Search Results (730)

Enterprise document management faces a significant challenge: traditional clustering methods focus solely on content similarity while ignoring organizational context, such as priority, workflow status, and temporal relevance. This paper introduces FLACON (Flag-Aware Context-sensitive Clustering), an information-theoretic approach that captures multi-dimensional document context through a six-dimensional flag system encompassing Type, Domain, Priority, Status, Relationship, and Temporal dimensions. FLACON formalizes document clustering as an entropy minimization problem, where the objective is to group documents with similar contextual characteristics. The approach combines a composite distance function—integrating semantic content, contextual flags, and temporal factors—with adaptive hierarchical clustering and efficient incremental updates. This design addresses key limitations of existing solutions, including context-aware systems that lack domain-specific intelligence and LLM-based methods that require prohibitive computational resources. Evaluation across nine dataset variations demonstrates notable improvements over traditional methods, including a 7.8-fold improvement in clustering quality (Silhouette Score: 0.311 vs. 0.040) and performance comparable to GPT-4 (89% of quality) while being ~7× faster (60 s vs. 420 s for 10 K documents). FLACON achieves $O\left(mlogn\right)$ complexity for incremental updates affecting $m$ documents and provides deterministic behavior, which is suitable for compliance requirements. Consistent performance across business emails, technical discussions, and financial news confirms the practical viability of this approach for large-scale enterprise document organization. Full article

This study integrates network toxicology with molecular docking technology to systematically elucidate the key molecular mechanisms and signaling pathways by which bisphenol A (BPA) induces obesity. By cross-referencing multiple databases—including the Comparative Toxicogenomics Database (CTD), SwissTarget prediction platform, and PharmMapper—potential BPA target genes were identified, yielding a total of 1326 candidate targets. Obesity-related genes were collected from GeneCards and OMIM databases, yielding 4570 disease-associated targets. Among these, 653 overlapping genes were identified as potential mediators linking BPA exposure to obesity. Protein interaction networks were constructed using STRING and Cytoscape, and the MCC algorithm identified five core hub genes: STAT3, MYC, TP53, IL6, and mTOR. Validation using random datasets demonstrated significant upregulation of these genes in the obesity group (p < 0.05), highlighting their potential central role in BPA-induced obesity effects. Functional enrichment analysis via GO and KEGG pathways indicated that BPA may promote obesity by interfering with endocrine signaling, activating lipid metabolism, and stimulating atherosclerosis pathways. Molecular docking analysis using CB-Dock2 confirmed strong binding affinity between BPA and core targets, providing structural evidence for their potential interactions. This study elucidates the potential biological mechanism by which BPA exacerbates obesity through endocrine disruption and metabolic reprogramming, employing a multidimensional approach encompassing cross-target analysis, pathway enrichment, and molecular interactions. It provides an innovative systems toxicology framework and empirical basis for assessing metabolic health risks induced by environmental pollutants. Full article

Geolocating Twitter users from social media data holds significant value in applications such as targeted advertising, disaster response, and social network analysis. However, existing social network-based geolocation methods tend to focus primarily on mention relations while neglecting other critical interactions like retweet relationships. Moreover, effectively integrating diverse social features remains a key challenge, which limits the overall performance of geolocation models. To address these issues, this paper proposes a novel Twitter user geolocation method based on multi-graph feature fusion with a gating mechanism, termed MGFGCN, which fully leverages heterogeneous social network information. Specifically, MGFGCN first constructs separate mention and retweet graphs to capture multi-dimensional user relationships. It then incorporates the Information Gain Ratio (IGR) to select discriminative keywords and generates Term Frequency–Inverse Document Frequency (TF-IDF) features, thereby enhancing the semantic representation of user nodes. Furthermore, to exploit complementary information across different graph structures, we propose a Structure-aware Gated Fusion Mechanism (SGFM) that dynamically captures differences and interactions between nodes from each graph, enabling the effective fusion of node representations into a unified representation for subsequent location inference. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art baselines in the Twitter user geolocation task across two public datasets. Full article

This paper investigates the risk determinants and spatial patterns of tax revenue loss due to illicit tobacco consumption across the 27 EU Member States from 2017 to 2022. Using a panel dataset covering economic, demographic, social, political, and behavioral dimensions, we apply principal component analysis to identify key factors associated with revenue loss, and hierarchical clustering to group countries with similar risk profiles. Geographic Information Systems visualize the spatial heterogeneity of fiscal vulnerabilities. Findings reveal that institutional and economic stability, international trade and market share, socio-economic inequality and tax burdens, health and well-being, demographic aging and social dynamics, tobacco taxation policy, and labor dynamics and shadow consumption structure the patterns of tax loss risk. Findings also highlight significant differences among Member States, emphasizing the multidimensional nature of fiscal risks. Full article

Background: The assessment of emotion recognition holds growing significance in research on the brain–computer interface and human–computer interaction. Among diverse physiological signals, electroencephalography (EEG) occupies a pivotal position in affective computing due to its exceptional temporal resolution and non-invasive acquisition. However, EEG signals are inherently complex, characterized by substantial noise contamination and high variability, posing considerable challenges to accurate assessment. Methods: To tackle these challenges, we propose a Triple Attention Network (TANet), a triple-attention EEG emotion recognition framework that integrates Conformer, Convolutional Block Attention Module (CBAM), and Mutual Cross-Modal Attention (MCA). The Conformer component captures temporal feature dependencies, CBAM refines spatial channel representations, and MCA performs cross-modal fusion of differential entropy and power spectral density features. Results: We evaluated TANet on two benchmark EEG emotion datasets, DEAP and SEED. On SEED, using a subject-specific cross-validation protocol, the model reached an average accuracy of 98.51 ± 1.40%. On DEAP, we deliberately adopted a segment-level splitting paradigm—in line with influential state-of-the-art methods—to ensure a direct and fair comparison of model architecture under an identical evaluation protocol. This approach, designed specifically to assess fine-grained within-trial pattern discrimination rather than cross-subject generalization, yielded accuracies of 99.69 ± 0.15% and 99.67 ± 0.13% for the valence and arousal dimensions, respectively. Compared with existing benchmark approaches under similar evaluation protocols, TANet delivers substantially better results, underscoring the strong complementary effects of its attention mechanisms in improving EEG-based emotion recognition performance. Conclusions: This work provides both theoretical insights into multi-dimensional attention for physiological signal processing and practical guidance for developing high-performance, robust EEG emotion assessment systems. Full article

Urban recreational spaces (URSs) are pivotal for enhancing resident well-being, making the accurate assessment of public perceptions crucial for quality optimization. Compared to traditional surveys, social media data provide a scalable means for multi-dimensional perception assessment. However, existing studies predominantly rely on single-modal data, which limits the comprehensive capturing of complex perceptions and lacks interpretability. To address these gaps, this study employs cutting-edge large vision–language models (LVLMs) and develops an interpretable model, Qwen2.5-VL-7B-SFT, through supervised fine-tuning on a manually annotated dataset. The model integrates visual-linguistic features to assess four perceptual dimensions of URSs: esthetics, attractiveness, cultural significance, and restorativeness. Crucially, we generate textual evidence for our judgments by identifying the key spatial elements and emotional characteristics associated with specific perceptions. By integrating multi-source built environment data with Optuna-optimized machine learning and SHAP analysis, we further decipher the nonlinear relationships between built environment variables and perceptual outcomes. The results are as follows: (1) Interpretable LVLMs are highly effective for urban spatial perception research. (2) URSs within Beijing’s Third Ring Road fall into four typologies, historical heritage, commercial entertainment, ecological-natural, and cultural spaces, with significant correlations observed between physical elements and emotional responses. (3) Historical heritage accessibility and POI density are identified as key predictors of public perception. Positive perception significantly improves when a block’s POI functional density exceeds 4000 units/km² or when its 500 m radius encompasses more than four historical heritage sites. Our methodology enables precise quantification of multidimensional URS perceptions, links built environment elements to perceptual mechanisms, and provides actionable insights for urban planning. Full article

This study explores the complex relationship between addiction and well-being among youth by examining social, behavioral, and economic factors. It aims to identify the key determinants influencing addiction and their impact on young individuals’ physical, mental, and social well-being. Utilizing a dataset including variables such as social isolation, academic decline, financial issues, and mental and physical health problems, the study applies correlation analysis and hierarchical clustering techniques to uncover significant patterns. The results reveal that behaviors like experimentation (ρ = 0.34), social isolation (ρ = 0.28), and financial stress (ρ = 0.22) are strongly associated with addiction. These findings suggest that early risk-taking behaviors, particularly experimentation, play a critical role in the development of addiction and highlight the importance of early intervention. Social and economic stressors are also key contributors, emphasizing the need for targeted prevention strategies. The study concludes that addiction among youth is a multidimensional issue requiring holistic responses, including enhanced social support, economic assistance, and improved access to healthcare. These insights can inform effective policies and interventions aimed at reducing addiction rates and promoting well-being in young populations. Full article

In the field of remote sensing (RS) object detection, efficient and accurate target recognition is crucial for applications such as national defense and maritime monitoring. However, existing detection methods either have high computational complexity, making them unsuitable for real-time applications, or suffer from feature redundancy issues that affect detection accuracy. To address these challenges, this paper proposes a Feature-Differentiated Perception (FDP) lightweight remote sensing object detection method, which optimizes computational efficiency while maintaining high detection accuracy. The proposed method introduces two critical innovations: (1) Dynamic mixed convolution (DM-Conv), which uses linear mapping to efficiently generate redundant feature maps, reducing convolutional computation. It combines features from different intermediate layers through weighted fusion, effectively reducing the number of channels and improving feature utilization. Channel refers to a single feature map in the multi-dimensional feature representation, where each channel corresponds to a specific feature pattern (e.g., edges, textures, or semantic information) learned by the network. (2) The Spatial Orthogonal Attention (SOA) mechanism, which enhances the ability to model long-range dependencies between distant pixels, thereby improving feature representation capability. Experiments on public remote sensing object detection datasets, including DOTA, HRSC2016, and UCMerced-LandUse, demonstrate that the proposed model achieves a significant reduction in computational complexity while maintaining nearly lossless detection accuracy. On the DOTA dataset, the proposed method achieves an mAP (mean Average Precision) of 79.37%, outperforming existing lightweight models in terms of both speed and accuracy. This study provides new insights and practical solutions for efficient remote sensing object detection in embedded and edge computing environments. Full article

The real estate industry, known for its complexity and exposure to systemic and idiosyncratic risks, requires increasingly sophisticated investment risk assessment tools. In this study, we present the Real Estate Construction Investment Risk (RECIR) model, a machine learning-based framework designed to quantify and manage multi-dimensional investment risks in construction projects. The model integrates diverse data sources, including macroeconomic indicators, property characteristics, market dynamics, and regulatory variables, to generate a composite risk metric called the total risk score. Unlike previous artificial intelligence (AI)-based approaches that primarily focus on forecasting prices, we incorporate regulatory compliance, forensic risk assessment, and explainable AI to provide a transparent and accountable decision support system. We train and validate the RECIR model using structured datasets such as the American Housing Survey and World Development Indicators, along with survey data from domain experts. The empirical results show the relatively high predictive accuracy of the RECIR model, particularly in highly volatile environments. Location score, legal context, and economic indicators are the dominant contributors to investment risk, which affirms the interpretability and strategic relevance of the model. By integrating AI with ethical oversight, we provide a scalable, governance-aware methodology for analyzing risks in the real estate sector. Full article

Federated learning has emerged as a promising approach for privacy-preserving model training across decentralized UAV swarm systems. However, challenges such as data heterogeneity, communication constraints, and limited computational resources significantly hinder convergence efficiency in real-world scenarios. This work introduces a communication-aware federated learning framework that integrates multi-dimensional cost modeling with dynamic client aggregation. The proposed cost function jointly considers communication overhead, computation latency, and training contribution. A Shapley-inspired client evaluation mechanism is incorporated to guide aggregation by prioritizing high-impact participants. In addition, a two-phase training strategy is devised to balance learning accuracy and resource efficiency across different training stages. Experimental results on the MNIST and CIFAR-10 benchmark datasets under non-IID settings demonstrate that the proposed method achieves faster convergence, higher accuracy, and reduced communication-computation cost. These results highlight its suitability for deployment in bandwidth-constrained, resource-limited UAV edge environments. Full article

Three-dimensional fragment assembly technology has significant application value in fields such as cultural relic restoration, medical image analysis, and industrial quality inspection. To address the common challenges of limited feature representation ability and insufficient assembling accuracy in existing methods, this paper proposes a geometry-aware hierarchical fragment assembly framework (GeoAssemble). The core contributions of our work are threefold: first, the framework utilizes DGCNN to extract local geometric features while integrating centroid relative positions to construct a multi-dimensional feature representation, thereby enhancing the identification quality of fracture points; secondly, it designs a two-stage matching strategy that combines global shape similarity coarse matching with local geometric affinity fine matching to effectively reduce matching ambiguity; finally, we propose an auxiliary transformation estimation mechanism based on the geometric center of fracture point clouds to robustly initialize pose parameters, thereby improving both alignment accuracy and convergence stability. Experiments conducted on both synthetic and real-world fragment datasets demonstrate that this method significantly outperforms baseline methods in matching accuracy and exhibits higher robustness in multi-fragment scenarios. Full article

Undergraduate dropout is a multidimensional phenomenon with implications for higher education, economic development, and social and cultural transformation, posing complex challenges for society as a whole. To address this, universities require effective dropout risk assessments for both domestic and international students, enabling the implementation of tailored strategies and support. This study sourced a dataset from multiple faculties, comprising 3544 records for domestic students (Portuguese) and 86 for international students, considering 23 features. To balance the data, Conditional Tabular Generative Adversarial Networks were utilized to generate 487 synthetic samples with comparable statistical characteristics for training (85%) while retaining the original 86 real samples for testing (15%), thus maintaining an identical train–test split for evaluating domestic students. An Automated Machine Learning framework, employing ensemble learning algorithms, achieved outstanding performance, with the Light Gradient Boosting Machine proving the most effective for domestic students and Categorical Boosting for international students, both achieving test accuracies exceeding 0.90. The analysis revealed that improving academic performance during the first and second semesters was key to reducing dropout risks. Once a satisfactory level was reached, further improvements had minimal impact. Therefore, the focus should be on achieving satisfactory grades. Other objective identity factors, such as age and gender, were less influential than academic performance. A web-based application incorporating the developed models was created, offering an open-access tool for forecasting dropout risks, with all code made publicly available for further research into undergraduate performance, which could be extended to other nations. Full article

This paper proposes a bearing fault diagnosis method based on the Dempster–Shafer evidence fusion of cloud model memberships from multi-channel data, which provides an explicable calculation process and a final result. Firstly, vibration signals from the drive end and fan end of the rolling bearing are used as dual-channel data sources to extract multi-dimensional features from time and frequency domains. Then, cloud models are employed to build models for each feature under different conditions, utilizing three digital characteristic parameters to characterize the distribution and uncertainty of features under different operating conditions. Thus, the membership degree vectors of test samples from two channels can be calculated using reference models. Subsequently, D-S evidence theory is applied to fuse membership degree vectors of the two channels, effectively enhancing the robustness and accuracy of the diagnosis. Experiments are conducted on the rolling bearing fault dataset from Case Western Reserve University. Results demonstrate that the proposed method achieves an accuracy of 96.32% using evidence fusion of the drive-end and fan-end data, which is obviously higher than that seen in preliminary single-channel diagnosis. Meanwhile, the final results can give suggestions of the possibilities of anther, which is benefit for technicists seeking to investigate the actual situation. Full article

Alcoholic beverages held significant importance in global dietary cultures. Their consumption was subject to the combined influence of sociocultural, economic, and psychological factors. As one of the world’s major alcohol consumption markets, China exhibited increasingly diverse drinking patterns, yet research on drinking behaviors based on the Chinese population remained relatively limited. This study employed a questionnaire-based survey to collect data. A total of 2119 Chinese adult alcohol consumers were recruited between October 2024 and April 2025. The sample encompassed individuals with diverse demographic backgrounds, including variations in gender, age, education level, monthly income, and occupation. Based on this dataset, multivariate logistic regression analysis was applied to systematically examine the key factors influencing drinking frequency among Chinese adult drinkers. The study found that the majority of drinkers in China engaged in low- to moderate-frequency drinking, with significant variations observed across different demographic groups: women aged 31–50 showed a higher proportion of high-frequency drinking, while individuals over 50 experienced a notable decline in drinking frequency. Individuals with smoking habits and higher stress levels were more likely to engage in high-frequency drinking. In contrast, those who report higher subjective well-being tended to exhibit moderate-frequency drinking patterns, characterized by moderate but non-excessive consumption. This study constructed a multi-dimensional profile of alcohol consumption behavior in China, thereby providing precise guidance for future product positioning and development, promoting high-quality development in the alcoholic beverage industry, and offering a scientific basis for advocating a culture of moderate and healthy drinking. Full article

As a well-known World Cultural Heritage Site, the Historic Centre of Macao’s historical buildings possess a wealth of decorative patterns. These patterns contain cultural esthetics, geographical environment, cultural traditions, and other elements from specific historical periods, deeply reflecting the evolution of religious rituals and political and economic systems throughout history. Through long-term research, this article constructs a dataset of 11,807 images of local decorative patterns of historical buildings in Macau, and proposes a fine-grained image classification method using the ConvNeXt-L model. The ConvNeXt-L model is an efficient convolutional neural network that has demonstrated excellent performance in image classification tasks in fields such as medicine and architecture. Its outstanding advantages lie in limited training samples, diverse image features, and complex scenes. The most typical advantage of this model is its structural integration of key design concepts from a Transformer, which significantly enhances the feature extraction and generalization ability of samples. In response to the objective reality that the decorative patterns of historical buildings in Macau have rich levels of detail and a limited number of functional building categories, ConvNeXt-L maximizes its ability to recognize and classify patterns while ensuring computational efficiency. This provides a more ideal technical path for the classification of small-sample complex images. This article constructs a deep learning system based on the PyTorch 1.11 framework and compares ResNet50, EfficientNet-B7, ViT-B/16, Swin-B, RegNet-Y-16GF, and ConvNeXt series models. The results indicate a positive correlation between model performance and structural complexity, with ConvNeXt-L being the most ideal in terms of accuracy in decorative pattern classification, due to its fusion of convolution and attention mechanisms. This study not only provides a multidimensional exploration for the protection and revitalization of Macao’s historical and cultural heritage and enriches theoretical support and practical foundations but also provides new research paths and methodological support for artificial intelligence technology to assist in the planning and decision-making of historical urban areas. Full article