary disease (COPD) remains a leading cause of death worldwide, with emphysema progression providing valuable insights into disease development. Clinical assessment approaches, including pulmonary function tests and high-resolution computed tomography, are limited by accessibility constraints and radiation exposure. This study, therefore, proposed an alternative approach by integrating the novel biomarker long non-coding interleukin-7 receptor α-subunit gene (lnc-Il7R), along with other easily accessible clinical and biochemical metrics, into machine learning (ML) models. Methods: This cohort study collected baseline characteristics, COPD Assessment Test (CAT) scores, and biochemical details from the enrolled participants. Associations with emphysema severity, defined by a low attenuation area percentage (LAA%) threshold of 15%, were evaluated using simple and multivariate-adjusted models. The dataset was then split into training and validation (80%) and test (20%) subsets. Five ML models were employed, with the best-performing model being further analyzed for feature importance. Results: The majority of participants were elderly males. Compared to the LAA% <15% group, the LAA% ≥15% group demonstrated a significantly higher body mass index (BMI), poor pulmonary function, and lower expression levels of lnc-Il7R (all p < 0.01). Fold changes in lnc-IL7R were strongly and negatively associated with LAA% (p < 0.01). The random forest (RF) model achieved the highest accuracy and area under the receiver operating characteristic curve (AUROC) across datasets. A feature importance analysis identified lnc-IL7R fold changes as the strongest predictor for emphysema classification (LAA% ≥15%), followed by CAT scores and BMI. Conclusions: Machine learning models incorporated accessible clinical and biochemical markers, particularly the novel biomarker lnc-IL7R, achieving classification accuracy and AUROC exceeding 75% in emphysema assessments. These findings offer promising opportunities for improving emphysema classification and COPD management. Full article