Journal of Intelligent & Fuzzy Systems - Volume 42, issue 4

Authors: Saif, Shahela | Tehseen, Samabia

Article Type: Research Article

Abstract: Deep learning has been used in computer vision to accomplish many tasks that were previously considered too complex or resource-intensive to be feasible. One remarkable application is the creation of deepfakes. Deepfake images change or manipulate a person’s face to give a different expression or identity by using generative models. Deepfakes applied to videos can change the facial expressions in a manner to associate a different speech with a person than the one originally given. Deepfake videos pose a serious threat to legal, political, and social systems as they can destroy the integrity of a person. Research solutions are being …designed for the detection of such deepfake content to preserve privacy and combat fake news. This study details the existing deepfake video creation techniques and provides an overview of the deepfake datasets that are publicly available. More importantly, we provide an overview of the deepfake detection methods, along with a discussion on the issues, challenges, and future research directions. The study aims to present an all-inclusive overview of deepfakes by providing insights into the deepfake creation techniques and the latest detection methods, facilitating the development of a robust and effective deepfake detection solution. Show more

Keywords: Video forgery, forgery detection, deepfakes, deepfake videos, deepfake detection

DOI: 10.3233/JIFS-210625

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 2989-3009, 2022

Authors: Fathy, E. | Ammar, E. | Helmy, M.A.

Article Type: Research Article

Abstract: In real-world problems, the parameters of optimization problems are uncertain. A class of multilevel linear programming (MLLP) with uncertainty problem models cannot be determined exactly. Hence, in this paper, we are concerned with studying the uncertainty of MLLP problems. The main motivation of this paper is to obtain the solution to a multilevel rough interval linear programming (MLRILP) problem. To obtain that, we start turning the problem into its competent crisp equivalent using the interval method. Moreover, we rely on three methods to address the problem of multiple levels. First, by applying the constraint method in which upper levels give …satisfactory solutions that are reasonable in rank order to the lower levels, second, by an interactive approach that uses the satisfaction test function, and third, by the fuzzy approach that is based on the concept of the tolerance membership function. A numerical example is given for illustration and to examine the validity of the approach. An application to deduce the optimality for the cost of the solid MLLP transportation problem in rough interval environment is presented. Show more

Keywords: Multilevel linear programming, constraint method, interactive approach, fuzzy approach, rough interval programming

DOI: 10.3233/JIFS-210694

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3011-3028, 2022

Authors: Tao, Nana | Ding, Chunxiao | Zhu, Yuanguo

Article Type: Research Article

Abstract: The pessimistic value of uncertain variables is a critical value to deal with optimization problems in environments with uncertainty. In many uncertain decision problems, pessimistic values at a certain level of reliability sometimes get attention, such as the problem that the objective function is time or cost. This article introduces two definitions of pessimistic value stability and attractivity. And the corresponding judgment conditions of attractivity are presented for linear differential systems with uncertainty. Furthermore, pessimistic value stability is analyzed for three kinds of nonlinear uncertain differential systems. Then pessimistic value attractivity is considered for a kind of nonlinear differential system …with uncertainty. Show more

Keywords: Pessimistic value, uncertainty, stability, attractivity, differential systems

DOI: 10.3233/JIFS-210744

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3029-3036, 2022

Authors: Liu, Xuwang | Li, Huihui | Qi, Wei

Article Type: Research Article

Abstract: With recent developments in information technology and the extensive promotion of Internet Plus, the use of online centralized procurement by governments and enterprise groups has become progressively more common, and the winning bid evaluation decision making method is particularly important in this context. However, experts might not be completely rational during the process of bid evaluation, which may induce the enhancement or repression of bid scores. To address such behaviors during the process of bid evaluation, an automatic mechanism to identify and correct such tendencies is proposed in this study. Because experts have different preferences for different alternatives, which are …directly reflected in the evaluation of attribute values. Based on selection preference, this paper proposes a selection preference method for solving the subjective weight of attributes. Firstly, the weights of relevant attributes are first determined via the entropy weight method and the selection preference method, and the weights corresponding to groups are determined according to the differences between the scores assigned by experts. Then, a grouped multi-attribute bid evaluation decision making method is proposed based on the selection preference. Finally, an example is used to verify the effectiveness of the method and its superiority over existing methods. Thus, a theoretical basis and a decision support mechanism are provided in this study for centralized procurement departments of governments and enterprises. Further, it also provides guidance for multi-attribute decision making problems with identical grouped features. Show more

Keywords: Centralized procurement, multi-attribute decision making, selection preference, entropy weight

DOI: 10.3233/JIFS-210748

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3037-3049, 2022

Authors: Ferrari, Allan Christian Krainski | Silva, Carlos Alexandre Gouvea da | Osinski, Cristiano | Pelacini, Douglas Antonio Firmino | Leandro, Gideon Villar | Coelho, Leandro dos Santos

Article Type: Research Article

Abstract: The Whale Optimization Algorithm (WOA) is a recent approach to the swarm intelligence field that can be explored in many global optimization applications. This paper proposes a new mechanism to tune the control parameters that influence the hunting process in the WOA to improve its convergence rate. This schema adjustment is made by a fuzzy inference system that uses the normalized fitness value of each whale and the hunting mechanism control parameters of WOA. The method proposed was tested and compared with the conventional WOA and another version that uses a fuzzy inference system as input information on the ratio …of the current iteration number and the maximum number of iterations. For performance analysis of the method proposed, all optimizers were evaluated with twenty-three benchmark optimization functions in the continuous domain. The algorithms were also implemented in the identification process of two real control system that are a boiler system and water supply network. For identification process, it is used the value of MSE (mean squared error) to available each algorithm. The simulation results show that the proposed fuzzy mechanism improves the convergence of the conventional WOA and it is competitive in relation to another fuzzy version adopted in the WOA design. Show more

Keywords: Humpback whale, Metaheuristics, optimization, identification process, Whale Optimization Algorithm

DOI: 10.3233/JIFS-210781

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3051-3066, 2022

Authors: Nguyen, Linh Anh

Article Type: Research Article

Abstract: The problem of checking whether a state in a finite fuzzy labeled transition system (FLTS) crisply simulates another is one of the fundamental problems of the theory of FLTSs. This problem is of the same nature as computing the largest crisp simulation between two finite FLTSs. A naive approach to the latter problem is to crisp the given FLTSs and then apply one of the currently known best methods to the obtained crisp labeled transition systems. The complexity of the resulting algorithms is of order O  (l  (m  + n ) n ), where l is the number of fuzzy values …occurring in the specification of the input FLTSs, m is the number of transitions and n is the number of states of the input FLTSs. In the worst case, l can be m  + n and O  (l  (m  + n ) n ) is the same as O  ((m  + n ) 2 n ). In this article, we design an efficient algorithm with the complexity O  ((m  + n ) n ) for computing the largest crisp simulation between two finite FLTSs. This gives a significant improvement. We also adapt our algorithm to computing the largest crisp simulation between two finite fuzzy automata. Show more

Keywords: Fuzzy labeled transition systems, fuzzy automata, simulation, bisimulation

DOI: 10.3233/JIFS-210792

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3067-3078, 2022

Authors: Yin, Longjun | Zhang, Qinghua | Zhao, Fan | Mou, Qiong | Xian, Sidong

Article Type: Research Article

Abstract: In uncertain information processing, new knowledge can be discovered by measuring the proximity between discovered and undiscovered knowledge. Pythagorean Fuzzy Sets (PFSs) is one of the important tools to describe the natural attributes of uncertain information. Therefore, how to appropriately measure the distance between PFSs is an important topic. The earth mover’s distance (EMD) is a real distance metric that can be used to describe the difference between two distribution laws. In this paper, a new distance measure for PFSs based on EMD is proposed. It is a new perspective to measure the distance between PFSs from the perspective of …distribution law. First, a new distance measure namely D EMD is presented and proven to satisfy the distance measurement axiom. Second, an example is given to illustrate the advantages of D EMD compared with other distance measures. Third, the problem statements and solving algorithms of pattern recognition, medical diagnosis and multi-criteria decision making (MCDM) problems are given. Finally, by comparing the application of different methods in pattern recognition, medical diagnosis and MCDM, the effectiveness and practicability of D EMD and algorithms presented in this paper are demonstrated. Show more

Keywords: Pythagorean Fuzzy Sets, Intuitionistic Fuzzy Sets, Pattern recognition, Medicinal diagnosis, Multi-criteria decision making

DOI: 10.3233/JIFS-210800

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3079-3092, 2022

Authors: Wang, Zhenggang | Jin, Jin

Article Type: Research Article

Abstract: Remote sensing image segmentation provides technical support for decision making in many areas of environmental resource management. But, the quality of the remote sensing images obtained from different channels can vary considerably, and manually labeling a mass amount of image data is too expensive and inefficiently. In this paper, we propose a point density force field clustering (PDFC) process. According to the spectral information from different ground objects, remote sensing superpixel points are divided into core and edge data points. The differences in the densities of core data points are used to form the local peak. The center of the …initial cluster can be determined by the weighted density and position of the local peak. An iterative nebular clustering process is used to obtain the result, and a proposed new objective function is used to optimize the model parameters automatically to obtain the global optimal clustering solution. The proposed algorithm can cluster the area of different ground objects in remote sensing images automatically, and these categories are then labeled by humans simply. Show more

Keywords: Remote sensing, core data, nebular clustering, parameter optimization, objective function

DOI: 10.3233/JIFS-210802

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3093-3106, 2022

Authors: Xi, Dejun | Qin, Yi | Wang, Zhiwen

Article Type: Research Article

Abstract: An efficient visual detection method is explored in this study to address the low accuracy and efficiency of manual detection for irregular gear pitting. The results of gear pitting detection are enhanced by embedding two attention modules into Deeplabv3 + to obtain an improved segmentation model called attention Deeplabv3. The attention mechanism of the proposed model endows the latter with an enhanced ability for feature representation of small and irregular objects and effectively improves the segmentation performance of Deeplabv3. The segmentation ability of attention Deeplabv3+ is verified by comparing its performance with those of other typical segmentation networks using two public …datasets, namely, Cityscapes and Voc2012. The proposed model is subsequently applied to segment gear pitting and tooth surfaces simultaneously, and the pitting area ratio is calculated. Experimental results show that attention Deeplabv3 has higher segmentation performance and measurement accuracy compared with the existing classical models under the same computing speed. Thus, the proposed model is suitable for measuring various gear pittings. Show more

Keywords: Image segmentation, Deeplabv3+, attention mechanism, feature expression, gear pitting

DOI: 10.3233/JIFS-210810

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3107-3120, 2022

Authors: Wei, Dongmei | Rong, Yuan | Garg, Harish | Liu, Jun

Article Type: Research Article

Abstract: Teaching quality evaluation (TQE) can not only improve teachers’ teaching skills, but also provide an important reference for school teaching management departments to formulate teaching reform measures and strengthen teaching management. TQE is a process of grading and ranking a given teachers based on the comprehensive consideration of multiple evaluation criteria by expert. The Maclaurin symmetric mean (MSM), as a powerful aggregation function, can capture the correlation among multiple input data more efficient. Although multitude weighted MSM operators have been developed to handle the Pythagorean fuzzy decision issues, these above operators do not possess the idempotency and reducibility during the …procedure of information fusion. To conquer these defects, we present the Pythagorean fuzzy reducible weighted MSM (PFRWMSM) operator and Pythagorean fuzzy reducible weighted geometric MSM (PFRWGMSM) operator to fuse Pythagorean fuzzy assessment information. Meanwhile, several worthwhile properties and especial cases of the developed operators are explored at length. Afterwards, we develop a novel Pythagorean fuzzy entropy based upon knowledge measure to ascertain the weights of attribute. Furthermore, an extended weighted aggregated sum product assessment (WASPAS) method is developed by combining the PFRWMSM operator, PFRWGMSM operator and entropy to settle the decision problems of unknown weight information. The efficiency of the proffered method is demonstrated by a teaching quality evaluation issue, as well as the discussion of sensitivity analysis for decision outcomes. Consequently, a comparative study of the presented method with the extant Pythagorean fuzzy approaches is conducted to display the superiority of the propounded approach. Show more

Keywords: Teaching quality evaluation, Pythagorean fuzzy set, information fusion, Reducible weighted MSM, WASPAS

DOI: 10.3233/JIFS-210821

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3121-3152, 2022