Subjects -> COMMUNICATIONS (Total: 518 journals)     - COMMUNICATIONS (446 journals)    - DIGITAL AND WIRELESS COMMUNICATION (31 journals)    - HUMAN COMMUNICATION (19 journals)    - MEETINGS AND CONGRESSES (7 journals)    - RADIO, TELEVISION AND CABLE (15 journals) DIGITAL AND WIRELESS COMMUNICATION (31 journals)
 Showing 1 - 31 of 31 Journals sorted alphabetically Ada : A Journal of Gender, New Media, and Technology       (Followers: 22) Advances in Image and Video Processing       (Followers: 24) Communications and Network       (Followers: 13) E-Health Telecommunication Systems and Networks       (Followers: 3) EURASIP Journal on Wireless Communications and Networking       (Followers: 14) Future Internet       (Followers: 84) Granular Computing IEEE Transactions on Wireless Communications       (Followers: 25) IEEE Wireless Communications Letters       (Followers: 41) IET Wireless Sensor Systems       (Followers: 17) International Journal of Communications, Network and System Sciences       (Followers: 9) International Journal of Digital Earth       (Followers: 14) International Journal of Embedded and Real-Time Communication Systems       (Followers: 9) International Journal of Interactive Communication Systems and Technologies       (Followers: 2) International Journal of Machine Intelligence and Sensory Signal Processing       (Followers: 3) International Journal of Mobile Computing and Multimedia Communications       (Followers: 2) International Journal of Satellite Communications and Networking       (Followers: 40) International Journal of Wireless and Mobile Computing       (Followers: 8) International Journal of Wireless Networks and Broadband Technologies       (Followers: 2) International Journals Digital Communication and Analog Signals       (Followers: 2) Journal of Digital Information       (Followers: 164) Journal of Interconnection Networks       (Followers: 1) Journal of the Southern Association for Information Systems       (Followers: 2) Mobile Media & Communication       (Followers: 10) Nano Communication Networks       (Followers: 5) Psychology of Popular Media Culture       (Followers: 2) Signal, Image and Video Processing       (Followers: 13) Ukrainian Information Space Vehicular Communications       (Followers: 4) Vista       (Followers: 2) Wireless Personal Communications       (Followers: 6)
Similar Journals
 Granular ComputingNumber of Followers: 0      Hybrid journal (It can contain Open Access articles) ISSN (Print) 2364-4966 - ISSN (Online) 2364-4974 Published by Springer-Verlag  [2467 journals]
• Domination in Pythagorean fuzzy graphs

Abstract: Abstract Pythagorean fuzzy set theory is much more flexible to deal with obscure and uncertain knowledge comparative to fuzzy set theory. The principal aim of this article is to expand the meanings of domination and cobondage for Pythagorean fuzzy graphs by introducing the meanings of normal domination number, abnormal independent number, normal cobondage set, and normal cobondage number. Some relevant results of these meanings describe their significance as well as applicability. We present a decision-making problem in real-world applied example which discusses the agents affecting a corporation’s yield. The presented model is, in fact, an agent-based model wherein the impact score of each agent is divided into two types of direct and indirect influences.
PubDate: 2023-01-16

• An optimization-based method for eliciting priorities from fuzzy
preference relations with a novel consistency index

Abstract: Abstract Preference relations could be originated from a decision making problem by pairwisely comparing a finite set of alternatives. In order to find an optimal solution, a feasible approach is to elicit the priorities from the derived preference relation. In this paper, we report an optimization-based approach to the priorities elicited from fuzzy preference relations (FPRs). The inherent relation between row/column vectors of FPRs with additive/multiplicative consistency is considered. Under additive consistency, the variance-based additive consistency index (VACI) of FPRs is constructed and some properties are studied. With the knowledge of multiplicative consistency, the concept of transformation-based multiplicative consistency index is proposed. Using numerical simulations, the thresholds of the proposed consistency indexes for FPRs with acceptable additive/multiplicative consistency are determined. A new method for deriving the priority vector from FPRs is proposed by constructing an optimization problem. The optimal solution is studied and some comparisons with the existing methods are made. Finally, numerical examples are carried out to show the effectiveness of the proposed approach.
PubDate: 2023-01-11

• Multi-criteria group decision-making based on an integrated PROMETHEE
approach with 2-tuple linguistic Fermatean fuzzy sets

Abstract: Abstract The preference ranking organization method for enrichment evaluation (PROMETHEE) technique is a comprehensive and efficient multi-criteria decision-making (MCDM) method. This research study is devoted to establishing an improved version of the PROMETHEE approach based on 2-tuple linguistic Fermatean fuzzy sets (2TLFFS) to address the MCDM problems when decision-makers use linguistic variables to convey their judgments about alternatives. The membership and non-membership functions of 2TLFFS are used to evaluate the weight of each criterion and the evaluation of each alternative for each criterion. We propose a new pairwise deviation formula using the score function, which is then employed to develop preference functions. To get the preferences for the alternatives, we take Gaussian and usual preference functions and use them to create a preference index matrix. The PROMETHEE I method is used to determine the partial order of alternatives by evaluating the positive outranking flow and negative outranking flow of alternatives. Furthermore, the PROMETHEE II approach obtains the total ranking of the alternatives by calculating the net outranking flow. Moreover, a flowchart is used to demonstrate the method proposed by the 2TLFF-PROMETHEE. Using a numerical example, specifically the choice of an appropriate bank manager, we establish the practical implications and realism of the proposed method. The results of the proposed work are then compared with those of the existing approach to more accurately reflect the capacity and effectiveness of the proposed work. Finally, we conclude that the 2TLFF-PROMETHEE technique established within a 2TFFS framework is highly effective and reliable in addressing MCGDM issues.Please check and confirm that the authors and their respective affiliations have been correctly identified and amend if necessary.I confirm.  Please see attched PDF file for minor corrections too.
PubDate: 2023-01-07

• Multicriteria group decision making based on projection measures on
complex Pythagorean fuzzy sets

Abstract: Abstract Complex Pythagoran fuzzy (C-PyF) set is an efficient tool to handle two dimensional periodic uncertain information which have various applications in fuzzy modeling and decision making. It is known that the aggregation operators influence decision making processes. Frank algebraic operator is one of the important and widely used operators in decision making techniques that deal with uncertain problems. This paper investigates arithmetic and geometric complex Pythagorean fuzzy Frank aggregation operators with the help of Frank operational laws. Further the necessary properties of the developed aggregation operators (AOs) are discussed. The distance and similarity measures of two C-PyF sets is still an open problem and distinguished research have been conducted. The complex projection measure is also one of the unexplored research areas in complex fuzzy scenario. The major part of this paper is dedicated to utilize C-PyF sets to develop complex Pythagorean fuzzy projection measure between alternatives and the relative complex Pythagorean fuzzy ideal solution (RCPFIS). Further, these AOs and complex projection measures have been employed in modeling a multicriteria group decision making (MCGDM) method. Then the proposed weighted C-PyF projection based MCGDM model is illustrated with an experimental analysis on frequency identification. Finally, a comparative study is conducted to show the validity of the proposed C-PyF projection model.
PubDate: 2023-01-01

• Feature ranking based on an improved granular neural network

Abstract: Abstract In this paper, we try to solve the feature ranking problem through an allocation of information granularity. In many real applications, people are more concerned with an ordered sequence, especially a sequence with a few most important features. However, the outcome of the feature selection methods is often not stable. We proposed an improved granular neural network framework to provide a comparable stable ordered sequence. Unlike other granular neural networks, this network uses information granules as input and generates granular output which is optimized with higher generality and specificity. This way, the construction of the sequence of ordered features is realized from a more comprehensive perspective (neither regression nor classification). The information granules are formed by allocating a level of information granularity onto numeric features and then being optimized through an optimization tool (genetic algorithm for instance). Computational experiments on both synthetic and real data sets are performed to compare the stability of our algorithm. The results show consistency with experts’ suggestions.
PubDate: 2023-01-01

• Enhancing drug–drug interaction prediction by three-way decision and
knowledge graph embedding

Abstract: Abstract Drug–Drug interaction (DDI) prediction is essential in pharmaceutical research and clinical application. Existing computational methods mainly extract data from multiple resources and treat it as binary classification. However, this cannot unambiguously tell the boundary between positive and negative samples owing to the incompleteness and uncertainty of derived data. A granular computing method called three-way decision is proved to be effective in making uncertain decision, but it relies on supplementary information to make delay decision. Recently, biomedical knowledge graph has been regarded as an important source to obtain abundant supplementary information about drugs. This paper proposes a three-way decision-based method called 3WDDI, in combination with knowledge graph embedding as supplementary features to enhance DDI prediction. The drug pairs are divided into positive, negative and boundary regions by Convolutional Neural Network (CNN) according to drug chemical structure feature. Further, delay decision is made for objects in the boundary region by integrating knowledge graph embedding feature to promote the accuracy of decision-making. The empirical results show that 3WDDI yields up to 0.8922, 0.9614, 0.9582, 0.8930 for Accuracy, AUPR, AUC and F1-score, respectively, and outperforms several baseline models.
PubDate: 2023-01-01

• Multiple attribute group decision-making based on novel probabilistic
ordered weighted cosine similarity operators with Pythagorean fuzzy
information

Abstract: Abstract The cosine similarity measure has been widely studied under different information environments. Generally, average cosine similarity values are used to find the degree of similarity between two sets of elements. This paper proposes some new cosine similarity aggregation operators based on the ordered weighted averaging (OWA) and the probabilistic ordered weighted averaging (POWA) operators. First, we define the generalized Pythagorean fuzzy ordered weighted cosine similarity (GPFOWCS) operator using the generalized ordered weighted averaging (GOWA) operator in the normalization process of the cosine similarity measure. Several mathematical properties, particular cases, and families of the GPFOWCS operator are discussed. Next, the work defines the generalized Pythagorean fuzzy probabilistic ordered weighted cosine similarity (GPFPOWCS) operator that integrates probabilistic information, OWA weighting vector, and Pythagorean fuzzy cosine similarity values in a single formulation. The GPFPOWCS operator satisfies various desirable properties and includes a wide range of particular cases. The further generalizations of GPFOWCS and GPFPOWCS operators are also introduced utilizing the quasi-arithmetic means in the normalization process of the cosine similarity values. Next, a new multiple attribute group decision-making (MAGDM) approach based on the GPFPOWCS operator is formulated in the Pythagorean fuzzy context and illustrated with a numerical example regarding the selection of robots in the Aeronautics company. A comparative study with the existing approach is also presented to demonstrate the superiority and advantage of our formulated method. The experimental results suggest that the proposed cosine similarity aggregation operators provide an ability to the decision-makers for analyzing the final decision in a wide range of scenarios under real-world complex situations.
PubDate: 2023-01-01

• An efficient method for solving neutrosophic Fredholm integral equations
of second kind

Abstract: Abstract In this article, a numerical method for the solution of neutrosophic Fredholm integral equation has been investigated. In addition, the neutrosophic Fredholm integral equation has been presented in the sense of $$(\alpha ,\beta ,\gamma )-$$ cut using Riemann integration approach. Some basic properties of neutrosophic calculus such as neutrosophic integral, neutrosophic continuity have been introduced. An iterative method has been modified in neutrosophic environment to find the numerical solution of Fredholm integral equation of second kind. The convergence of the iterative method in neutrosophic environment has been demonstrated in terms of some theorems. In the iterative method, trapezoidal rule has been used to evaluate the integral and find the approximate solution of the equation. In addition, the convergence of the trapezoidal approximations has been provided in terms of theorem. The algorithm of the proposed method has been given in the numerical method section, which briefly helps to understand the proposed method. A comparison of our method with other existing methods has been discussed to show the efficiency and reliability of our proposed method. In addition, a brief discussion about the advantages and limitations of our method has been provided. Some numerical examples have been examined to show the validation and effectiveness of the proposed method. In addition, different types of error analysis have been investigated by providing different types of tables and figures.
PubDate: 2023-01-01

• Coarsest granularity-based optimal reduct using A* search

Abstract: Abstract The optimal reduct computation problem aims to obtain the best reduct out of all possible reducts of a given decision system. In the rough set literature, two optimality criteria exist for computing an optimal reduct: shortest length based and coarsest granular space based. The coarsest granular space-based optimal reduct has the ability to induce a better generalizable classification model. The $$A^*RSOR$$ is an existing $$A^*$$ search-based optimal reduct computation algorithm that uses the coarsest granular space as an optimality criterion. This article proposes an improved coarsest granularity-based optimal reduct approach $$MA^*\_RSOR$$ through analyzing the search process’s behaviour in $$A^*RSOR$$ algorithm. To minimize the search space utilization and arrive at an optimal reduct in less time, suitable modifications are incorporated using the domain knowledge of rough set theory. The relevance of $$MA^*\_RSOR$$ is demonstrated through theoretical analysis and comparative experimental validation with state-of-the-art algorithms. The experimental results with benchmark data sets established that $$MA^*\_RSOR$$ achieves significant computational time gain ( $$49-99\%$$ ) and space reduction ( $$37-96\%$$ ) over $$A^*RSOR$$ . The $$MA^*\_RSOR$$ could induce classification models with significantly better classification accuracies than state-of-the-art shortest length-based optimal/near-optimal reduct computation algorithms. In addition, a coefficient of variation based $$CV_{\text {NonCore}}$$ heuristic is proposed for predicting when the $$MA^*\_RSOR$$ algorithm is appropriate to use. Experimental results validate the relevance of the heuristic as its prediction turned out correctly in 8 out of 10 data sets.
PubDate: 2023-01-01

• Modified Pi Sigma artificial neural networks for forecasting

Abstract: Abstract Pi Sigma artificial neural networks are a type of high-order neural network used in time series forecasting problems. In the Pi Sigma artificial neural networks, the weights between the hidden layer and the output layer are taken as constant and one, and the biases as constant and zero. Although this feature of the Pi Sigma artificial neural networks enables it to work with fewer parameters, it can also be seen as an obstacle to obtaining better forecasting performance. In this study, unlike classical Pi Sigma artificial neural networks, a modified Pi Sigma artificial neural network is proposed by taking the weights and biases as variables between the hidden layer and the output layer of the network. Thus, direct processing of the information coming to the output layer is prevented and the information coming to the output layer is weighted using different weights and bias values. The process of optimizing all the weights and bias values between the input and hidden layer, the hidden layer, and the output layer of the network is carried out together with the particle swarm optimization method. The proposed modified Pi Sigma artificial neural networks are compared with some other artificial neural networks in the literature by analyzing much well-known time series. As a result of the applications, it is seen that the forecasting performance of the modified Pi Sigma artificial neural networks is better than both the classical Pi Sigma artificial neural networks and many other artificial neural networks.
PubDate: 2023-01-01

• Linguistic multi-criteria decision-making aggregation model based on
situational ME-LOWA and ME-LOWGA operators

Abstract: Abstract The evaluated data with multiplicative or linguistic preferences should be aggregated with information fusion and aggregation that are important research topics in many fields, such as neural networks, fuzzy logic controllers, expert systems, group decision-making, and multi-criteria decision-making (MCDM). Ordered weighted averaging operators have been extensively adopted to handle MCDM problems. However, previous operators are usually independent of their situations and cannot reflect the change in decision situations. Besides, how to solve MCDM problems with feasible operators is still an interesting direction. To resolve above problems, a linguistic MCDM aggregation model is proposed in this paper, which contained two linguistic and situational operators, that is, situational maximal entropy linguistic ordered weighted averaging and maximal entropy linguistic ordered weighted geometric averaging operators. This proposed model has their ability to handle MCDM problems under different decision situations according to the decision-maker’s preference toward criteria. The proposed model is applied to two previous datasets, which are the evaluation of the best main battle tank and the best school in a university. The results of this paper indicate that the proposed model can deal with the situational group MCDM problems with linguistic or multiplicative and linguistic preferences based on proposed operators.
PubDate: 2023-01-01

• Knowledge and accuracy measure based on dual-hesitant fuzzy sets with
application to pattern recognition and site selection for solar power
plant

Abstract: Abstract Dual hesitant fuzzy set (DHFS) is an encyclopedic set that comprises fuzzy set, intuitionistic fuzzy set, and hesitant fuzzy set as its particular cases. Knowledge and accuracy measures in various vague environments are useful to study the problems in decision-making and pattern analysis. In this paper, we first propose a knowledge and accuracy measure based on DHFSs and contrast their performance with some existing measures in the dual-hesitant fuzzy environment. We also show the application of our proposed information measures (knowledge measure and accuracy measure) in solving the problem of site selection for the installation of a solar power plant. In the site selection problem in context of our proposed measures, we also investigate the suitability of an appropriate multiple criteria decision-making method. Finally, we show the application of our proposed dual-hesitant fuzzy accuracy measure in pattern recognition, where we show how our proposed accuracy measure is better than some exiting distance and similarity measures of DHFSs.
PubDate: 2023-01-01

• Multi-attribute group decision making based on T-spherical fuzzy soft
rough average aggregation operators

Abstract: Abstract This research article aims at establishing the foundations of generalized hybrid frameworks for dealing with uncertainties in knowledge-based systems. First, by combining the notions of picture fuzzy soft set, spherical fuzzy soft set, and T-spherical fuzzy soft set with a rough set, we introduce the novel models of Picture Fuzzy Soft Rough Sets (P $$_{\mathrm{c}}$$ FSRSs), Spherical Fuzzy Soft Rough Sets (S $$_{\mathrm{p}}$$ FSRSs), and T-Spherical Fuzzy Soft Rough Sets (T $$_{\mathrm{s}}$$ FSRSs) for the parameterized fuzzy modelling of inconsistent data. Moreover, we explore some basic operational laws and fundamental properties of the developed models. We introduce a family of promising aggregation operators, namely, picture fuzzy soft rough ordered weighted averaging operator (P $$_{\mathrm{c}}$$ FSROWAO), picture fuzzy soft rough ordered weighted geometric operator (P $$_{\mathrm{c}}$$ FSROWGO), spherical fuzzy soft rough ordered weighted averaging operator (S $$_{\mathrm{p}}$$ FSROWAO), spherical fuzzy soft rough ordered weighted geometric operator (S $$_{\mathrm{p}}$$ FSROWGO), T-spherical fuzzy soft rough ordered weighted averaging operator (T $$_{\mathrm{s}}$$ FSROWAO), and T-spherical fuzzy soft rough ordered weighted geometric operator (T $$_{\mathrm{s}}$$ FSROWGO). We inspect some dominant peculiarities of these proposed operators inclusive of idempotence, boundedness and monotonicity. Further, we design a proficient approach using the proposed operators to untangle the complexity behind multi-attribute group decision making in real-world problems. We validate the effectiveness of the proposed technique by investigating its high potential in two real-world case studies. Finally, we demonstrate a comparative analysis of the proposed methodology with existing decision-making techniques to substantiate the accountability of the developed strategy.
PubDate: 2023-01-01

• A perceptual computer for hierarchical portfolio selection based on
interval type-2 fuzzy sets

Abstract: Abstract Today’s advancements have made financial markets accessible to everyone; hence, portfolio selection has become an individualized decision-making problem without the need of being highly educated. Individual judgments, however, are subjective and are influenced by the individual’s background, experience, and views. Existing methods do not account for the personalized criteria and preferences or do not let people express their preferences and assessments using words or terms from natural languages. This paper proposes a framework for an individualized hierarchical portfolio selection system based on perceptual computing. The proposed method assists individuals to rank and select portfolios based on their personalized criteria and preferences and according to their subjective assessments. In this paper, words that are used to express one’s preferences, evaluations, and weights are modeled with interval type-2 fuzzy sets (IT2FS), which allows handling different levels of linguistic uncertainties with manageable computational complexities. The proposed method is applicable to any set of criteria and sub-criteria devised to evaluate portfolios. Moreover, it enables different individuals with different expertise levels to evaluate those criteria. The conducted experiments show that the proposed method, compared to other methods, is reliable and robust to the linguistic uncertainties and provide plausible recommendations.
PubDate: 2023-01-01

• Multicriteria decision-making based on the confidence level Q-rung
orthopair normal fuzzy aggregation operator

Abstract: Abstract Q-rung orthopair fuzzy sets have been widely utilized in recent years to encounter uncertainties. At the same time, the idea of normal fuzzy numbers seems closer to human thinking. The notion of the Q-rung orthopair normal fuzzy set is a more flexible tool to capture the uncertainties because of the combined concept of Q-rung orthopair fuzzy sets and normal fuzzy numbers. This paper proposes some new weighted averaging, weighted geometric, ordered weighted averaging, and ordered weighted geometric aggregation operators for Q-rung orthopair normal fuzzy numbers, which also comprise the confidence level for the alternatives given by the decision-maker. We then introduce a multicriteria decision-making approach based on these operators to get more rational results than the existing approaches. Furthermore, to prove the superiority of the proposed approach, a comparative analysis with the different existing methods has also been done. Finally, sensitivity analyses on the parameter Q and the confidence level of Q-rung orthopair normal fuzzy numbers have been demonstrated to highlight the importance of these parameters and to show the stability of the proposed method.
PubDate: 2023-01-01

• Multiple attribute decision making based on probabilistic generalized
orthopair fuzzy sets

Abstract: Abstract The advent of Yager’s generalized orthopair fuzzy sets (also called q-rung orthopair fuzzy sets) has brought more possibilities to accomplish the challenging task of modelling uncertainties. Compared with Pythagorean fuzzy sets and intuitionist fuzzy sets, q-rung orthopair fuzzy sets are more general in theory and more powerful in practice. Nevertheless, these extensions of fuzzy sets all assume that the membership and non-membership grades are equally important for every element. However, membership and non-membership grades may have different degrees of importance in real decision-making applications. Thus it may cause information loss if intuitionistic fuzzy sets or their extensions are used to describe initial decision information in such cases. To fill the gap, we consider adding the probability information which reflects the importance of membership and non-membership grades to further enhance generalized orthopair fuzzy sets in this study. Firstly, we put forth probability generalized orthopair fuzzy numbers, which extend generalized orthopair fuzzy numbers with membership and non-membership probabilities. We define some basic operations of probability generalized orthopair fuzzy numbers and investigate their related properties. We also presented a partial order $$\le _{L_{q}^{*}\times L^{*}}$$ and a lexicographic order $$\le _{(s,h)}$$ for comparing probability generalized orthopair fuzzy numbers. Also, we define the accuracy and (normalized) score functions of probability generalized orthopair fuzzy numbers, and discuss their basic properties. Secondly, three different probabilistic generalized orthopair fuzzy aggregation operators, namely the probabilistic generalized orthopair fuzzy simple weighted averaging operator, the probabilistic generalized orthopair fuzzy weighted averaging operator and the probabilistic generalized orthopair fuzzy weighted geometric operator are defined, and their fundamental properties are explored in detail. The Minkowski distance and closeness index of probabilistic generalized orthopair fuzzy numbers are proposed, which can be used to develop an attribute weight determination method. Thirdly, we introduce probabilistic generalized orthopair fuzzy sets, and develop two methods for solving multiple attribute decision making problems based on probabilistic generalized orthopair fuzzy sets. As an illustration, the proposed methods are used to solve a green supplier selection problem with unknown attribute weight information. Furthermore, we compare our methods with several existing decision-making approaches to validate the efficacy of the proposed methods.
PubDate: 2022-12-28

• Correlation coefficients for T-spherical fuzzy sets and their applications
in pattern analysis and multi-attribute decision-making

Abstract: Abstract T-spherical fuzzy set is an effective tool to deal with vagueness and uncertainty in real-life problems, especially in a situation when there are more than two circumstances, like in casting a ballot. The correlation coefficient of T-spherical fuzzy sets is a tool to calculate the association of two T-spherical fuzzy sets. It has several applications in various disciplines like science, management, and engineering. The noticeable applications incorporate pattern analysis, decision-making, medical diagnosis, and clustering. The aim of this article is to introduce some correlation coefficients for T-spherical fuzzy sets with their applications in pattern recognition and decision-making. The under discussion correlation coefficients are far more advantageous than the existing and many other tools used for T-spherical fuzzy sets, because they are used completely and demonstrate the nature as well as the limit of association between two T-spherical fuzzy sets. Further, an application of proposed correlation coefficients in pattern analysis is discussed here. In addition to it, the proposed correlation coefficients are applied to a multi-attribute decision-making problem, in which the selection of a suitable COVID-19 mask is presented. A comparative analysis has also been made to check the effectiveness of the proposed work with the existing correlation coefficients.
PubDate: 2022-12-26

• Defect classification of glass substrate using deep neuro-fuzzy network
with optimal parameter combination

Abstract: Abstract Currently, numerous smart products are based on glass substrates. However, defects that occur during the production of glass substrates affect the quality and safety of the final products. Accordingly, we developed an optimal-parameter-combination-based deep neuro-fuzzy network (O-DNFN) for classifying defects in glass substrate images. The proposed O-DNFN comprises a deep neuro-fuzzy network (DNFN) and uses the Taguchi method. The fusion layer of the DNFN uses four feature fusion methods. The neuro-fuzzy network in the DNFN serves as replacement to a fully connected network for the classification of defects in glass substrate images. Because O-DNFN model parameter selection is challenging, we used the Taguchi method to determine the optimal parameter combination through fewer experiments. The experimental results revealed that the accuracy rates of the proposed O-DNFN with global max pooling fusion and an LeNet model in classifying defects in glass substrate images were 91.8% and 88%, respectively.
PubDate: 2022-12-16

• Concept-wise granular computing for explainable artificial intelligence

Abstract: Abstract Artificial neural networks offer great classification performances, but their internal model works as a black box. This can prevent their outcomes to be employed in real-world decision-making processes, e.g., in smart manufacturing. To address this issue, the neural network should provide human-comprehensible explanations for their outcomes. This can be achieved by exploiting domain concepts and measuring their importance for the classification. To this aim, we implement an information granulation process via a neural network specifically trained to represent data instances featuring the same (different) concept’s item close to (far away from) each other. By combining the representations for each concept, we obtain the so-called conceptual space embedding. The classification is obtained by processing it via a neural network classifier. The conceptual space embedding (i) organizes the data instances according to their concepts-wise proximity, resulting in a very informative data representation; this translates into greater classification accuracy if compared to a concept-wise approach from the state-of-the-art; and (ii) encodes each concept in one of its parts; this enables the measurement of the importance of one concept by manipulating the corresponding part of the conceptual space embedding. The proposed approach has been tested with real-world data from smart manufacturing.
PubDate: 2022-12-13

• Analysis of incommensurate multi-order fuzzy fractional differential
equations under strongly generalized fuzzy Caputo’s differentiability

Abstract: Abstract Analytical studies of fuzzy fractional differential equations (FFDEs) of two different independent fractional orders are often complex and difficult. It is essential to develop comprehensive schemes for the solutions of FFDEs with independent orders. This article introduces and investigates the fully closed-form analytical solutions of FFDEs involving two different independent fractional orders under the strongly generalized Hukuhara differentiability (SGHD). Based on the concept of SGHD, we extract two possible solutions of FFDEs in terms of the Mittag-Leffler function. Potential solutions for homogeneous and inhomogeneous FFDEs are obtained using the definition of the fuzzy Laplace transform technique. Some interesting properties and results for the FFDEs are introduced using the concepts of SGHD. We illustrate some examples as applications to explain the effectiveness of our proposed results. FFDE has a variety of applications in science and engineering. To enhance the functional significance of this work, we solve the RLC circuit using the proposed technique in a fuzzy setting to analyze and interpret the theoretical results.
PubDate: 2022-11-20

JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762