International Journal of Fuzzy Systems最新文献

In general, Hausdorff distance considers the maximum distance between two sets, making it less sensitive to outliers. Besides, fuzzy clustering often encounters challenges such as noise and fuzziness in data. Hausdorff distance provides a degree of resistance to such challenges by considering the maximum distance between two sets rather than just the average distance or distance between centroids. This robustness makes it effective in handling fuzzy and uncertain data. Hence, in this paper Hausdorff distance is proposed on interval generalized improved fuzzy partitions fuzzy C-means clustering algorithm for symbolic interval data analysis (SIDA). In general, the SIDA extends traditional statistics to analyze complex data types like intervals, useful for imprecise or aggregated data. In these datasets, noise issues are inevitable. This paper addresses clustering for SIDA, focusing on handling noise. This paper proposes the interval generalized improved fuzzy partitions fuzzy C-means (IGIFPFCM) under Hausdorff distance clustering algorithm, which uses competitive learning to handle symbolic interval data with improved robustness and convergence performance. Besides, this algorithm is less sensitive to small perturbations or outliers in the datasets due to the Hausdorff distance considering the worst-case scenario (the farthest point) rather than averaging distances, which can be skewed by outliers. From the experimental results, the statistical results of convergence and efficiency on performance show that the proposed IGIFPFCM under Hausdorff distance clustering algorithm has better results for SIDA with large outliers and noise under Student's t-distribution.

In this paper, a predefined-time adaptive fuzzy tracking control method is proposed for uncertain nonlinear systems with multiple actuator constraints and external disturbances. The unknown dynamic part of the system is dealt with by means of the fuzzy approximation theory, and the unmeasured state in the system is approximated by the constructed fuzzy state observer. On the basis of the observer, a novel predefined-time control scheme is developed to ensure that the system can achieve the practical predefined time stable (PPTS). Combined with the stability analysis, the virtual control input with predefined time can be obtained, and its derivative can be estimated by the first-order filter. Theoretical analysis shows that the proposed controller achieves a small residual set of error convergence to the origin in a predefined time. Finally, the feasibility of the theoretical results is demonstrated through simulation examples.

Interval-valued picture fuzzy sets (IVPFSs) being the most advanced form of fuzzy sets (FSs) has more capacity to analyze the network state more intelligently. It is proven that IVPFS is most useful to solve many real life problems having uncertainties. In comparison with the other generalizations of fuzzy graphs (FGs), IVPFG is proven more beneficial in solving complicated problems containing uncertainties. In this study, we propose some new concepts of covering and matching in IVPFGs based on strong arcs. We begin our study by introducing the concepts of covering in IVPFGs which includes strong node covering (SNC), strong arc covering (SAC), strong arc covering number (SAC number), and strong independent set (SIS). Based on these terms, we provide several characterizations of different types of IVPFGs like complete IVPFGs and complete bipartite IVPFGs. Afterward, we introduce the terms matching, strong matching etc for IVPFGs. We also present some useful results related to some special IVPFGs with respect to these terms. Finally, we provide the utilization of strong arcs and SIS in order to arrange the meeting of the members of social network comprising players engaged in diverse games.

This paper aims to propose a novel correlation coefficient (CC) that is more realistic in a probabilistic dual hesitant fuzzy (PDHF) setting. As is well known, CC is a very useful tool for measuring the correlation between two sets and plays a crucial role in multi-attribute decision-making (MADM) issues. Some CCs in fuzzy settings have been proposed one after another, and decision-making methods based on CCs have been proposed and applied to related practical decision-making issues. However, when reviewing CC in PDHF setting, we found that the range of CC values is all [0,1], but this is not entirely in line with reality because the range of CC in the real number range is [−1,1]. Therefore, it is imperative to propose a novel CC that is more in line with reality. This not only provides theoretical support for the development of PDHFS but also better solves practical problems, which has very important theoretical and practical significance. Firstly, we defined the mean membership degree and mean non-membership degree of probabilistic dual hesitation fuzzy element (PDHFE). Secondly, in order to maintain consistency and order in the lengths of MD and NMD in two PDHFSs, a method of adding PDHFE to shorter MD or NMD and a sorting method after adding new elements were defined. Thirdly, a new CC and its weighted form have been developed, and some of its excellent performance has been studied in detail. Fourthly, a multi-attribute decision-making method based on PDHFWCC was established, and specific calculation steps were provided. Finally, the constructed MADM method will be used for evaluating project manager candidates to demonstrate the feasibility and practicality of the proposed MADM method. Meanwhile, a comparison was made between the MADM method and several existing MADM methods, demonstrating the effectiveness of the MADM method and highlighting its advantages.

In the Normative Multi-agent Systems (NorMAS) field, norms are designed and specified as regulatory mechanisms intending to outline the ideal and appropriate behavior for the agents. To that end, norms are enforced via sanctions, considering that agents can choose to comply with the norm. Enforcement of norms responds to norm violations (i.e., punishment) or compliance (i.e., reward), which has recently been accepted as a sanction. Also, fuzzy enforcement refers to norm enforcement based on provided fuzzy reasoning process outputs. In this paper, we propose a novel fuzzy enforcement approach called FE4NorOMAS for distributed Fuzzy Enforcement FOR Normative Open Multi-Agent Systems aiming to make sanctions more flexible in the sense that they will be performed over several levels of restrictions. Flexible sanctions allow autonomous agents to accommodate their behaviors according to the norm. The more the behavior follows the norm, the greater the reward. On the other hand, the greater the violation of the norm, the greater the penalty. The feasibility of the proposed approach is tested using several traffic signing system scenarios on the MaDKit agent platform.

ELECTRE TRI-C is a method for sorting problems with imprecise evaluations and stable criteria weights, typically for a single decision-maker. While some extensions have addressed uncertain criteria weights and outranking functions using hesitant fuzzy sets (HFS) and interval type 2 trapezoidal fuzzy numbers (IT2TrfN), there is a gap in handling situations where multiple decision-makers provide uncertain information. This paper presents an extension of the ELECTRE TRI-C method incorporating a stochastic framework to model HFS and IT2TrfN, thereby accommodating subjective judgments from multiple decision-makers. The extended method was validated by sorting 49 projects based on their criticality in a Brazilian electrical power company, involving three decision-makers. The application shows strong correlations in project rankings among decision-makers, but with some exceptions. However, significant variations in acceptability ratings for sorting among decision-makers lead to notable error dispersion, highlighting differences between ranking and sorting outcomes. The key contributions of our approach are as follows: (1) Integration of subjective judgments from multiple decision-makers using IT2TrFN and Monte Carlo Simulation for constructing outranking functions; (2) Aggregation of preferences from multiple decision-makers using HFS; (3) Stochastic processing of both quantitative and qualitative criteria; (4) Integration of linear equations to represent weight constraints; and (5) Introduction of a novel visualization method for comprehensive analysis of stochastic results, enhancing robustness analysis. The proposal’s advantages over alternative methods are also highlighted.

This study aims to guide policymakers in allocating resources and planning for the future by consistently estimating energy data trends. Because of the complexity and uncertainty of energy demand behavior and many influencing factors, we decide to take advantage of a fuzzy regression model to determine the actual relationships in the energy demand system and provide an accurate forecast of energy demand. For this purpose, because of energy demand drivers, fuzzy possibilistic approaches with symmetric and non-symmetric triangular coefficients are integrated with the autoregressive distributed lag (ARDL) model, each in a time-series format with feedback mechanisms inside. After regularizing the L1 (Lasso regression) and L2 (ridge regression) metrics to minimize the overfitting problem, the optimal fuzzy-ARDL model is obtained. Turkey’s primary energy consumption is projected based on the best model by benchmarking the static and dynamic possibilistic fuzzy regression models according to their training and test values.

Single abnormal gene structure of disorders, specifically the alpha (α) and beta (β) thalassemia recessive disorders are focused. From the NCBI website, the preferred DNA sequencing is downloaded. The objective is to study the structure of Single Abnormal Gene using modified Box counting principle and FFD-Fuzzy Fractal Dimension analysis. Initially the fractal dimension method is used and analyzed single abnormal gene structure with the help of box counting method where the grids are segmented into triangles. Further the analysis is enhanced through grid and triangular method of improved box counting methods named as Ruby Triangular dimension which is the novelty of the research. Comparison of Grid Dimension with Triangular Dimension based fractal and fuzzy fractal dimension in the severity of disease from its secondary structure of the disorder related genes structures are performed. Further the complexity of the Single Abnormal Gene structure evaluated to generate a unique Attractor for the prediction of the α-thalassemia and β-thalassemia disorder in earlier diagnosis, refer as bifurcation theory. The results shows that the triangular Ruby Dimension based improved box counting method facilitate quick with more exactitude. In grid method the size of the image should be 2ⁿ pixels and shrink to at most 2048 pixels, whereas the triangular pixels may be reduced to 2³ times than grid method. Hence, this novel Fuzzy Fractal Ruby Triangular Dimension method shows better results and can be applied for image of higher dimensions with the same procedure.

This paper presents a novel intelligent control method using an output recurrent fuzzy broad learning system (ORFBLS) for robust setpoint tracking control of nonlinear digital multi-input multi-output (MIMO) time-delay dynamic systems and one real industrial extrusion barrel, in order to effectively adapt to changing setpoints and exogenous disturbances. The weighting parameters of the used ORFBLS controller are iteratively updated using the deepest gradient descent algorithm to recursively minimize the quadratic form of tracking errors, and its closed-loop stability is well analyzed by establishing a sufficient inequality condition of a learning rate. The effectiveness, superiority, and applicability of the proposed controller are well demonstrated by conducting three comparative simulations and experimental results on a real extrusion barrel in a plastic injection molding machine. These results indicate that the proposed MIMO ORFBLS control method works well with a better robust setpoint tracking performance and a better disturbance rejection.

Intuitionistic fuzzy sets have been widely studied and applied as an important means of dealing with information uncertainty. However, the existing intuitionistic fuzzy sets and their extension methods are limited and single in their fuzzy spatial representation of information. Under this environment, this paper proposes a new generalized fuzzy set, called qth Rung Root Orthopair Fuzzy Sets (q-RROFS). Since the q-RROFS can adjust the range of fuzzy space expression by the parameter q, it is superior to intuitionistic fuzzy sets, SR-fuzzy sets, and CR-fuzzy sets. We give some definitions and properties of q-RROFS and give their proofs. Under the q-RROFS, we give its operations and properties and introduce four new weighted aggregation operators, namely, qth Rung Root Orthopair Fuzzy-weighted average operator (q-RROFWA), qth Rung Root Orthopair Fuzzy-weighted geometric operator (q-RROFWG), qth Rung Root Orthopair Fuzzy-weighted power average operator (q-RROFWPA), and qth Rung Root Orthopair Fuzzy-weighted power geometric operator (q-RROFWPG). We discuss the properties of these operators in detail and follow the proof procedure. Then, we give a Multi-criteria decision-making approach under q-RROFS. Finally, we illustrate the effectiveness and applicability of the proposed methodology through practical application examples and comparisons with other methods.