Search Results (1,176)

Forecasting fine particulate matter with a diameter of 2.5 μm (PM_2.5) is critically important due to its adverse effects on human health and environmental sustainability. Although ground-based monitoring stations provide accurate measurements, their limited spatial coverage restricts large-scale PM_2.5 assessment, especially in complex urban regions. Consequently, aerosol optical depth (AOD) derived from satellite imagery, combined with advanced deep learning (DL) techniques, has emerged as an effective alternative by offering wide spatial coverage and rich spatio-temporal information. This paper proposed an optimization-driven fuzzy transformer–deep belief network (ODFT-DBN) for accurate PM_2.5 air pollution prediction. The proposed framework integrates a fuzzy inference module to model uncertainty and nonlinear environmental relationships, a transformer encoder to capture long-range spatio-temporal dependencies, and a DBN to extract hierarchical features and improve prediction robustness. In addition, a novel multi-objective gray wolf optimizer (NMOGWO) is employed to jointly optimize the model hyper-parameters and fuzzy membership functions. The proposed approach is implemented for the city of Tehran, Iran, using meteorological variables, topographical features, ground-based PM_2.5 measurements, and satellite-derived AOD data. The ODFT-DBN model is compared with several benchmark methods, including bidirectional encoder representations from transformers (BERT), transformer, long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), DBN, and extreme gradient boosting (XGBoost). Experimental results demonstrate that the proposed framework achieves superior predictive performance, attaining an R² value of 0.94 and root mean square error (RMSE) of 0.8 μg/m³. Scatter plot analyses indicate a strong agreement between predicted and observed PM_2.5 values, while the proposed model exhibits low variance, stable convergence behavior, and acceptable computational time. Overall, the results confirm the effectiveness, robustness, and practical applicability of the proposed ODFT-DBN framework for spatio-temporal PM_2.5 forecasting. Full article

This study examines the critical barriers to circular supply chain transformation in Vietnam’s textile and apparel industry using an integrated decision-making framework that combines Spherical Fuzzy Sets (SFSs), SF-Delphi, and SF-AHP. Circular supply chain transformation can help reduce textile waste, improve material recovery, strengthen traceability, and support sustainable development. However, its implementation is still limited by several economic, technological, regulatory, and managerial challenges. By collecting expert opinions and prioritizing barriers according to their relative importance, this study identifies the most influential barriers in the Vietnamese textile context. The SF-Delphi stage validated 22 barriers, and the SF-AHP results indicate that high investment cost, lack of traceability, lack of advanced technologies for reverse logistics, uncertainty in return on investment, and lack of sectoral standardization are the most critical barriers. The study also suggests practical directions, including phased investment, improved traceability systems, stronger reverse logistics technologies, and clearer textile-specific standards. The findings provide useful insights for firms, policymakers, and researchers seeking to support circular supply chain transformation in Vietnam’s textile and apparel industry. Full article

This study proposes a multidimensional decision-support model for assessing the strategic implications of Digital Transformation (DT) in SMEs under conditions of uncertainty. The study addresses the challenge of measuring the digital impact of DT across value creation, strategic management maturity, and sustainability dimensions. A conceptual framework grounded in strategic management and digital transformation literature is operationalized using the Fuzzy TOPSIS method. A controlled stochastic simulation was conducted to generate a synthetic dataset representing 30 heterogeneous SMEs for computational model-validation purposes. The proposed framework generates three dimension-level performance indices and one aggregated Global Digital Impact Index (GDII). The simulation results illustrate the analytical potential of the framework to support multidimensional digital impact assessment under uncertainty. The study contributes a fuzzy-based evaluation framework capable of integrating value creation, strategic management maturity, and sustainability within a unified digital impact assessment model. Full article

Background: High-technology supply chains are interdependent logistics infrastructures in which digital, energy, manufacturing, cloud and orbital layers are tightly coupled. This paper examines how such layering changes supply chain resilience and systemic vulnerability. Methods: The paper develops an analytical–conceptual framework linking supply chain resilience, interdependent infrastructure theory and network topology. It introduces Topological Phase Vulnerability (TPV), capturing proximity to structural fragility thresholds, and the Shock Amplification Coefficient (SAC), conceptualizing disruption amplification as a function of centrality concentration, cross-layer coupling and reconfiguration capacity. The framework is supported by a fuzzy-inspired diagnostic scorecard and stylized assessment of alternative infrastructure configurations. Orbital computing is an extreme illustrative context because it combines dependence on advanced semiconductor fabrication, hyperscale cloud orchestration, energy systems, launch capacity and logistics coordination. Results: Highly centralized configurations are more likely to transform local disruptions into cross-layer cascades, whereas modular and distributed configurations are more likely to contain disruption through redundancy, substitutability and rerouting. Conclusions: Resilience in next-generation logistics infrastructure depends not only on capacity or component reliability, but also on topology. Centrality dispersion, modularity and reconfiguration capacity are critical design principles for reducing shock amplification in high-technology supply chains. Full article

This study aims to identify and prioritize digital economy factors affecting inflation and to determine effective policy strategies for managing digitally driven inflationary pressures in the context of financial systems and risk dynamics. The analysis considers twelve key digital economy indicators, including e-commerce penetration, digital payment systems, internet infrastructure, price transparency, digital advertising, Industry 4.0 technologies, data-driven inventory and demand systems, fintech adoption, cryptocurrency usage, and digital financial access. In parallel, eight policy strategies are evaluated, covering digital price transparency, expansion of digital payments, digital logistics optimization, digital public services, smart manufacturing, intelligent-based demand forecasting, fintech integration, and digital workforce development. The study employs a novel intelligent-supported decision-making framework integrating an attention-based expert weighting approach, generalized fractal fuzzy sets, the MEREC method, and the ARLON technique. The empirical design is based on expert evaluations obtained from ten specialists with at least 12 years of experience in digital economy, finance, and policymaking. Rather than relying on country-specific or time-series inflation datasets, the study examines the structural relationship between digitalization and inflation through a multi-criteria expert-based approach, with data collected in 2025. The findings indicate that e-commerce penetration and the prevalence of digital payment systems are the most influential factors affecting inflation. In addition, digital price transparency and the expansion of digital payment systems emerge as the most effective strategies for mitigating inflationary pressures. These results provide important insights into how digital transformation reshapes inflation dynamics, monetary transmission mechanisms, and inflation-related financial risks. The proposed model offers a robust and systematic framework for analyzing inflation in digitalized economies and supports policymakers and financial decision-makers in managing emerging risks in intelligent-driven economic environments. Full article

Poland’s energy transition represents a structurally complex case of decarbonization in a coal-dependent economy, where declining hard coal consumption, increasing renewable energy production, growing natural gas use, and continued economic expansion interact within the same energy–economic system. This study assesses the evolution of emission pressure in Poland between 2000 and 2023 using a Fuzzy Multi-Criteria Evaluation (FMCE) framework. The analysis integrates four system-level variables: gross domestic product, hard coal consumption, natural gas consumption, and renewable electricity production, the latter transformed into an inverse fuzzy variable representing insufficient renewable energy penetration. The FMCE-based emission pressure index was constructed using min–max normalization, continuous fuzzy membership degrees, weighted aggregation, and component-level decomposition. The results show that Poland’s emission pressure was highest in the early phase of the analyzed period, especially in 2000–2007, when the energy system remained strongly shaped by coal dependence. The years 2008–2013 formed an unstable transitional phase, while 2014–2018 showed a more stable moderate-pressure configuration. After 2018, the index declined markedly, indicating a shift toward lower emission pressure; however, only selected years reached the formal low-pressure category, which suggests that a stable low-emission regime has not yet been fully established. The decomposition confirms that hard coal was the dominant contributor to emission pressure for most of the period, although its relative contribution declined over time. Renewable energy development increasingly weakened emission pressure, while natural gas played an ambiguous transitional role by partly replacing coal but maintaining fossil-fuel dependence. The study contributes to energy-transition research by proposing an interpretable fuzzy composite index for tracking structural emission pressure over time. The findings underline the need for continued coal phase-down, accelerated renewable energy integration, grid modernization, and careful governance of natural gas as a transitional fuel in Poland’s pathway toward a lower-emission energy system. Full article

Max-type fuzzy difference equations constitute an emerging research area arising from the integration of fuzzy mathematics and discrete dynamical systems. By characterizing uncertainty through fuzzy numbers, these equations provide rigorous mathematical modeling tools for practical problems involving both discreteness and uncertainty. This paper systematically investigates the dynamical properties of a class of max-type fuzzy difference equations. First, fuzzy set theory is used to transform the fuzzy difference equation into a corresponding system of parametric ordinary difference equations. Then, using the iterative method, inequality techniques, and mathematical induction, an expression for the periodic solutions of the max-type ordinary difference equation is derived, from which an expression for the periodic solutions of the max-type fuzzy difference equation is further obtained. In addition, the boundedness and persistence of the solutions to the fuzzy difference equation are proved. Finally, numerical simulations are conducted in MATLAB 2024, and the results illustrate the theoretical findings. This study not only enriches the theoretical framework of fuzzy difference equations but also provides new insights and methodological support for the modeling and analysis of uncertain discrete systems. Full article

Parkinson’s disease is a progressive neurodegenerative disorder characterized by motor impairments that significantly affect handwriting and fine motor control. Recent advances in artificial intelligence have enabled the non-invasive analysis of handwritten patterns as reliable digital biomarkers for early Parkinson’s disease detection. However, existing deep-learning approaches often struggle with diagnostic uncertainty and lack interpretability, limiting their clinical reliability and practical adoption. Moreover, models trained on single datasets frequently exhibit poor generalization across heterogeneous handwriting sources. This study uses two image-based handwriting datasets and one CSV-based HandPD feature dataset, including the Parkinson’s Augmented Handwriting Dataset, Parkinson’s Drawings Dataset, and HandPD Spiral/Meander feature records. A Transformer-based architecture is employed to learn global motor patterns from handwriting images, followed by a fuzzy-logic-based decision layer to handle uncertainty and improve robustness. The novelty of this work lies in integrating Transformer-driven deep feature learning with fuzzy clinical reasoning, supported by an AIC-based handcrafted feature analysis for interpretability. The model performance is evaluated using accuracy, precision, recall, F1-score, MCC, and AUC metrics. The experimental results demonstrate that the proposed Transformer–Fuzzy framework consistently outperforms CNN and Transformer-only baselines, achieving superior classification performance and robust generalization across all datasets, thereby establishing its effectiveness for reliable and interpretable Parkinson’s disease screening. Full article

Emerging-market equity exchanges require regime forecasting systems that are continuous in time, robust to heavy-tailed distributions, and optimised against false alarms. No existing method addresses all three simultaneously, and no prior study has reported a crisis false-alarm rate on JSE equities. We propose S-NODE-ANF-RRC: a stochastic neural ODE within an Adaptive Neuro-Fuzzy Risk-Regime Clustering architecture, integrated by a Milstein scheme with Lyapunov-regularised dual-loss training. The system is evaluated as a one-step-ahead probabilistic forecaster ($h=1$ trading day) on 2696 daily observations across 17 JSE securities (March 2015–March 2026). Gaussian mixture clustering on raw features (kurtosis 54.8) inflates ARI by 1.3×; log-transformation corrects this artefact. Two operational profiles emerge: the N-ODE-ANF-RRC achieves the lowest cost (10,350 bp, 65.1% below GMM) and longest lead time (0.71 days); the S-NODE-ANF-RRC achieves the lowest false alarm rate among probabilistic architectures (FAR = 0.051), with a 42.0% cost reduction versus GMM (McNemar $p=0.027$, power $1-\beta =0.73$; bootstrap CI [5250, 19,600] bp excludes zero). Ablation confirms drift, diffusion, and dual-loss as the minimum viable daily-frequency configuration. Full article

Regional water systems in rapidly urbanizing hilly basin cities are affected by hydrological variability, population concentration, industrial water demand, and water-use efficiency. This study evaluated the water resources carrying capacity (WRCC) of Jinhua City, southeastern China, from 2011 to 2023 using an integrated 15-indicator system covering water resources support, water-use and population pressure, economic structure and water-use efficiency, and ecological and environmental support. Indicator definitions, units, directions, and data sources were harmonized using official water resources bulletins and statistical records. A combined weighting method integrating the modified Analytic Hierarchy Process and the entropy weight method was coupled with a fuzzy matter-element model and the Hamming closeness measure. WRCC grades were assigned using standard-derived Hamming closeness thresholds based on pooled-reference membership transformation. Obstacle degree, leave-one-indicator-out sensitivity, and redundancy diagnostics were further used for interpretation and robustness assessment. The combined weights were mainly concentrated in water-use and population pressure (35.85%), water resources support (26.77%), and economic structure and water-use efficiency (26.10%). Industrial water use, per capita comprehensive water use, population density, water consumption per 10,000 yuan industrial value added, and water consumption per 10,000 yuan GDP had the highest indicator weights. Annual Hamming closeness ranged from 0.2621 to 0.6391. Jinhua’s WRCC reached Grade II in 2015, 2019, 2020, and 2021, while the remaining years were classified as Grade III. The highest closeness occurred in 2019, whereas 2022 and 2023 declined to Grade III and were close to the II/III threshold. Obstacle diagnosis showed that water-use and population pressure were the dominant subsystem obstacles. Sensitivity analysis showed that the peak year and the lowest year remained unchanged across all leave-one-indicator-out scenarios, whereas the boundary years showed grade sensitivity. The results provide a transparent annual assessment and diagnostic evidence for WRCC management. Full article

Indoor air quality has a significant impact on occupant health, comfort, and productivity in residential and commercial indoor environments. This paper proposes an IoT-edge enabled deep–fuzzy hybrid framework for real-time IAQ prediction and adaptive control. The proposed system integrates IoT-based environmental sensing, Temporal Fusion Transformer-based multivariate forecasting, knowledge distillation, edge-deployed Bi-LSTM inference, and Mamdani fuzzy logic control within a unified IAQ management architecture. A composite Comfort Risk Index is introduced to combine environmental parameters and occupant discomfort feedback into a single adaptive control indicator. Experimental evaluation under varying indoor conditions demonstrated strong forecasting performance, with prediction accuracies reaching 96.3% for CO₂ and 95.7% for PM_2.5 prediction, while reducing inference latency from 575 ms to 295 ms. Comparative analysis against baseline threshold-based control strategies further indicated improved comfort stability, smoother actuator behavior, and reduced estimated actuator operating intensity during deployment. The proposed framework also demonstrated resilient operation under simulated sensor-failure conditions while maintaining low computational overhead suitable for resource-constrained IoT-edge environments. Overall, the results indicate that combining lightweight deep learning models with interpretable fuzzy control can provide an effective, scalable, and energy-aware solution for intelligent real-time IAQ optimization in smart indoor environments. Full article

Prefabricated mechanical, electrical, and plumbing (MEP) systems have been increasingly adopted in energy station projects; however, systematic evaluation frameworks capable of integrating construction performance, cost constraints, and uncertain multi-indicator assessments remain limited. To address this gap, this study constructs an Analytic Hierarchy Process (AHP)–Entropy–Fuzzy evaluation framework to assess the comprehensive benefits of BIM-enabled prefabricated MEP construction in energy stations. A hierarchical evaluation system was established based on five dimensions: schedule, quality, cost, safety, and environmental performance, and ten secondary indicators were defined. The Analytic Hierarchy Process was used to determine expert-based subjective weights, the entropy method was applied to capture objective data variability, and multiplicative normalization was employed to obtain combined weights. A fuzzy comprehensive evaluation model was then introduced to transform heterogeneous construction records into comparable benefit levels and scores. The prefabricated method scored 87.80 and was classified as “high”, whereas the conventional method scored 60.85 and was classified as “low”. A Technique for Order Preference by Similarity to Ideal Solution (TOPSIS)-based sensitivity analysis further showed that, under 10%, 20%, and 50% criterion-weight perturbations, the prefabricated group consistently achieved higher closeness coefficients than the conventional group. The smallest margin occurred when the schedule weight was reduced by 50%, but the prefabricated group retained a positive advantage. The results demonstrate that Building Information Modeling (BIM)-enabled prefabricated MEP construction can achieve superior overall project performance through the coordinated optimization of schedule, cost, safety, quality, and environmental objectives, offering a practical evaluation framework and decision-support tool for the industrialized delivery of future energy infrastructure projects. Full article

Student dropout remains an important challenge in higher education because it affects degree completion, institutional resource efficiency, workforce preparation, and students’ long-term socioeconomic opportunities. This requires not only accurate predictions but also decision support that is both reliable and aware of uncertainty. This study posits that the amalgamation of probabilistic modeling, uncertainty quantification, and graph-based refinement can augment both predictive reliability and decision support for the early detection of dropouts. A reliability-centered predictive framework is presented, integrating Educational Competition Optimization (ECO)-based feature selection, probabilistic Support Vector Classification (SVC), isotonic regression for probability calibration, and split conformal prediction for distribution-free uncertainty quantification. In addition, a similarity-driven Graph-based Fuzzy Cellular Automata (Graph-FCA) refinement mechanism is developed, where student relationships are modeled using a k-nearest neighbor graph with radial basis function similarity. Entropy-based confidence weighting is used to control uncertainty-aware propagation. An Explainable Artificial Intelligence layer based on SHAP provides both global and local interpretability, and fairness-aware evaluation assesses consistency across demographic groups. The suggested framework maintains predictive performance while improving probabilistic reliability. The Graph-FCA refinement achieves an accuracy of 0.7503, which is close to the calibrated ECO–SVC baseline (Accuracy = 0.7537; Macro-F1 = 0.6704) and also reduces the Brier score. The conformal prediction layer achieves empirical coverage close to the desired confidence level, ensuring reliable uncertainty estimates. The ECO–SVC–Conformal–GraphFCA framework transforms traditional classification into a reliable, understandable, and uncertainty-aware early warning system, enhancing its usefulness for ethical and informed decision-making in engineering education. Full article

Wikidata provides extensive coverage of tourism-related Points of Interest (POIs), yet its heterogeneous type system and uneven metadata limit its direct use in smart tourism applications. This paper presents an end-to-end pipeline that transforms Wikidata POIs into a compact and interpretable tourism-oriented representation supporting multi-category assignments. We collect POIs from six countries—Greece, Italy, Spain, Norway, Sweden, and Denmark—and construct a dataset that integrates core identifiers with textual descriptions, type information, heritage indicators, geographic coordinates, and Wikipedia sitelinks. We introduce an eight-category tourism taxonomy capturing key themes, including cultural venues, archaeological and historic sites, monuments, fortifications, religious sites, protected areas, natural features, and coastal or water locations. As a reproducible baseline, category likelihoods are estimated using sentence embeddings and similarity to category anchor descriptions, producing a probability vector for each POI. Building on this baseline, we propose a fuzzy inference layer that integrates embedding-based probabilities with structured Wikidata signals to generate interpretable membership degrees across categories and enable principled multi-category classification. This fusion is particularly valuable for smart tourism applications, as it supports robust faceted exploration and personalized recommendations (e.g., “historic + coastal”), while providing evidence-based explanations that enhance user trust and facilitate curator oversight when POI metadata is sparse or ambiguous. The resulting pipeline produces ranked POI catalogs by country and category, country-level tourism profiles, and diagnostic views for examining uncertain cases. The approach is fully reproducible and readily adaptable to other geographic regions or domain taxonomies. Full article

Background: Evaluating centralized purchasing performance is a complex multi-criteria decision-making problem involving uncertainty, linguistic assessments, and subjective judgments from internal clients. Existing approaches provide limited support for handling these characteristics simultaneously. Methods: This study proposes a Mamdani fuzzy inference model integrating four criteria: Service Quality, Responsiveness, Compliance, and Collaboration. The fuzzy rule base was developed using expert knowledge and organizational evaluation practices. The model was applied to a real industrial case study based on an annual evaluation conducted collaboratively by four internal evaluators. Results: The model transformed qualitative assessments into an interpretable performance score while capturing interactions among evaluation criteria and handling uncertainty in the evaluation process. Conclusions: The proposed approach provides a structured decision-support framework for evaluating centralized purchasing performance. It enables the integration of linguistic assessments and expert knowledge, offering a flexible and coherent evaluation tool for industrial environments. Full article