for Journals by Title or ISSN
for Articles by Keywords
help
Followed Journals
Journal you Follow: 0
 
Sign Up to follow journals, search in your chosen journals and, optionally, receive Email Alerts when new issues of your Followed Journals are published.
Already have an account? Sign In to see the journals you follow.
Journal Cover
Information Sciences
Journal Prestige (SJR): 1.635
Citation Impact (citeScore): 5
Number of Followers: 199  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 0020-0255
Published by Elsevier Homepage  [3163 journals]
  • Evolutionary algorithm with ensemble strategies based on maximum a
           posteriori for continuous optimization
    • Authors: Asmaa Ghoumari; Amir Nakib; Patrick Siarry
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Asmaa Ghoumari, Amir Nakib, Patrick Siarry
      To be efficient and reach the best solution, evolutionary algorithms (EAs) are composed of three evolutionary operators: selection, crossover and mutation. Nevertheless, there is no established rule to choose them from a large panel of operators available in the literature. In this paper, a Maximum A Posteriori (MAP) principle based rule is proposed to palliate the operators’ selection problem for solving different kinds of continuous optimization problems. This learning based approach allows switching between different strategies during the optimization. This algorithm is called Maximum a posteriori based Evolutionary Algorithm (MEA). Experimental analysis was performed and proved its efficiency and robustness on a large set of 34 problems.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.041
      Issue No: Vol. s 460–461 (2018)
       
  • Aspect-based opinion ranking framework for product reviews using a
           Spearman's rank correlation coefficient method
    • Authors: Ashok Kumar J; Abirami S
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Ashok Kumar J, Abirami S
      Opinion mining (also called sentiment analysis) is a type of natural language processing for computing people's opinions and emotions. It detects opinions from structured, semi-structured, and unstructured social media contents at different levels, such as the document, word, sentence, and aspect levels. In all these levels except aspect, opinion mining identifies the overall subjectivity or sentiment polarities. An aspect level is described as a part or an attribute of an entity. It exactly describes people's likes and dislikes in social media contents. In this paper, we propose a new framework for ranking products based on aspects. First, the system identifies the aspects of products. Second, the aspects and their opinion words are identified and visualized from the products’ reviews using a Harel–Koren fast multiscale layout. Third, the network visualization is constructed and modeled, and a Spearman's rank correlation coefficient based opinion ranking method is applied to rank the products based on positive and negative ranks. Fourth, the supervised learning methods (Naïve Bayes, Maximum Entropy, and Support Vector Machine) are employed for the aspect-based sentiment classification task. Finally, the performance of the system is measured by the experimental results.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.003
      Issue No: Vol. s 460–461 (2018)
       
  • Zero-day malware detection using transferred generative adversarial
           networks based on deep autoencoders
    • Authors: Jin-Young Kim; Seok-Jun Bu; Sung-Bae Cho
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Jin-Young Kim, Seok-Jun Bu, Sung-Bae Cho
      Detecting malicious software (malware) is important for computer security. Among the different types of malware, zero-day malware is problematic because it cannot be removed by antivirus systems. Existing malware detection mechanisms use stored malware characteristics, which hinders detecting zero-day attacks where altered malware is generated to avoid detection by antivirus systems. To detect malware including zero-day attacks robustly, this paper proposes a novel method called transferred deep-convolutional generative adversarial network (tDCGAN), which generates fake malware and learns to distinguish it from real malware. The data generated from a random distribution are similar but not identical to the real data: it includes modified features compared with real data. The detector learns various malware features using real data and modified data generated by the tDCGAN based on a deep autoencoder (DAE), which extracts appropriate features and stabilizes the GAN training. Before training the GAN, the DAE learns malware characteristics, produces general data, and transfers this capacity for stable training of the GAN generator. The trained discriminator passes down the ability to capture malware features to the detector, using transfer learning. We show that tDCGAN achieves 95.74% average classification accuracy which is higher than that of other models and increases the learning stability. It is also the most robust against modeled zero-day attacks compared to others.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.04.092
      Issue No: Vol. s 460–461 (2018)
       
  • Global graph diffusion for interactive object extraction
    • Authors: Tao Wang; Jian Yang; Quansen Sun; Zexuan Ji; Peng Fu; Qi Ge
      Pages: 103 - 114
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Tao Wang, Jian Yang, Quansen Sun, Zexuan Ji, Peng Fu, Qi Ge
      Many interactive image segmentation methods design energy functions based on the local relationship of neighboring pixels, which is insufficient at capturing the abundant information of an image, and these methods are susceptible to many problems, such as sensitivity to seeds and under-segmentation of boundaries. To solve these problems, this paper explores utilizing the global relationship for interactive image segmentation. To effectively obtain the global information of the image, we first propose a robust affinity diffusion (RAD) method to propagate the local affinity graph. Compared with the existing diffusion-based approaches, the advantage of RAD is that it can converge to an effective limit value, which makes the diffusion process more computationally efficient and easier to control. The segmentation model is then constructed based on this convergent global graph. To efficiently utilize the global information, the energy function is designed by the multiplication of the global affinity matrix and a prior probability vector. The use of global information can significantly improve the segmentation performance. Experiments on challenging data sets demonstrate that RAD can obtain better results than state-of-the-art methods.

      PubDate: 2018-05-30T11:56:29Z
      DOI: 10.1016/j.ins.2018.05.040
      Issue No: Vol. 460-461 (2018)
       
  • Birds of a feather flock together: Visual representation with scale and
           class consistency
    • Authors: Chunjie Zhang; Chenghua Li; Dongyuan Lu; Jian Cheng; Qi Tian
      Pages: 115 - 127
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Chunjie Zhang, Chenghua Li, Dongyuan Lu, Jian Cheng, Qi Tian
      There are three problems with a local-feature based representation scheme. First, local regions are often densely extracted or determined through detection without considering the scales of local regions. Second, local features are encoded separately, leaving the relationship among them unconsidered. Third, local features are simply encoded without considering the class information. To solve these problems, in this paper, we propose a scale and class consistent local-feature encoding method for image representation, which is achieved through the dense extraction of local features in different scale spaces, and the subsequent learning of the encoding parameters. In addition, instead of encoding each local feature independently, we jointly optimize the encoding parameters of the local features. Moreover, we also impose class consistency during the local-feature encoding process. We test the discriminative power of image representations on image classification tasks. Experiments on several public image datasets demonstrate that the proposed method achieves a superior performance compared with many other local-feature based methods.

      PubDate: 2018-06-02T12:12:59Z
      DOI: 10.1016/j.ins.2018.05.048
      Issue No: Vol. 460-461 (2018)
       
  • Data envelopment analysis based fuzzy multi-objective portfolio selection
           model involving higher moments
    • Authors: Mukesh Kumar Mehlawat; Arun Kumar; Sanjay Yadav; Wei Chen
      Pages: 128 - 150
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Mukesh Kumar Mehlawat, Arun Kumar, Sanjay Yadav, Wei Chen
      We study the portfolio selection problem from the perspective of incorporating more information about the non-normality of asset returns by considering the mean-variance-skewness-kurtosis framework. Using additional criteria (namely asset turnover, earnings per share, earnings per share growth rate, leverage ratio, price/earnings ratio, and beta (β) value), we employ data envelopment analysis technique to construct a benefit criterion from the efficiency scores of the assets. To incorporate the uncertainty and vagueness of real financial markets, the input data (with respect of all criteria) are assumed as (λ, ρ) interval-valued fuzzy numbers constructed using the historical data. Marginal impacts of the assets on higher moments of the portfolio are used to formulate a fuzzy multi-objective linear programming model. The constraints of the proposed model include the bounds on investment in individual assets, full utilization of the investment capital, and no short selling of assets. The signed distance ranking method is used to obtain a numeric optimization model, which is solved through a weighted max-min approach (in order to incorporate the investor’s preferences regarding investment criteria). A case of real financial market portfolio selection is presented to demonstrate the efficiency of both the proposed model and the solution method.

      PubDate: 2018-06-02T12:12:59Z
      DOI: 10.1016/j.ins.2018.05.043
      Issue No: Vol. 460-461 (2018)
       
  • Online signature verification modeled by stability oriented reference
           signatures
    • Authors: Rafal Doroz; Przemyslaw Kudlacik; Piotr Porwik
      Pages: 151 - 171
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Rafal Doroz, Przemyslaw Kudlacik, Piotr Porwik
      Signature verification is widely used in the fields of finance, access control and security. However, one of the biggest problems associated with signature verification is its instability. This instability may concern specific fragments of a signature or its entirety. The location of the unstable fragments in a signature depends on individual writing styles, which makes the signature verification more difficult, resulting in a negative impact on recognition effectiveness. In this paper the authors propose a new method of signature verification. The key stage of this approach is the determination of reference signature stability. The proposed signature stability measure, based on fuzzy set theory, is a biometric strategy that has never been used before. The fragments of one reference signature that differ from the corresponding fragments of the remaining reference signatures of the same person are treated as unstable fragments and will not be taken into consideration when comparing the reference sample with the signature being verified. The proposed method employs fuzzy sets to extract a signature’s stable fragments. To test the proposed method’s performance, seven different classifiers were used: PSO oriented, k-Nearest-Neighbor, Naive Bayes, Random Forest, RIDOR, Support Vector Machine and J48. Experiments conducted on the two independent datasets demonstrated that the method proposed here returns highly satisfactory results, outperforming the other state-of-the-art methods.

      PubDate: 2018-06-02T12:12:59Z
      DOI: 10.1016/j.ins.2018.05.049
      Issue No: Vol. 460-461 (2018)
       
  • A greedy-metaheuristic 3-stage approach to construct covering arrays
    • Authors: Idelfonso Izquierdo-Marquez; Jose Torres-Jimenez; Brenda Acevedo-Juárez; Himer Avila-George
      Pages: 172 - 189
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Idelfonso Izquierdo-Marquez, Jose Torres-Jimenez, Brenda Acevedo-Juárez, Himer Avila-George
      Covering arrays are combinatorial designs used as test-suites in software and hardware testing. Because of their practical applications, the construction of covering arrays with a smaller number of rows is desirable. In this work we develop a greedy-metaheuristic 3-stage approach to construct covering arrays that improve some of the best-known ones. In the first stage, a covering perfect hash family is created using a metaheuristic approach; this initial array may not be complete, and so the derived covering array may have missing tuples. In the second stage, the covering perfect hash family is converted to a covering array and, in case there are missing tuples, a greedy approach completes the covering array through the addition of some rows. The third stage is an iterative postoptimization stage that combines two greedy algorithms and a metaheuristic algorithm; the greedy algorithms detect and reduce redundancy in the covering array, and the metaheuristic algorithm covers the tuples that may become uncovered after the reduction of redundancy. The effectiveness of our greedy-metaheuristic 3-stage approach is assessed through the construction of covering arrays of order four and strengths 3–6; the main results are the improvement of 9473 covering arrays of strength three, 9303 of strength four, 2150 of strength five, and 291 of strength six. To see how to apply covering arrays to real testing scenarios, the final part of this work presents the use of covering arrays of order four for setting up a composting process.

      PubDate: 2018-06-02T12:12:59Z
      DOI: 10.1016/j.ins.2018.05.047
      Issue No: Vol. 460-461 (2018)
       
  • Residuated skew lattices
    • Authors: Yuan Zhi; Xiangnan Zhou; Qingguo Li
      Pages: 190 - 201
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Yuan Zhi, Xiangnan Zhou, Qingguo Li
      Skew lattices are one of the most successful non-commutative generalizations of lattices. Motivated by the study of residuation on ordered structures and that of skew Boolean algebras and skew Heyting algebras, in this paper, we introduce the concept of residuated skew lattices as a new non-commutative version of residuated lattices. The axiomatization and localization for residuated skew lattices are obtained. Moreover, a characterization of residuation on skew lattices via adjointness is presented. Meanwhile, three special subvarieties: distributive residuated skew lattices, skew MTL-algebras and skew BL-algebras, are investigated. In particular, we show that every skew Heyting algebra is a reduct of a special residuated skew lattice.

      PubDate: 2018-06-02T12:12:59Z
      DOI: 10.1016/j.ins.2018.05.045
      Issue No: Vol. 460-461 (2018)
       
  • Mixed co-occurrence of local binary patterns and Hamming-distance-based
           local binary patterns
    • Authors: Feiniu Yuan; Xue Xia; Jinting Shi
      Pages: 202 - 222
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Feiniu Yuan, Xue Xia, Jinting Shi
      Local binary patterns (LBP) have powerful discriminative capabilities. However, traditional methods with LBP histograms cannot capture spatial structures of LBP codes. To extract the spatial structures of an LBP code map, we compute and encode the Hamming distances between LBP codes of a center point and its neighbors on the LBP code map to generate a new code, which is called Hamming-distance-based local binary patterns (HDLBP). Then, we calculate a joint histogram of LBP and HDLBP to represent the LBP co-occurrence with HDLBP (LBPCoHDLBP). Circular bit-wise shift techniques are used to align HDLBP with LBP for rotation invariance. To achieve scale invariance, we extract the feature of LBPCoHDLBP from each scale and concatenate all features of different scales. Finally, we use the sum of absolute differences (SAD) between the intensities of the center point and its neighbors to weight LBPCoHDLBP for further improvement. Extensive experiments show that our method achieves better performance for smoke detection, texture classification and material recognition than most existing methods and is more computationally efficient.

      PubDate: 2018-06-02T12:12:59Z
      DOI: 10.1016/j.ins.2018.05.033
      Issue No: Vol. 460-461 (2018)
       
  • A semantic-preserving differentially private method for releasing query
           logs
    • Authors: David Sánchez; Montserrat Batet; Alexandre Viejo; Mercedes Rodríguez-García; Jordi Castellà-Roca
      Pages: 223 - 237
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): David Sánchez, Montserrat Batet, Alexandre Viejo, Mercedes Rodríguez-García, Jordi Castellà-Roca
      Query logs are of great interest for data analysis. They allow characterizing user profiles, user behaviors and search habits. However, since query logs usually contain personal information, data controllers should implement appropriate data protection mechanisms before releasing them for secondary use. In the past, the anonymization of query logs was tackled from the perspective of statistical disclosure control and by relying on privacy models such as k-anonymity, which do not scale well with the high dimensionality and dynamicity of query logs. To offer better privacy protection, some authors have recently embraced the robust privacy guarantees of ɛ-differential privacy. However, this comes at the cost of limiting the number and types of analyses that can be made on the protected queries. To tackle this issue, in this paper we propose a privacy protection method for query logs that joins the flexibility and convenience of privacy-preserving data releases with the strong privacy guarantees of ɛ-differential privacy. Moreover, to retain the analytical utility of the protected query, we have put special care in capturing, managing and preserving the semantics of the queries during the protection process. The empirical experiments we report show that our method produces differentially private query logs that are more useful for analysis than related works.

      PubDate: 2018-06-02T12:12:59Z
      DOI: 10.1016/j.ins.2018.05.046
      Issue No: Vol. 460-461 (2018)
       
  • Robust time-weighted guaranteed cost control of uncertain periodic
           piecewise linear systems
    • Authors: Xiaochen Xie; James Lam; Chenchen Fan
      Pages: 238 - 253
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Xiaochen Xie, James Lam, Chenchen Fan
      This paper studies the design problem of periodic piecewise guaranteed cost controllers for a class of continuous-time uncertain periodic piecewise linear systems using a time-weighted quadratic cost function. By developing Lyapunov functions with quadratic cost matrices to a time-varying form, sufficient conditions are proposed to ensure the exponential stability of the closed-loop system and a guaranteed upper bound of the cost function. To minimize the upper bound in the controller design process, an iterative algorithm is developed to solve the problem via convex optimization. The effectiveness of our proposed algorithm is demonstrated via a numerical example, and the impact of time-weighted cost is illustrated by simulation results.

      PubDate: 2018-06-05T12:53:20Z
      DOI: 10.1016/j.ins.2018.05.052
      Issue No: Vol. 460-461 (2018)
       
  • A note on similarity relations between fuzzy attribute-oriented concept
           lattices
    • Authors: Gabriel Ciobanu; Cristian Văideanu
      Pages: 254 - 263
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Gabriel Ciobanu, Cristian Văideanu
      Studying fuzzy attribute-oriented concept lattices has been a challenging issue of Formal Concept Analysis. In [19], the author introduced a fuzzy similarity relation between two collections of L-sets and proved some properties of this similarity type. In this paper, based on a duality technique which allowed us to transfer some properties from antitone to isotone fuzzy concept lattices, we provide alternative proofs for the inequality relations between the similarity of fuzzy attribute-oriented concept lattices and the similarity of the fuzzy contexts.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.034
      Issue No: Vol. 460-461 (2018)
       
  • A quick position control strategy based on optimization algorithm for a
           class of first-order nonholonomic system
    • Authors: Pan Zhang; Xuzhi Lai; Yawu Wang; Chun-Yi Su; Min Wu
      Pages: 264 - 278
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Pan Zhang, Xuzhi Lai, Yawu Wang, Chun-Yi Su, Min Wu
      In this paper, we develop a quick and effective position control strategy based on the differential evolution (DE) algorithm for a planar three-link passive-active-active (PAA) underactuated system with first-order nonholonomic constraint. Due to the existence of the constraint, when the angular velocities of the two active links are proportional, the planar PAA system is transformed from a first-order nonholonomic system to a holonomic system like an Acrobot. Making full use of the angular constraint of the like-Acrobot, we employ the DE algorithm to calculate the target angles of all links and the target ratio between the angular velocities of the two active links. After that, one continuous controller for one active link is designed to ensure the target ratio in the whole control process; meantime, the other continuous controller for the other active link is designed to make its angle asymptotically converge to the corresponding target value. In this way, the angles of all links can asymptotically converge to the corresponding target values according to the angular constraint, and thus the position control of the system is realized using the continuous control method. Finally, the simulation results demonstrate the quickness and effectiveness of our proposed control method.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.054
      Issue No: Vol. 460-461 (2018)
       
  • A semi-heterogeneous approach to combining crude oil price forecasts
    • Authors: Jue Wang; Xiang Li; Tao Hong; Shouyang Wang
      Pages: 279 - 292
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Jue Wang, Xiang Li, Tao Hong, Shouyang Wang
      Crude oil price forecasting has received increased attentions due to its significant role in the global economy. Accurate crude oil price forecasts often lead to a rapid new production development with higher quality and less cost. Making such accurate forecasts, however, is challenging due to the intrinsic complexity of oil market mechanism. Many techniques have been tested in the crude oil price forecasting literature. Although forecast combination is a well-known method to improve forecast accuracy, generating forecasts using various techniques tend to be labor intensive. How to efficiently generate many individual forecasts for combination becomes a research question in crude oil price forecasting. Recently, several signal decomposition methods have been suggested for processing the oil price signals. In this paper, we propose a semi-heterogeneous approach to combining crude oil price forecasts, which interacts a set of decomposition methods with a set of forecasting techniques. We first decompose the original price series using four decomposition methods, such as Wavelet Analysis, Singular Spectral Analysis, Empirical Mode Decomposition, and Variational Mode Decomposition. We then use four different forecasting techniques, such as Autoregressive Models, Autoregressive Integrated Moving Average Models, Artificial Neural Networks, and Support Vector Regression Models, to forecast the components from each decomposition methods. Finally, we reconstruct the price forecasts from the forecasted components. This process generates 16 price forecasts in total for combination. We test the combination based on all individual forecasts, as well as a subset of the individual forecasts selected using Tabu Search. The experimental results demonstrate that the forecasting models with the addition of a decomposition technique can have an error reduction of 30.6% compared to benchmark models on average. The combined forecasts outperform the individual forecasts on average. Furthermore, comparing with the heterogeneous combination of 4 individual forecasts, the semi-heterogeneous combinations reduce the errors by 56.6% (w/o Tabu Search) and 61.6% (w/ Tabu Search).

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.026
      Issue No: Vol. 460-461 (2018)
       
  • Exemplar-based facial expression recognition
    • Authors: Nacer Farajzadeh; Mahdi Hashemzadeh
      Pages: 318 - 330
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Nacer Farajzadeh, Mahdi Hashemzadeh
      Facial expressions exhibit very important and judgmental information regarding our emotions and feelings. They show our true intentions to audiences and help them to interpret what we really do mean. Thus, developing such an automatic facial expression system to facilitate the human-machine interaction is of much interest. So far, many algorithms have been proposed to recognize facial expressions that basically employ a complex model to find an answer to the following question: “[to] which expressions’ category does this sample belong”' Instead, we propose to build a pool of simple models that are employed together to find an answer to an even simpler question, which is as follows: “which known emotion is this sample similar to”' In this way, we are trying to find the most similarly perceived (a prior knowledge) emotion among the other emotions so far. The most interesting advantage of this method is to employ the extra available knowledge of the pre-perceived emotions that have been provided by experts over time. Another advantage is to avoid the categorization of expressions in advance, which yield a more general system. The performance of our facial expression system is evaluated on five publicly available facial expression datasets; these are CK, CK+, JAFFE, TFEID, and MMI. The results of the experiments show that our system achieves high recognition accuracy, and the comparison of its performance with the state-of-the art algorithms indicates that the proposed system is highly desirable among competitors.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.057
      Issue No: Vol. 460-461 (2018)
       
  • End to end communication rate-based adaptive fault tolerant control of
           multi-agent systems under unreliable interconnections
    • Authors: Liang Zhao; Guang-Hong Yang
      Pages: 331 - 345
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Liang Zhao, Guang-Hong Yang
      The active fault tolerant control (FTC) problem for nonidentical high-order multi-agent systems (MASs) with network disconnections and actuator faults is studied in this paper. To address the challenges incurred by network disconnections, a novel FTC method based on the end-to-end communication rates is proposed, where the MAS is considered as a cyber-physical system (CPS). In the cyber components, the pre-specified minimum values of the end-to-end communication rates are used to determine the status of network connection, then a logic-based switching control approach is designed to deal with the network disconnections. In the physical components, a cooperative controller and a high-gain observer-like protocol are presented to compensate the actuator faults and the nonidentical nonlinearities. Compared with the previous turning mechanisms based on the output errors method, the end-to-end communication rates method is a more direct way to determine status of network connection. Finally, a simulation is given to validate the effectiveness of the proposed method.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.051
      Issue No: Vol. 460-461 (2018)
       
  • A Gaussian pyramid approach to Bouligand–Minkowski fractal
           descriptors
    • Authors: João Batista Florindo; Dalcimar Casanova; Odemir Martinez Bruno
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): João Batista Florindo, Dalcimar Casanova, Odemir Martinez Bruno
      This work proposes a method to extract features from texture images by applying a Gaussian pyramid multiscale approach to the Bouligand–Minkowski fractal descriptors. The proposal starts from the texture image and computes the stack of multi-resolution images that compose the pyramid, in both directions, of reduction and expansion. In the following, each image in the stack is mapped onto a surface, which is dilated by spheres with variable radii and the dilation volumes are used to compute the Bouligand–Minkowski fractal descriptors for each level. Both the descriptors of each level and combinations with descriptors from the original image are verified in the classification of well-known databases of textural images. The proposed method outperformed other classical and state-of-the-art descriptors with a significant advantage in most cases, including situations where random noise is added to the images.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.037
      Issue No: Vol. 459 (2018)
       
  • Novel algorithms for cost-sensitive classification and knowledge discovery
           
    • Authors: Michael J. Siers; Md Zahidul Islam
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Michael J. Siers, Md Zahidul Islam
      Software defect prediction (SDP) involves using machine learning to locate bugs in source code. Datasets used for SDP are typically affected by an issue called class imbalance. Traditional learning algorithms do not perform well on class imbalanced datasets. Cost-sensitive learning has been used in SDP to minimise the monetary costs incurred by predictions. We propose a framework which produces cost-sensitive predictions and also mitigates class imbalance. Since our algorithm builds a decision forest classifier, knowledge can be extracted by manual inspection of the individual decision trees. To enhance this knowledge discovery process, we propose an algorithm for extracting the most interesting patterns from a decision forest. Our algorithm calculates interestingness as the potential financial gain of knowing the pattern. We then present a process which combines the above-mentioned techniques into an end-to-end cost-sensitive knowledge discovery process. This process is demonstrated by extracting knowledge from four software projects undertaken by the National Aeronautics and Space Administration (NASA).

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.035
      Issue No: Vol. 459 (2018)
       
  • Toward quality assessment of Boolean matrix factorizations
    • Authors: Radim Belohlavek; Jan Outrata; Martin Trnecka
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Radim Belohlavek, Jan Outrata, Martin Trnecka
      Boolean matrix factorization has become an important direction in data analysis. In this paper, we examine the question of how to assess the quality of Boolean matrix factorization algorithms. We critically examine the current approaches, and argue that little attention has been paid to this problem so far and that a systematic approach to it is missing. We regard quality assessment of factorization algorithms as a multifaceted problem, identify major views with respect to which quality needs to be assessed, and present various observations on the available algorithms in this regard. Due to its primary importance, we concentrate on the quality of collections of factors computed from data, present a method to assess this quality, and evaluate this method by experiments.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.016
      Issue No: Vol. 459 (2018)
       
  • Non-uniform Multi-rate Estimator based Periodic Event-Triggered Control
           for resource saving
    • Authors: Ángel Cuenca; Minghui Zheng; Masayoshi Tomizuka; Sergio Sánchez
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Ángel Cuenca, Minghui Zheng, Masayoshi Tomizuka, Sergio Sánchez
      This paper proposes a systematic non-uniform multi-rate estimation and control framework for a periodic event-triggered system which is subject to external disturbance and sensor noise. When the disturbance dynamic model is available, and in order to efficiently estimate the state variable and disturbance from non-uniform slow-rate measurements, a time-varying Kalman filter is designed. When the disturbance dynamic model is not available, a disturbance observer is proposed as an alternative approach. Both the Kalman filter and the disturbance observer are proposed in a non-uniform multi-rate format. Such disturbance estimation enables faster controller updating in spite of slower measurement. Interlacing techniques are used in the control system to uniformly distribute the computational load at each fast sampling instance. Compared to the conventional time-triggered sampling paradigm, the control solution is able to reduce the resource utilization, while maintaining a satisfactory control performance. The proposed control solution will reduce the number of transmissions among devices, which enhances the energy and computational efficiency. Simulation results are provided to validate the effectiveness and benefits of the proposed control algorithms.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.038
      Issue No: Vol. 459 (2018)
       
  • Privacy preserving multi-party computation delegation for deep learning in
           cloud computing
    • Authors: Xu Ma; Fangguo Zhang; Xiaofeng Chen; Jian Shen
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Xu Ma, Fangguo Zhang, Xiaofeng Chen, Jian Shen
      The recent advances in deep learning have improved the state of the art in artificial intelligence, and one of the most important stimulants of this success is the large volume of data. Although collaborative learning can improve the learning accuracy by incorporating more datasets into the learning process, serious privacy issues have also emerged from the training data. In this paper, we propose a new framework for privacy-preserving multi-party deep learning in cloud computing, where the large volume of training data is distributed among many parties. Our system enables multiple parties to learn the same neural network model, which is generated based on the aggregate dataset, and the privacy of the local dataset and learning model is protected against the cloud server. Extensive analysis shows that our schemes satisfy the security requirements of verifiability and privacy. Our implementation and experiments demonstrate that our system has a manageable computational efficiency and can be applied to a wide range of privacy-sensitive areas in deep learning.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.005
      Issue No: Vol. 459 (2018)
       
  • Greedy orthogonal matching pursuit for subspace clustering to improve
           graph connectivity
    • Authors: Changchen Zhao; Wen-Liang Hwang; Chun-Liang Lin; Weihai Chen
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Changchen Zhao, Wen-Liang Hwang, Chun-Liang Lin, Weihai Chen
      Subspace clustering methods based on self-expressiveness model have recently attracted much attention. However, there exists a gap between subspace-preserving coefficient and the final clustering result due to the lack of graph connectivity. The problem has not been well tackled in the published literature. This paper significantly improves the graph connectivity by adding an effective projection step to the recently proposed method SSC-OMP. With this projection step, it is possible to establish a theoretical guarantee that the subspace-preserving condition leads directly to the exact clustering result, which bridges the gap. Moreover, the potential advantage of the proposed algorithm over prior methods is its robustness to noise. Experimental results demonstrate that the proposed approach enjoys a high clustering accuracy and a fast processing speed in comparison with state-of-the-art algorithms.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.032
      Issue No: Vol. 459 (2018)
       
  • GCOTraj: A storage approach for historical trajectory data sets using grid
           cells ordering
    • Authors: Shengxun Yang; Zhen He; Yi-Ping Phoebe Chen
      Pages: 1 - 19
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Shengxun Yang, Zhen He, Yi-Ping Phoebe Chen
      Vast amounts of trajectory data have been collected due to the popularity of GPS devices. Analyzing this wealth of data is important, thus highlighting the need to efficiently index and store this large amount of data on secondary storage to allow for efficient retrieval. Existing approaches index trajectories based on data partitioning index structures such as R-trees or space partitioning index structures such as quad-trees. R-tree like data structures, when used for indexing trajectories, result in large overlapping minimum bounding boxes and are therefore inefficient for the indexing and storage of large trajectory data sets. Existing approaches based on space partitioning do not allow the tradeoff of time versus space constraints in a way that is sensitive to query patterns. This paper proposes a new indexing and storage approach called GCOTraj, which partitions a large spatio-temporal data space into multi-dimensional grid cells and orders these grid cells in two different ways, first via traditional space filling curves which are not sensitive to query patterns; and second, via the Graph-Based Ordering approach (GBO) which is a state-of-the-art workload-based ordering technique for multidimensional data. GCOTraj clusters and stores trajectories to secondary storage based on the ordering produced by ordering algorithms. A good ordering will result in less disk seeks when retrieving disk blocks to answer a query. In addition, GCOTraj uses an index to spot the targeted data on disk and reduce the redundant data retrieved therefore reducing disk IO. Extensive experiments suggest that GCOTraj outperforms the state-of-the-art trajectory storage scheme TrajStore by a factor of up to 16.07 in IO time to answer range queries.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.04.087
      Issue No: Vol. 459 (2018)
       
  • On dynamic consensus processes in group decision making problems
    • Authors: I.J. Pérez; F.J. Cabrerizo; S. Alonso; Y.C. Dong; F. Chiclana; E. Herrera-Viedma
      Pages: 20 - 35
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): I.J. Pérez, F.J. Cabrerizo, S. Alonso, Y.C. Dong, F. Chiclana, E. Herrera-Viedma
      Consensus in group decision making requires discussion and deliberation between the group members with the aim to reach a decision that reflects the opinions of every group member in order for it to be acceptable by everyone. Traditionally, the consensus reaching problem is theoretically modelled as a multi stage negotiation process, i.e. an iterative process with a number of negotiation rounds, which ends when the consensus level achieved reaches a minimum required threshold value. In real world decision situations, both the consensus process environment and specific parameters of the theoretical model can change during the negotiation period. Consequently, there is a need for developing dynamic consensus process models to represent effectively and realistically the dynamic nature of the group decision making problem. Indeed, over the past few years, static consensus models have given way to new dynamic approaches in order to manage parameter variability or to adapt to environment changes. This paper presents a systematic literature review on the recent evolution of consensus reaching models under dynamic environments and critically analyse their advantages and limitations.

      PubDate: 2018-05-28T11:51:34Z
      DOI: 10.1016/j.ins.2018.05.017
      Issue No: Vol. 459 (2018)
       
  • Stability analysis of token-based wireless networked control systems under
           deception attacks
    • Authors: Dajun Du; Changda Zhang; Haikuan Wang; Xue Li; Huosheng Hu; Taicheng Yang
      Pages: 168 - 182
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Dajun Du, Changda Zhang, Haikuan Wang, Xue Li, Huosheng Hu, Taicheng Yang
      Currently cyber-security has attracted a lot of attention, in particular in wireless industrial control networks (WICNs). In this paper, the stability of wireless networked control systems (WNCSs) under deception attacks is studied with a token-based protocol applied to the data link layer (DLL) of WICNS. Since deception attacks cause the stability problem of WNCSs by changing the data transmitted over wireless network, it is important to detect deception attacks, discard the injected false data and compensate for the missing data (i.e., the discarded original data with the injected false data). The main contributions of this paper are: (1) With respect to the character of the token-based protocol, a switched system model is developed. Different from the traditional switched system where the number of subsystems is fixed, in our new model this number will be changed under deception attacks. (2) For this model, a new Kalman filter (KF) is developed for the purpose of attack detection and the missing data reconstruction. (3) For the given linear feedback WNCSs, when the noise level is below a threshold derived in this paper, the maximum allowable duration of deception attacks is obtained to maintain the exponential stability of the system. Finally, a numerical example based on a linearized model of an inverted pendulum is provided to demonstrate the proposed design.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.04.085
      Issue No: Vol. 459 (2018)
       
  • Special Section on Distributed Event-Triggered Control and Estimation in
           Resource-Constrained Cooperative Networks
    • Authors: Qing-Long Han; Min-Rui Fei
      Pages: 183 - 185
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Qing-Long Han, Min-Rui Fei


      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.056
      Issue No: Vol. 459 (2018)
       
  • Robust event-triggered control for networked control systems
    • Authors: Dan Liu; Guang-Hong Yang
      Pages: 186 - 197
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Dan Liu, Guang-Hong Yang
      This paper is concerned with event-triggered dynamic output feedback control for networked control systems subject to communication delays. Two event-triggered conditions are predefined independently to check in an asynchronous matter if sampled signals from the sensor and control input signals from the controller should be transmitted to the controller and the actuator, respectively. As a result, communication resources can be further saved. Then, under the proposed framework, the closed-loop system is modeled as a switched system with a time-delay, based on which a novel exponential stability criterion is derived. This criterion is of less conservatism due to that the chosen Lyapunov–Krasovskii functional is not necessarily decreased. Moreover, the control gains and event-triggered parameters can be co-designed if the related linear matrix inequalities are feasible. The effectiveness of the proposed method is demonstrated via two numerical examples.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.02.057
      Issue No: Vol. 459 (2018)
       
  • Stochastic self-triggered MPC for linear constrained systems under
           additive uncertainty and chance constraints
    • Authors: Jicheng Chen; Qi Sun; Yang Shi
      Pages: 198 - 210
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Jicheng Chen, Qi Sun, Yang Shi
      This paper presents a stochastic self-triggered model predictive control (MPC) scheme for linear systems with additive uncertainty, and with the states and inputs being subject to chance constraints. In the proposed control scheme, the succeeding sampling time instant and current control inputs are computed online by solving a formulated optimization problem. The chance constraints are reformulated into a deterministic fashion by leveraging the Cantelli’s inequality. Under few mild assumptions, the online computational complexity of the proposed control scheme is similar to that of a nominal self-triggered MPC. Furthermore, initial constraints are incorporated into the MPC problem to guarantee the recursive feasibility of the scheme, and the stability conditions of the system have been developed. Finally, numerical examples are provided to illustrate the achievable performance of the proposed control strategy.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.021
      Issue No: Vol. 459 (2018)
       
  • On quantized H∞ filtering for multi-rate systems under stochastic
           communication protocols: The finite-horizon case
    • Authors: Shuai Liu; Zidong Wang; Licheng Wang; Guoliang Wei
      Pages: 211 - 223
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Shuai Liu, Zidong Wang, Licheng Wang, Guoliang Wei
      In this paper, the finite-horizon H ∞ filtering problem is investigated for a class of linear discrete-time multi-rate systems with quantization effects under the stochastic communication protocol (SCP). The SCP is adopted to mitigate the undesirable data collision phenomenon resulting from the limited bandwidth of communication networks. Governed by a Markov chain, the SCP is employed to determine which sensor node should be granted the access right at each transmission instant. In order to cope with the difficulty caused by the asynchronous sampling, a lifting technique is utilized to convert the multi-rate system into a single-rate one with the identical slow sampling rate. The main purpose of the addressed problem is to design a set of time-varying filters for the multi-rate systems such that, for all admissible multi-sampling periods and quantization effects under the SCP, the H ∞ constraint is satisfied over a finite-horizon. By resorting to the complete square method and the Riccati difference equation (RDE) technique, sufficient conditions are established to ensure the existence of the desired filters. Then, the filter parameters are explicitly expressed in terms of the solution to two coupled backward RDEs. Finally, a numerical example is presented to demonstrate the effectiveness of the proposed filter design algorithm.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.02.050
      Issue No: Vol. 459 (2018)
       
  • Adaptive consensus for high-order unknown nonlinear multi-agent systems
           with unknown control directions and switching topologies
    • Authors: Mohammad Hadi Rezaei; Meisam Kabiri; Mohammad Bagher Menhaj
      Pages: 224 - 237
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Mohammad Hadi Rezaei, Meisam Kabiri, Mohammad Bagher Menhaj
      In this paper, we provide a comprehensive assessment of the consensus of high-order nonlinear multi-agent systems with input saturation and time-varying disturbance under switching topologies. The control directions and model parameters of agents are supposed to be unknown. Our approach is based on transforming the problem of consensus for a network that consists of high-order nonlinear agents to that of perturbed first-order multi-agent systems. The unknown part of dynamics is cancelled using radial basis neural networks. Nussbaum gains and auxiliary systems are respectively employed to overcome the unknown input direction and the saturation. Adaptive sliding mode control is used to compensate for the time-varying disturbance and the imperfect approximation of the developed neural network as well. Through Lyapunov analysis, it is shown that the overall closed-loop system maintains asymptotic stability. Finally, our approach is applied to a group of multiple single-link flexible joint manipulators to highlight better its merit.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.04.089
      Issue No: Vol. 459 (2018)
       
  • Adaptive fixed-time bipartite tracking consensus control for unknown
           nonlinear multi-agent systems: An information classification mechanism
    • Authors: Haijiao Yang; Dan Ye
      Pages: 238 - 254
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Haijiao Yang, Dan Ye
      This paper is concerned with the problem of bipartite tracking consensus for high-order unknown nonlinear multi-agent systems with actuator faults. Unlike the traditional condition that the directed signed graph is structurally balanced, a directed signed graph containing a spanning tree is considered. Besides, the consensus errors are required to satisfy both the prescribed performance and fast convergence (fixed-time). By proposing an information classification mechanism, each agent selectively uses neighbor information such that agents in the system are divided into two styles, which transform the bipartite tracking consensus problem into a general tracking consensus problem. By using neural networks and adaptive technologies to approximate unknown functions, the adaptive fault-tolerant fixed-time consensus controllers are developed. All signals in the system are bounded within a fixed time. Moreover, the bipartite consensus errors satisfy the prescribed performance by selecting appropriately predefined performance functions. Stability analysis and simulation results further verify the effectiveness of the proposed method.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.04.016
      Issue No: Vol. 459 (2018)
       
  • Rolling optimization formation control for multi-agent systems under
           unknown prior desired shapes
    • Authors: Hao Su; Gong-You Tang
      Pages: 255 - 264
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Hao Su, Gong-You Tang
      This paper deals with the optimal formation control problem of multi-agent systems under a prior unknown desired shapes. The objective of this paper is to accomplish a rolling optimal formation of multi-agent systems by incorporating trajectory tracking and energy saving control into a unified framework. First, according to the real-time desired position offset between each follower and the leader, the rolling optimization performance indexes are introduced. Then, a distributed rolling optimization algorithm is proposed to realize the desired formation of multi-agent systems under the minimum energy consumption of agents. Finally, several simulation examples are conducted to illustrate the effectiveness of the proposed design algorithm.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.04.023
      Issue No: Vol. 459 (2018)
       
  • Synchronization regions of discrete-time dynamical networks with impulsive
           couplings
    • Authors: Zengyang Li; Hui Liu; Jun-an Lu; Zhigang Zeng; Jinhu Lü
      Pages: 265 - 277
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Zengyang Li, Hui Liu, Jun-an Lu, Zhigang Zeng, Jinhu Lü
      This paper deals with synchronization of a class of discrete-time dynamical networks. First, a novel model for discrete-time dynamical networks with impulsive couplings between nodes is proposed. Second, both global and local stability of synchronization manifold is investigated using the multiple Lyapunov function method and some inequality techniques. As a result, several synchronization criteria are obtained. Third, two illustrative examples are given to validate the effectiveness of the proposed synchronization criteria. Analysis on the synchronization regions of the discrete-time dynamical network with metapopulation dynamics is further made, which reveals such a finding that either a relatively large coupling strength or a short impulsive interval is not necessarily beneficial to synchronization of the discrete-time dynamical network.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.05.027
      Issue No: Vol. 459 (2018)
       
  • Event-triggered consensus for linear continuous-time multi-agent systems
           based on a predictor
    • Authors: Jian Sun; Qiuling Yang; Xiaoyu Liu; Jie Chen
      Pages: 278 - 289
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Jian Sun, Qiuling Yang, Xiaoyu Liu, Jie Chen
      In this paper, the problem of an event-triggered consensus for a linear continuous-time multi-agent system is investigated. A new event-triggered consensus protocol based on a predictor is proposed to achieve consensus while not requiring continuous communication among agents. The predictor utilizes an artificial closed-loop system to predict the future state of each agent. With the proposed consensus protocol, each agent only needs to monitor its own states to determine its event-triggered instants. When an event of an agent is triggered, the agent immediately updates its consensus protocol and sends its state information to its neighbors. When an agent receives state information from its neighbors, the agent immediately updates its consensus protocol and predictor. A necessary and sufficient condition that solves the consensus problem is derived. Moreover, it is proved that Zeno behaviors are excluded. Finally, some numerical examples are given to illustrate that, with the proposed protocol, a multi-agent system can achieve consensus while greatly reducing event-triggered times.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.03.028
      Issue No: Vol. 459 (2018)
       
  • Event-triggered leader-following consensus for multi-agent systems with
           semi-Markov switching topologies
    • Authors: Jiangtao Dai; Ge Guo
      Pages: 290 - 301
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Jiangtao Dai, Ge Guo
      This paper investigates the event-triggered leader-following consensus problem for a multi-agent system with semi-Markov switching topologies. A sampled-data-based event-triggered transmission scheme is introduced to reduce unnecessary communication. By modeling the switching of network topologies by a semi-Markov process and adopting an event-triggered transmission scheme, a new consensus protocol is proposed. Compared with the traditional Markovian switching topologies, the transition rates in the semi-Markov switching topologies are time-varying, which is more general and practicable. Through utilization of an appropriate Lyapunov–Krasovskii functional, some sufficient conditions are derived, which guarantee that the leader-following consensus can be achieved in mean-square sense. Moreover, the consensus gain matrices and parameter of the event-triggered scheme can be efficiently solved out. Finally, a numerical example illustrates the effectiveness of the proposed design technique.

      PubDate: 2018-06-08T12:55:36Z
      DOI: 10.1016/j.ins.2018.04.054
      Issue No: Vol. 459 (2018)
       
  • Sparsity measure of a network graph: Gini index
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Swati Goswami, C.A. Murthy, Asit K. Das
      This article explores the problem of formulating a general measure of sparsity of network graphs. Based on an available definition sparsity of a dataset, namely Gini index, it provides a way to define sparsity measure of a network graph. We name the sparsity measure so introduced as sparsity index. Sparsity measures are commonly associated with six properties, namely, Robin Hood, Scaling, Rising Tide, Cloning, Bill Gates and Babies. Sparsity index directly satisfies four of these six properties; does not satisfy Cloning and satisfies Scaling for some specific cases. A comparison of the proposed index is drawn with Edge Density (the proportion of the sum of degrees of all nodes in a graph compared to the total possible degrees in the corresponding fully connected graph), by showing mathematically that as the edge density of an undirected graph increases, its sparsity index decreases. The paper highlights how the proposed sparsity measure can reveal important properties of a network graph. Further, a relationship has been drawn analytically between the sparsity index and the exponent term of a power law distribution (a distribution known to approximate the degree distribution of a wide variety of network graphs). To illustrate application of the proposed index, a community detection algorithm for network graphs is presented. The algorithm produces overlapping communities with no input requirement on number or size of the communities; has a computational complexity O(n 2), where n is the number of nodes of the graph. The results validated on artificial and real networks show its effectiveness.

      PubDate: 2018-06-18T12:02:38Z
       
  • Certificateless public key encryption with equality test
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Haipeng Qu, Zhen Yan, Xi-Jun Lin, Qi Zhang, Lin Sun
      In this paper, we present the concept of certificateless public key encryption with equality test (CL-PKEET), which integrates certificateless public key cryptography (CL-PKC) into public key encryption with equality test (PKEET) to solve the key escrow problem of identity-based encryption with equality test (IBEET). In the CL-PKEET scheme, the receiver first computes his private key with the receiver’s secret value and the partial private key generated by the key generation center (KGC). The trapdoor is generated with this private key. Then, using the trapdoor, the receiver authorizes the cloud server to test the equivalence between his ciphertexts and others’ ciphertexts. We formalize the system model and definition of CL-PKEET, propose the security models by considering four types of adversaries, and then present a concrete CL-PKEET scheme. Our proposal achieves the IND-CCA security against adversaries without trapdoor, and the OW-CCA security against adversaries with trapdoor. Furthermore, compared with IBEET and PKEET, our proposal which has the features of CL-PKC solves certificate management and key escrow problems simultaneously.

      PubDate: 2018-06-18T12:02:38Z
       
  • Sampled-data synchronization of chaotic Lur’e systems via an
           adaptive event-triggered approach
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Tao Li, Ruiting Yuan, Shumin Fei, Zhengtao Ding
      In this paper, based on nonuniform sampling, the master-slave synchronization in a class of Lur’e systems is studied via using the sampled outputs of error system. Different from existing results, the transmission of control signals is determined by a novel adaptive event-triggered scheme, where the triggering thresholds depend on the dynamic behaviors of controlled systems rather than the predetermined constants as some traditional ones. Through choosing two augmented Lyapunov–Krasovskii functionals (LKFs), some delay-dependent synchronization criteria are formulated and the conservatism can be effectively reduced owing to the utilization of Wirtinger-based inequalities and delay-product-type LKF terms. Especially, the existence of the controller can be easily checked since the derived conditions are presented via LMI forms. Finally, two numerical examples with comparisons and simulations are given to illustrate the proposed results.

      PubDate: 2018-06-18T12:02:38Z
       
  • Estimating dynamical dimensions from noisy observations
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Jack Murdoch Moore, Michael Small
      Knowledge of the dynamical dimension mitigates the “curse of dimensionality” by permitting analysis in dimension lower than that of the original state vectors. The description length quantifies complexity and so allows us to use Occam’s razor to estimate the dynamical dimension underlying noisily observed data. Applying our method, based on the description length, to a coarsely sampled scalar time series requires the choice of only one parameter; an embedding dimension. For the three systems considered in this study observed amid observational noise, a single choice of embedding dimension does provide reasonable estimates of the dynamical dimension. The spatial distribution of local estimates of dynamical dimension aids visualisation and provides extra insight into the geometric structure of many systems.

      PubDate: 2018-06-18T12:02:38Z
       
  • Contradiction separation based dynamic multi-clause synergized automated
           deduction
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Yang Xu, Jun Liu, Shuwei Chen, Xiaomei Zhong, Xingxing He
      Resolution as a famous rule of inference has played a key role in automated reasoning for over five decades. A number of variants and refinements of resolution have been also studied, essentially, they are all based on binary resolution, that is, the cutting rule of the complementary pair while every deduction involves only two clauses. In the present work, we consider an extension of binary resolution rule, which is proposed as a novel contradiction separation based inference rule for automated deduction, targeted for dynamic and multiple (two or more) clauses handling in a synergized way, while binary resolution is its special case. This contradiction separation based dynamic multi-clause synergized automated deduction theory is then proved to be sound and complete. The development of this new extension is motivated not only by our view to show that such a new rule of inference can be generic, but also by our wish that this inference rule could provide a basis for more efficient automated deduction algorithms and systems.

      PubDate: 2018-06-18T12:02:38Z
       
  • On Convergence Properties of Implicit Self-paced Objective
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Zilu Ma, Shiqi Liu, Deyu Meng, Yong Zhang, SioLong Lo, Zhi Han
      Self-paced learning (SPL) is a new methodology that simulates the learning principle of humans/animals to start learning easier aspects of a learning task, and then gradually take more complex examples into training. This new-coming learning regime has been empirically substantiated to be effective in various computer vision and pattern recognition tasks. Recently, it has been proved that the SPL regime has a close relationship with a implicit self-paced objective function. While this implicit objective could provide helpful interpretations to the effectiveness, especially the robustness, insights under the SPL paradigms, there are still no theoretical results to verify such relationship. To this issue, we provide some convergence results on the implicit objective of SPL. Specifically, we will prove that the learning process of SPL always converges to critical points of this implicit objective under some mild conditions. This result verifies the intrinsic relationship between SPL and this implicit objective, and makes the previous robustness analysis on SPL complete and theoretically rational.

      PubDate: 2018-06-18T12:02:38Z
       
  • Insensitive stochastic gradient twin support vector machines for large
           scale problems
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Zhen Wang, Yuan-Hai Shao, Lan Bai, Chun-Na Li, Li-Ming Liu, Nai-Yang Deng
      Within the large scale classification problem, the stochastic gradient descent method called PEGASOS has been successfully applied to support vector machines (SVMs). In this paper, we propose a stochastic gradient twin support vector machine (SGTSVM) based on the twin support vector machine (TWSVM). Compared to PEGASOS, our method is insensitive to stochastic sampling. Furthermore, we prove the convergence of SGTSVM and the approximation between TWSVM and SGTSVM under uniform sampling, whereas PEGASOS is almost surely convergent and only has an opportunity to obtain an approximation to SVM. In addition, we extend SGTSVM to nonlinear classification problems via a kernel trick. Experiments on artificial and publicly available datasets show that our method has stable performance and can handle large scale problems easily.

      PubDate: 2018-06-18T12:02:38Z
       
  • Adaptive decomposition-based evolutionary approach for multiobjective
           sparse reconstruction
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volume 462
      Author(s): Bai Yan, Qi Zhao, Zhihai Wang, J. Andrew Zhang
      This paper aims at solving the sparse reconstruction (SR) problem via a multiobjective evolutionary algorithm. Existing multiobjective evolutionary algorithms for the SR problem have high computational complexity, especially in high-dimensional reconstruction scenarios. Furthermore, these algorithms focus on estimating the whole Pareto front rather than the knee region, thus leading to limited diversity of solutions in knee region and waste of computational effort. To tackle these issues, this paper proposes an adaptive decomposition-based evolutionary approach (ADEA) for the SR problem. Firstly, we employ the decomposition-based evolutionary paradigm to guarantee a high computational efficiency and diversity of solutions in the whole objective space. Then, we propose a two-stage iterative soft-thresholding (IST)-based local search operator to improve the convergence. Finally, we develop an adaptive decomposition-based environmental selection strategy, by which the decomposition in the knee region can be adjusted dynamically. This strategy enables to focus the selection effort on the knee region and achieves low computational complexity. Experimental results on simulated signals, benchmark signals and images demonstrate the superiority of ADEA in terms of reconstruction accuracy and computational efficiency, compared to five state-of-the-art algorithms.

      PubDate: 2018-06-18T12:02:38Z
       
  • Context-aware result inference in crowdsourcing
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Yili Fang, Hailong Sun, Guoliang Li, Richong Zhang, Jingpeng Huai
      Many result inference methods have been proposed to address the quality-control problem in crowdsourcing. However, existing methods are ineffective for context-sensitive tasks ( CSTs ), e.g., handwriting recognition, translation, speech transcription, where context correlation within a task cannot be ignored for two reasons. Firstly, it is ineffective to crowdsource a whole CST (e.g., recognizing handwritten texts) and use task-level inference methods to infer the answer, because it is rather hard to correctly complete a whole complicated task. Secondly, although a CST is composed of a set of atomic subtasks (e.g., recognizing a handwritten word), it is unsuitable to split it into multiple subtasks and adopt a subtask-level inference algorithm to infer the result, because this will lose the context correlation (e.g., phrases) among subtasks and increase the difficulty to complete a task. Thus it calls for a new approach to handling CSTs . In this work, we study the result inference problem for CSTs and propose a context-aware inference algorithm. We design an inference algorithm by incorporating the context information. Furthermore, we introduce an iterative method to improve the quality. The results of experiments on real-world CSTs demonstrated the superiority of our approach compared with the state-of-the-art methods.

      PubDate: 2018-06-18T12:02:38Z
       
  • Filtering of two-dimensional periodic Roesser systems subject to
           dissipativity
    • Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Jie Tao, Zheng-Guang Wu, Yuanqing Wu
      In this note, the problem of dissipativity-based filtering of two-dimensional (2D) periodic Roesser systems is investigated. A discrete-time periodic Roesser model extensively used in practical systems is introduced to describe 2D periodic systems. Moreover, it is assumed that the periods of the augmented system in horizontal and vertical directions are the same, which can greatly simplify stability analyses. By resorting to the periodic Lyapunov functional approach that depends on periodical property of the augmented system, less conservative results for the existence of 2D periodic filter are presented to ensure the asymptotic stability and 2D ( Q 1 , Q 2 , Q 3 ) − β -dissipativity. Particularly, the parameters of 2D periodic filter are derived with convex optimization method. Simulation results are provided to verify the effectiveness and merits of the theoretical findings. In addition, the correlation between optimal dissipative performance indices and different Lyapunov functions is revealed.

      PubDate: 2018-06-18T12:02:38Z
       
  • Markov kernels and tribes
    • Authors: Anatolij
      Abstract: Publication date: September 2018
      Source:Information Sciences, Volumes 460–461
      Author(s): Anatolij Dvurečenskij
      We define an ordering on the set of bounded Markov kernels associated with a tribe of fuzzy sets. We show that under this order, the set of bounded Markov kernels is a Dedekind σ-complete lattice. In addition, we define a sum of bounded Markov kernels such that the set of bounded Markov kernels is a lattice-ordered semigroup. If we concentrate only to sharp bounded Markov kernels, then this set is even a Dedekind σ-complete ℓ-group with strong unit. We show that our methods work also for bounded Markov kernels associated with Ts -tribes of fuzzy sets, where Ts is any Frank t-norm and s ∈ (0, ∞).

      PubDate: 2018-05-28T11:51:34Z
       
  • Mining diversified association rules in big datasets: A
           cluster/GPU/genetic approach
    • Authors: Youcef Djenouri; Asma Belhadi Philippe Fournier-Viger Hamido Fujita
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Youcef Djenouri, Asma Belhadi, Philippe Fournier-Viger, Hamido Fujita
      Association rule mining is a popular data mining task, which has important in many domains. Because the task of association rule mining is very time consuming, evolutionary and swarm based algorithms have been designed to find approximate solutions. However, these approaches still have long execution times, especially when applied on dense and big databases, or when low minsup and minconf threshold values are used. Moreover, these approaches suffer from the lack of diversity in the rules presented to the user. To address these drawbacks of previous algorithms, this paper proposes an efficient parallel algorithm named CGPUGA. It is a genetic algorithm that runs on clusters of GPUs to efficiently discover diversified association rules. It benefits from cluster computing to generate rules. Then, to evaluate rules, which is the most time consuming task, the designed algorithm relies on the massively parallel GPU threads. Furthermore, to deal with the issue of rule quality, the search space of rules is partitioned into several regions assigned to different workers, and rules found by each workers are the merged to ensure diversification. The designed approach has been empirically compared with state-of-the-art algorithms using small, medium, large and big datasets. Results reveal that CGPUGA is 600 times faster than the sequential version of the algorithm for big datasets. Moreover, it outperforms state-of-the-art high performance computing based association rule mining algorithms for real big datasets such as Pokec, Webdocs and Wikilinks. In terms of rule quality, results show that the designed CGPUGA algorithm provides rules of higher quality compared to the state-of-the-art NIGGAR, MSP-MPSO and MPGA algorithms for diversified association rule mining.

      PubDate: 2018-05-28T11:51:34Z
       
  • Learning in the compressed data domain: Application to milk quality
           prediction
    • Authors: Dixon Vimalajeewa; Chamil Kulatunga Donagh Berry
      Abstract: Publication date: August 2018
      Source:Information Sciences, Volume 459
      Author(s): Dixon Vimalajeewa, Chamil Kulatunga, Donagh P. Berry
      Smart dairy farming has become one of the most exciting and challenging area in cloud-based data analytics. Transfer of raw data from all farms to a central cloud is currently not feasible as applications are generating more data while internet connectivity is lacking in rural farms. As a solution, Fog computing has become a key factor to process data near the farm and derive farm insights by exchanging data between on-farm applications and transferring some data to the cloud. In this context, learning in the compressed data domain, where de-compression is not necessary, is highly desirable as it minimizes the energy used for communication/computation, reduces required memory/storage, and improves application latency. Mid-infrared spectroscopy (MIRS) is used globally to predict several milk quality parameters as well as deriving many animal-level phenotypes. Therefore, compressed learning on MIRS data is beneficial both in terms of data processing in the Fog, as well as storing large data sets in the cloud. In this paper, we used principal component analysis and wavelet transform as two techniques for compressed learning to convert MIRS data into a compressed data domain. The study derives near lossless compression parameters for both techniques to transform MIRS data without impacting the prediction accuracy for a selection of milk quality traits.

      PubDate: 2018-05-28T11:51:34Z
       
 
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
 
Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs
Your IP address: 54.225.31.188
 
About JournalTOCs
API
Help
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-