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

Authors: Zhu, Wenhua | Peng, Hu | Leng, Chaohui | Deng, Changshou | Wu, Zhijian

Article Type: Research Article

Abstract: Breast cancer is a severe disease for women health, however, with expensive diagnostic cost or obsolete medical technique, many patients are hard to obtain prompt medical treatment. Thus, efficient detection result of breast cancer while lower medical cost may be a promising way to protect women health. Breast cancer detection using all features will take a lot of time and computational resources. Thus, in this paper, we proposed a novel framework with surrogate-assisted firefly algorithm (FA) for breast cancer detection (SFA-BCD). As an advanced evolutionary algorithm (EA), FA is adopted to make feature selection, and the machine learning as classifier …identify the breast cancer. Moreover, the surrogate model is utilized to decrease computation cost and expensive computation, which is the approximation function built by offline data to the real object function. The comprehensive experiments have been conducted under several breast cancer dataset derived from UCI. Experimental results verified that the proposed framework with surrogate-assisted FA significantly reduced the computation cost. Show more

Keywords: Breast cancer detection, firefly algorithm, machine learning, surrogate model, feature selection

DOI: 10.3233/JIFS-201124

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8915-8926, 2021

Authors: Iranmanesh, Seyed Mehdi | Nasrabadi, Nasser M.

Article Type: Research Article

Abstract: In this paper, we present a simple approach to train Generative Adversarial Networks (GANs) in order to avoid a mode collapse issue. Implicit models such as GANs tend to generate better samples compared to explicit models that are trained on tractable data likelihood. However, GANs overlook the explicit data density characteristics which leads to undesirable quantitative evaluations and mode collapse. To bridge this gap, we propose a hybrid generative adversarial network (HGAN) for which we can enforce data density estimation via an autoregressive model and support both adversarial and likelihood framework in a joint training manner which diversify the …estimated density in order to cover different modes. We propose to use an adversarial network to transfer knowledge from an autoregressive model (teacher) to the generator (student) of a GAN model. A novel deep architecture within the GAN formulation is developed to adversarially distill the autoregressive model information in addition to simple GAN training approach. We conduct extensive experiments on real-world datasets (i.e., MNIST, CIFAR-10, STL-10) to demonstrate the effectiveness of the proposed HGAN under qualitative and quantitative evaluations. The experimental results show the superiority and competitiveness of our method compared to the baselines. Show more

Keywords: Generative adversarial network, adversarial training, mode collapse, network distillation, autoregressive model

DOI: 10.3233/JIFS-201202

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8927-8938, 2021

Authors: Liu, Peide | Hendalianpour, Ayad | Hamzehlou, Mohammad

Article Type: Research Article

Abstract: The present study investigates a two-echelon supply chain including a usual retailer and two competing manufacturers. The objective function of our model is the maximization of the whole profit of the supply chain, which consists of the stochastic demand, shortage cost, and holding costs. This paper aims to analyze a single period with two products to define the optimum retail prices and wholesales under different game theory approaches (e.g., Bertrand, cooperation, and Stackelberg competitions) based on Double Interval Grey Numbers (DIGN). The other aim of this paper is to specify the price using the manufacturers and the common retailer and …considering the stochastic different channel power structures and demand function. In this paper, it is considered that different power structures of channel members may affect the optimal pricing decisions. In this paper, two pricing policies of manufacturers, eight pricing models and various structures of distribution channel members are utilized. In these pricing models, the impacts of retail substitutability are evaluated on the decisions of the chain members and the equilibrium profits. In this paper, the products are substitutable and the demand is stochastic. In this model, the demand is not certain then, we may have shortages or unsold products. Finally, sensitivity analysis is provided for illustrating the theoretical outcomes established in each case. Show more

Keywords: Pricing, stochastic demand, supply chain, game theory, double interval grey numbers

DOI: 10.3233/JIFS-201206

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8939-8961, 2021

Authors: Rababa, Salahaldeen | Al-Badarneh, Amer

Article Type: Research Article

Abstract: Large-scale datasets collected from heterogeneous sources often require a join operation to extract valuable information. MapReduce is an efficient programming model for processing large-scale data. However, it has some limitations in processing heterogeneous datasets. This is because of the large amount of redundant intermediate records that are transferred through the network. Several filtering techniques have been developed to improve the join performance, but they require multiple MapReduce jobs to process the input datasets. To address this issue, the adaptive filter-based join algorithms are presented in this paper. Specifically, three join algorithms are introduced to perform the processes of filters creation …and redundant records elimination within a single MapReduce job. A cost analysis of the introduced join algorithms shows that the I/O cost is reduced compared to the state-of-the-art filter-based join algorithms. The performance of the join algorithms was evaluated in terms of the total execution time and the total amount of I/O data transferred. The experimental results show that the adaptive Bloom join, semi-adaptive intersection Bloom join, and adaptive intersection Bloom join decrease the total execution time by 30%, 25%, and 35%, respectively; and reduce the total amount of I/O data transferred by 18%, 25%, and 50%, respectively. Show more

Keywords: Join algorithms, big data management, query optimization, MapReduce

DOI: 10.3233/JIFS-201220

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8963-8980, 2021

Authors: Lu, Ting | Xiang, Yan | Liang, Junge | Zhang, Li | Zhang, Mingfang

Article Type: Research Article

Abstract: The grand challenge of cross-domain sentiment analysis is that classifiers trained in a specific domain are very sensitive to the discrepancy between domains. A sentiment classifier trained in the source domain usually have a poor performance in the target domain. One of the main strategies to solve this problem is the pivot-based strategy, which regards the feature representation as an important component. However, part-of-speech information was not considered to guide the learning of feature representation and feature mapping in previous pivot-based models. Therefore, we present a fused part-of-speech vectors and attention-based model (FAM) . In our model, we fuse part-of-speech …vectors and feature word embeddings as the representation of features, giving deep semantics to mapping features. And we adopt Multi-Head attention mechanism to train the cross-domain sentiment classifier to obtain the connection between different features. The results of 12 groups comparative experiments on the Amazon dataset demonstrate that our model outperforms all baseline models in this paper. Show more

Keywords: Part-of-speech vectors, Multi-Head attention mechanism, cross-domain sentiment analysis

DOI: 10.3233/JIFS-201295

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8981-8989, 2021

Authors: Jamil, Faisal | Kim, DoHyeun

Article Type: Research Article

Abstract: In recent few years, the widespread applications of indoor navigation have compelled the research community to propose novel solutions for detecting objects position in the Indoor environment. Various approaches have been proposed and implemented concerning the indoor positioning systems. This study propose an fuzzy inference based Kalman filter to improve the position estimation in indoor navigation. The presented system is based on FIS based Kalman filter aiming at predicting the actual sensor readings from the available noisy sensor measurements. The proposed approach has two main components, i.e., multi sensor fusion algorithm for positioning estimation and FIS based Kalman filter algorithm. …The position estimation module is used to determine the object location in an indoor environment in an accurate way. Similarly, the FIS based Kalman filter is used to control and tune the Kalman filter by considering the previous output as a feedback. The Kalman filter predicts the actual sensor readings from the available noisy readings. To evaluate the proposed approach, the next-generation inertial measurement unit is used to acquire a three-axis gyroscope and accelerometer sensory data. Lastly, the proposed approach’s performance has been investigated considering the MAD, RMSE, and MSE metrics. The obtained results illustrate that the FIS based Kalman filter improve the prediction accuracy against the traditional Kalman filter approach. Show more

Keywords: ANN, FIS based Kalman Filter, navigation system, inertial measurement unit, indoor navigation, sensors fusion

DOI: 10.3233/JIFS-201352

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 8991-9005, 2021

Authors: Subudhi, Jyotirmayee | Indumathi, P.

Article Type: Research Article

Abstract: Non-Orthogonal Multiple Access (NOMA) provides a positive solution for multiple access issues and meets the criteria of fifth-generation (5G) networks by improving service quality that includes vast convergence and energy efficiency. The problem is formulated for maximizing the sum rate of MIMO-NOMA by assigning power to multiple layers of users. In order to overcome these problems, two distinct evolutionary algorithms are applied. In particular, the recently implemented Salp Swarm Algorithm (SSA) and the prominent Optimization of Particle Swarm (PSO) are utilized in this process. The MIMO-NOMA model optimizes the power allocation by layered transmission using the proposed Joint User Clustering …and Salp Particle Swarm Optimization (PPSO) power allocation algorithm. Also, the closed-form expression is extracted from the current Channel State Information (CSI) on the transmitter side for the achievable sum rate. The efficiency of the proposed optimal power allocation algorithm is evaluated by the spectral efficiency, achievable rate, and energy efficiency of 120.8134bits/s/Hz, 98Mbps, and 22.35bits/Joule/Hz respectively. Numerical results have shown that the proposed PSO algorithm has improved performance than the state of art techniques in optimization. The outcomes on the numeric values indicate that the proposed PSO algorithm is capable of accurately improving the initial random solutions and converging to the optimum. Show more

Keywords: Energy efficiency, MIMO-NOMA, Non-orthogonal multiple access, PSO optimization, power allocation, layered transmission, user clustering

DOI: 10.3233/JIFS-201412

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 9007-9019, 2021

Authors: He, Peng | Wang, Xue-ping

Article Type: Research Article

Abstract: This paper first describes a characterization of a lattice L which can be represented as the collection of all up-sets of a poset. It then obtains a representation of a complete distributive lattice L 0 which can be embedded into the lattice L such that all infima, suprema, the top and bottom elements are preserved under the embedding by defining a monotonic operator on a poset. This paper finally studies the algebraic characterization of a finite distributive.

Keywords: 03E72, 06D05, L-fuzzy set, cut set, complete distributive lattice, embedding, monotonic operator

DOI: 10.3233/JIFS-201430

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 9021-9030, 2021

Authors: Xiao, Hui-Min | Wang, Mei-Qi | Cao, Yan-Li | Guo, Yu-Jie

Article Type: Research Article

Abstract: In this paper, to improve the situation of singleness of selecting results in hesitant fuzzy set decision-making and expand the range of choices for decision makers, we construct a hesitant fuzzy set clustering algorithm combined with fuzzy matroid operation. The algorithm synthesizes the r-cut set, fuzzy shrinking matroids in the fuzzy matroids and the operational properties of the fuzzy derived matroids, the r value also is used to connect the two types of fuzzy matroids to form a clustering algorithm. Finally, we apply the algorithm to the hesitant fuzzy set decision-making of job seekers choosing recruitment websites, each recruitment website …as an optional scheme is divided into three categories of excellent to inferior schemes to provide job seekers with ideas and methods for favorably selecting recruitment websites. Show more

Keywords: Hesitant fuzzy set decision-making, fuzzy matroid, contraction matroid, derived matroid, clustering algorithm

DOI: 10.3233/JIFS-201476

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 9031-9039, 2021

Authors: Sahoo, Arun Kumar | Panigrahi, Tapas Kumar | Dhiman, Gaurav | Singh, Krishna Kant | Singh, Akansha

Article Type: Research Article

Abstract: In this paper, an enhanced version of the emperor penguin optimization algorithm is proposed for solving dynamic economic dispatch (DED) problem incorporating renewable energy sources and microgrid. Dynamic economic load dispatch optimally shares the power on an hourly basis for a day among the committed generating units to satisfy the feasible load demand. Emission of pollutants from the combustion fossil fuel and gradual depletion of fossil fuel encourages the usage of renewable energy sources. Implementation of renewable energy sources with the reinforcement of green energy transforms the fossil fuel-based plant into a hybrid generating plant. The increase in power production …with the increase in electricity demand implicates challenges for economical operation. The proposed algorithm is applied to the DED problem for fossil fuel based and renewable energy system to find economic schedule of generated power among the committed generating units. The proposed optimization algorithm is inspired by the huddling behavior of the emperor penguin. The exploration strategy is enhanced by adapting oppositional based learning. Chaotic mapping is used to maintain a proper balance between exploration and exploitation in the entire search space, which minimizes the cost of generation in the power system. Show more

Keywords: Dynamic economic dispatch (DED), emperor penguin optimization (EPO), chaotic oppositional learning-based emperor penguin optimization (COLEPO), constraints, wind energy, micro grid

DOI: 10.3233/JIFS-201483

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 5, pp. 9041-9058, 2021