Search Results (1,143)

Traditional fuzzy decision-making often relies on manual expert calibration, which is labor-intensive and susceptible to subjective bias. This study addresses these limitations by proposing a novel framework that transforms the intrinsic probabilistic outputs of Large Language Models (LLMs) into Triangular Fuzzy Numbers (TFNs). We introduce a multi-temperature sampling strategy coupled with weighted quantile aggregation and an adaptive interval adjustment mechanism to systematically map model stochasticity to fuzzy possibility distributions. Empirical validation on a structured prototype dataset demonstrates that the proposed method achieves high consistency with expert consensus, with GPT-4.2 exhibiting superior central accuracy and Gemini-2.5 excelling in uncertainty coverage. Furthermore, in complex unstructured scenarios involving business public opinion, the integration of Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG) significantly corrects cognitive biases and converges uncertainty boundaries. This research establishes a rigorous pathway from generative AI probabilities to fuzzy decision theory, offering a robust automated solution for quantitative risk assessment and intelligent decision support. Full article

The escalation of geopolitical tensions has forced global manufacturers to reconfigure their supply chains. While Digital Transformation (DT) is widely touted as a primary driver of resilience, traditional variance-based research often assumes a symmetric, linear relationship that applies universally across firms. This study challenges this assumption through the lens of Complexity Theory. Viewing supply chains as Complex Adaptive Systems (CASs), we employ Fuzzy-Set Qualitative Comparative Analysis (fsQCA) on a stratified sample of 928 manufacturers in a geopolitical high-risk zone (Taiwan). We identify equifinal pathways to Organizational Resilience, revealing a fundamental asymmetry between organizational types. The results suggest that while large enterprises rely on a resource-intensive strategy—which we term the “Digital Fortress” configurational metaphor (combining high digital maturity and agility as a core condition)—SMEs can achieve high resilience through an “Agile Dodger” configuration, leveraging operational agility and niche positioning without necessitating high digital maturity. This study contributes to the systems literature by mapping the “topology of resilience” and offering tailored configurational pathways that complement traditional variance-based perspectives in volatile ecosystems. Full article

Background: This study examines the systemic barriers constraining the development of India’s shipbuilding industry and identifies leverage points for effective policy intervention. Methods: A mixed-methods design was adopted, combining the Delphi technique with fuzzy DEMATEL to capture expert consensus and causal interdependencies among barriers. A panel of 20 experts, drawn from academia, the government, shipbuilding and ship repair, ports, logistics, and maritime consultancy, participated in two iterative Delphi rounds. An initial list of 21 barriers was refined to 10 based on convergence thresholds. These barriers were then analysed using a seven-step fuzzy DEMATEL procedure to distinguish causal drivers from dependent factors. Results: High raw material costs emerged as the most dominant causal barrier, with the highest net influence (R−C = 0.540), followed by high working capital requirements (R−C = 0.103) and complex regulatory frameworks (R−C = 0.275). Shortages of skilled labour, inefficiencies in ship design, and delays in clearances were largely effect-type barriers shaped by upstream structural conditions. Sensitivity analysis confirmed the stability of barrier rankings under alternative expert weighting scenarios. Conclusions: Policy efforts should prioritise reducing input cost disadvantages, strengthening long-term policy support, and rationalising regulatory processes, rather than focusing solely on downstream operational symptoms. The study is limited to expert judgement in the Indian shipbuilding sector. Future research could extend this framework to comparative country settings or integrate causal analysis with econometric evidence to further strengthen policy design. Contribution: Unlike prior thematic studies, this research provides an integrated causal mapping of structural, financial, and institutional barriers specific to Indian shipbuilding, enabling policy sequencing rather than simple ranking. 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

Given the increasing frequency and intensity of floods, which are mostly caused by continuous climate change and growing human pressures on the environment, accurately identifying areas that are susceptible to flooding is a crucial priority for risk reduction and long-term land use planning. Thus, this research examines multilevel flood susceptibility mapping across North Macedonia, using 328 past flood occurrences, 14 conditioning variables derived from a digital elevation model, simplified lithology, and calculated direct runoff. The methodology integrates fuzzy set theory (Fuzzy), analytic hierarchy process (AHP), weighted linear combination (WLC), and random forest (RF) approaches. The two-stage process employs distinct sets of conditioning factors in sequential flood susceptibility mapping: first, generating Fuzzy/AHP/WLC predictions and pseudo-absence data, and second, producing five RF predictions by varying pseudo-absences and binary cutoffs. Validation results indicate that the very high susceptibility class (0.8–1.0) of the Fuzzy/AHP/WLC model predicted 46.6% of flood pixels within 31.6% of the total area. In comparison, the very high susceptibility class of the RF models predicted 88.5%, 78.3%, 60.6%, 48.5%, and 28.3% of flood pixels within 54.7%, 42.2%, 30.5%, 27.0%, and 25.1% of the total area, respectively. The RF models achieved area under the curve (AUC) values exceeding 0.850, with a maximum of 0.966. Additionally, areas of high and low uncertainty were highlighted using a standard deviation map created from the RF models, highlighting agreement/disagreement and potential locations for methodological improvement and focused sampling. The findings also highlight the potential of the multilevel technique for mapping flood susceptibility and call for more research into its potential for future studies and practical uses. Full article

In this study, we introduce new versions of fuzzy fractional integral operators for both one- and two-variable cases. Using these operators, several Hermite–Hadamard-type ($H$-type) inclusions are established for fuzzy-number-valued convex functions ($F$·$N\cdot V$-functions) and $F$·$N\cdot V$-coordinated convex functions. These results are obtained by employing $F$·$N\cdot V$-weighted functions within the framework of the newly defined Hadamard and generalized fractional integrals in one- and two-dimensional settings. The use of generalized fractional integral operators provides a unified approach that encompasses a wide class of classical and modern fractional integrals, including the fuzzy Riemann–Liouville and Hadamard types. This unified setting enables the derivation of more comprehensive and flexible inequality results in the fuzzy-number context. The inclusions obtained in this work significantly extend and generalize several known $H\cdot H$-type inequalities previously established for real-valued and interval-valued functions ($I\cdot V$-functions). Furthermore, the proposed results yield a variety of meaningful special cases by specifying suitable kernel functions and parameters of the generalized fractional integrals. In particular, we derive new weighted $H\cdot H$-type inclusions involving logarithmic functions in the fuzzy-number framework. These findings underscore the effectiveness of generalized fractional integrals in capturing nonlocal behavior and uncertainty, and they provide new tools for further investigations in fuzzy analysis, fractional calculus, and generalized convexity. Full article

We propose a reformulated notion of Levitin–Polyak (abbreviated as LP) well posedness for fuzzy optimization problems formulated in the fuzzy order-preserving (FOP) setting, where minimizing sequences are governed by a total ordering defined on fuzzy intervals. Under this formulation, we present verifiable sufficient conditions that guarantee LP well-posed behavior. These conditions are derived using ranking mechanisms that maintain interval order relations and ensure solution comparability. One central contribution is an equivalence-based theoretical characterization of LP well posedness obtained through an examination of the topological properties of the approximate solution mapping, particularly its closed-graph structure and upper semicontinuity. In addition, convergence of approximating solution sequences is investigated under the upper Hausdorff metric, leading to stability results for the associated solution sets. The established criteria provide a comprehensive framework for analyzing the convergence performance of algorithms designed for fuzzy optimization environments. Full article

The rapid growth of Digital Financial Services (DFSs), including what is occurring in Indonesia, necessitates evaluation methods that are capable of objectively and systematically handling multiple assessment criteria. Therefore, this study aimed to propose a hybrid FSS–CRITIC–TOPSIS framework for selecting optimal DFSs. Fuzzy soft sets (FSSs) were used to model uncertainty and subjectivity in criterion assessments. The Criteria Importance Through Inter-criteria Correlation (CRITIC) method determined the weights objectively based on the degree of contrast and inter-criteria correlation. Subsequently, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method was used to rank the alternatives based on the closeness to the ideal solution. The incorporation led to a formally defined decision operator, $\mathcal{T}$, which mapped FSS to complete preference orderings while ensuring provable stability and strong discriminative properties. The framework was applied to five major Indonesian digital wallets, namely ShopeePay, GoPay, OVO, LinkAja, and DANA, as well as being evaluated across five criteria. This framework identified DANA as the optimal alternative, with a score of 0.9282, followed by ShopeePay (0.8354) and GoPay (0.6958). Comparative analysis with other methods showed a near-perfect ranking correlation ($\rho =0.9–1$), with a more proportional score distribution and ranking results that reflected actual conditions. Sensitivity analysis also confirmed robustness, with ranking changes remaining logically consistent underweight variations. In conclusion, the FSS-CRITIC-TOPSIS framework provided an effective, mathematically rigorous method for multi-criteria decision-making (MCDM) under uncertainty, which applied to digital wallet selection as well as potential extension to broader evaluation contexts supporting SDGs 8, 9, and 10. Full article

This paper presents a fuzzy satisfaction-based intelligent framework for early-stage multiobjective sizing of a buck DC–DC converter under uncertain operating conditions. Lightweight closed-form estimators are used to evaluate inductor current ripple, output voltage ripple, and efficiency, including an explicit decomposition of ripple into capacitive and ESR-induced components to distinguish capacitance-dominated and ESR-dominated regimes. Engineering targets for ripple, efficiency, and passive size/cost pressure are mapped to reproducible piecewise membership functions and aggregated into a bounded overall satisfaction score using a weighted geometric operator; alternative non-compensatory and OWA-type aggregators are considered for sensitivity analysis. The resulting nonconvex design problem is solved via a compact two-stage derivative-free strategy that combines global screening with an interpretable Takagi–Sugeno (TSK) rule-based refinement layer, which generates bounded, physics-consistent updates of the design variables and supports rapid feasibility restoration followed by preference-driven tuning. Uncertainty in operating conditions and parameter drift is addressed through scenario evaluation and worst-case or average-case aggregation of satisfaction, linking the fuzzy decision objective to robust scenario design. Numerical studies for a 24 ± 4 V to 12 V converter illustrate regime-dependent adaptation: in low-ESR conditions, ripple improvement is driven mainly by capacitance/frequency adjustments, while in high-ESR conditions, the rule base shifts corrections toward inductor and frequency choices that reduce ESR-dominated ripple. Full article

Load forecasting for Integrated Energy Systems (IESs) is critical to enabling multi-energy coordinated optimization and low-carbon scheduling. Facing multi-load types and multi-site high-dimensional heterogeneous data, there remains a global learning challenge stemming from insufficient representation of spatiotemporal coupling features. In response to the multi-source heterogeneous characteristics of IES loads, this paper designs a Spatiotemporal Topology Encoder that maps load data into a tensorized multi-energy spatiotemporal topological representation via fuzzy classification and multi-scale ranking. In parallel, we construct a MultiScale Hybrid Convolver to extract multi-scale, multi-level global spatiotemporal features of multi-energy load representations. We further develop a Temporal Segmentation Transformer and a Steady-State Exponentially Gated Memory Unit, and design a jointly optimized forecasting model that enforces global dynamic correlations and local, steady-state preservation. Altogether, we propose a multi-scale spatiotemporal fusion and steady-state memory-driven load forecasting method for integrated energy systems (MSTF-SMDN). Extensive experiments on a public real-world dataset from Arizona State University demonstrate the superiority of the proposed approach: compared to the strongest baseline, MSTF-SMDN reduces cooling load RMSE by 16.09%, heating load RMSE by 12.97%, and electric load RMSE by 6.14%, while achieving R² values of 0.99435, 0.98701, and 0.96722, respectively, confirming its feasibility, efficiency, and promising potential for multi-energy load forecasting in IES. Full article

The fashion industry is one of the most resource-intensive sectors, generating major environmental impacts such as greenhouse gas emissions, excessive water and land use, and pollution from waste and microplastics. Fast fashion intensifies these issues through overproduction and overconsumption. However, growing consumer awareness and regulatory pressure are pushing brands to adopt Circular Economy (CE) and sustainability strategies, including resale platforms, recycling programs, and sustainability frameworks. Despite these efforts, their real effectiveness remains uncertain. This study investigates which CE and sustainability strategies are most common among fast fashion companies and how they can mitigate key environmental impacts. Using a Fuzzy Cognitive Maps (FCM) model, the research quantitatively evaluates the effects of various circular and sustainable strategies across the supply chain. Ten key strategies were identified, revealing that isolated actions are often ineffective. Instead, an integrated, systemic approach combining multiple initiatives is essential to achieve meaningful sustainability improvements. Full article

To address the topological mismatch between signal space and physical space caused by uneven signal feature distribution in indoor non-line-of-sight and complex topological environments, this paper proposes an indoor positioning algorithm based on Energy-domain Fingerprint Manifold Graph Total Variation (EFM-GTV). To mitigate neighborhood distortion caused by uneven high-dimensional signal feature distribution, a UMAP manifold topology graph construction method based on fuzzy simplicial sets is designed to establish a graph basis consistent with physical space topology. To reduce false matching risks in global search, a physical topology pruning strategy combining Jaccard similarity is proposed, effectively eliminating pseudo-connections. Building upon this foundation, we introduced an optimization model based on graph total variation, reformulating the positioning problem as a graph signal recovery task. This approach effectively overcomes signal fluctuation interference in complex topologies like U-shaped corridors, achieving robust position estimation. Experiments demonstrate that this algorithm effectively leverages manifold structure constraints to correct NLOS errors. On real-world field test datasets, compared to traditional weighted algorithms, the average positioning accuracy improves to 1.4267 m, with maximum positioning error reduced by over 50%, achieving high-precision robust positioning. Full article

We introduce fuzzy skew maps as a levelwise ($\alpha$-cut) extension of robustly chaotic skew transformations of S-unimodal maps to epistemically uncertain environments. Our central hypothesis is that the robust-chaos mechanism of the underlying skew family transfers to fuzzy parameter uncertainty in a set-based (not probabilistic) sense is as follows: for every $\alpha \in [0,1]$, the induced crisp family $\{F(·,q):q\in {\left[\tilde{q}\right]}_{\alpha }\}$ preserves the absence of periodic windows and maintains strictly positive Lyapunov exponents. This yields a precise notion of fuzzy robustness that is distinct from interval enclosures (pure bounds) and stochastic robustness (average-case guarantees). We also formalize fuzzy topological entropy via the extension principle and discuss its basic structural properties under mild continuity assumptions. For chaos-based image encryption, fuzzification provides an uncertainty-aware key representation and stabilizes cryptographic indicators across $\alpha$-cuts as follows: in our experiments, NPCR remains within $99.58$–$99.64\%$, UACI within $33.41$–$33.52\%$, and the cipher entropy is near 8 bits, while pixel correlation stays close to zero. These results support fuzzy skew maps as a robust primitive for secure information systems operating under parametric uncertainty. Full article

This study addresses the gap between predictive optimization and monitoring-oriented risk concentration by introducing a hierarchical Fuzzy Cognitive Map (FCM) framework for financial risk assessment. Financial distress prediction models are employed to estimate firm-level default probabilities and are required to comply with regulatory standards. IFRS 9 and Basel III/IV frameworks emphasize model explainability, scenario analysis and causal transparency, which are essential for compliance purposes. The methodology aggregates correlated financial ratios into financial concepts through unsupervised clustering. Concepts interact through a learned coupling matrix and a controlled multi-step propagation, which enables the amplification of risk signals. A small residual correction is applied at the final readout, preserving the interpretability of the proposed framework. The framework was applied to two severely imbalanced benchmark bankruptcy datasets. It achieved higher precision–recall performance than Logistic Regression (PR–AUC $\approx 0.32$ vs. $0.27$), improved calibration (Brier score $\approx 0.046$ vs. $0.089$) and maintained competitive Recall@Top–K under tight supervisory monitoring budgets. Hierarchical FCM achieved predictive performance comparable to nonlinear models while maintaining concept-level interpretability. Our findings demonstrate that structured concept aggregation combined with interaction-based propagation provides a transparent alternative to purely predictive black-box models in financial distress assessment and is aligned with regulatory frameworks. Full article

As traffic demand increases and intelligent transportation systems continue to develop, traffic signal control must operate reliably in complex and heterogeneous network environments, especially under communication instability. Traditional approaches often lack sufficient resilience when facing packet loss, delay, and other communication disturbances. This study proposes a resilient collaborative control (RCC) method for transportation hubs that explicitly considers communication reliability. A multi-layer computational framework is developed to support real-time mapping and interaction between physical and virtual networks. A fuzzy-logic-based communication state perception model is introduced to guide adaptive control-mode switching. To improve network-level performance, a recovery-oriented optimization algorithm is applied for dynamic load balancing across the hub area. Co-simulation results show that, compared with traditional adaptive control, the proposed method reduces average vehicle delay by 42.3%, increases network speed by 52.3%, shortens recovery time by 63%, and improves the resilience index to 0.87. These results support the effectiveness of the proposed framework within the evaluated co-simulation setting. Full article