FCTA 2025 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 43
Title:

Quantum Genetic Algorithm Tuning of Interval Type-2 Fuzzy State Feedback Controllers for MAGLEV Servosystems
Authors:

Israel da Silva Felix de Lima and Fábio Meneghetti Ugulino de Araújo
Abstract: Controlling magnetic levitation systems is a significant challenge due to their inherent nonlinearity, open-loop instability, and high sensitivity to uncertainties. While classical controllers struggle to provide robust performance under these conditions, advanced intelligent controllers often lack a systematic method for parameter tuning, limiting their practical effectiveness. This paper addresses these challenges by applying and evaluating an adapted quantum-inspired genetic algorithm, in comparison to a standard genetic algorithm, for the optimization of interval type-2 fuzzy state feedback controllers for magnetic levitation servocontrol. The approach leverages the robustness of interval type-2 fuzzy controllers to handle imprecisions and the optimization capabilities of these quantum-inspired algorithms to systematically tune controller parameters. The system architecture integrates a nonlinear magnetic levitation model, local controllers designed via pole placement, and a fuzzy controller that combines these through parallel distributed compensation. Both algorithms optimize the controller’s desired poles to minimize the Integral of Time-weighted Absolute Error performance metric. Simulations compare the performance of type-1 and interval type-2 fuzzy controllers, optimized by both algorithms, against non-optimized versions. Results reveal a trade-off: the controller optimized by the standard genetic algorithm achieved the lowest Integral of Time-weighted Absolute Error (6.163e-04), an improvement of 61.05% over the original, while the controller optimized by the quantum-inspired genetic algorithm yielded the lowest Root Mean Square error (0.736 mm), though both exhibited a higher overshoot. The methodology offers a flexible, computationally efficient solution for complex nonlinear systems, with potential for industrial applications. Future work may focus on multi-objective optimization to reduce overshoot and on the direct tuning of the controller’s Footprint of Uncertainty, or integrate neural networks for improved dynamic performance.
Paper Nr: 104
Title:

Haemoproteus: Infected Cells Detection in Pigeon Blood Smears Using a Fuzzy Logic-Based Framework
Authors:

Evangelia Petraki, Magnolia Maria Conde-Felipe and Carlos M. Travieso-González
Abstract: Haemoproteus columbae is a globally prevalent avian haemo sporidian parasite that infects domestic and feral pigeons (Columba livia). Diagnosing the parasitic infection requires the manual microscopic examination of blood smears by trained professionals, a time-consuming, tedious and subjective task. The main focus of this study is the presentation of a fuzzy logic-based system for the classification of histopathological cells in pigeon blood smear images and its comparison with a conventional threshold-based algorithm. The fuzzy approach yielded a cell detection F1 score of 0.9816 and a pathological cell F1 score of 0.828; the threshold method achieved similar overall detection (red blood cell and pathological cell detection F1-scores 0.9569 and 0.9197 respectively) but it has lower interpretability.
Paper Nr: 106
Title:

Predicting Slump, Slump Flow and Compressive Strength of Concrete Using Type-1 TSK Fuzzy System
Authors:

Ali Aghajari, Samin Yadollahi, Hooman Tahayori, Ali Bahadori-Jahromi and Amirhossein Moharrer
Abstract: Concrete is one of the most important construction materials in industry because of its versatile applicability in all commercials and industrial construction. Slump test measures the workability or consistency of concrete and slump flow test evaluates the flowability of the self-compacting concrete (SCC). Producing concrete with the acceptable slump value and the entire testing procedure are complex and uncertain. In this research, slump, slump flow and compressive strength tests of concrete will be examined by developing a Type-1 Takagi-Sugeno-Kang (TSK) fuzzy inference system. In this study the FIS is evaluated by metrics like root mean squared error (RMSE) and mean absolute error (MAE). The results obtained from the implemented fuzzy inference system in this research shows competitive performance compared to the existing machine learning and neural network models.
Paper Nr: 125
Title:

An Explainable Histopathological Nuclei Classification System Based on Fuzzy Decision Trees
Authors:

Pietro Ducange, Masoume Gholizade, Francesco Marcelloni, Giustino Claudio Miglionico and Fabrizio Ruffini
Abstract: The automatic classification of cell nuclei in histopathological images constitutes a fundamental component in the development of computer-aided diagnosis systems, offering valuable support in clinical decision-making and treatment planning. Despite the notable performance achieved by Deep Learning (DL) models in this domain, their limited interpretability remains a significant barrier to their adoption, especially in safety-critical fields such as healthcare. This study presents an explainable Nucleus Classification (NuC) system based on Fuzzy Decision Tree (FDT). The proposed approach leverages as input a set of human-interpretable numerical features extracted from the images of segmented nuclei. The system is evaluated on the PanNuke dataset, with a specific focus on the testicular tissue subset, and benchmarked against a Multi-Layer Perceptron (MLP) employed as a reference opaque model. Experimental results indicate that the FDT-based system attains competitive classification performance while offering intrinsically interpretable, rule-based outputs. In addition, we perform an explainability analysis demonstrating the proposed model’s capacity to generate linguistically meaningful rules that are consistent with domain-specific histopathological knowledge
Short Papers
Paper Nr: 39
Title:

Fuzzy Interval-Valued Real Options in Supply Chain Acquisition under Geopolitical Risk
Authors:

Jani Kinnunen, Irina Georgescu and Pekka Virkki
Abstract: Political shift from free trade to protectionism and emerging and escalating trade and military conflicts have amplified geopolitical risk, disruptions in global supply chains, and making these threats central to business decisions. Yet, systematic methods to assess and manage such risks remain scarce. To address this gap, we propose a novel fuzzy real options framework under geopolitical risk, integrating managerial adaptability with interval-valued scenarios. While real options theory captures the value of managerial flexibility in volatile, long-term investments, fuzzy modeling accounts for inherent ambiguity and imprecision. Building on the fuzzy root-mean-square (RMS) fuzzy pay-off method for real option valuation, our extended approach, interval RMS-FPOM, utilizes interval-valued trapezoidal fuzzy numbers to enhance risk representation and support decision-making. The method is compared to the center-ofgravity payoff approach, highlighting its advantages in practical application. A numerical example of supply chain disruption risk illustrates how real options, independent or sequential, can be exercised by firms internally or, for instance, through acquisitions to build strategic synergies. This framework provides a robust tool for valuing real options in high-uncertainty environments, such as supply chain networks, enabling more informed decisions under uncertain geopolitical tensions. In practical terms, this framework offers managers a more nuanced tool to evaluate supply chain investments, such as acquiring new facilities or switching suppliers, under the ambiguous and often unquantifiable conditions imposed by geopolitical instability, thereby improving strategic decision-making in volatile global markets.
Paper Nr: 56
Title:

Linguistic Interpretation of Natural Data Using Intermediate Quantifiers Relate to Graded Cube of Opposition
Authors:

Petra Murinova and Karel Fiala
Abstract: This paper focuses on the use of fuzzy natural logic for analyzing scientific data and describing it in linguistic expression. The outcome consists of IF-THEN rules that utilize evaluative linguistic expressions, enabling the characterization of quantitative data using vague terms such as “very small”, “large”, “medium”, and so on. Therefore, we demonstrate that the theory of intermediate quantifiers (a component of fuzzy natural logic) can be applied to these outputs automatically, allowing for more natural linguistic summaries. In addition, we introduce the idea of using generalized Peterson’s logical syllogisms which relate to graded Peterson’s cube of opposition for more detailed data analysis.
Paper Nr: 89
Title:

The Limits of Crispness: A Systematic Evaluation and New Perspective for Open Government Data (OGD) Taxonomies
Authors:

Janick Spycher and Edy Portmann
Abstract: Open Government Data (OGD) taxonomies are critical classification artifacts that structure knowledge to facilitate the understanding, analysis, and comparison of complex data and their impacts, yet their evaluation often lacks a consistent methodological foundation. This paper addresses this gap in two ways. First, it introduces a comprehensive framework for evaluating OGD taxonomies, synthesized from foundational and state-of-the-art literature in Design Science Research (DSR) and Information Systems (IS). This framework provides a structured lens to assess design process rigor, intrinsic artifact quality, and utility. Second, the paper applies this framework in a detailed, systematic evaluation of three prominent and diverse OGD taxonomies. The results of this analysis reveal a clear trend towards more rigorous development methods over time. However, they also expose a common, critical limitation rooted in the classical definition of a taxonomy: their reliance on crisp, mutually exclusive categories struggles to represent the nuanced, overlapping, and ambiguous nature of real-world OGD phenomena. This "problem of crispness" hinders their practical utility and explanatory power. As a solution, we argue for a fundamental shift in perspective. Specifically, we propose adopting fuzzy logic principles, including linguistic variables and fuzzy modifiers, to introduce flexibility and cognitive plausibility into taxonomy design. Finally, we provide a detailed blueprint outlining how such fuzzy-enhanced taxonomies can be methodically designed, implemented, and applied, thereby advancing both theoretical foundations and practical applications in the OGD field. To our knowledge, this is among the first systematic evaluations of OGD taxonomies employing a rigorously derived evaluation framework.
Paper Nr: 90
Title:

Image Denoising Using a Gerchberg-Saxton Based Data-Set and Fuzzy Logic Reasoning
Authors:

Eran Gur, Daniel Havivi and Samer Zahaykeh
Abstract: In many imaging systems the output is a noisy version of the required image due to inaccuracies in the setup or low-quality equipment. Obtaining the clean high-resolution image from its noisy version is a problem that many image processing setups have tried to deal with, some more successfully and others less. In this work the authors suggest using a large data set of images for which we know the original undamaged image, build an optimal reconstruction filter for each one using iterative methods and use this data base of filters to generate a fuzzy logic inference engine that will welcome a new unknown noisy image and by comparing it to the database generate a single reconstruction filter to denoise that image. The authors present the process of building the database and the final denoising filter and show excellent correlation results in terms of image reconstruction.
Paper Nr: 95
Title:

Selection of Fuzzy Regression Models by AIC
Authors:

Julien Rosset and Laurent Donzé
Abstract: We consider the task of selecting an optimal sub-model among a collection of fuzzy linear regression models. The Akaike criterion, also known as AIC, is a well-established measure for assessing competing models. Using the extension principle of Zadeh, we develop a simple procedure that involves sampling crisp data from fuzzy numbers to construct fuzzy AICs. We advocate a non-parametric approach, based on the empirical likelihood concept, to compute the likelihood function. Indeed, the fuzzy distribution of the stochastic part of the fuzzy regression model is not easily trackable, and no a priori distribution is theoretically justified. An empirical application shows the practicality of the method. Indeed, a collection of sub-models could be easily ordered by the generalised signed distance according to their AIC. Other ranking methods could also be applied.
Paper Nr: 128
Title:

An Elliptic Intuitionistic Fuzzy Model for Evaluating Habilitated Academic Staff Productivity in Higher Education
Authors:

Velichka Traneva, Cengiz Kahraman, Stoyan Tranev and Venelin Todorov
Abstract: This paper presents an Elliptic Intuitionistic Fuzzy Quad (E-IFQ) extension of our prior Intuitionistic Fuzzy (IF) productivity model and its circular IF variant for evaluating habilitated academic staff in STEM higher education. Productivity is assessed across core dimensions (research output, teaching/mentoring load, project leadership, academic service). Unlike the IF and circular IF models, the E-IFQ aggregation yields a centroid (aggregated membership and non-membership degrees) that can differ due to the asymmetric representation of uncertainty. The novelty lies in substituting the symmetric (circular) hesitation zone with an elliptical one, parameterized by a major and a minor axis. These axes capture asymmetric dispersion in expert assessments, allowing disagreement to manifest differently along the membership and non-membership directions. This representation separates the central value (consensus) from directional uncertainty (asymmetry), enriching interpretability and highlighting the nature of evaluator disagreement. A numerical case study illustrates that, under uneven evidence across criteria, the E-IFQ model yields more informative evaluation profiles than the circular IF counterpart, pinpointing whether disagreement concentrates in positive or negative assessments, while also capturing changes in the central score. This geometric refinement supports transparent reporting and nuanced, uncertainty-aware promotion and planning decisions at institutional level.
Paper Nr: 147
Title:

Fuzzy Implications Recursively Defined via Disjunction and Conjunction
Authors:

Alexander Sakharov
Abstract: Fuzzy models are specified by certain t-norms and t-conorms as conjunction and disjunction truth functions, respectively. The truth values of implication formulas are recursively defined via the truth values of smaller formulas including all subformulas. These models are characterized by a subset of classical first-order logic. This subset is specified as a sequent calculus with nonstandard implication inference rules. This logical characterization is possible due to the recursive implication truth functions, and it justifies the use of this class of truth functions in fuzzy systems.
Paper Nr: 93
Title:

Fuzzy Cognitive Maps Modeling for Robotics Control
Authors:

Mariana Zeitune and Regina Lanzillotti
Abstract: This paper presents a fuzzy control methodology for guiding robotic movements based on Fuzzy Cognitive Maps (FCMs). The proposed model integrates fuzzification, causal reasoning via an adjacency matrix, and defuzzifi-cation to determine real-time motor commands in an Arduino-based mobile robot. Linguistic Terms were defined for distance and speed. The influence weights were assigned and tuned through experimental test. The methodology was validated through physical experiments in which sensor readings and control outputs showed coherent behavior, demonstrating the model's ability to adapt to obstacle proximity and respond with appropriate movement adjustments. The results indicate that the FCM-based approach is a viable alternative for embedded robotic control systems, combining interpretability with responsive decision-making.
Paper Nr: 130
Title:

Comparison of Fully Electric SUV Cars by Using Interval-Valued Proportional Spherical Fuzzy Analytic Hierarchy Process
Authors:

Cengiz Kahraman, Velichka Traneva and Stoyan Tranev
Abstract: The rapid development of electric vehicle technology has led to a significant increase in the popularity of fully electric sport utility vehicles (SUVs), which offer environmental benefits and operational efficiency. However, the decision-making process for selecting the most suitable electric SUV model involves multiple criteria and inherent uncertainties. This paper proposes a novel approach for evaluating and ranking fully electric SUV alternatives using the Interval-Valued Proportional Spherical Fuzzy Analytic Hierarchy Process (IVPSF AHP). This method integrates the strengths of proportional fuzzy logic, spherical fuzzy sets, and interval-valued data to better capture expert judgments under uncertainty. A comprehensive set of evaluation criteria—including technical, economic, environmental, functional, safety, and market factors—is considered. Five SUV alternatives with similar purchasing costs are analyzed. The results indicate that brand reliability, purchase price, and driving range are the most significant factors in the selection process. The proposed methodology provides a robust and flexible decision support tool for complex multi-criteria evaluations in the electric vehicle market.