Journal of Intelligent & Fuzzy Systems - Volume 40, issue 5

Authors: Gan, Zibang | Zeng, Biqing | Cheng, Lianglun | Liu, Shuai | Yang, Heng | Xu, Mayi | Ding, Meirong

Article Type: Research Article

Abstract: In multi-turn dialogue generation, dialogue contexts have been shown to have an important influence on the reasoning of the next round of dialogue. A multi-turn dialogue between two people should be able to give a reasonable response according to the relevant context. However, the widely used hierarchical recurrent encoder-decoder model and the latest model that detecting the relevant contexts with self-attention are facing the same problem. Their given response doesn’t match the identity of the current speaker, which we call it role ambiguity. In this paper, we propose a new model, named RoRePo, to tackle this problem by detecting the …role information and relative position information. Firstly, as a part of the decoder input, we add a role embedding to identity different speakers. Secondly, we incorporate self-attention mechanism with relative position representation to dialogue context understanding. Besides, the design of our model architecture considers the influence of latent variables in generating more diverse responses. Experimental results of our evaluations on the DailyDialog and DSTC7_AVSD datasets show that our proposed model advances in multi-turn dialogue generation. Show more

Keywords: Dialogue system, natural language generation, multi-turn dialogue, deep learning

DOI: 10.3233/JIFS-202641

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10003-10015, 2021

Authors: Akram, Muhammad | Shumaiza,

Article Type: Research Article

Abstract:  The q -rung picture fuzzy sets serve the fuzzy set theory as a competent, broader and accomplished extension of q -rung orthopair fuzzy sets and picture fuzzy sets which exhibit excellent performance in modeling the obscure data beyond the limits of existing approaches owing to the parameter q and three real valued membership functions. The accomplished strategy of VIKOR method is established on the major concepts of regret measure and group utility measure to specify the compromise solution. Further, TOPSIS method is another well established multi-criteria decision-making strategy that finds out the best solution with reference to the distances …from ideal solutions. In this research study, we propose the innovative and modified versions of VIKOR and TOPSIS techniques using the numerous advantages of q -rung picture fuzzy information for obtaining the compromise results and rankings of alternatives in decision-making problems with the help of two different point-scales of linguistic variables. The procedure for the entropy weighting information is adopted to compute the normal weights of attributes. The q -rung picture fuzzy VIKOR (q -RPF VIKOR) method utilizes ascending order to rank the alternatives on the basis of maximum group utility and minimum individual regret of opponent. Moreover, a compromise solution is established by scrutinizing the acceptable advantage and the stability of decision. In the case of TOPSIS technique, the distances of alternatives to ideal solutions are determined by employing the Euclidean distance between q -rung picture fuzzy numbers. The TOPSIS method provides the ranking of alternatives by considering the descending order of closeness coefficients. For explanation, the presented methodologies are practiced to select the right housing society and the suitable industrial robot. The comparative results of the proposed techniques with four existing approaches are also presented to validate their accuracy and effectiveness. Show more

Keywords: q-Rung picture fuzzy numbers, VIKOR, TOPSIS, entropy weight information, decision-making

DOI: 10.3233/JIFS-202646

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10017-10042, 2021

Authors: Shi, Xiaoping | Zou, Shiqi | Song, Shenmin | Guo, Rui

Article Type: Research Article

Abstract:  The asset-based weapon target assignment (ABWTA) problem is one of the important branches of the weapon target assignment (WTA) problem. Due to the current large-scale battlefield environment, the ABWTA problem is a multi-objective optimization problem (MOP) with strong constraints, large-scale and sparse properties. The novel model of the ABWTA problem with the operation error parameter is established. An evolutionary algorithm for large-scale sparse problems (SparseEA) is introduced as the main framework for solving large-scale sparse ABWTA problem. The proposed framework (SparseEA-ABWTA) mainly addresses the issue that problem-specific initialization method and genetic operators with a reward strategy can generate solutions efficiently …considering the sparsity of variables and an improved non-dominated solution selection method is presented to handle the constraints. Under the premise of constructing large-scale cases by the specific case generator, two numerical experiments on four outstanding multi-objective evolutionary algorithms (MOEAs) show Runtime of SparseEA-ABWTA is faster nearly 50% than others under the same convergence and the gap between MOEAs improved by the mechanism of SparseEA-ABWTA and SparseEA-ABWTA is reduced to nearly 20% in the convergence and distribution. Show more

Keywords: Weapon target assignment, multi-objective optimization, evolutionary algorithm, reward strategy, non-dominated solution selection

DOI: 10.3233/JIFS-202679

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10043-10061, 2021

Authors: Wang, Jing | Yang, Yichuan

Article Type: Research Article

Abstract: We introduce rough approximations into basic algebras. After investigating elementary properties of the upper (lower) approximations in basic algebras and discussing the convexity of these two approximations in linearly ordered basic algebras, we generalize related results for MV-algebras, lattice ordered effect algebras, and orthomodular lattices to basic algebras. We also study the relationship between upper (lower) rough ideals of basic algebras and upper (lower) approximations of their homomorphic images.

Keywords: Basic algebras, rough approximations, rough ideals, homomorphic images, 03G25, 06B10

DOI: 10.3233/JIFS-202699

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10063-10071, 2021

Authors: Pang, Zhicheng | Li, Hong | Wang, Chiyu | Shi, Jiawen | Zhou, Jiale

Article Type: Research Article

Abstract: In practice, the class imbalance is prevalent in sentiment classification tasks, which is harmful to classifiers. Recently, over-sampling strategies based on data augmentation techniques have caught the eyes of researchers. They generate new samples by rewriting the original samples. Nevertheless, the samples to be rewritten are usually selected randomly, which means that useless samples may be selected, thus adding this type of samples. Based on this observation, we propose a novel balancing strategy for text sentiment classification. Our approach takes word replacement as foundation and can be divided into two stages, which not only can balance the class distribution of …training set, but also can modify noisy data. In the first stage, we perform word replacement on specific samples instead of random samples to obtain new samples. According to the noise detection, the second stage revises the sentiment of noisy samples. Toward this aim, we propose an improved term weighting called TF-IGM-CW for imbalanced text datasets, which contributes to extracting the target rewritten samples and feature words. We conduct experiments on four public sentiment datasets. Results suggest that our method outperforms several other resampling methods and can be integrated with various classification algorithms easily. Show more

Keywords: Imbalanced text sentiment classification, resampling, noise modification, data augmentation, word replacement

DOI: 10.3233/JIFS-202716

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10073-10086, 2021

Authors: Jiang, Bichuan | Shu, Lan

Article Type: Research Article

Abstract: In this paper, we study the evolutionary game dynamics of the death-birth process with interval payoffs on graphs. First of all, we derive the interval replication dynamic equation. Secondly, we derive the fixation probability of the B-C prisoner’s dilemma game based on the death-birth process under the condition of weak selection, analyze the condition of the strategy fixed in the population, that is the condition of strategy A being dominant is analyzed. So we can judge whether natural selection is beneficial to strategy A in the game process through this condition. Finally, the feasibility of this method is …verified by several examples. Show more

Keywords: Interval-valued functions, death-birth process, fixation probability, evolutionary dynamics

DOI: 10.3233/JIFS-202774

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10087-10098, 2021

Authors: Lai, Xiaocong | Li, Hua | Pan, Ying

Article Type: Research Article

Abstract: With the increasing attention to the environment and air quality, PM2.5 has been paid more and more attention. It is expected to excavate useful information in meteorological data to predict air pollution, however, the air quality is greatly affected by meteorological factors, and how to establish an effective air quality prediction model has always been a problem that people urgently need to solve. This paper proposed a combined model based on feature selection and Support Vector Machine (SVM) for PM2.5 prediction. Firstly, aiming at the influence of meteorological factors on PM2.5, a feature selection method based on linear causality is …proposed to find out the causality between features and select the features with strong causality, so as to remove the redundant features in air pollution data and reduce the workload of data analysis. Then, a method based on SVM is proposed to analyze and solve the nonlinear problems in the data, for reducing the prediction error, a method of particle swarm optimization is also used to optimize SVM parameters. Finally, the above methods are combined into a prediction model, which is suitable for the current air pollution control. 12 representative data sets on the UCI (University of California, Irvine) website are used to verify the combined model, and the experimental results show that the model is feasible and effective. Show more

Keywords: Feature selection, linear regression, support vector machine, combined forecasting model, PM2.5 prediction

DOI: 10.3233/JIFS-202812

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10099-10113, 2021

Authors: Jiang, Zhiwei | Wei, Guiwu | Wu, Jiang | Chen, Xudong

Article Type: Research Article

Abstract: With the development of society, people’s living standard is constantly improving. Meanwhile, people need various food to satisfy their needs in daily life. Under this situation, more and more food enterprises are appearing in the market. However, some issues about food safety come out. Because of the huge number of food company, managers are difficult in achieving profitability. Therefore, some of the managers try to use some unhealthy materials to produce food in the society. So, it is important for people to distinguish healthy and unhealthy food enterprises in their daily life. In order to help government discern and control …the quality of healthy food enterprises in the market, we need to propose an effective evaluation system in estimating food enterprises. In this paper, we introduce a method of evaluating the quality degree of food enterprises which can help us to distinguish enterprises effectively. As we all know, the method of TODIM is widely used in multiple attribute decision making (MADM). In this article, we describe the extended TODIM which based on the cumulative prospect theory (CPT) with picture fuzzy numbers (PF-CPT-TODIM) and use it to evaluate food companies. What’s more, we use entropy method to decide the weights of various attributes. Finally, we select optimal enterprise by using the PF-CPT-TODIM method. Furthermore, we use the comparison of the results of classical PF-TODIM method and PFWA operators to test the availability of PF-CPT-TODIM. It not only can enrich decision-making methods but also make up for the traditional PF-TODIM method in considering the psychological aspects of decision makers. Show more

Keywords: Multiple attribute group decision making (MAGDM), CPT-TODIM, picture fuzzy sets (PFSs), food enterprise, quality credit evaluation

DOI: 10.3233/JIFS-202839

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10115-10128, 2021

Authors: Zuo, Jiankai | Zhang, Yaying

Article Type: Research Article

Abstract: In the field of intelligent robot engineering, whether it is humanoid, bionic or vehicle robots, the driving forms of standing, moving and walking, and the consciousness discrimination of the environment in which they are located have always been the focus and difficulty of research. Based on such problems, Naive Bayes Classifier (NBC), Support Vector Machine(SVM), k-Nearest-Neighbor (KNN), Decision Tree (DT), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) were introduced to conduct experiments. The six individual classifiers have an obvious effect on a particular type of ground, but the overall performance is poor. Therefore, the paper proposes a “Novel Hybrid …Evolutionary Learning” method (NHEL) which combines every single classifier by means of weighted voting and adopts an improved genetic algorithm (GA) to obtain the optimal weight. According to the fitness function and evolution times, this paper designs the adaptively changing crossover and mutation rate and applies the conjugate gradient (CG) to enhance GA. By making full use of the global search capabilities of GA and the fast local search ability of CG, the convergence speed is accelerated and the search precision is upgraded. The experimental results show that the performance of the proposed model is significantly better than individual machine learning and ensemble classifiers. Show more

Keywords: Hybrid classification model, improved GA, machine learning, ground recognition

DOI: 10.3233/JIFS-202940

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10129-10143, 2021

Authors: Khoshaim, Ahmad Bakr | Qiyas, Muhammad | Abdullah, Saleem | Naeem, Muhammad | Muneeza,

Article Type: Research Article

Abstract: This article is an advanced approach to picture fuzzy set through the application of cubic set theory. For instance, we establish the idea of the picture cubic fuzzy sets (PCFSs) theory and define several operations for PCFS. Also, presented some weighted aggregation operators under picture cubic fuzzy information, so called picture cubic fuzzy weighted averaging (PCFWA) operator, picture cubic fuzzy order weighted averaging (PCFOWA) operator, picture cubic fuzzy weighted geometric (PCFWG) operator, and picture cubic fuzzy order weighted geometric (PCFOWG) operator. Further, we study their fundamental properties and showed the relationship among these aggregation operators. In order to determine the …feasibility and practicality of the mentioned new technique, we developed multi-attribute group decision -making algorithm with picture cubic fuzzy environment. Further, the developed method applied to supply chain management and for implementation, consider numerical application of supply chain management. Compared the developed approach with other preexisting aggregation operators, and we concluded that the defined technique is better, reliable and effective. Show more

Keywords: Picture cubic fuzzy sets, picture cubic fuzzy average aggregation operators, picture cubic fuzzy geometric aggregation operators, multi-attribute decision-making

DOI: 10.3233/JIFS-200194

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 10145-10162, 2021