Journal of Intelligent & Fuzzy Systems - Volume 39, issue 5

Authors: Xiao, Lu | Zhang, Siqi | Wei, Guiwu | Wu, Jiang | Wei, Cun | Guo, Yanfeng | Wei, Yu

Article Type: Research Article

Abstract: Since people around the world have gradually attached importance to resource conservation, various countries are actively taking measures to promote environmental protection and sustainable development. Green supply chain management (GSCM) have emerged in this context. Thus, in this essay, a novel intuitionistic fuzzy multiple attribute group decision making (MAGDM) method is designed to tackle this issue. First of all, CRITIC (Criteria Importance Through Inter-criteria Correlation) method is utilized to determine the weights of criteria. Later, the conventional Taxonomy method is extended to the intuitionistic fuzzy environment to compute the value of development attribute of each supplier. Then, the optimal one …can be determined. Eventually, an application about green supplier selection in steel industry is presented, and a comparative analysis is made to demonstrate the superiority of the proposed method. The main features of the proposed algorithm are that they provide a practical solution for selecting GSCM and presents an objective weighting method to enhance the effectiveness of the algorithm. Show more

Keywords: Multiple attribute group decision making (MAGDM), green supply chain management (GSCM), intuitionistic fuzzy sets (IFSs), taxonomy method, CRITIC method, steel industry

DOI: 10.3233/JIFS-200709

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7247-7258, 2020

Authors: Pan, Xingguang | Wang, Shitong

Article Type: Research Article

Abstract: The feature reduction fuzzy c-means (FRFCM) algorithm has been proven to be effective for clustering data with redundant/unimportant feature(s). However, the FRFCM algorithm still has the following disadvantages. 1) The FRFCM uses the mean-to-variance-ratio (MVR) index to measure the feature importance of a dataset, but this index is affected by data normalization, i.e., a large MVR value of original feature(s) may become small if the data are normalized, and vice versa. Moreover, the MVR value(s) of the important feature(s) of a dataset may not necessarily be large. 2) The feature weights obtained by the FRFCM are sensitive to the initial …cluster centers and initial feature weights. 3) The FRFCM algorithm may be unable to assign the proper weights to the features of a dataset. Thus, in the feature reduction learning process, important features may be discarded, but unimportant features may be retained. These disadvantages can cause the FRFCM algorithm to discard important feature components. In addition, the threshold for the selection of the important feature(s) of the FRFCM may not be easy to determine. To mitigate the disadvantages of the FRFCM algorithm, we first devise a new index, named the marginal kurtosis measure (MKM), to measure the importance of each feature in a dataset. Then, a novel and robust feature reduction fuzzy c-means clustering algorithm called the FRFCM-MKM, which incorporates the marginal kurtosis measure into the FRFCM, is proposed. Furthermore, an accurate threshold is introduced to select important feature(s) and discard unimportant feature(s). Experiments on synthetic and real-world datasets demonstrate that the FRFCM-MKM is effective and efficient. Show more

Keywords: Fuzzy c-means, feature reduction learning, marginal kurtosis measure, mean-to-variance ratio

DOI: 10.3233/JIFS-200714

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7259-7279, 2020

Authors: He, Tongze | Guo, Caili | Chu, Yunfei | Yang, Yang | Wang, Yanjun

Article Type: Research Article

Abstract: Community Question Answering (CQA) websites has become an important channel for people to acquire knowledge. In CQA, one key issue is to recommend users with high expertise and willingness to answer the given questions, i.e., expert recommendation. However, a lot of existing methods consider the expert recommendation problem in a static context, ignoring that the real-world CQA websites are dynamic, with users’ interest and expertise changing over time. Although some methods that utilize time information have been proposed, their performance improvement can be limited due to fact that they fail they fail to consider the dynamic change of both user …interests and expertise. To solve these problems, we propose a deep learning based framework for expert recommendation to exploit user interest and expertise in a dynamic environment. For user interest, we leverage Long Short-Term Memory (LSTM) to model user’s short-term interest so as to capture the dynamic change of users’ interests. For user expertise, we design user expertise network, which leverages feedback on users’ historical behavior to estimate their expertise on new question. We propose two methods in user expertise network according to whether the dynamic property of expertise is considered. The experimental results on a large-scale dataset from a real-world CQA site demonstrate the superior performance of our method. Show more

Keywords: Expert recommendation, user modeling, neural network, community question answering

DOI: 10.3233/JIFS-200729

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7281-7292, 2020

Authors: Xu, Junxiang | Zhang, Jin | Guo, Jingni

Article Type: Research Article

Abstract: Taking into account the uncertainties of the factors of in-transit transportation cost, hub transshipment cost, hub construction cost, in-transit transportation time, hub transshipment time, and demand, this study uses triangular fuzzy numbers, expected value criteria, and distribution of credibility measure to minimise the total transportation cost of the hub-and-spoke road-rail combined transport (RRCT) network and the maximum transportation limit time between the origin and destination of the network. Firstly, a non-linear programming mathematical model is constructed for the regional hub-and-spoke RRCT network based on uncertain cost-time-demand. Then, an improved genetic algorithm is designed to obtain an optimized scheme. The algorithm …uses genetic algorithm to search the global space, and uses two local search methods, i.e. shift and exchange, to search the local space. Finally, the RRCT network along the Yaan-Linzhi section of the Sichuan-Tibet Railway is used as the research object to verify the applicability and effectiveness of the regional hub-and-spoke RRCT network model and the algorithm proposed in the study. Show more

Keywords: Road-rail combined transport, hub-and-spoke network, uncertain factor, improved genetic algorithm, Sichuan-Tibet Railway

DOI: 10.3233/JIFS-200748

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7293-7313, 2020

Authors: Wei, Lixin | Zhang, JinLu | Fan, Rui | Li, Xin | Sun, Hao

Article Type: Research Article

Abstract: In this article, an effective method, called an adaptive covariance strategy based on reference points (RPCMA-ES) is proposed for multi-objective optimization. In the proposed algorithm, search space is divided into independent sub-regions by calculating the angle between the objective vector and the reference vector. The reference vectors can be used not only to decompose the original multi-objective optimization problem into a number of single-objective subproblems, but also to elucidate user preferences to target a preferred subset of the whole Pareto front (PF). In this respect, any single objective optimizers can be easily used in this algorithm framework. Inspired by the …multi-objective estimation of distribution algorithms, covariance matrix adaptation evolution strategy (CMA-ES) is involved in RPCMA-ES. A state-of-the-art optimizer for single-objective continuous functions is the CMA-ES, which has proven to be able to strike a good balance between the exploration and the exploitation of search space. Furthermore, in order to avoid falling into local optimality and make the new mean closer to the optimal solution, chaos operator is added based on CMA-ES. By comparing it with four state-of-the-art multi-objective optimization algorithms, the simulation results show that the proposed algorithm is competitive and effective in terms of convergence and distribution. Show more

Keywords: Multi-objective optimization problem, Reference point, Covariance matrix adaptation evolutionary strategy, Chaos operator

DOI: 10.3233/JIFS-200749

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7315-7332, 2020

Authors: Zuo, Mingcheng | Dai, Guangming

Article Type: Research Article

Abstract: When optimizing complicated engineering design problems, the search spaces are usually extremely nonlinear, leading to the great difficulty of finding optima. To deal with this challenge, this paper introduces a parallel learning-selection-based global optimization framework (P-lsGOF), which can divide the global search space to numbers of sub-spaces along the variables learned from the principal component analysis. The core search algorithm, named memory-based adaptive differential evolution algorithm (MADE), is parallel implemented in all sub-spaces. MADE is an adaptive differential evolution algorithm with the selective memory supplement and shielding of successful control parameters. The efficiency of MADE on CEC2017 unconstrained problems and …CEC2011 real-world problems is illustrated by comparing with recently published state-of-the-art variants of success-history based adaptative differential evolution algorithm with linear population size reduction (L-SHADE) The performance of P-lsGOF on CEC2011 problems shows that the optimized results by individually conducting MADE can be further improved. Show more

Keywords: Parallel optimization framework, real-world problems, learning-based differential evolution

DOI: 10.3233/JIFS-200753

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7333-7361, 2020

Authors: Chen, Chen | Ma, Feng | Liu, Jialun | Negenborn, Rudy R. | Liu, Yuanchang | Yan, Xinping

Article Type: Research Article

Abstract: Human experience is regarded as an indispensable part of artificial intelligence in the process of controlling or decision making for autonomous cargo ships. In this paper, a novel Deep Q-Network-based (DQN) approach is proposed, which performs satisfactorily in controlling a cargo ship automatically without any human experience. At the very beginning, we use the model of KRISO Very Large Crude Carrier (KVLCC2) to describe a cargo ship. To manipulate this ship has to conquer great inertia and relatively insufficient driving force. Subsequently, customary waterways, regulations, conventions are described with Artificial Potential Field and value-functions in DQN. Based on this, the …artificial intelligence of planning and controlling a cargo ship can be obtained by undertaking sufficient training, which can control the ship directly, while avoiding collisions, keeping its position in the middle of the route as much as possible. In simulation experiments, it is demonstrated that such an approach performs better than manual works and other traditional methods in most conditions, which makes the proposed method a promising solution in improving the autonomy level of cargo ships. Show more

Keywords: Deep Q-network, reinforcement learning, artificial intelligence, autonomous ships

DOI: 10.3233/JIFS-200754

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7363-7379, 2020

Authors: Hashmi, Masooma Raza | Riaz, Muhammad | Smarandache, Florentin

Article Type: Research Article

Abstract: This manuscript contributes a progressive mathematical model for the analysis of novel coronavirus (COVID-19) and improvement of the victim from COVID-19 with some suitable circumstances. We investigate the innovative approach of the m-polar neutrosophic set (MPNS) to deal with the hesitations and obscurities of objects and rational thinking in decision-making obstacles. In this article, we propose the generalized weighted aggregation and generalized Einstein weighted aggregation operators in the context of m-polar neutrosophic numbers (MPNNs). The motivational aim of this paper is that we present a case study based on data amalgamation for the diagnosis of COVID-19 and examine with the …help of MPN-data. By using the proposed technique on generalized operators, we discuss the recovery of the victim with the time factor, proper medication, and some suitable circumstances. Ultimately, we present the advantages and productiveness of the proposed algorithm under the influence of parameter ð to the recovery results. The versatility and superiority of the proposed methodology with some existing approaches can be observed by the comparative analysis. Show more

Keywords: m-polar neutrosphic set (MPNS), m-polar neutrosophic generalized weighted aggregation (MPNGWA) operator, m-polar neutrosophic generalized Einstein weighted aggregation (MPNGEWA) operator, multi-criteria decision-making (MCDM) for medical diagnosis, Recovery of patient, comparative analysis

DOI: 10.3233/JIFS-200761

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7381-7401, 2020

Authors: Huang, Yangke | Wang, Zhiming

Article Type: Research Article

Abstract: Network pruning has been widely used to reduce the high computational cost of deep convolutional neural networks(CNNs). The dominant pruning methods, channel pruning, removes filters in layers based on their importance or sparsity training. But these methods often give limited acceleration ratio and encounter difficulties when pruning CNNs with skip connections. Block pruning methods take a sequence of consecutive layers (e.g., Conv-BN-ReLu) as a block and remove entire block each time. However, previous methods usually introduce new parameters to help pruning and lead additional parameters and extra computations. This work proposes a novel multi-granularity pruning approach that combines block pruning …with channel pruning (BPCP). The block pruning (BP) module remove blocks by directly searches the redundant blocks with gradient descent and leaves no extra parameters in final models, which is friendly to hardware optimization. The channel pruning (CP) module remove redundant channels based on importance criteria and handles CNNs with skip connections properly, which further improves the overall compression ratio. As a result, for CIFAR10, BPCP reduces the number of parameters and MACs of a ResNet56 model up to 78.9% and 80.3% respectively with <3% accuracy drop. In terms of speed, it gives a 3.17 acceleration ratio. Our code has been made available at https://github.com/Pokemon-Huang/BPCP . Show more

Keywords: Neural network compression, network pruning, residual networks

DOI: 10.3233/JIFS-200771

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7403-7410, 2020

Authors: Nataraj, Sathees Kumar | Paulraj, M. P. | Bin Abdullah, Ahmad Nazri | Bin Yaacob, Sazali

Article Type: Research Article

Abstract: In this paper, a speech-to-text translation model has been developed for Malaysian speakers based on 41 classes of Phonemes. A simple data acquisition algorithm has been used to develop a MATLAB graphical user interface (GUI) for recording the isolated word speech signals from 35 non-native Malaysian speakers. The collected database consists of 86 words with 41 classes of phoneme based on Affricatives, Diphthongs, Fricatives, Liquid, Nasals, Semivowels and Glides, Stop and Vowels. The speech samples are preprocessed to eliminate the undesirable artifacts and the fuzzy voice classifier has been employed to classify the samples into voiced sequence and unvoiced sequence. …The voiced sequences are divided into frame segments and for each frame, the Linear Predictive co-efficients features are obtained from the voiced sequence. Then the feature sets are formed by deriving the LPC features from all the extracted voiced sequences, and used for classification. The isolated words chosen based on the phonemes are associated with the extracted features to establish classification system input-output mapping. The data are then normalized and randomized to rearrange the values into definite range. The Multilayer Neural Network (MLNN) model has been developed with four combinations of input and hidden activation functions. The neural network models are trained with 60%, 70% and 80% of the total data samples. The neural network architecture was aimed at creating a robust model with 60%, 70%, and 80% of the feature set with 25 trials. The trained network model is validated by simulating the network with the remaining 40%, 30%, and 20% of the set. The reliability of trained network models were compared by measuring true-positive, false-negative, and network classification accuracy. The LPC features show better discrimination and the MLNN neural network models trained using the LPC spectral band features gives better recognition. Show more

Keywords: Fuzzy voice classifier, Malaysian English pronunciation, linear predictive coefficients (LPCC), neural network models (MLNN).

DOI: 10.3233/JIFS-200780

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 5, pp. 7411-7429, 2020