Journal of Intelligent & Fuzzy Systems - Volume 35, issue 5

Authors: Saad, Syed | Malik, H.

Article Type: Research Article

Abstract: Strength of high performance concrete (HPC) is not depends upon water to cement ration only but it is also persuaded by the several components of the concrete. The HPC is a vastly compound material, which create its behavior property very difficult in modeling to analyze. The main aim of this paper is to provide the utilization possibilities of Gene Expression Programming (GEP) to predict the HPC compressive strength (HPCCS) at highly complex behavior. A set of 1030 samples of HPC was collected from open access repository that was developed in the laboratory and represented suitable experimental results, which includes eight …attributes (i.e., age, blast furnaces slag, cement, fly ash, water, superplasticizer, fine aggregate and coarse aggregate). The obtained results are compared with other computational intelligence technique (i.e., RBF neural Network) to validate the performance analysis of the proposed approach. This method is used to predict the HPCCS in high strength level. Moreover, as per available literature, this is the first attempt to implement the GEP in this domain to predict the HPCCS. Show more

Keywords: GEP, high performance concrete, compressive strength, prediction, radial basis function

DOI: 10.3233/JIFS-169822

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5403-5418, 2018

Article Type: Other

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5419-5419, 2018

Authors: Mehmood, Zahid | Rashid, Muhammad | Rehman, Amjad | Saba, Tanzila | Dawood, Hassan | Dawood, Hussain

Article Type: Research Article

Abstract: Due to the fast growth of multimedia archives, the semantic gap is becoming a vital problem between machine learning based semantic concepts and local features of the image to retrieve images accurately. To address this issue, the proposed method of this article introduces two novel methods for effective image retrieval known as visual words integration after clustering (VWIaC) and feature integration before clustering (FIbC). These methods use complementary features of histograms of oriented gradients (HOG) and oriented FAST and rotated BRIEF (ORB) descriptors founded on the bag-of-words (BoW) model for salient objects within the images to build smaller and larger …sizes of codebooks. To achieve higher efficiency in terms of specificity of the image retrieval system, the codebook of larger sizes are preferred, while larger sizes codebook produces low sensitivity and vice versa. The proposed method of VWIaC produces two smaller sizes codebooks to achieve higher sensitivity. After that visual words of both smaller size codebooks are integrated to produce larger size codebook, which improves the specificity of the proposed method. The performance of the proposed method is tested on three standard image benchmarks, which verifies its vigorous performance as compared to an FIbC method and recent CBIR methods. Show more

Keywords: Image visuals search, complementary image visuals, object retrieval, clustering, complementary features

DOI: 10.3233/JIFS-171137

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5421-5434, 2018

Authors: Sajjad Ali Khan, Muhammad | Ali, Asad | Abdullah, Saleem | Amin, Fazli | Hussain, Fawad

Article Type: Research Article

Abstract: Pythagorean Hesitant fuzzy set (PHFS) which permits the membership degree and non-membership degree of an element to a set represented by several possible values is deliberated as a powerful tool to express uncertain information in the process of multi-attribute decision making (MADM) problems. In this paper, we propose a novel approach based on TOPSIS method and the maximizing deviation method for solving MADM problems where the evaluation information provided by the decision makers (DMs) is expressed in form of Pythagorean hesitant fuzzy numbers and the information about attribute weights is incomplete. To determine the attribute weight we develop an optimization …model based on maximizing deviation method. Finally we provide a practical decision-making problem to demonstrate the implementation process of the proposed method. Show more

Keywords: Pythagorean hesitant fuzzy set, maximizing deviation method, TOPSIS method

DOI: 10.3233/JIFS-171190

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5435-5448, 2018

Authors: Jin, Hai | Qamar, Saqib | Zheng, Ran | Ahmad, Parvez

Article Type: Research Article

Abstract: Convolutional neural networks (CNNs) are important methods in deep learning. They have presented up-to-date performance in different challenging areas, such as natural language processing and computer vision. These powerful and efficient neural networks implement training slowly under a massive number of network training parameters. The primary challenge is to reduce the training time for large volumetric data. CNNs have a small number of parameters at convolutional layers and a large number of parameters at fully connected layers. Training time can be reduced by the use of computing parallelism according to the characteristics of CNN layers. This paper presents an optimized …parallelism algorithm using a communication strategy for CNN training in distributed graphic processing units (GPUs). We use the butterfly reduction communication strategy and apply data and model parallelisms at convolutional and fully connected layers respectively. A model is divided among distributed GPUs, and each division of the model works according to the characteristics of CNNs. This hybrid parallel approach is more desirable than previous parallelism alternatives, such as data parallelism only and model parallelism alone, which have been applied to modern CNNs. Experimental results reveal that this parallel approach with butterfly communication strategy can enhance accuracy and decrease training time. Show more

Keywords: Deep learning, computer vision, parallel computing, CNNs

DOI: 10.3233/JIFS-171329

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5449-5466, 2018

Authors: Liu, Han Qiang | Zhang, Qing | Zhao, Feng

Article Type: Research Article

Abstract: In recent years, spectral clustering algorithm has been widely used in the field of pattern recognition and computer vision. How to construct an effective similarity matrix is the key issue of spectral clustering algorithm. In order to describe the uncertainty in the image and design the efficient similarity matrix for spectral clustering, an interval fuzzy spectral clustering ensemble algorithm for color image segmentation (IFSCE) is presented in this paper. Firstly, the color histogram is obtained by the just noticeable difference color threshold method. Then the interval fuzzy similarity measure based on color feature is constructed by utilizing the interval membership …degree and the image are grouped by normalized cut criterion under the similarity matrix produced by interval fuzzy similarity measure. Finally, the segmentation results with different optimal fuzzy factors combination are integrated to get the final result. The experimental results on real images show that the proposed algorithm behaves well in the segmentation accuracy and visual segmentation result. Show more

Keywords: Spectral clustering, interval fuzzy theory, similarity matrix, clustering ensemble, image segmentation

DOI: 10.3233/JIFS-171448

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5467-5476, 2018

Authors: Qu, Guohua | Wang, Yunhuan | Qu, Weihua | Li, Chunhua | Zhou, Haisheng

Article Type: Research Article

Abstract: (DHFNs) are very suitable to be used for depicting membership function and non-membership function in uncertain event. Motivated by the idea of Shapley-Choquet integral [Meng et al. Generalized hesitant fuzzy generalized Shapley-Choquet integral operators and their application in decision making, International Journal of Fuzzy Systems 16 (3) (2014), 400–410], in this paper we develop two Shapley generalized dual hesitant fuzzy generalized Choquet integral operators which globally consider the importance of elements in a set, and the correlations among them. Some important properties of the two operators are examined and apply them to develop an approach to dual hesitant fuzzy …multi-attribute decision making with incomplete weight information. Moreover, A new distance measure of DHFSs is defined. If the information about the weights of attributes is incompletely known, the model for the optimal fuzzy measure on attribute set is established Finally, two numerical examples are given in solving decision making problems and the results demonstrate the feasibility and effectiveness of using the two Shapley generalized dual hesitant fuzzy generalized Choquet integral operators. Show more

Keywords: Multi-attribute decision making, dual hesitant fuzzy element, fuzzy measure, Choquet integral, generalized Shapley function

DOI: 10.3233/JIFS-171837

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5477-5493, 2018

Authors: Grilo, Marcel Mendonça | de Moraes, Carlos Henrique Valério | Costa, Claudio Inácio de Almeida | Lambert-Torres, Germano

Article Type: Research Article

Abstract: This paper presents a methodology for a high-resolution urban spatial load demand forecasting. This methodology is meant to improve the visualization, analysis and inference of load density information in the electric distribution systems in the near future. The proposed methodology converts input data into grid maps and then divides the grid map into larger regions, which will have their expected growth according to convolution matrices and weighting factors that search for characteristics in the history of this region. The definition of the characteristics of the region’s growth is obtained by processing the imperialist competitive algorithm that searches the best array …of convolution, which will set the expected growth of the region. Thus, it is possible to obtain a spatial growth forecast of high resolution and with great precision, which are important factors for smart-grid planning. Show more

Keywords: Convolution, demand forecasting, imperialist competitive algorithm, load forecasting, power distribution planning, smart grid

DOI: 10.3233/JIFS-171971

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5495-5506, 2018

Authors: Farahani, Hadi | Moshiri, Saman

Article Type: Research Article

Abstract: The purpose of the current article is to introduce a propositional linear time temporal logic of common knowledge. This logic can be utilized for reasoning when the agents should commonly know the information that may change over time. This is the main advantage of our logic over the existing temporal logics of knowledge in the literature. We provide a language, as well as appropriate semantics for our logic. We also introduce a resolution-based proof method for this logic by adopting the approach proposed by Dixon et al. [11, 14 ]. This resolution system is based upon a separated normal form …. We prove that our resolution system is sound and complete. More importantly, to justify our approach, we apply our resolution method to specify and verify the anonymity properties of Chaum’s dining cryptographers protocol [4 ]. Show more

Keywords: Temporal logic, common knowledge, resolution, proof, verification, protocol

DOI: 10.3233/JIFS-17988

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5507-5522, 2018

Authors: Singh, Akanksha | Kumar, Amit | Appadoo, S.S.

Article Type: Research Article

Abstract: Kumar and Garg (Applied Intelligence, 2017, 10.1007/s10489-017-1067-0 ) pointed out the limitations of some existing methods for solving intuitionistic fuzzy multi-attribute decision-making (MADM) problems. Also, to overcome the limitations, Kumar and Garg proposed a connection number (CN) based method for solving intuitionistic fuzzy MADM problems. In this paper, it is shown that the ranking method, used in Step 5 of Kumar and Garg’s method for comparing connection numbers (CNs), fails to compare two distinct CNs. Hence, Kumar and Garg’s method fails to rank the alternatives of intuitionistic fuzzy MADM problems. Furthermore, to overcome the limitation of Kumar and Garg’s method, …a new ranking method (named as Mehar ranking method) is proposed for comparing CNs. Show more

Keywords: Set pair analysis, connection number (CN), intuitionistic fuzzy set, decision-making problems

DOI: 10.3233/JIFS-181040

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 5, pp. 5523-5528, 2018