Search Results (1,281)

Word sense induction (WSI) aims to automatically discover the different senses of a word from contextual usage without predefined sense inventories. However, existing distributional clustering methods often suffer from dominant-sense bias and struggle to correctly identify minority senses. In this paper, we propose a definition-anchored reclassification framework for WSI that leverages large language models (LLMs) to generate explicit sense descriptions and refine cluster assignments. Unlike purely distributional approaches, our method integrates semantic definitions into the induction process. Our method improves instance-level alignment by introducing a trade-off with global structural consistency, as it shifts the decision process from geometric clustering to definition-based semantic matching. Experiments on the SemEval-2010 and SemEval-2013 datasets demonstrate that the proposed method consistently outperforms traditional clustering baselines and existing WSI systems across both structural metrics (NMI and V-measure) and instance-level metrics (F-B³ and Fuzzy-F-B³). In particular, our approach effectively mitigates dominant-sense bias and improves the recovery of minority senses by preserving them as distinct clusters while correctly assigning their instances. These results suggest that explicit semantic representations generated by LLMs provide a promising direction for addressing long-standing challenges in unsupervised word sense induction. Furthermore, unlike purely distributional clustering approaches, our method explicitly introduces LLM-generated semantic definitions as anchors, enabling more robust mitigation of dominant-sense bias and improved recall of minority senses. Full article

This study systematically investigated differences in volatile flavor profiles among fermented green plum wines by integrating gas chromatography–mass spectrometry (GC–MS), sensory evaluation, and odor activity value (OAV) analysis with machine learning and SHapley Additive exPlanations (SHAP) based feature interpretation. The primary objective was to evaluate the applicability of machine learning algorithms for flavor profiling of green plum wine. The results indicated that floral and fruity aromas were predominant in samples NG9, YM7, and YM9. Most green plum wines contained high levels of esters, with ethyl benzoate (up to 4820.53 μg/L), ethyl octanoate (up to 2640.83 μg/L), and benzenecarbaldehyde (up to 3432.96 μg/L) being the major contributors. Among the six classification algorithms compared, fuzzy c-means clustering provided the most distinct clustering structure, identifying three distinct flavor categories. Six machine learning models were subsequently established, of which the decision tree (DT) model exhibited the highest performance, with an accuracy of 95.13%. SHAP analysis further revealed that ethyl octanoate, benzyl ethanoate, and 2-phenylethyl ethanoate exerted the greatest influence on model predictions. Overall, these findings highlight the effectiveness of machine learning as a robust tool for the classification and interpretation of flavor characteristics in fermented fruit wines, with broad applicability in flavor science. Full article

Precision soil management is fundamental to the sustainable production of high-quality tea, yet the spatial integration of fertility and heavy metal safety remains a significant challenge. This study aimed to delineate multi-dimensional management zones (MZs) in the tea plantations of Tianmuhu, Jiangsu Province, by evaluating three clustering algorithms: K-means (KM), Fuzzy C-means (FCM), and Iterative Self-Organizing Data Analysis Technique (ISODATA). A total of 70 representative soil samples were analyzed for 10 properties. Descriptive statistics revealed pronounced spatial heterogeneity, particularly for Hg (CV = 71.04%) and P (CV = 61.83%). Pearson correlation and Principal Component Analysis (PCA) demonstrated strong synergistic relationships among organic matter (OM), nitrogen (N), and potassium (K) (r = 0.49–0.69, p < 0.01), which formed a distinct Fertility Factor on PC1. Conversely, PCA identified divergent sources for heavy metals, with Cr primarily governed by pedogenic processes (PC2), while Cd were associated with anthropogenic inputs. Guided by these distinct spatial drivers, this study separately delineated fertility and heavy metal safety MZs. The optimal number of clusters was determined by balancing statistical validity with spatial operationality via the Silhouette Coefficient (SC) and Smoothness Index (SI), with results indicating that a 2–3 zone scheme yielded the most favorable scores. Comparative analysis showed that for soil fertility, ISODATA outperformed KM and FCM by effectively capturing the high variability of P and producing statistically distinct zones (p < 0.05). For heavy metal pollution, FCM provided better partitioning by reflecting the continuous gradients of composite contaminants. Validation results showed that while 61% of the area was classified as high-fertility (ISODATA), approximately 63–75% fell into relatively higher heavy metal accumulation categories. This dual-objective zoning framework provides a scientific basis for site-specific fertilization and targeted environmental monitoring in the regional tea industry. Full article

With the increasing depth of mining operations, accurate identification and assessment of rock mass instability risks are crucial for ensuring mine safety. This study proposes an integrated framework combining the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), fuzzy comprehensive evaluation (FCE) and kernel density estimation (KDE) for the identification and dynamic assessment of high-risk zones in deep mining. Using microseismic monitoring data from a lead–zinc mine in Northwest China (January–June 2023), the HDBSCAN algorithm adaptively identified 86 high-density clusters from 11,638 events. The weights of five evaluation indicators (moment magnitude, apparent stress, stress drop, peak ground acceleration, and ringing count) were determined objectively using the Euclidean distance method. FCE was then applied to classify cluster risk levels, revealing that 70.9% of the clusters were rated as high-risk (Level IV). KDE further illustrated the spatiotemporal migration of high-risk zones, showing a systematic shift from northeast to southwest along stopes and roadways, driven by mining unloading and geological structures. The integrated HDBSCAN-FCE-KDE framework demonstrates strong applicability and reliability in identifying and predicting rock mass instability risks, providing a scientific basis for proactive risk management in deep mining environments. Full article

Background: Conventional analyses of physiological recovery often rely on discrete metrics that assume independence across time points, thereby ignoring intrinsic temporal continuity and masking substantial interindividual heterogeneity. This proof-of-concept study assesses the efficacy of Functional Data Analysis (FDA) as a promising framework for characterizing individual response dynamics following a functional threshold power (FTP) test. Methods: Physiological time-series data (including blood lactate, heart rate, blood pressure, and glucose levels) collected from 21 trained cyclists (10 professionals, 11 amateurs) were represented as functional objects using FDataGrid on the original sampling grid (0, 3, 5, 10, 20 min), without basis expansion or smoothing. We conducted unsupervised functional clustering (K-means; Fuzzy K-means) and supervised classification (Maximum Depth with Modified Band Depth, K-Nearest Neighbors, Nearest Centroid, functional QDA with parametric Gaussian covariance). Model performance was estimated via Repeated Stratified 5-Fold Cross-Validation with 10 repetitions (50 folds), reporting accuracy, balanced accuracy (mean ± SD), 95% CIs, permutation p-values, and sensitivity/specificity from aggregated confusion matrices. Results: Lactate (CL) and diastolic blood pressure (DBP) provided useful and statistically significant discrimination across several classifiers (e.g., KNN, Nearest Centroid, functional QDA), whereas heart rate showed modest discriminative value and glucose intermediate performance. Unsupervised analyses revealed distinct lactate recovery profiles and graded membership for hemodynamic/metabolic variables, supporting the value of FDA for resolving heterogeneity beyond group-average trends. Conclusions: FDA offers a feasible and informative approach for classifying recovery phenotypes while preserving temporal structure. Findings are promising but should be interpreted with caution due to the small sample size, sparse time points, and the need for external validation in larger, independent cohorts before translation into routine decision-making. Full article

With the rapid growth of data, feature selection has become essential for improving machine learning performance. However, most existing unsupervised feature selection methods rely on greedy strategies, which often lead to suboptimal solutions. Moreover, traditional information–theoretic approaches are primarily designed for discrete data and require discretization when applied to continuous data, potentially causing information loss. To address these issues, this paper proposes a global unsupervised feature selection method based on fuzzy mutual information (UFS-FMI). The proposed method integrates fuzzy set theory with information measures to quantify feature relevance and redundancy, and formulates a fractional optimization model. A combination of projection neural networks and kWTA neural networks is employed to achieve global optimization. Experimental results on nine UCI benchmark datasets demonstrate that UFS-FMI consistently outperforms several representative methods in terms of classification accuracy, clustering accuracy, and normalized mutual information (NMI). In particular, on datasets such as Movement_libras, Ionosphere, and Control, the proposed method achieves significantly improved classification performance, confirming its effectiveness and robustness. Full article

Granular modeling has emerged as an interpretable framework for nonlinear system representation by constructing clusters of meaningful data units within the input and output domains. Unlike conventional neuro-fuzzy models that yield crisp outputs, granular models generate fuzzy-set-based outputs, preserving uncertainty information. However, traditional granular architectures rely on linear aggregation mechanisms, limiting their expressive power and structural adaptability. This paper proposes a novel framework termed Logic-Based Fuzzy Granular Networks (LFGNs), in which conventional granular models are enhanced through the incorporation of fuzzy logical neurons implementing AND–OR operations. The proposed logic-based structure enables nonlinear interactions among induced granules while maintaining interpretability. To further improve predictive performance, LFGNs are embedded into a boosting framework, forming a boosted LFGN in which each LFGN acts as a weak learner. Extensive simulation studies on benchmark datasets indicate that the proposed approach outperforms conventional granular models and the existing boosting method in terms of regression accuracy. The integration of logical neurons, boosting, and fuzzy granular models provides a unified and robust granular modeling framework. Full article

Digital transformation is reshaping societies by promoting the adoption of advanced technologies. Moreover, the digitization of public services has become an important focus for governments. In this paper, digital government performance indicators are analyzed to improve the efficiency of digitizing public services. Based on this awareness, the seven main criteria and twenty-one sub-criteria are determined. Then, a fuzzy decision-making framework is proposed to evaluate digital government performance across 165 countries as alternatives. To the best of our knowledge, limited studies have investigated an integrated clustering-based fuzzy decision-making framework for evaluating digital government performance. The intuitionistic trapezoidal fuzzy number-based analytical hierarchy process (ITFNAHP), a part of the introduced framework, is developed to find the weights of the main criteria and sub-criteria. Digital technologies, innovation, and the economy are the most significant criteria for digital government operations. The k-means clustering method is then employed to group the alternatives. The four clusters are obtained from the clustering technique. Next, the technique of order preference similarity to ideal solution (TOPSIS) is introduced to rank the digital governments of each cluster. Switzerland, Rwanda, North Macedonia, and Eswatini are the top choices among others in each cluster, respectively. Additionally, a sensitivity analysis is conducted considering the ten different situations. In addition, the managerial and policy implications are discussed, including the achievement of Sustainable Development Goals (SDGs). Full article

Accurate monitoring of crop phenology is essential for precision agriculture and yield forecasting. However, satellite-derived time series often suffer from inherent noise, such as residual atmospheric effects and mixed pixels, as well as a frequent lack of ground-truth data in agriculture. In response, this study proposes an algorithm to define the type of spectral signatures for the principal phenological stages of crops, using them as the foundation for training supervised machine learning classification models. The algorithm was developed using Fuzzy C-Means (FCM) clustering to identify the spectral signature reference groups in winter wheat across the Burgos region (Spain) during the 2020 and 2021 growing seasons. To enhance cluster independence and biological coherence, a multi-step filtering process was implemented, including spectral purity (membership degree, SAM, and SAMder) and temporal coherence filters. The filtered and labeled dataset (80% original Burgos dataset) was used to train supervised classification models (KNN and XGBoost). The models’ reliability was verified through three wheat tests (remaining 20%), labeled using other clustering techniques, and an independent barley dataset from diverse geographic locations (Valladolid and Soria). The filtering process significantly improved cluster stability by removing outliers and transition spectral signatures. The supervised models demonstrated exceptional performance; the KNN model slightly outperformed XGB, achieving a mean Accuracy of 0.977, a Kappa of 0.967, and an F1-score of 0.977 in the wheat external test. Furthermore, the model showed, when applied to barley, that its phenological spectral signatures are equivalent in shape to those of wheat, with an Accuracy of 0.965 and an F1-score of 0.974. In addition, it was verified that the type spectral signatures remain the same regardless of the location. This study presents a robust classification tool capable of labeling four key phenological stages (tillering, stem elongation, ripening, and senescence) without ground truth. By effectively removing inherent satellite noise, the proposed methodology produces organized, cleaned datasets. This structured foundation is critical for future research integrating spectral signatures with harvester data to develop high-precision yield prediction models. Full article

As a foundational protocol in wireless sensor networks (WSNs), LEACH has long contended with the dual challenges of energy load balancing and security defense. To clarify the protocol’s evolutionary trajectory within the modern IoT context, this paper presents a systematic review and restructuring of LEACH’s optimization mechanisms. The core contributions of this study are threefold: First, it establishes a taxonomy for energy optimization in LEACH. It provides an in-depth analysis of how intelligent algorithms—such as fuzzy logic and meta-heuristics—reshape cluster head election and data transmission paths in heterogeneous network environments, thereby resolving the inherent blindness of traditional mechanisms. Second, it elucidates the evolutionary patterns of LEACH security mechanisms. The paper details the transition of defense strategies from early static encryption and authentication to dynamic countermeasure mechanisms, offering a clear framework for understanding the protocol’s defensive boundaries. Finally, addressing the bottleneck where high security levels often incur high energy costs, the paper explores the feasibility of incorporating zero-trust architecture (ZTA) into WSNs within the future outlook section. This discussion aims to provide a new theoretical perspective for future research on balancing enhanced defense capabilities with energy efficiency. Full article

Post-disaster emergency perishable material distribution is an essential part of emergency relief, which is of great significance to reducing disaster losses and casualties and improving rescue efficiency. However, in actual rescue, the demand information of disaster sites is often complex to determine, and the demand for emergency perishable materials needs to be clarified. Therefore, the single-cycle distribution makes it difficult to meet the demand for emergency perishable materials at disaster sites. To effectively improve the efficiency of emergency relief, this paper constructs a distribution optimization model with a multi-cycle vehicle path and the dual objectives of minimizing the distribution delay penalty and corruption cost and minimizing the unsatisfied demand. Initially, the fuzzy demand is addressed through the application of triangular fuzzy numbers and the most probable value weighting method. Following this, a two-stage optimization algorithm is devised by integrating the K-means++ algorithm with an enhanced Differential Evolutionary Whale Optimization Algorithm (DE-WOA). This algorithm operates by first clustering the affected points and subsequently solving the multi-objective model, thereby providing a robust methodology and strategic recommendations for the distribution of perishable materials across diverse scenarios. Our study reveals that the multi-objective model developed in this paper exhibits remarkable operability and practicality in the distribution of post-disaster emergency perishable materials, as evidenced by the verification via numerical examples. Through a comparison with the single-stage whale optimization algorithm, it is evident that the enhanced two-stage differential evolutionary whale optimization algorithm not only demonstrates a substantially faster convergence rate and a superior solution quality but also proves to be more suitably adapted to the proposed model. Significantly, the overall optimization performance has been augmented by 33%, thereby providing further substantiation of the efficacy of the designed improved algorithm. Full article

Green innovation is central to industrial ecological transition, yet heavily polluting firms often exhibit low-quality green innovation investment. Grounded in the government–enterprise–research–intermediary Quadruple Helix innovation ecosystem framework, this study integrates Necessary Condition Analysis (NCA) and fuzzy set qualitative comparative analysis (fsQCA) to examine 66 publicly listed heavily polluting manufacturing firms in China. The results show that fiscal subsidies and environmental taxes are necessary but not sufficient conditions for achieving high-quality green innovation investment. Moreover, high-quality outcomes arise through three equifinal pathways: the Government–Intermediary Dual-Drive Model, the Government–Enterprise–Intermediary Co-Directional Model, and the Government–Enterprise Symbiotic Model. Six configurations lead to non-high-quality green innovation investment, which cluster into Resource-Scarcity and Regulatory-Constrained models. A favorable macro environment further strengthens high-quality outcomes. These findings clarify how policy instruments and multi-actor collaboration jointly shape green innovation investment quality and provide actionable implications for heavily polluting firms and policymakers seeking sustainable development. Full article

This study investigates the interplay between university students’ motivational beliefs and their regulatory strategies when facing challenging academic tasks. Drawing on the Expectancy–Value–Cost (EVC) model, the research characterizes distinct motivational profiles based on perceived self-efficacy, task value, and perceived cost. A quantitative study was conducted with a sample of 1184 Chilean university students across various disciplines, including Engineering, Health Sciences, and Social Sciences. Participants identified a recent challenging task and completed a battery of validated instruments, including the Brief Regulation of Motivation Scale (BroMS) and scales for perceived cost, self-efficacy, and task value. Using Machine Learning techniques, specifically the Fuzzy C-Means (FCM) algorithm, the analysis identified four distinct student profiles (Agentic Mindset, Alienated Mindset, Paralyzed Mindset, Growth Mindset). These clusters were evaluated based on statistical indices (R², AIC, BIC, and Silhouette) and theoretical coherence. Subsequent ANOVA and post hoc analyses (Holm correction) revealed significant differences among these profiles in their reported levels of motivational regulation and willpower. The findings suggest that students with high self-efficacy and task value combined with manageable perceived costs employ more effective motivational regulation strategies. Conversely, profiles characterized by high perceived cost and low self-efficacy show diminished regulatory capacity. This research contributes to understanding how personal and task-related perceptions interact to shape volitional control in demanding academic environments, offering insights for targeted interventions to support academic persistence and success. Full article

Accurate classification of breast cancer histopathology images is essential for early diagnosis and effective clinical management. However, conventional deep learning models often exhibit performance degradation under limited labeled data and lack interpretability, which restricts their clinical applicability. To address these challenges, we propose GAFR-Net, a robust and interpretable Graph Attention and Fuzzy-Rule Network designed for histopathology image classification under scarce supervision (defined here as less than 10% labeled data). GAFR-Net constructs a similarity-driven graph to model inter-sample relationships and employs a multi-head graph attention mechanism to capture complex relational representations among heterogeneous tissue structures. Meanwhile, a differentiable fuzzy-rule module integrates intrinsic topological descriptors—such as node degree, clustering coefficient, and label consistency—into explicit and human-readable diagnostic rules. This architecture establishes transparent IF–THEN inference mappings that emulate the heuristic reasoning process of clinical experts, thereby enhancing model interpretability without relying on post-hoc explanation techniques. Extensive experiments conducted on three public benchmark datasets—BreakHis, Mini-DDSM, and ICIAR2018—demonstrate that GAFR-Net consistently surpasses state-of-the-art methods across multiple magnifications and classification settings. These results highlight the strong generalization capability and practical potential of GAFR-Net as a trustworthy decision-support framework for weakly supervised medical image analysis. Full article

The growth of the Italian craft beer sector has renewed interest in domestic hop cultivation, presenting a promising opportunity for farm diversification, despite challenges such as structural fragmentation and limited economic data. The study examines the structural and economic characteristics of Italian hop farms using harmonised microdata from the Farm Accountancy Data Network (FADN) for the years 2021 to 2023. The sample includes 13 farms (selected from an initial sample of 14 after outlier detection) with 32 validated farm-year observations, representing approximately 19% of Italy’s total hop-growing area. A multivariate analysis—combining Principal Component Analysis (PCA) and fuzzy C-means clustering—was performed using five key economic indicators: gross margin (GM), variable costs (VCs), hop production (Q_HOP), specialisation ratio (SH), and the coefficient of variation in the gross margin (GM_cv) as a proxy for income stability. The results identify three distinct farm profiles: (i) resilient specialised farms with high margins but significant income volatility; (ii) intermediate emerging farms; and (iii) diversified units where hops represent a secondary crop. The findings of this study provide an in-depth understanding of the economic strategies underpinning hop cultivation in Italy, which may be of interest to all organisations where hops are grown as an alternative crop. They offer concrete guidelines to policymakers to support the sector’s development through targeted measures that address issues relating to farm size, technical capabilities, and supply chain integration. Full article